From 8a214e997c4b5e42faa999c8475fecc57b30d222 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?S=C3=A9bastien=20Huss?= Date: Sun, 28 Jan 2024 10:02:31 +0100 Subject: [PATCH] fix --- monitor/alertmanager/datas.tf | 167 +++++++++ monitor/alertmanager/index.yaml | 111 ++++++ ...ertmanager-kube-promethe-alertmanager.yaml | 38 ++ ...ager-kube-promethe-alertmanager.rules.yaml | 142 ++++++++ ...ertmanager-kube-promethe-alertmanager.yaml | 33 ++ monitor/alertmanager/presentation.tf | 75 ++++ monitor/alertmanager/svc.tf | 33 ++ ..._alertmanager-kube-grafana-datasource.yaml | 19 + ...r-kube-promethe-alertmanager-overview.yaml | 22 ++ ...ertmanager-kube-promethe-alertmanager.yaml | 18 + ...ertmanager-kube-promethe-alertmanager.yaml | 20 ++ monitor/alerts-containers/datas.tf | 16 + monitor/alerts-containers/index.yaml | 24 ++ ...k8s.rules.container-cpu-usage-seconds.yaml | 28 ++ ...kube-k8s.rules.container-memory-cache.yaml | 26 ++ ...y-kube-k8s.rules.container-memory-rss.yaml | 26 ++ ...-kube-k8s.rules.container-memory-swap.yaml | 26 ++ ...k8s.rules.container-memory-working-se.yaml | 26 ++ ...ity-kube-k8s.rules.container-resource.yaml | 88 +++++ monitor/alerts-core/datas.tf | 16 + monitor/alerts-core/index.yaml | 24 ++ ...theus-community-kube-config-reloaders.yaml | 32 ++ ...ometheus-community-kube-general.rules.yaml | 67 ++++ ...us-community-kube-k8s.rules.pod-owner.yaml | 67 ++++ ...ty-kube-kube-prometheus-general.rules.yaml | 24 ++ ...-kube-prometheus-node-recording.rules.yaml | 32 ++ ...etheus-community-kube-kubernetes-apps.yaml | 258 ++++++++++++++ ...s-community-kube-kubernetes-resources.yaml | 122 +++++++ ...eus-community-kube-kubernetes-storage.yaml | 113 ++++++ ...nity-kube-kubernetes-system-apiserver.yaml | 64 ++++ ...munity-kube-kubernetes-system-kubelet.yaml | 140 ++++++++ ...heus-community-kube-kubernetes-system.yaml | 42 +++ monitor/dashboards-cluster/datas.tf | 16 + monitor/dashboards-cluster/index.yaml | 24 ++ ...-community-kube-k8s-resources-cluster.yaml | 22 ++ ...unity-kube-k8s-resources-multicluster.yaml | 22 ++ monitor/dashboards-minimal/datas.tf | 16 + monitor/dashboards-minimal/index.yaml | 24 ++ ...ometheus-community-kube-cluster-total.yaml | 22 ++ ...theus-community-kube-grafana-overview.yaml | 22 ++ ...theus-community-kube-namespace-by-pod.yaml | 22 ++ ...-community-kube-namespace-by-workload.yaml | 22 ++ ...community-kube-persistentvolumesusage.yaml | 22 ++ ...p_prometheus-community-kube-pod-total.yaml | 22 ++ ...metheus-community-kube-workload-total.yaml | 22 ++ monitor/dashboards-namespace/datas.tf | 16 + monitor/dashboards-namespace/index.yaml | 24 ++ ...ommunity-kube-k8s-resources-namespace.yaml | 22 ++ ...ube-k8s-resources-workloads-namespace.yaml | 22 ++ monitor/dashboards-workload/datas.tf | 16 + monitor/dashboards-workload/index.yaml | 24 ++ ...eus-community-kube-k8s-resources-node.yaml | 22 ++ ...heus-community-kube-k8s-resources-pod.yaml | 22 ++ ...community-kube-k8s-resources-workload.yaml | 22 ++ .../grafana/apps_v1_Deployment_grafana.yaml | 298 ++++++++++++++++ monitor/grafana/config.tf | 43 +++ monitor/grafana/datas.tf | 112 ++++++ monitor/grafana/index.yaml | 194 +++++++++++ ....coreos.com_v1_ServiceMonitor_grafana.yaml | 28 ++ monitor/grafana/presentation.tf | 72 ++++ ...ization.k8s.io_v1_RoleBinding_grafana.yaml | 20 ++ ....authorization.k8s.io_v1_Role_grafana.yaml | 16 + monitor/grafana/secret.tf | 19 + ...1_ConfigMap_grafana-config-dashboards.yaml | 26 ++ .../v1_PersistentVolumeClaim_grafana.yaml | 20 ++ .../grafana/v1_ServiceAccount_grafana.yaml | 13 + monitor/grafana/v1_Service_grafana.yaml | 22 ++ ...apps_v1_Deployment_kube-state-metrics.yaml | 82 +++++ monitor/kube-state-metrics/datas.tf | 49 +++ monitor/kube-state-metrics/index.yaml | 58 ++++ ...te-metrics-kube-pr-kube-state-metrics.yaml | 68 ++++ ..._v1_ServiceMonitor_kube-state-metrics.yaml | 24 ++ ...ClusterRoleBinding_kube-state-metrics.yaml | 22 ++ ....io_v1_ClusterRole_kube-state-metrics.yaml | 155 +++++++++ .../kube-state-metrics/ressources_no_ns.tf | 45 +++ .../v1_ServiceAccount_kube-state-metrics.yaml | 16 + .../v1_Service_kube-state-metrics.yaml | 28 ++ monitor/loki-dashboard/index.yaml | 83 +++++ .../v1_ConfigMap_loki-dashboards-1.yaml | 24 ++ .../v1_ConfigMap_loki-dashboards-2.yaml | 24 ++ monitor/loki/apps_v1_StatefulSet_loki.yaml | 124 +++++++ monitor/loki/config.tf | 91 +++++ monitor/loki/datas.tf | 77 ++++ monitor/loki/index.yaml | 106 ++++++ ...om_v1_PrometheusRule_loki-loki-alerts.yaml | 65 ++++ ...com_v1_PrometheusRule_loki-loki-rules.yaml | 98 ++++++ ...ing.coreos.com_v1_ServiceMonitor_loki.yaml | 35 ++ monitor/loki/v1_ConfigMap_loki-runtime.yaml | 15 + monitor/loki/v1_ServiceAccount_loki.yaml | 14 + monitor/loki/v1_Service_loki-headless.yaml | 25 ++ monitor/loki/v1_Service_loki-memberlist.yaml | 24 ++ monitor/loki/v1_Service_loki.yaml | 28 ++ monitor/monitor-control-plan/datas.tf | 20 ++ monitor/monitor-control-plan/index.yaml | 24 ++ ...usRule_prometheus-community-kube-etcd.yaml | 167 +++++++++ ...ube-kube-apiserver-availability.rules.yaml | 129 +++++++ ...ty-kube-kube-apiserver-burnrate.rules.yaml | 321 +++++++++++++++++ ...y-kube-kube-apiserver-histogram.rules.yaml | 30 ++ ...us-community-kube-kube-apiserver-slos.yaml | 76 ++++ ...s-community-kube-kube-scheduler.rules.yaml | 56 +++ ...-kubernetes-system-controller-manager.yaml | 29 ++ ...nity-kube-kubernetes-system-scheduler.yaml | 29 ++ ...r_prometheus-community-kube-apiserver.yaml | 40 +++ ...ommunity-kube-kube-controller-manager.yaml | 33 ++ ...r_prometheus-community-kube-kube-etcd.yaml | 29 ++ ...metheus-community-kube-kube-scheduler.yaml | 33 ++ .../monitor-control-plan/ressources_no_ns.tf | 45 +++ ...p_prometheus-community-kube-apiserver.yaml | 22 ++ ...eus-community-kube-controller-manager.yaml | 22 ++ ...figMap_prometheus-community-kube-etcd.yaml | 22 ++ ...p_prometheus-community-kube-scheduler.yaml | 22 ++ ...ommunity-kube-kube-controller-manager.yaml | 27 ++ ...e_prometheus-community-kube-kube-etcd.yaml | 27 ++ ...metheus-community-kube-kube-scheduler.yaml | 27 ++ ...ode-exporter-prometheus-node-exporter.yaml | 119 +++++++ monitor/node-exporter/datas.tf | 34 ++ monitor/node-exporter/index.yaml | 58 ++++ ...rter-kube-prometh-node-exporter.rules.yaml | 82 +++++ ...e-exporter-kube-prometh-node-exporter.yaml | 328 ++++++++++++++++++ ...de-exporter-kube-prometh-node-network.yaml | 29 ++ ...node-exporter-kube-prometh-node.rules.yaml | 56 +++ ...ode-exporter-prometheus-node-exporter.yaml | 28 ++ ...er-kube-prometh-node-cluster-rsrc-use.yaml | 22 ++ ...e-exporter-kube-prometh-node-rsrc-use.yaml | 22 ++ ...de-exporter-kube-prometh-nodes-darwin.yaml | 22 ++ ...gMap_node-exporter-kube-prometh-nodes.yaml | 22 ++ ...ode-exporter-prometheus-node-exporter.yaml | 17 + ...ode-exporter-prometheus-node-exporter.yaml | 28 ++ monitor/prometheus/datas.tf | 212 +++++++++++ monitor/prometheus/index.yaml | 126 +++++++ ...metheus-kube-prometheus-kubelet.rules.yaml | 32 ++ ...ometheus-kubernetes-system-kube-proxy.yaml | 29 ++ ...prometheus-kube-prometheus-prometheus.yaml | 280 +++++++++++++++ ...or_prometheus-kube-prometheus-coredns.yaml | 29 ++ ...prometheus-kube-prometheus-kube-proxy.yaml | 29 ++ ...or_prometheus-kube-prometheus-kubelet.yaml | 95 +++++ ...prometheus-kube-prometheus-prometheus.yaml | 32 ++ monitor/prometheus/presentation.tf | 75 ++++ monitor/prometheus/prometheus.tf | 62 ++++ ...prometheus-kube-prometheus-prometheus.yaml | 23 ++ ...prometheus-kube-prometheus-prometheus.yaml | 33 ++ monitor/prometheus/ressources_no_ns.tf | 45 +++ monitor/prometheus/svc.tf | 33 ++ ...us-kube-prometheus-grafana-datasource.yaml | 38 ++ ...rometheus-kube-prometheus-k8s-coredns.yaml | 22 ++ ...ap_prometheus-kube-prometheus-kubelet.yaml | 22 ++ ...prometheus-kube-prometheus-prometheus.yaml | 22 ++ ...gMap_prometheus-kube-prometheus-proxy.yaml | 22 ++ ...prometheus-kube-prometheus-prometheus.yaml | 18 + ...prometheus-kube-prometheus-prometheus.yaml | 19 + ...ce_prometheus-kube-prometheus-coredns.yaml | 26 ++ ...prometheus-kube-prometheus-kube-proxy.yaml | 27 ++ .../promtail/apps_v1_DaemonSet_promtail.yaml | 95 +++++ monitor/promtail/config.tf | 94 +++++ monitor/promtail/datas.tf | 38 ++ monitor/promtail/index.yaml | 73 ++++ ...coreos.com_v1_ServiceMonitor_promtail.yaml | 19 + ...k8s.io_v1_ClusterRoleBinding_promtail.yaml | 19 + ...zation.k8s.io_v1_ClusterRole_promtail.yaml | 24 ++ monitor/promtail/ressources_no_ns.tf | 45 +++ .../promtail/v1_ServiceAccount_promtail.yaml | 13 + .../promtail/v1_Service_promtail-metrics.yaml | 22 ++ 162 files changed, 8560 insertions(+) create mode 100644 monitor/alertmanager/datas.tf create mode 100644 monitor/alertmanager/index.yaml create mode 100644 monitor/alertmanager/monitoring.coreos.com_v1_Alertmanager_alertmanager-kube-promethe-alertmanager.yaml create mode 100644 monitor/alertmanager/monitoring.coreos.com_v1_PrometheusRule_alertmanager-kube-promethe-alertmanager.rules.yaml create mode 100644 monitor/alertmanager/monitoring.coreos.com_v1_ServiceMonitor_alertmanager-kube-promethe-alertmanager.yaml create mode 100644 monitor/alertmanager/presentation.tf create mode 100644 monitor/alertmanager/svc.tf create mode 100644 monitor/alertmanager/v1_ConfigMap_alertmanager-kube-grafana-datasource.yaml create mode 100644 monitor/alertmanager/v1_ConfigMap_alertmanager-kube-promethe-alertmanager-overview.yaml create mode 100644 monitor/alertmanager/v1_Secret_alertmanager-alertmanager-kube-promethe-alertmanager.yaml create mode 100644 monitor/alertmanager/v1_ServiceAccount_alertmanager-kube-promethe-alertmanager.yaml create mode 100644 monitor/alerts-containers/datas.tf create mode 100644 monitor/alerts-containers/index.yaml create mode 100644 monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-cpu-usage-seconds.yaml create mode 100644 monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-memory-cache.yaml create mode 100644 monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-memory-rss.yaml create mode 100644 monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-memory-swap.yaml create mode 100644 monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-memory-working-se.yaml create mode 100644 monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-resource.yaml create mode 100644 monitor/alerts-core/datas.tf create mode 100644 monitor/alerts-core/index.yaml create mode 100644 monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-config-reloaders.yaml create mode 100644 monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-general.rules.yaml create mode 100644 monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.pod-owner.yaml create mode 100644 monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-prometheus-general.rules.yaml create mode 100644 monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-prometheus-node-recording.rules.yaml create mode 100644 monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-apps.yaml create mode 100644 monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-resources.yaml create mode 100644 monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-storage.yaml create mode 100644 monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-system-apiserver.yaml create mode 100644 monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-system-kubelet.yaml create mode 100644 monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-system.yaml create mode 100644 monitor/dashboards-cluster/datas.tf create mode 100644 monitor/dashboards-cluster/index.yaml create mode 100644 monitor/dashboards-cluster/v1_ConfigMap_prometheus-community-kube-k8s-resources-cluster.yaml create mode 100644 monitor/dashboards-cluster/v1_ConfigMap_prometheus-community-kube-k8s-resources-multicluster.yaml create mode 100644 monitor/dashboards-minimal/datas.tf create mode 100644 monitor/dashboards-minimal/index.yaml create mode 100644 monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-cluster-total.yaml create mode 100644 monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-grafana-overview.yaml create mode 100644 monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-namespace-by-pod.yaml create mode 100644 monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-namespace-by-workload.yaml create mode 100644 monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-persistentvolumesusage.yaml create mode 100644 monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-pod-total.yaml create mode 100644 monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-workload-total.yaml create mode 100644 monitor/dashboards-namespace/datas.tf create mode 100644 monitor/dashboards-namespace/index.yaml create mode 100644 monitor/dashboards-namespace/v1_ConfigMap_prometheus-community-kube-k8s-resources-namespace.yaml create mode 100644 monitor/dashboards-namespace/v1_ConfigMap_prometheus-community-kube-k8s-resources-workloads-namespace.yaml create mode 100644 monitor/dashboards-workload/datas.tf create mode 100644 monitor/dashboards-workload/index.yaml create mode 100644 monitor/dashboards-workload/v1_ConfigMap_prometheus-community-kube-k8s-resources-node.yaml create mode 100644 monitor/dashboards-workload/v1_ConfigMap_prometheus-community-kube-k8s-resources-pod.yaml create mode 100644 monitor/dashboards-workload/v1_ConfigMap_prometheus-community-kube-k8s-resources-workload.yaml create mode 100644 monitor/grafana/apps_v1_Deployment_grafana.yaml create mode 100644 monitor/grafana/config.tf create mode 100644 monitor/grafana/datas.tf create mode 100644 monitor/grafana/index.yaml create mode 100644 monitor/grafana/monitoring.coreos.com_v1_ServiceMonitor_grafana.yaml create mode 100644 monitor/grafana/presentation.tf create mode 100644 monitor/grafana/rbac.authorization.k8s.io_v1_RoleBinding_grafana.yaml create mode 100644 monitor/grafana/rbac.authorization.k8s.io_v1_Role_grafana.yaml create mode 100644 monitor/grafana/secret.tf create mode 100644 monitor/grafana/v1_ConfigMap_grafana-config-dashboards.yaml create mode 100644 monitor/grafana/v1_PersistentVolumeClaim_grafana.yaml create mode 100644 monitor/grafana/v1_ServiceAccount_grafana.yaml create mode 100644 monitor/grafana/v1_Service_grafana.yaml create mode 100644 monitor/kube-state-metrics/apps_v1_Deployment_kube-state-metrics.yaml create mode 100644 monitor/kube-state-metrics/datas.tf create mode 100644 monitor/kube-state-metrics/index.yaml create mode 100644 monitor/kube-state-metrics/monitoring.coreos.com_v1_PrometheusRule_kube-state-metrics-kube-pr-kube-state-metrics.yaml create mode 100644 monitor/kube-state-metrics/monitoring.coreos.com_v1_ServiceMonitor_kube-state-metrics.yaml create mode 100644 monitor/kube-state-metrics/rbac.authorization.k8s.io_v1_ClusterRoleBinding_kube-state-metrics.yaml create mode 100644 monitor/kube-state-metrics/rbac.authorization.k8s.io_v1_ClusterRole_kube-state-metrics.yaml create mode 100644 monitor/kube-state-metrics/ressources_no_ns.tf create mode 100644 monitor/kube-state-metrics/v1_ServiceAccount_kube-state-metrics.yaml create mode 100644 monitor/kube-state-metrics/v1_Service_kube-state-metrics.yaml create mode 100644 monitor/loki-dashboard/index.yaml create mode 100644 monitor/loki-dashboard/v1_ConfigMap_loki-dashboards-1.yaml create mode 100644 monitor/loki-dashboard/v1_ConfigMap_loki-dashboards-2.yaml create mode 100644 monitor/loki/apps_v1_StatefulSet_loki.yaml create mode 100644 monitor/loki/config.tf create mode 100644 monitor/loki/datas.tf create mode 100644 monitor/loki/index.yaml create mode 100644 monitor/loki/monitoring.coreos.com_v1_PrometheusRule_loki-loki-alerts.yaml create mode 100644 monitor/loki/monitoring.coreos.com_v1_PrometheusRule_loki-loki-rules.yaml create mode 100644 monitor/loki/monitoring.coreos.com_v1_ServiceMonitor_loki.yaml create mode 100644 monitor/loki/v1_ConfigMap_loki-runtime.yaml create mode 100644 monitor/loki/v1_ServiceAccount_loki.yaml create mode 100644 monitor/loki/v1_Service_loki-headless.yaml create mode 100644 monitor/loki/v1_Service_loki-memberlist.yaml create mode 100644 monitor/loki/v1_Service_loki.yaml create mode 100644 monitor/monitor-control-plan/datas.tf create mode 100644 monitor/monitor-control-plan/index.yaml create mode 100644 monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-etcd.yaml create mode 100644 monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-apiserver-availability.rules.yaml create mode 100644 monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-apiserver-burnrate.rules.yaml create mode 100644 monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-apiserver-histogram.rules.yaml create mode 100644 monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-apiserver-slos.yaml create mode 100644 monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-scheduler.rules.yaml create mode 100644 monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-system-controller-manager.yaml create mode 100644 monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-system-scheduler.yaml create mode 100644 monitor/monitor-control-plan/monitoring.coreos.com_v1_ServiceMonitor_prometheus-community-kube-apiserver.yaml create mode 100644 monitor/monitor-control-plan/monitoring.coreos.com_v1_ServiceMonitor_prometheus-community-kube-kube-controller-manager.yaml create mode 100644 monitor/monitor-control-plan/monitoring.coreos.com_v1_ServiceMonitor_prometheus-community-kube-kube-etcd.yaml create mode 100644 monitor/monitor-control-plan/monitoring.coreos.com_v1_ServiceMonitor_prometheus-community-kube-kube-scheduler.yaml create mode 100644 monitor/monitor-control-plan/ressources_no_ns.tf create mode 100644 monitor/monitor-control-plan/v1_ConfigMap_prometheus-community-kube-apiserver.yaml create mode 100644 monitor/monitor-control-plan/v1_ConfigMap_prometheus-community-kube-controller-manager.yaml create mode 100644 monitor/monitor-control-plan/v1_ConfigMap_prometheus-community-kube-etcd.yaml create mode 100644 monitor/monitor-control-plan/v1_ConfigMap_prometheus-community-kube-scheduler.yaml create mode 100644 monitor/monitor-control-plan/v1_Service_prometheus-community-kube-kube-controller-manager.yaml create mode 100644 monitor/monitor-control-plan/v1_Service_prometheus-community-kube-kube-etcd.yaml create mode 100644 monitor/monitor-control-plan/v1_Service_prometheus-community-kube-kube-scheduler.yaml create mode 100644 monitor/node-exporter/apps_v1_DaemonSet_node-exporter-prometheus-node-exporter.yaml create mode 100644 monitor/node-exporter/datas.tf create mode 100644 monitor/node-exporter/index.yaml create mode 100644 monitor/node-exporter/monitoring.coreos.com_v1_PrometheusRule_node-exporter-kube-prometh-node-exporter.rules.yaml create mode 100644 monitor/node-exporter/monitoring.coreos.com_v1_PrometheusRule_node-exporter-kube-prometh-node-exporter.yaml create mode 100644 monitor/node-exporter/monitoring.coreos.com_v1_PrometheusRule_node-exporter-kube-prometh-node-network.yaml create mode 100644 monitor/node-exporter/monitoring.coreos.com_v1_PrometheusRule_node-exporter-kube-prometh-node.rules.yaml create mode 100644 monitor/node-exporter/monitoring.coreos.com_v1_ServiceMonitor_node-exporter-prometheus-node-exporter.yaml create mode 100644 monitor/node-exporter/v1_ConfigMap_node-exporter-kube-prometh-node-cluster-rsrc-use.yaml create mode 100644 monitor/node-exporter/v1_ConfigMap_node-exporter-kube-prometh-node-rsrc-use.yaml create mode 100644 monitor/node-exporter/v1_ConfigMap_node-exporter-kube-prometh-nodes-darwin.yaml create mode 100644 monitor/node-exporter/v1_ConfigMap_node-exporter-kube-prometh-nodes.yaml create mode 100644 monitor/node-exporter/v1_ServiceAccount_node-exporter-prometheus-node-exporter.yaml create mode 100644 monitor/node-exporter/v1_Service_node-exporter-prometheus-node-exporter.yaml create mode 100644 monitor/prometheus/datas.tf create mode 100644 monitor/prometheus/index.yaml create mode 100644 monitor/prometheus/monitoring.coreos.com_v1_PrometheusRule_prometheus-kube-prometheus-kubelet.rules.yaml create mode 100644 monitor/prometheus/monitoring.coreos.com_v1_PrometheusRule_prometheus-kube-prometheus-kubernetes-system-kube-proxy.yaml create mode 100644 monitor/prometheus/monitoring.coreos.com_v1_PrometheusRule_prometheus-kube-prometheus-prometheus.yaml create mode 100644 monitor/prometheus/monitoring.coreos.com_v1_ServiceMonitor_prometheus-kube-prometheus-coredns.yaml create mode 100644 monitor/prometheus/monitoring.coreos.com_v1_ServiceMonitor_prometheus-kube-prometheus-kube-proxy.yaml create mode 100644 monitor/prometheus/monitoring.coreos.com_v1_ServiceMonitor_prometheus-kube-prometheus-kubelet.yaml create mode 100644 monitor/prometheus/monitoring.coreos.com_v1_ServiceMonitor_prometheus-kube-prometheus-prometheus.yaml create mode 100644 monitor/prometheus/presentation.tf create mode 100644 monitor/prometheus/prometheus.tf create mode 100644 monitor/prometheus/rbac.authorization.k8s.io_v1_ClusterRoleBinding_prometheus-kube-prometheus-prometheus.yaml create mode 100644 monitor/prometheus/rbac.authorization.k8s.io_v1_ClusterRole_prometheus-kube-prometheus-prometheus.yaml create mode 100644 monitor/prometheus/ressources_no_ns.tf create mode 100644 monitor/prometheus/svc.tf create mode 100644 monitor/prometheus/v1_ConfigMap_prometheus-kube-prometheus-grafana-datasource.yaml create mode 100644 monitor/prometheus/v1_ConfigMap_prometheus-kube-prometheus-k8s-coredns.yaml create mode 100644 monitor/prometheus/v1_ConfigMap_prometheus-kube-prometheus-kubelet.yaml create mode 100644 monitor/prometheus/v1_ConfigMap_prometheus-kube-prometheus-prometheus.yaml create mode 100644 monitor/prometheus/v1_ConfigMap_prometheus-kube-prometheus-proxy.yaml create mode 100644 monitor/prometheus/v1_Secret_prometheus-kube-prometheus-prometheus.yaml create mode 100644 monitor/prometheus/v1_ServiceAccount_prometheus-kube-prometheus-prometheus.yaml create mode 100644 monitor/prometheus/v1_Service_prometheus-kube-prometheus-coredns.yaml create mode 100644 monitor/prometheus/v1_Service_prometheus-kube-prometheus-kube-proxy.yaml create mode 100644 monitor/promtail/apps_v1_DaemonSet_promtail.yaml create mode 100644 monitor/promtail/config.tf create mode 100644 monitor/promtail/datas.tf create mode 100644 monitor/promtail/index.yaml create mode 100644 monitor/promtail/monitoring.coreos.com_v1_ServiceMonitor_promtail.yaml create mode 100644 monitor/promtail/rbac.authorization.k8s.io_v1_ClusterRoleBinding_promtail.yaml create mode 100644 monitor/promtail/rbac.authorization.k8s.io_v1_ClusterRole_promtail.yaml create mode 100644 monitor/promtail/ressources_no_ns.tf create mode 100644 monitor/promtail/v1_ServiceAccount_promtail.yaml create mode 100644 monitor/promtail/v1_Service_promtail-metrics.yaml diff --git a/monitor/alertmanager/datas.tf b/monitor/alertmanager/datas.tf new file mode 100644 index 0000000..b7cc2bc --- /dev/null +++ b/monitor/alertmanager/datas.tf @@ -0,0 +1,167 @@ +locals { + authentik_url = "http://authentik.${var.domain}-auth.svc" + authentik_token = data.kubernetes_secret_v1.authentik.data["AUTHENTIK_BOOTSTRAP_TOKEN"] + common-labels = { + "vynil.solidite.fr/owner-name" = var.instance + "vynil.solidite.fr/owner-namespace" = var.namespace + "vynil.solidite.fr/owner-category" = var.category + "vynil.solidite.fr/owner-component" = var.component + "app.kubernetes.io/managed-by" = "vynil" + "app.kubernetes.io/instance" = var.instance + } + rb-patch = <<-EOF + - op: replace + path: /subjects/0/namespace + value: "${var.namespace}" + EOF +} + +data "kubernetes_secret_v1" "authentik" { + metadata { + name = "authentik" + namespace = "${var.domain}-auth" + } +} + +data "kustomization_overlay" "data" { + common_labels = local.common-labels + namespace = var.namespace + resources = [for file in fileset(path.module, "*.yaml"): file if file != "index.yaml" && length(regexall("ClusterRole",file))<1] + patches { + target { + kind = "Alertmanager" + name = "alertmanager-kube-promethe-alertmanager" + } + patch = <<-EOF + apiVersion: monitoring.coreos.com/v1 + kind: Alertmanager + metadata: + name: alertmanager-kube-promethe-alertmanager + spec: + image: "${var.images.alertmanager.registry}/${var.images.alertmanager.repository}:${var.images.alertmanager.tag}" + version: ${var.images.alertmanager.tag} + externalUrl: http://${var.component}-${var.instance}.${var.namespace}:9093 + replicas: ${var.replicas} + listenLocal: ${var.listenLocal} + logLevel: "${var.logLevel}" + retention: "${var.retention}" + EOF + } + patches { + target { + kind = "ConfigMap" + name = "alertmanager-kube-grafana-datasource" + } + patch = <<-EOF + apiVersion: v1 + kind: ConfigMap + metadata: + name: alertmanager-operated + data: + datasource.yaml: |- + apiVersion: 1 + datasources: + - name: Alertmanager + type: alertmanager + uid: alertmanager + url: http://${var.component}-${var.instance}.${var.namespace}:9093/ + access: proxy + jsonData: + handleGrafanaManagedAlerts: false + implementation: prometheus + EOF + } + patches { + target { + kind = "ServiceMonitor" + name = "alertmanager-kube-promethe-alertmanager" + } + patch = <<-EOF + - op: replace + path: /spec/namespaceSelector/matchNames/0 + value: "${var.namespace}" + EOF + } + patches { + target { + kind = "PrometheusRule" + name = "alertmanager-kube-promethe-alertmanager.rules" + } + patch = <<-EOF +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: alertmanager-kube-promethe-alertmanager.rules +spec: + groups: + - name: alertmanager.rules + rules: + - alert: AlertmanagerFailedReload + expr: |- + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + max_over_time(alertmanager_config_last_reload_successful{job="alertmanager-kube-promethe-alertmanager",namespace="${var.namespace}"}[5m]) == 0 + - alert: AlertmanagerMembersInconsistent + expr: |- + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + max_over_time(alertmanager_cluster_members{job="alertmanager-kube-promethe-alertmanager",namespace="${var.namespace}"}[5m]) + < on (namespace,service,cluster) group_left + count by (namespace,service,cluster) (max_over_time(alertmanager_cluster_members{job="alertmanager-kube-promethe-alertmanager",namespace="${var.namespace}"}[5m])) + - alert: AlertmanagerFailedToSendAlerts + expr: |- + ( + rate(alertmanager_notifications_failed_total{job="alertmanager-kube-promethe-alertmanager",namespace="${var.namespace}"}[5m]) + / + ignoring (reason) group_left rate(alertmanager_notifications_total{job="alertmanager-kube-promethe-alertmanager",namespace="${var.namespace}"}[5m]) + ) + > 0.01 + - alert: AlertmanagerClusterFailedToSendAlerts + expr: |- + min by (namespace,service, integration) ( + rate(alertmanager_notifications_failed_total{job="alertmanager-kube-promethe-alertmanager",namespace="${var.namespace}", integration=~`.*`}[5m]) + / + ignoring (reason) group_left rate(alertmanager_notifications_total{job="alertmanager-kube-promethe-alertmanager",namespace="${var.namespace}", integration=~`.*`}[5m]) + ) + > 0.01 + - alert: AlertmanagerClusterFailedToSendAlerts + expr: |- + min by (namespace,service, integration) ( + rate(alertmanager_notifications_failed_total{job="alertmanager-kube-promethe-alertmanager",namespace="${var.namespace}", integration!~`.*`}[5m]) + / + ignoring (reason) group_left rate(alertmanager_notifications_total{job="alertmanager-kube-promethe-alertmanager",namespace="${var.namespace}", integration!~`.*`}[5m]) + ) + > 0.01 + - alert: AlertmanagerConfigInconsistent + expr: |- + count by (namespace,service,cluster) ( + count_values by (namespace,service,cluster) ("config_hash", alertmanager_config_hash{job="alertmanager-kube-promethe-alertmanager",namespace="${var.namespace}"}) + ) + != 1 + - alert: AlertmanagerClusterDown + expr: |- + ( + count by (namespace,service,cluster) ( + avg_over_time(up{job="alertmanager-kube-promethe-alertmanager",namespace="${var.namespace}"}[5m]) < 0.5 + ) + / + count by (namespace,service,cluster) ( + up{job="alertmanager-kube-promethe-alertmanager",namespace="${var.namespace}"} + ) + ) + >= 0.5 + - alert: AlertmanagerClusterCrashlooping + expr: |- + ( + count by (namespace,service,cluster) ( + changes(process_start_time_seconds{job="alertmanager-kube-promethe-alertmanager",namespace="${var.namespace}"}[10m]) > 4 + ) + / + count by (namespace,service,cluster) ( + up{job="alertmanager-kube-promethe-alertmanager",namespace="${var.namespace}"} + ) + ) + >= 0.5 + EOF + } +} diff --git a/monitor/alertmanager/index.yaml b/monitor/alertmanager/index.yaml new file mode 100644 index 0000000..9da8129 --- /dev/null +++ b/monitor/alertmanager/index.yaml @@ -0,0 +1,111 @@ +--- +apiVersion: vinyl.solidite.fr/v1beta1 +kind: Component +category: monitor +metadata: + name: alertmanager + description: null +options: + retention: + default: 120h + examples: + - 120h + type: string + ingress_class: + default: traefik + examples: + - traefik + type: string + logLevel: + default: info + examples: + - info + type: string + sub_domain: + default: alertmanager + examples: + - alertmanager + type: string + images: + default: + alertmanager: + pullPolicy: IfNotPresent + registry: quay.io + repository: prometheus/alertmanager + tag: v0.26.0 + examples: + - alertmanager: + pullPolicy: IfNotPresent + registry: quay.io + repository: prometheus/alertmanager + tag: v0.26.0 + properties: + alertmanager: + default: + pullPolicy: IfNotPresent + registry: quay.io + repository: prometheus/alertmanager + tag: v0.26.0 + properties: + pullPolicy: + default: IfNotPresent + enum: + - Always + - Never + - IfNotPresent + type: string + registry: + default: quay.io + type: string + repository: + default: prometheus/alertmanager + type: string + tag: + default: v0.26.0 + type: string + type: object + type: object + domain: + default: your-company + examples: + - your-company + type: string + listenLocal: + default: false + examples: + - false + type: boolean + app_group: + default: monitor + examples: + - monitor + type: string + domain_name: + default: your_company.com + examples: + - your_company.com + type: string + issuer: + default: letsencrypt-prod + examples: + - letsencrypt-prod + type: string + replicas: + default: 1 + examples: + - 1 + type: integer +dependencies: +- dist: null + category: share + component: authentik-forward +providers: + kubernetes: true + authentik: true + kubectl: true + postgresql: null + mysql: null + restapi: true + http: true + gitea: null +tfaddtype: null diff --git a/monitor/alertmanager/monitoring.coreos.com_v1_Alertmanager_alertmanager-kube-promethe-alertmanager.yaml b/monitor/alertmanager/monitoring.coreos.com_v1_Alertmanager_alertmanager-kube-promethe-alertmanager.yaml new file mode 100644 index 0000000..2dc191e --- /dev/null +++ b/monitor/alertmanager/monitoring.coreos.com_v1_Alertmanager_alertmanager-kube-promethe-alertmanager.yaml @@ -0,0 +1,38 @@ +# Source: kube-prometheus-stack/templates/alertmanager/alertmanager.yaml +apiVersion: monitoring.coreos.com/v1 +kind: Alertmanager +metadata: + name: alertmanager-kube-promethe-alertmanager + namespace: vynil-monitor + labels: + app: kube-prometheus-stack-alertmanager + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: alertmanager + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "alertmanager" + heritage: "Helm" +spec: + image: "quay.io/prometheus/alertmanager:v0.26.0" + version: v0.26.0 + replicas: 1 + listenLocal: false + serviceAccountName: alertmanager-kube-promethe-alertmanager + externalUrl: http://alertmanager-kube-promethe-alertmanager.vynil-monitor:9093 + paused: false + logFormat: "logfmt" + logLevel: "info" + retention: "120h" + alertmanagerConfigSelector: {} + alertmanagerConfigNamespaceSelector: {} + routePrefix: "/" + securityContext: + fsGroup: 2000 + runAsGroup: 2000 + runAsNonRoot: true + runAsUser: 1000 + seccompProfile: + type: RuntimeDefault + portName: http-web \ No newline at end of file diff --git a/monitor/alertmanager/monitoring.coreos.com_v1_PrometheusRule_alertmanager-kube-promethe-alertmanager.rules.yaml b/monitor/alertmanager/monitoring.coreos.com_v1_PrometheusRule_alertmanager-kube-promethe-alertmanager.rules.yaml new file mode 100644 index 0000000..3a0d7b7 --- /dev/null +++ b/monitor/alertmanager/monitoring.coreos.com_v1_PrometheusRule_alertmanager-kube-promethe-alertmanager.rules.yaml @@ -0,0 +1,142 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/alertmanager.rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: alertmanager-kube-promethe-alertmanager.rules + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: alertmanager + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "alertmanager" + heritage: "Helm" +spec: + groups: + - name: alertmanager.rules + rules: + - alert: AlertmanagerFailedReload + annotations: + description: Configuration has failed to load for {{ $labels.namespace }}/{{ $labels.pod}}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerfailedreload + summary: Reloading an Alertmanager configuration has failed. + expr: |- + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + max_over_time(alertmanager_config_last_reload_successful{job="alertmanager-kube-promethe-alertmanager",namespace="vynil-monitor"}[5m]) == 0 + for: 10m + labels: + severity: critical + - alert: AlertmanagerMembersInconsistent + annotations: + description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} has only found {{ $value }} members of the {{$labels.job}} cluster. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagermembersinconsistent + summary: A member of an Alertmanager cluster has not found all other cluster members. + expr: |- + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + max_over_time(alertmanager_cluster_members{job="alertmanager-kube-promethe-alertmanager",namespace="vynil-monitor"}[5m]) + < on (namespace,service,cluster) group_left + count by (namespace,service,cluster) (max_over_time(alertmanager_cluster_members{job="alertmanager-kube-promethe-alertmanager",namespace="vynil-monitor"}[5m])) + for: 15m + labels: + severity: critical + - alert: AlertmanagerFailedToSendAlerts + annotations: + description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} failed to send {{ $value | humanizePercentage }} of notifications to {{ $labels.integration }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerfailedtosendalerts + summary: An Alertmanager instance failed to send notifications. + expr: |- + ( + rate(alertmanager_notifications_failed_total{job="alertmanager-kube-promethe-alertmanager",namespace="vynil-monitor"}[5m]) + / + ignoring (reason) group_left rate(alertmanager_notifications_total{job="alertmanager-kube-promethe-alertmanager",namespace="vynil-monitor"}[5m]) + ) + > 0.01 + for: 5m + labels: + severity: warning + - alert: AlertmanagerClusterFailedToSendAlerts + annotations: + description: The minimum notification failure rate to {{ $labels.integration }} sent from any instance in the {{$labels.job}} cluster is {{ $value | humanizePercentage }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclusterfailedtosendalerts + summary: All Alertmanager instances in a cluster failed to send notifications to a critical integration. + expr: |- + min by (namespace,service, integration) ( + rate(alertmanager_notifications_failed_total{job="alertmanager-kube-promethe-alertmanager",namespace="vynil-monitor", integration=~`.*`}[5m]) + / + ignoring (reason) group_left rate(alertmanager_notifications_total{job="alertmanager-kube-promethe-alertmanager",namespace="vynil-monitor", integration=~`.*`}[5m]) + ) + > 0.01 + for: 5m + labels: + severity: critical + - alert: AlertmanagerClusterFailedToSendAlerts + annotations: + description: The minimum notification failure rate to {{ $labels.integration }} sent from any instance in the {{$labels.job}} cluster is {{ $value | humanizePercentage }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclusterfailedtosendalerts + summary: All Alertmanager instances in a cluster failed to send notifications to a non-critical integration. + expr: |- + min by (namespace,service, integration) ( + rate(alertmanager_notifications_failed_total{job="alertmanager-kube-promethe-alertmanager",namespace="vynil-monitor", integration!~`.*`}[5m]) + / + ignoring (reason) group_left rate(alertmanager_notifications_total{job="alertmanager-kube-promethe-alertmanager",namespace="vynil-monitor", integration!~`.*`}[5m]) + ) + > 0.01 + for: 5m + labels: + severity: warning + - alert: AlertmanagerConfigInconsistent + annotations: + description: Alertmanager instances within the {{$labels.job}} cluster have different configurations. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerconfiginconsistent + summary: Alertmanager instances within the same cluster have different configurations. + expr: |- + count by (namespace,service,cluster) ( + count_values by (namespace,service,cluster) ("config_hash", alertmanager_config_hash{job="alertmanager-kube-promethe-alertmanager",namespace="vynil-monitor"}) + ) + != 1 + for: 20m + labels: + severity: critical + - alert: AlertmanagerClusterDown + annotations: + description: '{{ $value | humanizePercentage }} of Alertmanager instances within the {{$labels.job}} cluster have been up for less than half of the last 5m.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclusterdown + summary: Half or more of the Alertmanager instances within the same cluster are down. + expr: |- + ( + count by (namespace,service,cluster) ( + avg_over_time(up{job="alertmanager-kube-promethe-alertmanager",namespace="vynil-monitor"}[5m]) < 0.5 + ) + / + count by (namespace,service,cluster) ( + up{job="alertmanager-kube-promethe-alertmanager",namespace="vynil-monitor"} + ) + ) + >= 0.5 + for: 5m + labels: + severity: critical + - alert: AlertmanagerClusterCrashlooping + annotations: + description: '{{ $value | humanizePercentage }} of Alertmanager instances within the {{$labels.job}} cluster have restarted at least 5 times in the last 10m.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclustercrashlooping + summary: Half or more of the Alertmanager instances within the same cluster are crashlooping. + expr: |- + ( + count by (namespace,service,cluster) ( + changes(process_start_time_seconds{job="alertmanager-kube-promethe-alertmanager",namespace="vynil-monitor"}[10m]) > 4 + ) + / + count by (namespace,service,cluster) ( + up{job="alertmanager-kube-promethe-alertmanager",namespace="vynil-monitor"} + ) + ) + >= 0.5 + for: 5m + labels: + severity: critical \ No newline at end of file diff --git a/monitor/alertmanager/monitoring.coreos.com_v1_ServiceMonitor_alertmanager-kube-promethe-alertmanager.yaml b/monitor/alertmanager/monitoring.coreos.com_v1_ServiceMonitor_alertmanager-kube-promethe-alertmanager.yaml new file mode 100644 index 0000000..140f473 --- /dev/null +++ b/monitor/alertmanager/monitoring.coreos.com_v1_ServiceMonitor_alertmanager-kube-promethe-alertmanager.yaml @@ -0,0 +1,33 @@ +# Source: kube-prometheus-stack/templates/alertmanager/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: alertmanager-kube-promethe-alertmanager + namespace: vynil-monitor + labels: + app: kube-prometheus-stack-alertmanager + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: alertmanager + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "alertmanager" + heritage: "Helm" +spec: + + selector: + matchLabels: + app: kube-prometheus-stack-alertmanager + release: "alertmanager" + self-monitor: "true" + namespaceSelector: + matchNames: + - "vynil-monitor" + endpoints: + - port: http-web + enableHttp2: true + path: "/metrics" + - port: reloader-web + scheme: http + path: "/metrics" \ No newline at end of file diff --git a/monitor/alertmanager/presentation.tf b/monitor/alertmanager/presentation.tf new file mode 100644 index 0000000..6e2aa81 --- /dev/null +++ b/monitor/alertmanager/presentation.tf @@ -0,0 +1,75 @@ +locals { + dns_name = "${var.sub_domain}.${var.domain_name}" + dns_names = [local.dns_name] + app_name = var.component == var.instance ? var.instance : format("%s-%s", var.component, var.instance) + icon = "favicon.ico" + request_headers = { + "Content-Type" = "application/json" + Authorization = "Bearer ${data.kubernetes_secret_v1.authentik.data["AUTHENTIK_BOOTSTRAP_TOKEN"]}" + } + service = { + "name" = "alertmanager-operated" + "port" = { + "number" = 9093 + } + } +} + +module "ingress" { + source = "git::https://git.solidite.fr/vynil/kydah-modules.git//ingress" + component = "" + instance = var.instance + namespace = var.namespace + issuer = var.issuer + ingress_class = var.ingress_class + labels = local.common-labels + dns_names = local.dns_names + middlewares = [module.forward.middleware] + services = [local.service] + providers = { + kubectl = kubectl + } +} + +module "application" { + source = "git::https://git.solidite.fr/vynil/kydah-modules.git//application" + component = var.component + instance = var.instance + app_group = var.app_group + dns_name = local.dns_name + icon = local.icon + protocol_provider = module.forward.provider-id + providers = { + authentik = authentik + } +} + +provider "restapi" { + uri = "http://authentik.${var.domain}-auth.svc/api/v3/" + headers = local.request_headers + create_method = "PATCH" + update_method = "PATCH" + destroy_method = "PATCH" + write_returns_object = true + id_attribute = "name" +} + +module "forward" { + source = "git::https://git.solidite.fr/vynil/kydah-modules.git//forward" + component = var.component + instance = var.instance + domain = var.domain + namespace = var.namespace + ingress_class = var.ingress_class + labels = local.common-labels + dns_names = local.dns_names + service = local.service + icon = local.icon + request_headers = local.request_headers + providers = { + restapi = restapi + http = http + kubectl = kubectl + authentik = authentik + } +} diff --git a/monitor/alertmanager/svc.tf b/monitor/alertmanager/svc.tf new file mode 100644 index 0000000..c5220bb --- /dev/null +++ b/monitor/alertmanager/svc.tf @@ -0,0 +1,33 @@ +locals { + svc-label = merge(local.common-labels, { + "app" = "kube-prometheus-stack-prometheus" + "release" = "prometheus" + "self-monitor" = "true" + + }) +} +resource "kubectl_manifest" "svc" { + yaml_body = <<-EOF + apiVersion: v1 + kind: Service + metadata: + name: "${var.component}-${var.instance}" + namespace: "${var.namespace}" + labels: ${jsonencode(local.svc-label)} + spec: + ports: + - name: http-web + port: 9093 + targetPort: 9093 + protocol: TCP + - name: reloader-web + appProtocol: http + port: 8080 + targetPort: reloader-web + selector: + app.kubernetes.io/name: alertmanager + alertmanager: alertmanager-kube-promethe-alertmanager + sessionAffinity: None + type: "ClusterIP" + EOF +} diff --git a/monitor/alertmanager/v1_ConfigMap_alertmanager-kube-grafana-datasource.yaml b/monitor/alertmanager/v1_ConfigMap_alertmanager-kube-grafana-datasource.yaml new file mode 100644 index 0000000..be5fdf9 --- /dev/null +++ b/monitor/alertmanager/v1_ConfigMap_alertmanager-kube-grafana-datasource.yaml @@ -0,0 +1,19 @@ +apiVersion: v1 +kind: ConfigMap +metadata: + name: alertmanager-kube-grafana-datasource + labels: + grafana_datasource: "1" + app: alertmanager +data: + datasource.yaml: |- + apiVersion: 1 + datasources: + - name: Alertmanager + type: alertmanager + uid: alertmanager + url: http://alertmanager-operated.vynil-monitor:9093/ + access: proxy + jsonData: + handleGrafanaManagedAlerts: false + implementation: prometheus \ No newline at end of file diff --git a/monitor/alertmanager/v1_ConfigMap_alertmanager-kube-promethe-alertmanager-overview.yaml b/monitor/alertmanager/v1_ConfigMap_alertmanager-kube-promethe-alertmanager-overview.yaml new file mode 100644 index 0000000..d100e5f --- /dev/null +++ b/monitor/alertmanager/v1_ConfigMap_alertmanager-kube-promethe-alertmanager-overview.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/alertmanager-overview.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: alertmanager-kube-promethe-alertmanager-overview + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: alertmanager + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "alertmanager" + heritage: "Helm" +data: + alertmanager-overview.json: |- + {"__inputs":[],"__requires":[],"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":1,"hideControls":false,"id":null,"links":[],"refresh":"30s","rows":[{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","description":"current set of alerts stored in the Alertmanager","fill":1,"fillGradient":0,"gridPos":{},"id":2,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(alertmanager_alerts{namespace=~\"$namespace\",service=~\"$service\"}) by (namespace,service,instance)","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Alerts","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"none","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"none","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","description":"rate of successful and invalid alerts received by the Alertmanager","fill":1,"fillGradient":0,"gridPos":{},"id":3,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(rate(alertmanager_alerts_received_total{namespace=~\"$namespace\",service=~\"$service\"}[$__rate_interval])) by (namespace,service,instance)","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} Received","refId":"A"},{"expr":"sum(rate(alertmanager_alerts_invalid_total{namespace=~\"$namespace\",service=~\"$service\"}[$__rate_interval])) by (namespace,service,instance)","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} Invalid","refId":"B"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Alerts receive rate","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Alerts","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","description":"rate of successful and invalid notifications sent by the Alertmanager","fill":1,"fillGradient":0,"gridPos":{},"id":4,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":"integration","seriesOverrides":[],"spaceLength":10,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(rate(alertmanager_notifications_total{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (integration,namespace,service,instance)","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} Total","refId":"A"},{"expr":"sum(rate(alertmanager_notifications_failed_total{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (integration,namespace,service,instance)","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} Failed","refId":"B"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"$integration: Notifications Send Rate","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","description":"latency of notifications sent by the Alertmanager","fill":1,"fillGradient":0,"gridPos":{},"id":5,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":"integration","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99,\n sum(rate(alertmanager_notification_latency_seconds_bucket{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (le,namespace,service,instance)\n) \n","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} 99th Percentile","refId":"A"},{"expr":"histogram_quantile(0.50,\n sum(rate(alertmanager_notification_latency_seconds_bucket{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (le,namespace,service,instance)\n) \n","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} Median","refId":"B"},{"expr":"sum(rate(alertmanager_notification_latency_seconds_sum{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (namespace,service,instance)\n/\nsum(rate(alertmanager_notification_latency_seconds_count{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (namespace,service,instance)\n","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} Average","refId":"C"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"$integration: Notification Duration","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Notifications","titleSize":"h6","type":"row"}],"schemaVersion":14,"style":"dark","tags":["alertmanager-mixin"],"templating":{"list":[{"current":{"text":"Prometheus","value":"Prometheus"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{"text":"","value":""},"datasource":"$datasource","hide":0,"includeAll":false,"label":"namespace","multi":false,"name":"namespace","options":[],"query":"label_values(alertmanager_alerts, namespace)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{"text":"","value":""},"datasource":"$datasource","hide":0,"includeAll":false,"label":"service","multi":false,"name":"service","options":[],"query":"label_values(alertmanager_alerts, service)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{"text":"all","value":"$__all"},"datasource":"$datasource","hide":2,"includeAll":true,"label":null,"multi":false,"name":"integration","options":[],"query":"label_values(alertmanager_notifications_total{integration=~\".*\"}, integration)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Alertmanager / Overview","uid":"alertmanager-overview","version":0} \ No newline at end of file diff --git a/monitor/alertmanager/v1_Secret_alertmanager-alertmanager-kube-promethe-alertmanager.yaml b/monitor/alertmanager/v1_Secret_alertmanager-alertmanager-kube-promethe-alertmanager.yaml new file mode 100644 index 0000000..16d9bbb --- /dev/null +++ b/monitor/alertmanager/v1_Secret_alertmanager-alertmanager-kube-promethe-alertmanager.yaml @@ -0,0 +1,18 @@ +# Source: kube-prometheus-stack/templates/alertmanager/secret.yaml +apiVersion: v1 +kind: Secret +metadata: + name: alertmanager-alertmanager-kube-promethe-alertmanager + namespace: vynil-monitor + labels: + app: kube-prometheus-stack-alertmanager + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: alertmanager + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "alertmanager" + heritage: "Helm" +data: + alertmanager.yaml: "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" \ No newline at end of file diff --git a/monitor/alertmanager/v1_ServiceAccount_alertmanager-kube-promethe-alertmanager.yaml b/monitor/alertmanager/v1_ServiceAccount_alertmanager-kube-promethe-alertmanager.yaml new file mode 100644 index 0000000..bc12630 --- /dev/null +++ b/monitor/alertmanager/v1_ServiceAccount_alertmanager-kube-promethe-alertmanager.yaml @@ -0,0 +1,20 @@ +--- +# Source: kube-prometheus-stack/templates/alertmanager/serviceaccount.yaml +apiVersion: v1 +kind: ServiceAccount +metadata: + name: alertmanager-kube-promethe-alertmanager + namespace: vynil-monitor + labels: + app: kube-prometheus-stack-alertmanager + app.kubernetes.io/name: kube-prometheus-stack-alertmanager + app.kubernetes.io/component: alertmanager + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: alertmanager + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "alertmanager" + heritage: "Helm" +automountServiceAccountToken: true \ No newline at end of file diff --git a/monitor/alerts-containers/datas.tf b/monitor/alerts-containers/datas.tf new file mode 100644 index 0000000..9797980 --- /dev/null +++ b/monitor/alerts-containers/datas.tf @@ -0,0 +1,16 @@ +locals { + common-labels = { + "vynil.solidite.fr/owner-name" = var.instance + "vynil.solidite.fr/owner-namespace" = var.namespace + "vynil.solidite.fr/owner-category" = var.category + "vynil.solidite.fr/owner-component" = var.component + "app.kubernetes.io/managed-by" = "vynil" + "app.kubernetes.io/instance" = var.instance + } +} + +data "kustomization_overlay" "data" { + common_labels = local.common-labels + namespace = var.namespace + resources = [for file in fileset(path.module, "*.yaml"): file if file != "index.yaml"] +} diff --git a/monitor/alerts-containers/index.yaml b/monitor/alerts-containers/index.yaml new file mode 100644 index 0000000..0539038 --- /dev/null +++ b/monitor/alerts-containers/index.yaml @@ -0,0 +1,24 @@ +--- +apiVersion: vinyl.solidite.fr/v1beta1 +kind: Component +category: monitor +metadata: + name: alerts-containers + description: null +options: + useless: + default: true + examples: + - true + type: boolean +dependencies: [] +providers: + kubernetes: true + authentik: null + kubectl: true + postgresql: null + mysql: null + restapi: null + http: null + gitea: null +tfaddtype: null diff --git a/monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-cpu-usage-seconds.yaml b/monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-cpu-usage-seconds.yaml new file mode 100644 index 0000000..17e81db --- /dev/null +++ b/monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-cpu-usage-seconds.yaml @@ -0,0 +1,28 @@ +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.container_cpu_usage_seconds_total.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-k8s.rules.container-cpu-usage-seconds + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: k8s.rules.container_cpu_usage_seconds_total + rules: + - expr: |- + sum by (cluster, namespace, pod, container) ( + irate(container_cpu_usage_seconds_total{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}[5m]) + ) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) ( + 1, max by (cluster, namespace, pod, node) (kube_pod_info{node!=""}) + ) + record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate \ No newline at end of file diff --git a/monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-memory-cache.yaml b/monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-memory-cache.yaml new file mode 100644 index 0000000..b7a7f9d --- /dev/null +++ b/monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-memory-cache.yaml @@ -0,0 +1,26 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.container_memory_cache.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-k8s.rules.container-memory-cache + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: k8s.rules.container_memory_cache + rules: + - expr: |- + container_memory_cache{job="kubelet", metrics_path="/metrics/cadvisor", image!=""} + * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (1, + max by (cluster, namespace, pod, node) (kube_pod_info{node!=""}) + ) + record: node_namespace_pod_container:container_memory_cache \ No newline at end of file diff --git a/monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-memory-rss.yaml b/monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-memory-rss.yaml new file mode 100644 index 0000000..b804bdf --- /dev/null +++ b/monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-memory-rss.yaml @@ -0,0 +1,26 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.container_memory_rss.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-k8s.rules.container-memory-rss + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: k8s.rules.container_memory_rss + rules: + - expr: |- + container_memory_rss{job="kubelet", metrics_path="/metrics/cadvisor", image!=""} + * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (1, + max by (cluster, namespace, pod, node) (kube_pod_info{node!=""}) + ) + record: node_namespace_pod_container:container_memory_rss \ No newline at end of file diff --git a/monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-memory-swap.yaml b/monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-memory-swap.yaml new file mode 100644 index 0000000..547bd9b --- /dev/null +++ b/monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-memory-swap.yaml @@ -0,0 +1,26 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.container_memory_swap.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-k8s.rules.container-memory-swap + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: k8s.rules.container_memory_swap + rules: + - expr: |- + container_memory_swap{job="kubelet", metrics_path="/metrics/cadvisor", image!=""} + * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (1, + max by (cluster, namespace, pod, node) (kube_pod_info{node!=""}) + ) + record: node_namespace_pod_container:container_memory_swap \ No newline at end of file diff --git a/monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-memory-working-se.yaml b/monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-memory-working-se.yaml new file mode 100644 index 0000000..adbaefe --- /dev/null +++ b/monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-memory-working-se.yaml @@ -0,0 +1,26 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.container_memory_working_set_bytes.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-k8s.rules.container-memory-working-se + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: k8s.rules.container_memory_working_set_bytes + rules: + - expr: |- + container_memory_working_set_bytes{job="kubelet", metrics_path="/metrics/cadvisor", image!=""} + * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (1, + max by (cluster, namespace, pod, node) (kube_pod_info{node!=""}) + ) + record: node_namespace_pod_container:container_memory_working_set_bytes \ No newline at end of file diff --git a/monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-resource.yaml b/monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-resource.yaml new file mode 100644 index 0000000..f798aa2 --- /dev/null +++ b/monitor/alerts-containers/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.container-resource.yaml @@ -0,0 +1,88 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.container_resource.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-k8s.rules.container-resource + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: k8s.rules.container_resource + rules: + - expr: |- + kube_pod_container_resource_requests{resource="memory",job="kube-state-metrics"} * on (namespace, pod, cluster) + group_left() max by (namespace, pod, cluster) ( + (kube_pod_status_phase{phase=~"Pending|Running"} == 1) + ) + record: cluster:namespace:pod_memory:active:kube_pod_container_resource_requests + - expr: |- + sum by (namespace, cluster) ( + sum by (namespace, pod, cluster) ( + max by (namespace, pod, container, cluster) ( + kube_pod_container_resource_requests{resource="memory",job="kube-state-metrics"} + ) * on (namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( + kube_pod_status_phase{phase=~"Pending|Running"} == 1 + ) + ) + ) + record: namespace_memory:kube_pod_container_resource_requests:sum + - expr: |- + kube_pod_container_resource_requests{resource="cpu",job="kube-state-metrics"} * on (namespace, pod, cluster) + group_left() max by (namespace, pod, cluster) ( + (kube_pod_status_phase{phase=~"Pending|Running"} == 1) + ) + record: cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests + - expr: |- + sum by (namespace, cluster) ( + sum by (namespace, pod, cluster) ( + max by (namespace, pod, container, cluster) ( + kube_pod_container_resource_requests{resource="cpu",job="kube-state-metrics"} + ) * on (namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( + kube_pod_status_phase{phase=~"Pending|Running"} == 1 + ) + ) + ) + record: namespace_cpu:kube_pod_container_resource_requests:sum + - expr: |- + kube_pod_container_resource_limits{resource="memory",job="kube-state-metrics"} * on (namespace, pod, cluster) + group_left() max by (namespace, pod, cluster) ( + (kube_pod_status_phase{phase=~"Pending|Running"} == 1) + ) + record: cluster:namespace:pod_memory:active:kube_pod_container_resource_limits + - expr: |- + sum by (namespace, cluster) ( + sum by (namespace, pod, cluster) ( + max by (namespace, pod, container, cluster) ( + kube_pod_container_resource_limits{resource="memory",job="kube-state-metrics"} + ) * on (namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( + kube_pod_status_phase{phase=~"Pending|Running"} == 1 + ) + ) + ) + record: namespace_memory:kube_pod_container_resource_limits:sum + - expr: |- + kube_pod_container_resource_limits{resource="cpu",job="kube-state-metrics"} * on (namespace, pod, cluster) + group_left() max by (namespace, pod, cluster) ( + (kube_pod_status_phase{phase=~"Pending|Running"} == 1) + ) + record: cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits + - expr: |- + sum by (namespace, cluster) ( + sum by (namespace, pod, cluster) ( + max by (namespace, pod, container, cluster) ( + kube_pod_container_resource_limits{resource="cpu",job="kube-state-metrics"} + ) * on (namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( + kube_pod_status_phase{phase=~"Pending|Running"} == 1 + ) + ) + ) + record: namespace_cpu:kube_pod_container_resource_limits:sum \ No newline at end of file diff --git a/monitor/alerts-core/datas.tf b/monitor/alerts-core/datas.tf new file mode 100644 index 0000000..9797980 --- /dev/null +++ b/monitor/alerts-core/datas.tf @@ -0,0 +1,16 @@ +locals { + common-labels = { + "vynil.solidite.fr/owner-name" = var.instance + "vynil.solidite.fr/owner-namespace" = var.namespace + "vynil.solidite.fr/owner-category" = var.category + "vynil.solidite.fr/owner-component" = var.component + "app.kubernetes.io/managed-by" = "vynil" + "app.kubernetes.io/instance" = var.instance + } +} + +data "kustomization_overlay" "data" { + common_labels = local.common-labels + namespace = var.namespace + resources = [for file in fileset(path.module, "*.yaml"): file if file != "index.yaml"] +} diff --git a/monitor/alerts-core/index.yaml b/monitor/alerts-core/index.yaml new file mode 100644 index 0000000..445c7ef --- /dev/null +++ b/monitor/alerts-core/index.yaml @@ -0,0 +1,24 @@ +--- +apiVersion: vinyl.solidite.fr/v1beta1 +kind: Component +category: monitor +metadata: + name: alerts-core + description: null +options: + useless: + default: true + examples: + - true + type: boolean +dependencies: [] +providers: + kubernetes: true + authentik: null + kubectl: true + postgresql: null + mysql: null + restapi: null + http: null + gitea: null +tfaddtype: null diff --git a/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-config-reloaders.yaml b/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-config-reloaders.yaml new file mode 100644 index 0000000..6cb4803 --- /dev/null +++ b/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-config-reloaders.yaml @@ -0,0 +1,32 @@ +--- +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/config-reloaders.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-config-reloaders + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: config-reloaders + rules: + - alert: ConfigReloaderSidecarErrors + annotations: + description: 'Errors encountered while the {{$labels.pod}} config-reloader sidecar attempts to sync config in {{$labels.namespace}} namespace. + + As a result, configuration for service running in {{$labels.pod}} may be stale and cannot be updated anymore.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/configreloadersidecarerrors + summary: config-reloader sidecar has not had a successful reload for 10m + expr: max_over_time(reloader_last_reload_successful{namespace=~".+"}[5m]) == 0 + for: 10m + labels: + severity: warning \ No newline at end of file diff --git a/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-general.rules.yaml b/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-general.rules.yaml new file mode 100644 index 0000000..9d9a381 --- /dev/null +++ b/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-general.rules.yaml @@ -0,0 +1,67 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/general.rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-general.rules + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: general.rules + rules: + - alert: TargetDown + annotations: + description: '{{ printf "%.4g" $value }}% of the {{ $labels.job }}/{{ $labels.service }} targets in {{ $labels.namespace }} namespace are down.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/targetdown + summary: One or more targets are unreachable. + expr: 100 * (count(up == 0) BY (cluster, job, namespace, service) / count(up) BY (cluster, job, namespace, service)) > 10 + for: 10m + labels: + severity: warning + - alert: Watchdog + annotations: + description: 'This is an alert meant to ensure that the entire alerting pipeline is functional. + + This alert is always firing, therefore it should always be firing in Alertmanager + + and always fire against a receiver. There are integrations with various notification + + mechanisms that send a notification when this alert is not firing. For example the + + "DeadMansSnitch" integration in PagerDuty. + + ' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/watchdog + summary: An alert that should always be firing to certify that Alertmanager is working properly. + expr: vector(1) + labels: + severity: none + - alert: InfoInhibitor + annotations: + description: 'This is an alert that is used to inhibit info alerts. + + By themselves, the info-level alerts are sometimes very noisy, but they are relevant when combined with + + other alerts. + + This alert fires whenever there''s a severity="info" alert, and stops firing when another alert with a + + severity of ''warning'' or ''critical'' starts firing on the same namespace. + + This alert should be routed to a null receiver and configured to inhibit alerts with severity="info". + + ' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/infoinhibitor + summary: Info-level alert inhibition. + expr: ALERTS{severity = "info"} == 1 unless on (namespace) ALERTS{alertname != "InfoInhibitor", severity =~ "warning|critical", alertstate="firing"} == 1 + labels: + severity: none \ No newline at end of file diff --git a/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.pod-owner.yaml b/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.pod-owner.yaml new file mode 100644 index 0000000..0971db0 --- /dev/null +++ b/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-k8s.rules.pod-owner.yaml @@ -0,0 +1,67 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/k8s.rules.pod_owner.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-k8s.rules.pod-owner + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: k8s.rules.pod_owner + rules: + - expr: |- + max by (cluster, namespace, workload, pod) ( + label_replace( + label_replace( + kube_pod_owner{job="kube-state-metrics", owner_kind="ReplicaSet"}, + "replicaset", "$1", "owner_name", "(.*)" + ) * on (replicaset, namespace) group_left(owner_name) topk by (replicaset, namespace) ( + 1, max by (replicaset, namespace, owner_name) ( + kube_replicaset_owner{job="kube-state-metrics"} + ) + ), + "workload", "$1", "owner_name", "(.*)" + ) + ) + labels: + workload_type: deployment + record: namespace_workload_pod:kube_pod_owner:relabel + - expr: |- + max by (cluster, namespace, workload, pod) ( + label_replace( + kube_pod_owner{job="kube-state-metrics", owner_kind="DaemonSet"}, + "workload", "$1", "owner_name", "(.*)" + ) + ) + labels: + workload_type: daemonset + record: namespace_workload_pod:kube_pod_owner:relabel + - expr: |- + max by (cluster, namespace, workload, pod) ( + label_replace( + kube_pod_owner{job="kube-state-metrics", owner_kind="StatefulSet"}, + "workload", "$1", "owner_name", "(.*)" + ) + ) + labels: + workload_type: statefulset + record: namespace_workload_pod:kube_pod_owner:relabel + - expr: |- + max by (cluster, namespace, workload, pod) ( + label_replace( + kube_pod_owner{job="kube-state-metrics", owner_kind="Job"}, + "workload", "$1", "owner_name", "(.*)" + ) + ) + labels: + workload_type: job + record: namespace_workload_pod:kube_pod_owner:relabel \ No newline at end of file diff --git a/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-prometheus-general.rules.yaml b/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-prometheus-general.rules.yaml new file mode 100644 index 0000000..f7c1d99 --- /dev/null +++ b/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-prometheus-general.rules.yaml @@ -0,0 +1,24 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-prometheus-general.rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-kube-prometheus-general.rules + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: kube-prometheus-general.rules + rules: + - expr: count without(instance, pod, node) (up == 1) + record: count:up1 + - expr: count without(instance, pod, node) (up == 0) + record: count:up0 \ No newline at end of file diff --git a/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-prometheus-node-recording.rules.yaml b/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-prometheus-node-recording.rules.yaml new file mode 100644 index 0000000..74c92c8 --- /dev/null +++ b/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-prometheus-node-recording.rules.yaml @@ -0,0 +1,32 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-prometheus-node-recording.rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-kube-prometheus-node-recording.rules + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: kube-prometheus-node-recording.rules + rules: + - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[3m])) BY (instance) + record: instance:node_cpu:rate:sum + - expr: sum(rate(node_network_receive_bytes_total[3m])) BY (instance) + record: instance:node_network_receive_bytes:rate:sum + - expr: sum(rate(node_network_transmit_bytes_total[3m])) BY (instance) + record: instance:node_network_transmit_bytes:rate:sum + - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m])) WITHOUT (cpu, mode) / ON(instance) GROUP_LEFT() count(sum(node_cpu_seconds_total) BY (instance, cpu)) BY (instance) + record: instance:node_cpu:ratio + - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m])) + record: cluster:node_cpu:sum_rate5m + - expr: cluster:node_cpu:sum_rate5m / count(sum(node_cpu_seconds_total) BY (instance, cpu)) + record: cluster:node_cpu:ratio \ No newline at end of file diff --git a/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-apps.yaml b/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-apps.yaml new file mode 100644 index 0000000..438101a --- /dev/null +++ b/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-apps.yaml @@ -0,0 +1,258 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-apps.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-kubernetes-apps + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: kubernetes-apps + rules: + - alert: KubePodCrashLooping + annotations: + description: 'Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) is in waiting state (reason: "CrashLoopBackOff").' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepodcrashlooping + summary: Pod is crash looping. + expr: max_over_time(kube_pod_container_status_waiting_reason{reason="CrashLoopBackOff", job="kube-state-metrics", namespace=~".*"}[5m]) >= 1 + for: 15m + labels: + severity: warning + - alert: KubePodNotReady + annotations: + description: Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready state for longer than 15 minutes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepodnotready + summary: Pod has been in a non-ready state for more than 15 minutes. + expr: |- + sum by (namespace, pod, cluster) ( + max by (namespace, pod, cluster) ( + kube_pod_status_phase{job="kube-state-metrics", namespace=~".*", phase=~"Pending|Unknown|Failed"} + ) * on (namespace, pod, cluster) group_left(owner_kind) topk by (namespace, pod, cluster) ( + 1, max by (namespace, pod, owner_kind, cluster) (kube_pod_owner{owner_kind!="Job"}) + ) + ) > 0 + for: 15m + labels: + severity: warning + - alert: KubeDeploymentGenerationMismatch + annotations: + description: Deployment generation for {{ $labels.namespace }}/{{ $labels.deployment }} does not match, this indicates that the Deployment has failed but has not been rolled back. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentgenerationmismatch + summary: Deployment generation mismatch due to possible roll-back + expr: |- + kube_deployment_status_observed_generation{job="kube-state-metrics", namespace=~".*"} + != + kube_deployment_metadata_generation{job="kube-state-metrics", namespace=~".*"} + for: 15m + labels: + severity: warning + - alert: KubeDeploymentReplicasMismatch + annotations: + description: Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has not matched the expected number of replicas for longer than 15 minutes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentreplicasmismatch + summary: Deployment has not matched the expected number of replicas. + expr: |- + ( + kube_deployment_spec_replicas{job="kube-state-metrics", namespace=~".*"} + > + kube_deployment_status_replicas_available{job="kube-state-metrics", namespace=~".*"} + ) and ( + changes(kube_deployment_status_replicas_updated{job="kube-state-metrics", namespace=~".*"}[10m]) + == + 0 + ) + for: 15m + labels: + severity: warning + - alert: KubeDeploymentRolloutStuck + annotations: + description: Rollout of deployment {{ $labels.namespace }}/{{ $labels.deployment }} is not progressing for longer than 15 minutes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentrolloutstuck + summary: Deployment rollout is not progressing. + expr: |- + kube_deployment_status_condition{condition="Progressing", status="false",job="kube-state-metrics", namespace=~".*"} + != 0 + for: 15m + labels: + severity: warning + - alert: KubeStatefulSetReplicasMismatch + annotations: + description: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has not matched the expected number of replicas for longer than 15 minutes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetreplicasmismatch + summary: StatefulSet has not matched the expected number of replicas. + expr: |- + ( + kube_statefulset_status_replicas_ready{job="kube-state-metrics", namespace=~".*"} + != + kube_statefulset_status_replicas{job="kube-state-metrics", namespace=~".*"} + ) and ( + changes(kube_statefulset_status_replicas_updated{job="kube-state-metrics", namespace=~".*"}[10m]) + == + 0 + ) + for: 15m + labels: + severity: warning + - alert: KubeStatefulSetGenerationMismatch + annotations: + description: StatefulSet generation for {{ $labels.namespace }}/{{ $labels.statefulset }} does not match, this indicates that the StatefulSet has failed but has not been rolled back. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetgenerationmismatch + summary: StatefulSet generation mismatch due to possible roll-back + expr: |- + kube_statefulset_status_observed_generation{job="kube-state-metrics", namespace=~".*"} + != + kube_statefulset_metadata_generation{job="kube-state-metrics", namespace=~".*"} + for: 15m + labels: + severity: warning + - alert: KubeStatefulSetUpdateNotRolledOut + annotations: + description: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} update has not been rolled out. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetupdatenotrolledout + summary: StatefulSet update has not been rolled out. + expr: |- + ( + max without (revision) ( + kube_statefulset_status_current_revision{job="kube-state-metrics", namespace=~".*"} + unless + kube_statefulset_status_update_revision{job="kube-state-metrics", namespace=~".*"} + ) + * + ( + kube_statefulset_replicas{job="kube-state-metrics", namespace=~".*"} + != + kube_statefulset_status_replicas_updated{job="kube-state-metrics", namespace=~".*"} + ) + ) and ( + changes(kube_statefulset_status_replicas_updated{job="kube-state-metrics", namespace=~".*"}[5m]) + == + 0 + ) + for: 15m + labels: + severity: warning + - alert: KubeDaemonSetRolloutStuck + annotations: + description: DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} has not finished or progressed for at least 15 minutes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetrolloutstuck + summary: DaemonSet rollout is stuck. + expr: |- + ( + ( + kube_daemonset_status_current_number_scheduled{job="kube-state-metrics", namespace=~".*"} + != + kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics", namespace=~".*"} + ) or ( + kube_daemonset_status_number_misscheduled{job="kube-state-metrics", namespace=~".*"} + != + 0 + ) or ( + kube_daemonset_status_updated_number_scheduled{job="kube-state-metrics", namespace=~".*"} + != + kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics", namespace=~".*"} + ) or ( + kube_daemonset_status_number_available{job="kube-state-metrics", namespace=~".*"} + != + kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics", namespace=~".*"} + ) + ) and ( + changes(kube_daemonset_status_updated_number_scheduled{job="kube-state-metrics", namespace=~".*"}[5m]) + == + 0 + ) + for: 15m + labels: + severity: warning + - alert: KubeContainerWaiting + annotations: + description: pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container {{ $labels.container}} has been in waiting state for longer than 1 hour. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecontainerwaiting + summary: Pod container waiting longer than 1 hour + expr: sum by (namespace, pod, container, cluster) (kube_pod_container_status_waiting_reason{job="kube-state-metrics", namespace=~".*"}) > 0 + for: 1h + labels: + severity: warning + - alert: KubeDaemonSetNotScheduled + annotations: + description: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are not scheduled.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetnotscheduled + summary: DaemonSet pods are not scheduled. + expr: |- + kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics", namespace=~".*"} + - + kube_daemonset_status_current_number_scheduled{job="kube-state-metrics", namespace=~".*"} > 0 + for: 10m + labels: + severity: warning + - alert: KubeDaemonSetMisScheduled + annotations: + description: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are running where they are not supposed to run.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetmisscheduled + summary: DaemonSet pods are misscheduled. + expr: kube_daemonset_status_number_misscheduled{job="kube-state-metrics", namespace=~".*"} > 0 + for: 15m + labels: + severity: warning + - alert: KubeJobNotCompleted + annotations: + description: Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more than {{ "43200" | humanizeDuration }} to complete. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubejobnotcompleted + summary: Job did not complete in time + expr: |- + time() - max by (namespace, job_name, cluster) (kube_job_status_start_time{job="kube-state-metrics", namespace=~".*"} + and + kube_job_status_active{job="kube-state-metrics", namespace=~".*"} > 0) > 43200 + labels: + severity: warning + - alert: KubeJobFailed + annotations: + description: Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete. Removing failed job after investigation should clear this alert. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubejobfailed + summary: Job failed to complete. + expr: kube_job_failed{job="kube-state-metrics", namespace=~".*"} > 0 + for: 15m + labels: + severity: warning + - alert: KubeHpaReplicasMismatch + annotations: + description: HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has not matched the desired number of replicas for longer than 15 minutes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubehpareplicasmismatch + summary: HPA has not matched desired number of replicas. + expr: |- + (kube_horizontalpodautoscaler_status_desired_replicas{job="kube-state-metrics", namespace=~".*"} + != + kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics", namespace=~".*"}) + and + (kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics", namespace=~".*"} + > + kube_horizontalpodautoscaler_spec_min_replicas{job="kube-state-metrics", namespace=~".*"}) + and + (kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics", namespace=~".*"} + < + kube_horizontalpodautoscaler_spec_max_replicas{job="kube-state-metrics", namespace=~".*"}) + and + changes(kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics", namespace=~".*"}[15m]) == 0 + for: 15m + labels: + severity: warning + - alert: KubeHpaMaxedOut + annotations: + description: HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has been running at max replicas for longer than 15 minutes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubehpamaxedout + summary: HPA is running at max replicas + expr: |- + kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics", namespace=~".*"} + == + kube_horizontalpodautoscaler_spec_max_replicas{job="kube-state-metrics", namespace=~".*"} + for: 15m + labels: + severity: warning \ No newline at end of file diff --git a/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-resources.yaml b/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-resources.yaml new file mode 100644 index 0000000..ddb895b --- /dev/null +++ b/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-resources.yaml @@ -0,0 +1,122 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-resources.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-kubernetes-resources + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: kubernetes-resources + rules: + - alert: KubeCPUOvercommit + annotations: + description: Cluster {{ $labels.cluster }} has overcommitted CPU resource requests for Pods by {{ $value }} CPU shares and cannot tolerate node failure. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuovercommit + summary: Cluster has overcommitted CPU resource requests. + expr: |- + sum(namespace_cpu:kube_pod_container_resource_requests:sum{job="kube-state-metrics",}) by (cluster) - (sum(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster) - max(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster)) > 0 + and + (sum(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster) - max(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster)) > 0 + for: 10m + labels: + severity: warning + - alert: KubeMemoryOvercommit + annotations: + description: Cluster {{ $labels.cluster }} has overcommitted memory resource requests for Pods by {{ $value | humanize }} bytes and cannot tolerate node failure. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryovercommit + summary: Cluster has overcommitted memory resource requests. + expr: |- + sum(namespace_memory:kube_pod_container_resource_requests:sum{}) by (cluster) - (sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster) - max(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster)) > 0 + and + (sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster) - max(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster)) > 0 + for: 10m + labels: + severity: warning + - alert: KubeCPUQuotaOvercommit + annotations: + description: Cluster {{ $labels.cluster }} has overcommitted CPU resource requests for Namespaces. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuquotaovercommit + summary: Cluster has overcommitted CPU resource requests. + expr: |- + sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(cpu|requests.cpu)"})) by (cluster) + / + sum(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"}) by (cluster) + > 1.5 + for: 5m + labels: + severity: warning + - alert: KubeMemoryQuotaOvercommit + annotations: + description: Cluster {{ $labels.cluster }} has overcommitted memory resource requests for Namespaces. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryquotaovercommit + summary: Cluster has overcommitted memory resource requests. + expr: |- + sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(memory|requests.memory)"})) by (cluster) + / + sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster) + > 1.5 + for: 5m + labels: + severity: warning + - alert: KubeQuotaAlmostFull + annotations: + description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaalmostfull + summary: Namespace quota is going to be full. + expr: |- + kube_resourcequota{job="kube-state-metrics", type="used"} + / ignoring(instance, job, type) + (kube_resourcequota{job="kube-state-metrics", type="hard"} > 0) + > 0.9 < 1 + for: 15m + labels: + severity: info + - alert: KubeQuotaFullyUsed + annotations: + description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotafullyused + summary: Namespace quota is fully used. + expr: |- + kube_resourcequota{job="kube-state-metrics", type="used"} + / ignoring(instance, job, type) + (kube_resourcequota{job="kube-state-metrics", type="hard"} > 0) + == 1 + for: 15m + labels: + severity: info + - alert: KubeQuotaExceeded + annotations: + description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaexceeded + summary: Namespace quota has exceeded the limits. + expr: |- + kube_resourcequota{job="kube-state-metrics", type="used"} + / ignoring(instance, job, type) + (kube_resourcequota{job="kube-state-metrics", type="hard"} > 0) + > 1 + for: 15m + labels: + severity: warning + - alert: CPUThrottlingHigh + annotations: + description: '{{ $value | humanizePercentage }} throttling of CPU in namespace {{ $labels.namespace }} for container {{ $labels.container }} in pod {{ $labels.pod }}.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/cputhrottlinghigh + summary: Processes experience elevated CPU throttling. + expr: |- + sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by (cluster, container, pod, namespace) + / + sum(increase(container_cpu_cfs_periods_total{}[5m])) by (cluster, container, pod, namespace) + > ( 25 / 100 ) + for: 15m + labels: + severity: info \ No newline at end of file diff --git a/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-storage.yaml b/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-storage.yaml new file mode 100644 index 0000000..9cc5f63 --- /dev/null +++ b/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-storage.yaml @@ -0,0 +1,113 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-storage.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-kubernetes-storage + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: kubernetes-storage + rules: + - alert: KubePersistentVolumeFillingUp + annotations: + description: The PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} on Cluster {{ $labels.cluster }} is only {{ $value | humanizePercentage }} free. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumefillingup + summary: PersistentVolume is filling up. + expr: |- + ( + kubelet_volume_stats_available_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"} + / + kubelet_volume_stats_capacity_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"} + ) < 0.03 + and + kubelet_volume_stats_used_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"} > 0 + unless on (cluster, namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1 + unless on (cluster, namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1 + for: 1m + labels: + severity: critical + - alert: KubePersistentVolumeFillingUp + annotations: + description: Based on recent sampling, the PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} on Cluster {{ $labels.cluster }} is expected to fill up within four days. Currently {{ $value | humanizePercentage }} is available. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumefillingup + summary: PersistentVolume is filling up. + expr: |- + ( + kubelet_volume_stats_available_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"} + / + kubelet_volume_stats_capacity_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"} + ) < 0.15 + and + kubelet_volume_stats_used_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"} > 0 + and + predict_linear(kubelet_volume_stats_available_bytes{job="kubelet", namespace=~".*", metrics_path="/metrics"}[6h], 4 * 24 * 3600) < 0 + unless on (cluster, namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1 + unless on (cluster, namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1 + for: 1h + labels: + severity: warning + - alert: KubePersistentVolumeInodesFillingUp + annotations: + description: The PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} on Cluster {{ $labels.cluster }} only has {{ $value | humanizePercentage }} free inodes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumeinodesfillingup + summary: PersistentVolumeInodes are filling up. + expr: |- + ( + kubelet_volume_stats_inodes_free{job="kubelet", namespace=~".*", metrics_path="/metrics"} + / + kubelet_volume_stats_inodes{job="kubelet", namespace=~".*", metrics_path="/metrics"} + ) < 0.03 + and + kubelet_volume_stats_inodes_used{job="kubelet", namespace=~".*", metrics_path="/metrics"} > 0 + unless on (cluster, namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1 + unless on (cluster, namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1 + for: 1m + labels: + severity: critical + - alert: KubePersistentVolumeInodesFillingUp + annotations: + description: Based on recent sampling, the PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} on Cluster {{ $labels.cluster }} is expected to run out of inodes within four days. Currently {{ $value | humanizePercentage }} of its inodes are free. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumeinodesfillingup + summary: PersistentVolumeInodes are filling up. + expr: |- + ( + kubelet_volume_stats_inodes_free{job="kubelet", namespace=~".*", metrics_path="/metrics"} + / + kubelet_volume_stats_inodes{job="kubelet", namespace=~".*", metrics_path="/metrics"} + ) < 0.15 + and + kubelet_volume_stats_inodes_used{job="kubelet", namespace=~".*", metrics_path="/metrics"} > 0 + and + predict_linear(kubelet_volume_stats_inodes_free{job="kubelet", namespace=~".*", metrics_path="/metrics"}[6h], 4 * 24 * 3600) < 0 + unless on (cluster, namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1 + unless on (cluster, namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1 + for: 1h + labels: + severity: warning + - alert: KubePersistentVolumeErrors + annotations: + description: The persistent volume {{ $labels.persistentvolume }} on Cluster {{ $labels.cluster }} has status {{ $labels.phase }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumeerrors + summary: PersistentVolume is having issues with provisioning. + expr: kube_persistentvolume_status_phase{phase=~"Failed|Pending",job="kube-state-metrics"} > 0 + for: 5m + labels: + severity: critical \ No newline at end of file diff --git a/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-system-apiserver.yaml b/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-system-apiserver.yaml new file mode 100644 index 0000000..d045348 --- /dev/null +++ b/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-system-apiserver.yaml @@ -0,0 +1,64 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-apiserver.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-kubernetes-system-apiserver + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: kubernetes-system-apiserver + rules: + - alert: KubeClientCertificateExpiration + annotations: + description: A client certificate used to authenticate to kubernetes apiserver is expiring in less than 7.0 days. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclientcertificateexpiration + summary: Client certificate is about to expire. + expr: apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and on (job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 604800 + for: 5m + labels: + severity: warning + - alert: KubeClientCertificateExpiration + annotations: + description: A client certificate used to authenticate to kubernetes apiserver is expiring in less than 24.0 hours. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclientcertificateexpiration + summary: Client certificate is about to expire. + expr: apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and on (job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 86400 + for: 5m + labels: + severity: critical + - alert: KubeAggregatedAPIErrors + annotations: + description: Kubernetes aggregated API {{ $labels.name }}/{{ $labels.namespace }} has reported errors. It has appeared unavailable {{ $value | humanize }} times averaged over the past 10m. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeaggregatedapierrors + summary: Kubernetes aggregated API has reported errors. + expr: sum by (name, namespace, cluster)(increase(aggregator_unavailable_apiservice_total{job="apiserver"}[10m])) > 4 + labels: + severity: warning + - alert: KubeAggregatedAPIDown + annotations: + description: Kubernetes aggregated API {{ $labels.name }}/{{ $labels.namespace }} has been only {{ $value | humanize }}% available over the last 10m. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeaggregatedapidown + summary: Kubernetes aggregated API is down. + expr: (1 - max by (name, namespace, cluster)(avg_over_time(aggregator_unavailable_apiservice{job="apiserver"}[10m]))) * 100 < 85 + for: 5m + labels: + severity: warning + - alert: KubeAPITerminatedRequests + annotations: + description: The kubernetes apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapiterminatedrequests + summary: The kubernetes apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests. + expr: sum(rate(apiserver_request_terminations_total{job="apiserver"}[10m])) / ( sum(rate(apiserver_request_total{job="apiserver"}[10m])) + sum(rate(apiserver_request_terminations_total{job="apiserver"}[10m])) ) > 0.20 + for: 5m + labels: + severity: warning \ No newline at end of file diff --git a/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-system-kubelet.yaml b/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-system-kubelet.yaml new file mode 100644 index 0000000..11f25da --- /dev/null +++ b/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-system-kubelet.yaml @@ -0,0 +1,140 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-kubelet.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-kubernetes-system-kubelet + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: kubernetes-system-kubelet + rules: + - alert: KubeNodeNotReady + annotations: + description: '{{ $labels.node }} has been unready for more than 15 minutes.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodenotready + summary: Node is not ready. + expr: kube_node_status_condition{job="kube-state-metrics",condition="Ready",status="true"} == 0 + for: 15m + labels: + severity: warning + - alert: KubeNodeUnreachable + annotations: + description: '{{ $labels.node }} is unreachable and some workloads may be rescheduled.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodeunreachable + summary: Node is unreachable. + expr: (kube_node_spec_taint{job="kube-state-metrics",key="node.kubernetes.io/unreachable",effect="NoSchedule"} unless ignoring(key,value) kube_node_spec_taint{job="kube-state-metrics",key=~"ToBeDeletedByClusterAutoscaler|cloud.google.com/impending-node-termination|aws-node-termination-handler/spot-itn"}) == 1 + for: 15m + labels: + severity: warning + - alert: KubeletTooManyPods + annotations: + description: Kubelet '{{ $labels.node }}' is running at {{ $value | humanizePercentage }} of its Pod capacity. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubelettoomanypods + summary: Kubelet is running at capacity. + expr: |- + count by (cluster, node) ( + (kube_pod_status_phase{job="kube-state-metrics",phase="Running"} == 1) * on (instance,pod,namespace,cluster) group_left(node) topk by (instance,pod,namespace,cluster) (1, kube_pod_info{job="kube-state-metrics"}) + ) + / + max by (cluster, node) ( + kube_node_status_capacity{job="kube-state-metrics",resource="pods"} != 1 + ) > 0.95 + for: 15m + labels: + severity: info + - alert: KubeNodeReadinessFlapping + annotations: + description: The readiness status of node {{ $labels.node }} has changed {{ $value }} times in the last 15 minutes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodereadinessflapping + summary: Node readiness status is flapping. + expr: sum(changes(kube_node_status_condition{job="kube-state-metrics",status="true",condition="Ready"}[15m])) by (cluster, node) > 2 + for: 15m + labels: + severity: warning + - alert: KubeletPlegDurationHigh + annotations: + description: The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{ $value }} seconds on node {{ $labels.node }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletplegdurationhigh + summary: Kubelet Pod Lifecycle Event Generator is taking too long to relist. + expr: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile{quantile="0.99"} >= 10 + for: 5m + labels: + severity: warning + - alert: KubeletPodStartUpLatencyHigh + annotations: + description: Kubelet Pod startup 99th percentile latency is {{ $value }} seconds on node {{ $labels.node }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletpodstartuplatencyhigh + summary: Kubelet Pod startup latency is too high. + expr: histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le)) * on (cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"} > 60 + for: 15m + labels: + severity: warning + - alert: KubeletClientCertificateExpiration + annotations: + description: Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificateexpiration + summary: Kubelet client certificate is about to expire. + expr: kubelet_certificate_manager_client_ttl_seconds < 604800 + labels: + severity: warning + - alert: KubeletClientCertificateExpiration + annotations: + description: Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificateexpiration + summary: Kubelet client certificate is about to expire. + expr: kubelet_certificate_manager_client_ttl_seconds < 86400 + labels: + severity: critical + - alert: KubeletServerCertificateExpiration + annotations: + description: Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificateexpiration + summary: Kubelet server certificate is about to expire. + expr: kubelet_certificate_manager_server_ttl_seconds < 604800 + labels: + severity: warning + - alert: KubeletServerCertificateExpiration + annotations: + description: Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificateexpiration + summary: Kubelet server certificate is about to expire. + expr: kubelet_certificate_manager_server_ttl_seconds < 86400 + labels: + severity: critical + - alert: KubeletClientCertificateRenewalErrors + annotations: + description: Kubelet on node {{ $labels.node }} has failed to renew its client certificate ({{ $value | humanize }} errors in the last 5 minutes). + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificaterenewalerrors + summary: Kubelet has failed to renew its client certificate. + expr: increase(kubelet_certificate_manager_client_expiration_renew_errors[5m]) > 0 + for: 15m + labels: + severity: warning + - alert: KubeletServerCertificateRenewalErrors + annotations: + description: Kubelet on node {{ $labels.node }} has failed to renew its server certificate ({{ $value | humanize }} errors in the last 5 minutes). + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificaterenewalerrors + summary: Kubelet has failed to renew its server certificate. + expr: increase(kubelet_server_expiration_renew_errors[5m]) > 0 + for: 15m + labels: + severity: warning + - alert: KubeletDown + annotations: + description: Kubelet has disappeared from Prometheus target discovery. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletdown + summary: Target disappeared from Prometheus target discovery. + expr: absent(up{job="kubelet", metrics_path="/metrics"} == 1) + for: 15m + labels: + severity: critical \ No newline at end of file diff --git a/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-system.yaml b/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-system.yaml new file mode 100644 index 0000000..754b847 --- /dev/null +++ b/monitor/alerts-core/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-system.yaml @@ -0,0 +1,42 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-kubernetes-system + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: kubernetes-system + rules: + - alert: KubeVersionMismatch + annotations: + description: There are {{ $value }} different semantic versions of Kubernetes components running. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeversionmismatch + summary: Different semantic versions of Kubernetes components running. + expr: count by (cluster) (count by (git_version, cluster) (label_replace(kubernetes_build_info{job!~"kube-dns|coredns"},"git_version","$1","git_version","(v[0-9]*.[0-9]*).*"))) > 1 + for: 15m + labels: + severity: warning + - alert: KubeClientErrors + annotations: + description: Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance }}' is experiencing {{ $value | humanizePercentage }} errors.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclienterrors + summary: Kubernetes API server client is experiencing errors. + expr: |- + (sum(rate(rest_client_requests_total{job="apiserver",code=~"5.."}[5m])) by (cluster, instance, job, namespace) + / + sum(rate(rest_client_requests_total{job="apiserver"}[5m])) by (cluster, instance, job, namespace)) + > 0.01 + for: 15m + labels: + severity: warning \ No newline at end of file diff --git a/monitor/dashboards-cluster/datas.tf b/monitor/dashboards-cluster/datas.tf new file mode 100644 index 0000000..9797980 --- /dev/null +++ b/monitor/dashboards-cluster/datas.tf @@ -0,0 +1,16 @@ +locals { + common-labels = { + "vynil.solidite.fr/owner-name" = var.instance + "vynil.solidite.fr/owner-namespace" = var.namespace + "vynil.solidite.fr/owner-category" = var.category + "vynil.solidite.fr/owner-component" = var.component + "app.kubernetes.io/managed-by" = "vynil" + "app.kubernetes.io/instance" = var.instance + } +} + +data "kustomization_overlay" "data" { + common_labels = local.common-labels + namespace = var.namespace + resources = [for file in fileset(path.module, "*.yaml"): file if file != "index.yaml"] +} diff --git a/monitor/dashboards-cluster/index.yaml b/monitor/dashboards-cluster/index.yaml new file mode 100644 index 0000000..dc3f31d --- /dev/null +++ b/monitor/dashboards-cluster/index.yaml @@ -0,0 +1,24 @@ +--- +apiVersion: vinyl.solidite.fr/v1beta1 +kind: Component +category: monitor +metadata: + name: dashboards-cluster + description: null +options: + useless: + default: true + examples: + - true + type: boolean +dependencies: [] +providers: + kubernetes: true + authentik: null + kubectl: true + postgresql: null + mysql: null + restapi: null + http: null + gitea: null +tfaddtype: null diff --git a/monitor/dashboards-cluster/v1_ConfigMap_prometheus-community-kube-k8s-resources-cluster.yaml b/monitor/dashboards-cluster/v1_ConfigMap_prometheus-community-kube-k8s-resources-cluster.yaml new file mode 100644 index 0000000..bab2795 --- /dev/null +++ b/monitor/dashboards-cluster/v1_ConfigMap_prometheus-community-kube-k8s-resources-cluster.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-cluster.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: prometheus-community-kube-k8s-resources-cluster + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +data: + k8s-resources-cluster.json: |- + {"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"links":[],"refresh":"10s","rows":[{"collapse":false,"height":"100px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"format":"percentunit","id":1,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":2,"stack":false,"steppedLine":false,"targets":[{"expr":"cluster:node_cpu:ratio_rate5m{cluster=\"$cluster\"}","format":"time_series","instant":true,"refId":"A"}],"thresholds":"70,80","timeFrom":null,"timeShift":null,"title":"CPU Utilisation","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"singlestat","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"format":"percentunit","id":2,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":2,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"cpu\",cluster=\"$cluster\"})","format":"time_series","instant":true,"refId":"A"}],"thresholds":"70,80","timeFrom":null,"timeShift":null,"title":"CPU Requests Commitment","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"singlestat","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"format":"percentunit","id":3,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":2,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"cpu\",cluster=\"$cluster\"})","format":"time_series","instant":true,"refId":"A"}],"thresholds":"70,80","timeFrom":null,"timeShift":null,"title":"CPU Limits Commitment","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"singlestat","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"format":"percentunit","id":4,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":2,"stack":false,"steppedLine":false,"targets":[{"expr":"1 - sum(:node_memory_MemAvailable_bytes:sum{cluster=\"$cluster\"}) / sum(node_memory_MemTotal_bytes{job=\"node-exporter\",cluster=\"$cluster\"})","format":"time_series","instant":true,"refId":"A"}],"thresholds":"70,80","timeFrom":null,"timeShift":null,"title":"Memory Utilisation","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"singlestat","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"format":"percentunit","id":5,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":2,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"memory\",cluster=\"$cluster\"})","format":"time_series","instant":true,"refId":"A"}],"thresholds":"70,80","timeFrom":null,"timeShift":null,"title":"Memory Requests Commitment","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"singlestat","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"format":"percentunit","id":6,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":2,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"memory\",cluster=\"$cluster\"})","format":"time_series","instant":true,"refId":"A"}],"thresholds":"70,80","timeFrom":null,"timeShift":null,"title":"Memory Limits Commitment","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"singlestat","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Headlines","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":7,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace)","format":"time_series","legendFormat":"{{namespace}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Usage","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"CPU","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":8,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"Pods","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":0,"link":true,"linkTargetBlank":false,"linkTooltip":"Drill down to pods","linkUrl":"/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=${__data.fields.namespace}","pattern":"Value #A","thresholds":[],"type":"number","unit":"short"},{"alias":"Workloads","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":0,"link":true,"linkTargetBlank":false,"linkTooltip":"Drill down to workloads","linkUrl":"/d/a87fb0d919ec0ea5f6543124e16c42a5/k8s-resources-workloads-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=${__data.fields.namespace}","pattern":"Value #B","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Usage","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Requests","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Requests %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"CPU Limits","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #F","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Limits %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #G","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"Namespace","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":true,"linkTargetBlank":false,"linkTooltip":"Drill down to pods","linkUrl":"/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=${__value.text}","pattern":"namespace","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"sum(kube_pod_owner{job=\"kube-state-metrics\", cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"count(avg(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)","format":"table","instant":true,"legendFormat":"","refId":"B"},{"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true,"legendFormat":"","refId":"C"},{"expr":"sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true,"legendFormat":"","refId":"D"},{"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace) / sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true,"legendFormat":"","refId":"E"},{"expr":"sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true,"legendFormat":"","refId":"F"},{"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace) / sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true,"legendFormat":"","refId":"G"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Quota","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"CPU Quota","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":9,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace)","format":"time_series","legendFormat":"{{namespace}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory Usage (w/o cache)","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Memory","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":10,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"Pods","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":0,"link":true,"linkTargetBlank":false,"linkTooltip":"Drill down to pods","linkUrl":"/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=${__data.fields.namespace}","pattern":"Value #A","thresholds":[],"type":"number","unit":"short"},{"alias":"Workloads","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":0,"link":true,"linkTargetBlank":false,"linkTooltip":"Drill down to workloads","linkUrl":"/d/a87fb0d919ec0ea5f6543124e16c42a5/k8s-resources-workloads-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=${__data.fields.namespace}","pattern":"Value #B","thresholds":[],"type":"number","unit":"short"},{"alias":"Memory Usage","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Requests","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Requests %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"Memory Limits","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #F","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Limits %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #G","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"Namespace","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":true,"linkTargetBlank":false,"linkTooltip":"Drill down to pods","linkUrl":"/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=${__value.text}","pattern":"namespace","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"sum(kube_pod_owner{job=\"kube-state-metrics\", cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"count(avg(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)","format":"table","instant":true,"legendFormat":"","refId":"B"},{"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace)","format":"table","instant":true,"legendFormat":"","refId":"C"},{"expr":"sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true,"legendFormat":"","refId":"D"},{"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace) / sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true,"legendFormat":"","refId":"E"},{"expr":"sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true,"legendFormat":"","refId":"F"},{"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace) / sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)","format":"table","instant":true,"legendFormat":"","refId":"G"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Requests by Namespace","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Memory Requests","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":11,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"Current Receive Bandwidth","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Current Transmit Bandwidth","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Rate of Received Packets","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"pps"},{"alias":"Rate of Transmitted Packets","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"pps"},{"alias":"Rate of Received Packets Dropped","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"pps"},{"alias":"Rate of Transmitted Packets Dropped","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #F","thresholds":[],"type":"number","unit":"pps"},{"alias":"Namespace","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":true,"linkTargetBlank":false,"linkTooltip":"Drill down to pods","linkUrl":"/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=${__value.text}","pattern":"namespace","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"table","instant":true,"legendFormat":"","refId":"B"},{"expr":"sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"table","instant":true,"legendFormat":"","refId":"C"},{"expr":"sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"table","instant":true,"legendFormat":"","refId":"D"},{"expr":"sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"table","instant":true,"legendFormat":"","refId":"E"},{"expr":"sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"table","instant":true,"legendFormat":"","refId":"F"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Current Network Usage","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Current Network Usage","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":12,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"time_series","legendFormat":"{{namespace}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Receive Bandwidth","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":13,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"time_series","legendFormat":"{{namespace}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Transmit Bandwidth","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Bandwidth","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":14,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"avg(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"time_series","legendFormat":"{{namespace}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Average Container Bandwidth by Namespace: Received","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":15,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"avg(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"time_series","legendFormat":"{{namespace}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Average Container Bandwidth by Namespace: Transmitted","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Average Container Bandwidth by Namespace","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":16,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"time_series","legendFormat":"{{namespace}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Received Packets","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":17,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"time_series","legendFormat":"{{namespace}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Transmitted Packets","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Rate of Packets","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":18,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"time_series","legendFormat":"{{namespace}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Received Packets Dropped","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":19,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)","format":"time_series","legendFormat":"{{namespace}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Transmitted Packets Dropped","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Rate of Packets Dropped","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","decimals":null,"fill":10,"id":20,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"ceil(sum by(namespace) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval])))","format":"time_series","legendFormat":"{{namespace}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"IOPS(Reads+Writes)","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":21,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))","format":"time_series","legendFormat":"{{namespace}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"ThroughPut(Read+Write)","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Storage IO","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":22,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"sort":{"col":4,"desc":true},"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"IOPS(Reads)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":3,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"number","unit":"iops"},{"alias":"IOPS(Writes)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":3,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"iops"},{"alias":"IOPS(Reads + Writes)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":3,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"iops"},{"alias":"Throughput(Read)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Throughput(Write)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Throughput(Read + Write)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #F","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Namespace","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":true,"linkTargetBlank":false,"linkTooltip":"Drill down to pods","linkUrl":"/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=${__value.text}","pattern":"namespace","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"sum by(namespace) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"sum by(namespace) (rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))","format":"table","instant":true,"legendFormat":"","refId":"B"},{"expr":"sum by(namespace) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))","format":"table","instant":true,"legendFormat":"","refId":"C"},{"expr":"sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))","format":"table","instant":true,"legendFormat":"","refId":"D"},{"expr":"sum by(namespace) (rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))","format":"table","instant":true,"legendFormat":"","refId":"E"},{"expr":"sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))","format":"table","instant":true,"legendFormat":"","refId":"F"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Current Storage IO","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Storage IO - Distribution","titleSize":"h6"}],"schemaVersion":14,"style":"dark","tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{"text":"","value":""},"datasource":"$datasource","hide":2,"includeAll":false,"label":null,"multi":false,"name":"cluster","options":[],"query":"label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Kubernetes / Compute Resources / Cluster","uid":"efa86fd1d0c121a26444b636a3f509a8","version":0} \ No newline at end of file diff --git a/monitor/dashboards-cluster/v1_ConfigMap_prometheus-community-kube-k8s-resources-multicluster.yaml b/monitor/dashboards-cluster/v1_ConfigMap_prometheus-community-kube-k8s-resources-multicluster.yaml new file mode 100644 index 0000000..44b6567 --- /dev/null +++ b/monitor/dashboards-cluster/v1_ConfigMap_prometheus-community-kube-k8s-resources-multicluster.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-multicluster.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: prometheus-community-kube-k8s-resources-multicluster + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +data: + k8s-resources-multicluster.json: |- + {"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"links":[],"refresh":"10s","rows":[{"collapse":false,"height":"100px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"format":"percentunit","id":1,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":2,"stack":false,"steppedLine":false,"targets":[{"expr":"cluster:node_cpu:ratio_rate5m","format":"time_series","instant":true,"refId":"A"}],"thresholds":"70,80","timeFrom":null,"timeShift":null,"title":"CPU Utilisation","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"singlestat","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"format":"percentunit","id":2,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":2,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"cpu\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\", resource=\"cpu\"})","format":"time_series","instant":true,"refId":"A"}],"thresholds":"70,80","timeFrom":null,"timeShift":null,"title":"CPU Requests Commitment","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"singlestat","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"format":"percentunit","id":3,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":2,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"cpu\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\", resource=\"cpu\"})","format":"time_series","instant":true,"refId":"A"}],"thresholds":"70,80","timeFrom":null,"timeShift":null,"title":"CPU Limits Commitment","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"singlestat","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"format":"percentunit","id":4,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":2,"stack":false,"steppedLine":false,"targets":[{"expr":"1 - sum(:node_memory_MemAvailable_bytes:sum) / sum(node_memory_MemTotal_bytes{job=\"node-exporter\"})","format":"time_series","instant":true,"refId":"A"}],"thresholds":"70,80","timeFrom":null,"timeShift":null,"title":"Memory Utilisation","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"singlestat","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"format":"percentunit","id":5,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":2,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"memory\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\", resource=\"memory\"})","format":"time_series","instant":true,"refId":"A"}],"thresholds":"70,80","timeFrom":null,"timeShift":null,"title":"Memory Requests Commitment","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"singlestat","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"format":"percentunit","id":6,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":2,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"memory\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\", resource=\"memory\"})","format":"time_series","instant":true,"refId":"A"}],"thresholds":"70,80","timeFrom":null,"timeShift":null,"title":"Memory Limits Commitment","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"singlestat","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Headlines","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":0,"id":7,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate) by (cluster)","format":"time_series","legendFormat":"{{cluster}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Usage","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"CPU","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":8,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"CPU Usage","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Requests","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Requests %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"CPU Limits","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Limits %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"Cluster","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":true,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"/d/efa86fd1d0c121a26444b636a3f509a8/k8s-resources-cluster?var-datasource=$datasource&var-cluster=${__value.text}","pattern":"cluster","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate) by (cluster)","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"cpu\"}) by (cluster)","format":"table","instant":true,"legendFormat":"","refId":"B"},{"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate) by (cluster) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"cpu\"}) by (cluster)","format":"table","instant":true,"legendFormat":"","refId":"C"},{"expr":"sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"cpu\"}) by (cluster)","format":"table","instant":true,"legendFormat":"","refId":"D"},{"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate) by (cluster) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"cpu\"}) by (cluster)","format":"table","instant":true,"legendFormat":"","refId":"E"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Quota","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"CPU Quota","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":0,"id":9,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\"}) by (cluster)","format":"time_series","legendFormat":"{{cluster}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory Usage (w/o cache)","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Memory","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":10,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"Memory Usage","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Requests","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Requests %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"Memory Limits","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Limits %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"Cluster","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":true,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"/d/efa86fd1d0c121a26444b636a3f509a8/k8s-resources-cluster?var-datasource=$datasource&var-cluster=${__value.text}","pattern":"cluster","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\"}) by (cluster)","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"memory\"}) by (cluster)","format":"table","instant":true,"legendFormat":"","refId":"B"},{"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\"}) by (cluster) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"memory\"}) by (cluster)","format":"table","instant":true,"legendFormat":"","refId":"C"},{"expr":"sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"memory\"}) by (cluster)","format":"table","instant":true,"legendFormat":"","refId":"D"},{"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\"}) by (cluster) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"memory\"}) by (cluster)","format":"table","instant":true,"legendFormat":"","refId":"E"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Requests by Cluster","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Memory Requests","titleSize":"h6"}],"schemaVersion":14,"style":"dark","tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Kubernetes / Compute Resources / Multi-Cluster","uid":"b59e6c9f2fcbe2e16d77fc492374cc4f","version":0} \ No newline at end of file diff --git a/monitor/dashboards-minimal/datas.tf b/monitor/dashboards-minimal/datas.tf new file mode 100644 index 0000000..9797980 --- /dev/null +++ b/monitor/dashboards-minimal/datas.tf @@ -0,0 +1,16 @@ +locals { + common-labels = { + "vynil.solidite.fr/owner-name" = var.instance + "vynil.solidite.fr/owner-namespace" = var.namespace + "vynil.solidite.fr/owner-category" = var.category + "vynil.solidite.fr/owner-component" = var.component + "app.kubernetes.io/managed-by" = "vynil" + "app.kubernetes.io/instance" = var.instance + } +} + +data "kustomization_overlay" "data" { + common_labels = local.common-labels + namespace = var.namespace + resources = [for file in fileset(path.module, "*.yaml"): file if file != "index.yaml"] +} diff --git a/monitor/dashboards-minimal/index.yaml b/monitor/dashboards-minimal/index.yaml new file mode 100644 index 0000000..5441c1e --- /dev/null +++ b/monitor/dashboards-minimal/index.yaml @@ -0,0 +1,24 @@ +--- +apiVersion: vinyl.solidite.fr/v1beta1 +kind: Component +category: monitor +metadata: + name: dashboards-minimal + description: null +options: + useless: + default: true + examples: + - true + type: boolean +dependencies: [] +providers: + kubernetes: true + authentik: null + kubectl: true + postgresql: null + mysql: null + restapi: null + http: null + gitea: null +tfaddtype: null diff --git a/monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-cluster-total.yaml b/monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-cluster-total.yaml new file mode 100644 index 0000000..1b8c6e7 --- /dev/null +++ b/monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-cluster-total.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/cluster-total.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: prometheus-community-kube-cluster-total + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +data: + cluster-total.json: |- + {"__inputs":[],"__requires":[],"annotations":{"list":[{"builtIn":1,"datasource":"-- Grafana --","enable":true,"hide":true,"iconColor":"rgba(0, 211, 255, 1)","name":"Annotations & Alerts","type":"dashboard"}]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"id":null,"links":[],"panels":[{"collapse":false,"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":0},"id":2,"panels":[],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Current Bandwidth","titleSize":"h6","type":"row"},{"aliasColors":{},"bars":true,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":0,"y":1},"id":3,"legend":{"alignAsTable":true,"avg":false,"current":true,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":false,"linewidth":1,"links":[],"minSpan":24,"nullPointMode":"null","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":24,"stack":false,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))","format":"time_series","intervalFactor":1,"legendFormat":"{{namespace}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Current Rate of Bytes Received","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"series","name":null,"show":false,"values":["current"]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":true,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":12,"y":1},"id":4,"legend":{"alignAsTable":true,"avg":false,"current":true,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":false,"linewidth":1,"links":[],"minSpan":24,"nullPointMode":"null","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":24,"stack":false,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))","format":"time_series","intervalFactor":1,"legendFormat":"{{namespace}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Current Rate of Bytes Transmitted","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"series","name":null,"show":false,"values":["current"]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"columns":[{"text":"Time","value":"Time"},{"text":"Value #A","value":"Value #A"},{"text":"Value #B","value":"Value #B"},{"text":"Value #C","value":"Value #C"},{"text":"Value #D","value":"Value #D"},{"text":"Value #E","value":"Value #E"},{"text":"Value #F","value":"Value #F"},{"text":"Value #G","value":"Value #G"},{"text":"Value #H","value":"Value #H"},{"text":"namespace","value":"namespace"}],"datasource":"$datasource","fill":1,"fontSize":"90%","gridPos":{"h":9,"w":24,"x":0,"y":10},"id":5,"lines":true,"linewidth":1,"links":[],"minSpan":24,"nullPointMode":"null as zero","renderer":"flot","scroll":true,"showHeader":true,"sort":{"col":0,"desc":false},"spaceLength":10,"span":24,"styles":[{"alias":"Time","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Time","thresholds":[],"type":"hidden","unit":"short"},{"alias":"Current Bandwidth Received","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Current Bandwidth Transmitted","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Average Bandwidth Received","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Average Bandwidth Transmitted","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Rate of Received Packets","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"pps"},{"alias":"Rate of Transmitted Packets","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #F","thresholds":[],"type":"number","unit":"pps"},{"alias":"Rate of Received Packets Dropped","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #G","thresholds":[],"type":"number","unit":"pps"},{"alias":"Rate of Transmitted Packets Dropped","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #H","thresholds":[],"type":"number","unit":"pps"},{"alias":"Namespace","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":true,"linkTooltip":"Drill down","linkUrl":"d/8b7a8b326d7a6f1f04244066368c67af/kubernetes-networking-namespace-pods?orgId=1&refresh=30s&var-namespace=${__value.text}","pattern":"namespace","thresholds":[],"type":"number","unit":"short"}],"targets":[{"expr":"sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))","format":"table","instant":true,"intervalFactor":2,"legendFormat":"","refId":"A","step":10},{"expr":"sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))","format":"table","instant":true,"intervalFactor":2,"legendFormat":"","refId":"B","step":10},{"expr":"sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))","format":"table","instant":true,"intervalFactor":2,"legendFormat":"","refId":"C","step":10},{"expr":"sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))","format":"table","instant":true,"intervalFactor":2,"legendFormat":"","refId":"D","step":10},{"expr":"sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))","format":"table","instant":true,"intervalFactor":2,"legendFormat":"","refId":"E","step":10},{"expr":"sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))","format":"table","instant":true,"intervalFactor":2,"legendFormat":"","refId":"F","step":10},{"expr":"sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))","format":"table","instant":true,"intervalFactor":2,"legendFormat":"","refId":"G","step":10},{"expr":"sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))","format":"table","instant":true,"intervalFactor":2,"legendFormat":"","refId":"H","step":10}],"timeFrom":null,"timeShift":null,"title":"Current Status","type":"table"},{"collapse":true,"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":10},"id":6,"panels":[{"aliasColors":{},"bars":true,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":0,"y":11},"id":7,"legend":{"alignAsTable":true,"avg":false,"current":true,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":false,"linewidth":1,"links":[],"minSpan":24,"nullPointMode":"null","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":24,"stack":false,"steppedLine":false,"targets":[{"expr":"sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))","format":"time_series","intervalFactor":1,"legendFormat":"{{namespace}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Average Rate of Bytes Received","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"series","name":null,"show":false,"values":["current"]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":true,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":12,"y":11},"id":8,"legend":{"alignAsTable":true,"avg":false,"current":true,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":false,"linewidth":1,"links":[],"minSpan":24,"nullPointMode":"null","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":24,"stack":false,"steppedLine":false,"targets":[{"expr":"sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))","format":"time_series","intervalFactor":1,"legendFormat":"{{namespace}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Average Rate of Bytes Transmitted","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"series","name":null,"show":false,"values":["current"]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Average Bandwidth","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":11},"id":9,"panels":[],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Bandwidth History","titleSize":"h6","type":"row"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":24,"x":0,"y":12},"id":10,"legend":{"alignAsTable":true,"avg":true,"current":true,"hideEmpty":true,"hideZero":true,"max":true,"min":true,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"minSpan":24,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":24,"stack":true,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))","format":"time_series","intervalFactor":1,"legendFormat":"{{namespace}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Receive Bandwidth","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":24,"x":0,"y":21},"id":11,"legend":{"alignAsTable":true,"avg":true,"current":true,"hideEmpty":true,"hideZero":true,"max":true,"min":true,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"minSpan":24,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":24,"stack":true,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))","format":"time_series","intervalFactor":1,"legendFormat":"{{namespace}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Transmit Bandwidth","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"collapse":true,"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":30},"id":12,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":24,"x":0,"y":31},"id":13,"legend":{"alignAsTable":true,"avg":true,"current":true,"hideEmpty":true,"hideZero":true,"max":true,"min":true,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"minSpan":24,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":24,"stack":true,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))","format":"time_series","intervalFactor":1,"legendFormat":"{{namespace}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Received Packets","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":24,"x":0,"y":40},"id":14,"legend":{"alignAsTable":true,"avg":true,"current":true,"hideEmpty":true,"hideZero":true,"max":true,"min":true,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"minSpan":24,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":24,"stack":true,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))","format":"time_series","intervalFactor":1,"legendFormat":"{{namespace}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Transmitted Packets","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Packets","titleSize":"h6","type":"row"},{"collapse":true,"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":31},"id":15,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":24,"x":0,"y":50},"id":16,"legend":{"alignAsTable":true,"avg":true,"current":true,"hideEmpty":true,"hideZero":true,"max":true,"min":true,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"minSpan":24,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":24,"stack":true,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))","format":"time_series","intervalFactor":1,"legendFormat":"{{namespace}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Received Packets Dropped","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":24,"x":0,"y":59},"id":17,"legend":{"alignAsTable":true,"avg":true,"current":true,"hideEmpty":true,"hideZero":true,"max":true,"min":true,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":2,"links":[],"minSpan":24,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":24,"stack":true,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))","format":"time_series","intervalFactor":1,"legendFormat":"{{namespace}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Transmitted Packets Dropped","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":24,"x":0,"y":59},"id":18,"legend":{"alignAsTable":true,"avg":true,"current":true,"hideEmpty":true,"hideZero":true,"max":true,"min":true,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":2,"links":[{"targetBlank":true,"title":"What is TCP Retransmit?","url":"https://accedian.com/enterprises/blog/network-packet-loss-retransmissions-and-duplicate-acknowledgements/"}],"minSpan":24,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":24,"stack":true,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(rate(node_netstat_Tcp_RetransSegs{cluster=\"$cluster\"}[$interval:$resolution]) / rate(node_netstat_Tcp_OutSegs{cluster=\"$cluster\"}[$interval:$resolution])) by (instance))","format":"time_series","intervalFactor":1,"legendFormat":"{{instance}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of TCP Retransmits out of all sent segments","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"percentunit","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":24,"x":0,"y":59},"id":19,"legend":{"alignAsTable":true,"avg":true,"current":true,"hideEmpty":true,"hideZero":true,"max":true,"min":true,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":2,"links":[{"targetBlank":true,"title":"Why monitor SYN retransmits?","url":"https://github.com/prometheus/node_exporter/issues/1023#issuecomment-408128365"}],"minSpan":24,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":24,"stack":true,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(rate(node_netstat_TcpExt_TCPSynRetrans{cluster=\"$cluster\"}[$interval:$resolution]) / rate(node_netstat_Tcp_RetransSegs{cluster=\"$cluster\"}[$interval:$resolution])) by (instance))","format":"time_series","intervalFactor":1,"legendFormat":"{{instance}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of TCP SYN Retransmits out of all retransmits","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"percentunit","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Errors","titleSize":"h6","type":"row"}],"refresh":"10s","rows":[],"schemaVersion":18,"style":"dark","tags":["kubernetes-mixin"],"templating":{"list":[{"allValue":null,"auto":false,"auto_count":30,"auto_min":"10s","current":{"text":"5m","value":"5m"},"datasource":"$datasource","hide":0,"includeAll":false,"label":null,"multi":false,"name":"resolution","options":[{"selected":false,"text":"30s","value":"30s"},{"selected":true,"text":"5m","value":"5m"},{"selected":false,"text":"1h","value":"1h"}],"query":"30s,5m,1h","refresh":2,"regex":"","skipUrlSync":false,"sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"interval","useTags":false},{"allValue":null,"auto":false,"auto_count":30,"auto_min":"10s","current":{"text":"5m","value":"5m"},"datasource":"$datasource","hide":2,"includeAll":false,"label":null,"multi":false,"name":"interval","options":[{"selected":true,"text":"4h","value":"4h"}],"query":"4h","refresh":2,"regex":"","skipUrlSync":false,"sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"interval","useTags":false},{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{},"datasource":"$datasource","hide":2,"includeAll":false,"label":null,"multi":false,"name":"cluster","options":[],"query":"label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)","refresh":2,"regex":"","sort":0,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Kubernetes / Networking / Cluster","uid":"ff635a025bcfea7bc3dd4f508990a3e9","version":0} \ No newline at end of file diff --git a/monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-grafana-overview.yaml b/monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-grafana-overview.yaml new file mode 100644 index 0000000..d5b62b5 --- /dev/null +++ b/monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-grafana-overview.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/grafana-overview.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: prometheus-community-kube-grafana-overview + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +data: + grafana-overview.json: |- + {"annotations":{"list":[{"builtIn":1,"datasource":"-- Grafana --","enable":true,"hide":true,"iconColor":"rgba(0, 211, 255, 1)","name":"Annotations & Alerts","target":{"limit":100,"matchAny":false,"tags":[],"type":"dashboard"},"type":"dashboard"}]},"editable":true,"gnetId":null,"graphTooltip":0,"id":3085,"iteration":1631554945276,"links":[],"panels":[{"datasource":"$datasource","fieldConfig":{"defaults":{"mappings":[],"noValue":"0","thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]}},"overrides":[]},"gridPos":{"h":5,"w":6,"x":0,"y":0},"id":6,"options":{"colorMode":"value","graphMode":"area","justifyMode":"auto","orientation":"auto","reduceOptions":{"calcs":["mean"],"fields":"","values":false},"text":{},"textMode":"auto"},"pluginVersion":"8.1.3","targets":[{"expr":"grafana_alerting_result_total{job=~\"$job\", instance=~\"$instance\", state=\"alerting\"}","instant":true,"interval":"","legendFormat":"","refId":"A"}],"timeFrom":null,"timeShift":null,"title":"Firing Alerts","type":"stat"},{"datasource":"$datasource","fieldConfig":{"defaults":{"mappings":[],"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]}},"overrides":[]},"gridPos":{"h":5,"w":6,"x":6,"y":0},"id":8,"options":{"colorMode":"value","graphMode":"area","justifyMode":"auto","orientation":"auto","reduceOptions":{"calcs":["mean"],"fields":"","values":false},"text":{},"textMode":"auto"},"pluginVersion":"8.1.3","targets":[{"expr":"sum(grafana_stat_totals_dashboard{job=~\"$job\", instance=~\"$instance\"})","interval":"","legendFormat":"","refId":"A"}],"timeFrom":null,"timeShift":null,"title":"Dashboards","type":"stat"},{"datasource":"$datasource","fieldConfig":{"defaults":{"custom":{"align":null,"displayMode":"auto"},"mappings":[],"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]}},"overrides":[]},"gridPos":{"h":5,"w":12,"x":12,"y":0},"id":10,"options":{"showHeader":true},"pluginVersion":"8.1.3","targets":[{"expr":"grafana_build_info{job=~\"$job\", instance=~\"$instance\"}","instant":true,"interval":"","legendFormat":"","refId":"A"}],"timeFrom":null,"timeShift":null,"title":"Build Info","transformations":[{"id":"labelsToFields","options":{}},{"id":"organize","options":{"excludeByName":{"Time":true,"Value":true,"branch":true,"container":true,"goversion":true,"namespace":true,"pod":true,"revision":true},"indexByName":{"Time":7,"Value":11,"branch":4,"container":8,"edition":2,"goversion":6,"instance":1,"job":0,"namespace":9,"pod":10,"revision":5,"version":3},"renameByName":{}}}],"type":"table"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fieldConfig":{"defaults":{"links":[]},"overrides":[]},"fill":1,"fillGradient":0,"gridPos":{"h":8,"w":12,"x":0,"y":5},"hiddenSeries":false,"id":2,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"8.1.3","pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by (status_code) (irate(grafana_http_request_duration_seconds_count{job=~\"$job\", instance=~\"$instance\"}[1m])) ","interval":"","legendFormat":"{{status_code}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"RPS","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"$$hashKey":"object:157","format":"reqps","label":null,"logBase":1,"max":null,"min":null,"show":true},{"$$hashKey":"object:158","format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fieldConfig":{"defaults":{"links":[]},"overrides":[]},"fill":1,"fillGradient":0,"gridPos":{"h":8,"w":12,"x":12,"y":5},"hiddenSeries":false,"id":4,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"8.1.3","pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"exemplar":true,"expr":"histogram_quantile(0.99, sum(irate(grafana_http_request_duration_seconds_bucket{instance=~\"$instance\", job=~\"$job\"}[$__rate_interval])) by (le)) * 1","interval":"","legendFormat":"99th Percentile","refId":"A"},{"exemplar":true,"expr":"histogram_quantile(0.50, sum(irate(grafana_http_request_duration_seconds_bucket{instance=~\"$instance\", job=~\"$job\"}[$__rate_interval])) by (le)) * 1","interval":"","legendFormat":"50th Percentile","refId":"B"},{"exemplar":true,"expr":"sum(irate(grafana_http_request_duration_seconds_sum{instance=~\"$instance\", job=~\"$job\"}[$__rate_interval])) * 1 / sum(irate(grafana_http_request_duration_seconds_count{instance=~\"$instance\", job=~\"$job\"}[$__rate_interval]))","interval":"","legendFormat":"Average","refId":"C"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Request Latency","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"$$hashKey":"object:210","format":"ms","label":null,"logBase":1,"max":null,"min":null,"show":true},{"$$hashKey":"object:211","format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}}],"schemaVersion":30,"style":"dark","tags":[],"templating":{"list":[{"current":{"selected":true,"text":"dev-cortex","value":"dev-cortex"},"description":null,"error":null,"hide":0,"includeAll":false,"label":null,"multi":false,"name":"datasource","options":[],"query":"prometheus","queryValue":"","refresh":1,"regex":"","skipUrlSync":false,"type":"datasource"},{"allValue":".*","current":{"selected":false,"text":["default/grafana"],"value":["default/grafana"]},"datasource":"$datasource","definition":"label_values(grafana_build_info, job)","description":null,"error":null,"hide":0,"includeAll":true,"label":null,"multi":true,"name":"job","options":[],"query":{"query":"label_values(grafana_build_info, job)","refId":"Billing Admin-job-Variable-Query"},"refresh":1,"regex":"","skipUrlSync":false,"sort":0,"tagValuesQuery":"","tagsQuery":"","type":"query","useTags":false},{"allValue":".*","current":{"selected":false,"text":"All","value":"$__all"},"datasource":"$datasource","definition":"label_values(grafana_build_info, instance)","description":null,"error":null,"hide":0,"includeAll":true,"label":null,"multi":true,"name":"instance","options":[],"query":{"query":"label_values(grafana_build_info, instance)","refId":"Billing Admin-instance-Variable-Query"},"refresh":1,"regex":"","skipUrlSync":false,"sort":0,"tagValuesQuery":"","tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-6h","to":"now"},"timepicker":{"refresh_intervals":["10s","30s","1m","5m","15m","30m","1h","2h","1d"]},"timezone": "Europe/Paris","title":"Grafana Overview","uid":"6be0s85Mk","version":2} \ No newline at end of file diff --git a/monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-namespace-by-pod.yaml b/monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-namespace-by-pod.yaml new file mode 100644 index 0000000..4811303 --- /dev/null +++ b/monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-namespace-by-pod.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/namespace-by-pod.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: prometheus-community-kube-namespace-by-pod + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +data: + namespace-by-pod.json: |- + {"__inputs":[],"__requires":[],"annotations":{"list":[{"builtIn":1,"datasource":"-- Grafana --","enable":true,"hide":true,"iconColor":"rgba(0, 211, 255, 1)","name":"Annotations & Alerts","type":"dashboard"}]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"id":null,"links":[],"panels":[{"collapse":false,"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":0},"id":2,"panels":[],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Current Bandwidth","titleSize":"h6","type":"row"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"$datasource","decimals":0,"format":"time_series","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":9,"w":12,"x":0,"y":1},"height":9,"id":3,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"minSpan":12,"nullPointMode":"connected","nullText":null,"options":{"fieldOptions":{"calcs":["last"],"defaults":{"max":10000000000,"min":0,"title":"$namespace","unit":"Bps"},"mappings":[],"override":{},"thresholds":[{"color":"dark-green","index":0,"value":null},{"color":"dark-yellow","index":1,"value":5000000000},{"color":"dark-red","index":2,"value":7000000000}],"values":false}},"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"span":12,"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution]))","format":"time_series","instant":null,"intervalFactor":1,"legendFormat":"","refId":"A"}],"thresholds":"","timeFrom":null,"timeShift":null,"title":"Current Rate of Bytes Received","type":"gauge","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"$datasource","decimals":0,"format":"time_series","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":9,"w":12,"x":12,"y":1},"height":9,"id":4,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"minSpan":12,"nullPointMode":"connected","nullText":null,"options":{"fieldOptions":{"calcs":["last"],"defaults":{"max":10000000000,"min":0,"title":"$namespace","unit":"Bps"},"mappings":[],"override":{},"thresholds":[{"color":"dark-green","index":0,"value":null},{"color":"dark-yellow","index":1,"value":5000000000},{"color":"dark-red","index":2,"value":7000000000}],"values":false}},"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"span":12,"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution]))","format":"time_series","instant":null,"intervalFactor":1,"legendFormat":"","refId":"A"}],"thresholds":"","timeFrom":null,"timeShift":null,"title":"Current Rate of Bytes Transmitted","type":"gauge","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"columns":[{"text":"Time","value":"Time"},{"text":"Value #A","value":"Value #A"},{"text":"Value #B","value":"Value #B"},{"text":"Value #C","value":"Value #C"},{"text":"Value #D","value":"Value #D"},{"text":"Value #E","value":"Value #E"},{"text":"Value #F","value":"Value #F"},{"text":"pod","value":"pod"}],"datasource":"$datasource","fill":1,"fontSize":"100%","gridPos":{"h":9,"w":24,"x":0,"y":10},"id":5,"lines":true,"linewidth":1,"links":[],"minSpan":24,"nullPointMode":"null as zero","renderer":"flot","scroll":true,"showHeader":true,"sort":{"col":0,"desc":false},"spaceLength":10,"span":24,"styles":[{"alias":"Time","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Time","thresholds":[],"type":"hidden","unit":"short"},{"alias":"Bandwidth Received","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Bandwidth Transmitted","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Rate of Received Packets","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"pps"},{"alias":"Rate of Transmitted Packets","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"pps"},{"alias":"Rate of Received Packets Dropped","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"pps"},{"alias":"Rate of Transmitted Packets Dropped","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #F","thresholds":[],"type":"number","unit":"pps"},{"alias":"Pod","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":true,"linkTooltip":"Drill down","linkUrl":"d/7a18067ce943a40ae25454675c19ff5c/kubernetes-networking-pod?orgId=1&refresh=30s&var-namespace=$namespace&var-pod=${__value.text}","pattern":"pod","thresholds":[],"type":"number","unit":"short"}],"targets":[{"expr":"sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)","format":"table","instant":true,"intervalFactor":2,"legendFormat":"","refId":"A","step":10},{"expr":"sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)","format":"table","instant":true,"intervalFactor":2,"legendFormat":"","refId":"B","step":10},{"expr":"sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)","format":"table","instant":true,"intervalFactor":2,"legendFormat":"","refId":"C","step":10},{"expr":"sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)","format":"table","instant":true,"intervalFactor":2,"legendFormat":"","refId":"D","step":10},{"expr":"sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)","format":"table","instant":true,"intervalFactor":2,"legendFormat":"","refId":"E","step":10},{"expr":"sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)","format":"table","instant":true,"intervalFactor":2,"legendFormat":"","refId":"F","step":10}],"timeFrom":null,"timeShift":null,"title":"Current Status","type":"table"},{"collapse":false,"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":19},"id":6,"panels":[],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Bandwidth","titleSize":"h6","type":"row"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":0,"y":20},"id":7,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)","format":"time_series","intervalFactor":1,"legendFormat":"{{pod}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Receive Bandwidth","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":12,"y":20},"id":8,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)","format":"time_series","intervalFactor":1,"legendFormat":"{{pod}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Transmit Bandwidth","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"collapse":true,"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":29},"id":9,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":10,"w":12,"x":0,"y":30},"id":10,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)","format":"time_series","intervalFactor":1,"legendFormat":"{{pod}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Received Packets","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":10,"w":12,"x":12,"y":30},"id":11,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)","format":"time_series","intervalFactor":1,"legendFormat":"{{pod}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Transmitted Packets","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Packets","titleSize":"h6","type":"row"},{"collapse":true,"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":30},"id":12,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":10,"w":12,"x":0,"y":40},"id":13,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)","format":"time_series","intervalFactor":1,"legendFormat":"{{pod}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Received Packets Dropped","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":10,"w":12,"x":12,"y":40},"id":14,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)","format":"time_series","intervalFactor":1,"legendFormat":"{{pod}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Transmitted Packets Dropped","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Errors","titleSize":"h6","type":"row"}],"refresh":"10s","rows":[],"schemaVersion":18,"style":"dark","tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{},"datasource":"$datasource","hide":2,"includeAll":false,"label":null,"multi":false,"name":"cluster","options":[],"query":"label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)","refresh":2,"regex":"","sort":0,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":".+","auto":false,"auto_count":30,"auto_min":"10s","current":{"text":"kube-system","value":"kube-system"},"datasource":"$datasource","definition":"label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)","hide":0,"includeAll":true,"label":null,"multi":false,"name":"namespace","options":[],"query":"label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)","refresh":2,"regex":"","skipUrlSync":false,"sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"auto":false,"auto_count":30,"auto_min":"10s","current":{"text":"5m","value":"5m"},"datasource":"$datasource","hide":0,"includeAll":false,"label":null,"multi":false,"name":"resolution","options":[{"selected":false,"text":"30s","value":"30s"},{"selected":true,"text":"5m","value":"5m"},{"selected":false,"text":"1h","value":"1h"}],"query":"30s,5m,1h","refresh":2,"regex":"","skipUrlSync":false,"sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"interval","useTags":false},{"allValue":null,"auto":false,"auto_count":30,"auto_min":"10s","current":{"text":"5m","value":"5m"},"datasource":"$datasource","hide":2,"includeAll":false,"label":null,"multi":false,"name":"interval","options":[{"selected":true,"text":"4h","value":"4h"}],"query":"4h","refresh":2,"regex":"","skipUrlSync":false,"sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"interval","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Kubernetes / Networking / Namespace (Pods)","uid":"8b7a8b326d7a6f1f04244066368c67af","version":0} \ No newline at end of file diff --git a/monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-namespace-by-workload.yaml b/monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-namespace-by-workload.yaml new file mode 100644 index 0000000..1899995 --- /dev/null +++ b/monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-namespace-by-workload.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/namespace-by-workload.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: prometheus-community-kube-namespace-by-workload + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +data: + namespace-by-workload.json: |- + {"__inputs":[],"__requires":[],"annotations":{"list":[{"builtIn":1,"datasource":"-- Grafana --","enable":true,"hide":true,"iconColor":"rgba(0, 211, 255, 1)","name":"Annotations & Alerts","type":"dashboard"}]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"id":null,"links":[],"panels":[{"collapse":false,"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":0},"id":2,"panels":[],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Current Bandwidth","titleSize":"h6","type":"row"},{"aliasColors":{},"bars":true,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":0,"y":1},"id":3,"legend":{"alignAsTable":true,"avg":false,"current":true,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":false,"linewidth":1,"links":[],"minSpan":24,"nullPointMode":"null","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":24,"stack":false,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"time_series","intervalFactor":1,"legendFormat":"{{ workload }}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Current Rate of Bytes Received","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"series","name":null,"show":false,"values":["current"]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":true,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":12,"y":1},"id":4,"legend":{"alignAsTable":true,"avg":false,"current":true,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":false,"linewidth":1,"links":[],"minSpan":24,"nullPointMode":"null","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":24,"stack":false,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"time_series","intervalFactor":1,"legendFormat":"{{ workload }}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Current Rate of Bytes Transmitted","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"series","name":null,"show":false,"values":["current"]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"columns":[{"text":"Time","value":"Time"},{"text":"Value #A","value":"Value #A"},{"text":"Value #B","value":"Value #B"},{"text":"Value #C","value":"Value #C"},{"text":"Value #D","value":"Value #D"},{"text":"Value #E","value":"Value #E"},{"text":"Value #F","value":"Value #F"},{"text":"Value #G","value":"Value #G"},{"text":"Value #H","value":"Value #H"},{"text":"workload","value":"workload"}],"datasource":"$datasource","fill":1,"fontSize":"90%","gridPos":{"h":9,"w":24,"x":0,"y":10},"id":5,"lines":true,"linewidth":1,"links":[],"minSpan":24,"nullPointMode":"null as zero","renderer":"flot","scroll":true,"showHeader":true,"sort":{"col":0,"desc":false},"spaceLength":10,"span":24,"styles":[{"alias":"Time","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Time","thresholds":[],"type":"hidden","unit":"short"},{"alias":"Current Bandwidth Received","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Current Bandwidth Transmitted","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Average Bandwidth Received","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Average Bandwidth Transmitted","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Rate of Received Packets","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"pps"},{"alias":"Rate of Transmitted Packets","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #F","thresholds":[],"type":"number","unit":"pps"},{"alias":"Rate of Received Packets Dropped","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #G","thresholds":[],"type":"number","unit":"pps"},{"alias":"Rate of Transmitted Packets Dropped","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #H","thresholds":[],"type":"number","unit":"pps"},{"alias":"Workload","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":true,"linkTooltip":"Drill down","linkUrl":"d/728bf77cc1166d2f3133bf25846876cc/kubernetes-networking-workload?orgId=1&refresh=30s&var-namespace=$namespace&var-type=$type&var-workload=${__value.text}","pattern":"workload","thresholds":[],"type":"number","unit":"short"}],"targets":[{"expr":"sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true,"intervalFactor":2,"legendFormat":"","refId":"A","step":10},{"expr":"sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true,"intervalFactor":2,"legendFormat":"","refId":"B","step":10},{"expr":"sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true,"intervalFactor":2,"legendFormat":"","refId":"C","step":10},{"expr":"sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true,"intervalFactor":2,"legendFormat":"","refId":"D","step":10},{"expr":"sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true,"intervalFactor":2,"legendFormat":"","refId":"E","step":10},{"expr":"sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true,"intervalFactor":2,"legendFormat":"","refId":"F","step":10},{"expr":"sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true,"intervalFactor":2,"legendFormat":"","refId":"G","step":10},{"expr":"sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true,"intervalFactor":2,"legendFormat":"","refId":"H","step":10}],"timeFrom":null,"timeShift":null,"title":"Current Status","type":"table"},{"collapse":true,"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":19},"id":6,"panels":[{"aliasColors":{},"bars":true,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":0,"y":20},"id":7,"legend":{"alignAsTable":true,"avg":false,"current":true,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":false,"linewidth":1,"links":[],"minSpan":24,"nullPointMode":"null","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":24,"stack":false,"steppedLine":false,"targets":[{"expr":"sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"time_series","intervalFactor":1,"legendFormat":"{{ workload }}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Average Rate of Bytes Received","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"series","name":null,"show":false,"values":["current"]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":true,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":12,"y":20},"id":8,"legend":{"alignAsTable":true,"avg":false,"current":true,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":false,"linewidth":1,"links":[],"minSpan":24,"nullPointMode":"null","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":24,"stack":false,"steppedLine":false,"targets":[{"expr":"sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"time_series","intervalFactor":1,"legendFormat":"{{ workload }}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Average Rate of Bytes Transmitted","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"series","name":null,"show":false,"values":["current"]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Average Bandwidth","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":29},"id":9,"panels":[],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Bandwidth HIstory","titleSize":"h6","type":"row"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":0,"y":38},"id":10,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"time_series","intervalFactor":1,"legendFormat":"{{workload}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Receive Bandwidth","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":12,"y":38},"id":11,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"time_series","intervalFactor":1,"legendFormat":"{{workload}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Transmit Bandwidth","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"collapse":true,"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":39},"id":12,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":0,"y":40},"id":13,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"time_series","intervalFactor":1,"legendFormat":"{{workload}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Received Packets","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":12,"y":40},"id":14,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"time_series","intervalFactor":1,"legendFormat":"{{workload}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Transmitted Packets","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Packets","titleSize":"h6","type":"row"},{"collapse":true,"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":40},"id":15,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":0,"y":41},"id":16,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"time_series","intervalFactor":1,"legendFormat":"{{workload}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Received Packets Dropped","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":12,"y":41},"id":17,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"time_series","intervalFactor":1,"legendFormat":"{{workload}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Transmitted Packets Dropped","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Errors","titleSize":"h6","type":"row"}],"refresh":"10s","rows":[],"schemaVersion":18,"style":"dark","tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{},"datasource":"$datasource","hide":2,"includeAll":false,"label":null,"multi":false,"name":"cluster","options":[],"query":"label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)","refresh":2,"regex":"","sort":0,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"auto":false,"auto_count":30,"auto_min":"10s","current":{"text":"kube-system","value":"kube-system"},"datasource":"$datasource","definition":"label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)","hide":0,"includeAll":false,"label":null,"multi":false,"name":"namespace","options":[],"query":"label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)","refresh":2,"regex":"","skipUrlSync":false,"sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"auto":false,"auto_count":30,"auto_min":"10s","current":{"text":"","value":""},"datasource":"$datasource","definition":"label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\"}, workload_type)","hide":0,"includeAll":true,"label":null,"multi":false,"name":"type","options":[],"query":"label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\"}, workload_type)","refresh":2,"regex":"","skipUrlSync":false,"sort":0,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"auto":false,"auto_count":30,"auto_min":"10s","current":{"text":"5m","value":"5m"},"datasource":"$datasource","hide":0,"includeAll":false,"label":null,"multi":false,"name":"resolution","options":[{"selected":false,"text":"30s","value":"30s"},{"selected":true,"text":"5m","value":"5m"},{"selected":false,"text":"1h","value":"1h"}],"query":"30s,5m,1h","refresh":2,"regex":"","skipUrlSync":false,"sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"interval","useTags":false},{"allValue":null,"auto":false,"auto_count":30,"auto_min":"10s","current":{"text":"5m","value":"5m"},"datasource":"$datasource","hide":2,"includeAll":false,"label":null,"multi":false,"name":"interval","options":[{"selected":true,"text":"4h","value":"4h"}],"query":"4h","refresh":2,"regex":"","skipUrlSync":false,"sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"interval","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Kubernetes / Networking / Namespace (Workload)","uid":"bbb2a765a623ae38130206c7d94a160f","version":0} \ No newline at end of file diff --git a/monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-persistentvolumesusage.yaml b/monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-persistentvolumesusage.yaml new file mode 100644 index 0000000..acfd1af --- /dev/null +++ b/monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-persistentvolumesusage.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/persistentvolumesusage.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: prometheus-community-kube-persistentvolumesusage + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +data: + persistentvolumesusage.json: |- + {"__inputs":[],"__requires":[],"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"id":null,"links":[],"refresh":"10s","rows":[{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":2,"interval":"1m","legend":{"alignAsTable":true,"avg":true,"current":true,"max":true,"min":true,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":9,"stack":true,"steppedLine":false,"targets":[{"expr":"(\n sum without(instance, node) (topk(1, (kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n -\n sum without(instance, node) (topk(1, (kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n)\n","format":"time_series","intervalFactor":1,"legendFormat":"Used Space","refId":"A"},{"expr":"sum without(instance, node) (topk(1, (kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n","format":"time_series","intervalFactor":1,"legendFormat":"Free Space","refId":"B"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Volume Space Usage","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(50, 172, 45, 0.97)","rgba(237, 129, 40, 0.89)","rgba(245, 54, 54, 0.9)"],"datasource":"$datasource","format":"percent","gauge":{"maxValue":100,"minValue":0,"show":true,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{},"id":3,"interval":"1m","legend":{"alignAsTable":true,"rightSide":true},"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"span":3,"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"max without(instance,node) (\n(\n topk(1, kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n -\n topk(1, kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n)\n/\ntopk(1, kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n* 100)\n","format":"time_series","intervalFactor":2,"legendFormat":"","refId":"A"}],"thresholds":"80, 90","title":"Volume Space Usage","tooltip":{"shared":false},"type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Dashboard Row","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":4,"interval":"1m","legend":{"alignAsTable":true,"avg":true,"current":true,"max":true,"min":true,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":9,"stack":true,"steppedLine":false,"targets":[{"expr":"sum without(instance, node) (topk(1, (kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n","format":"time_series","intervalFactor":1,"legendFormat":"Used inodes","refId":"A"},{"expr":"(\n sum without(instance, node) (topk(1, (kubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n -\n sum without(instance, node) (topk(1, (kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n)\n","format":"time_series","intervalFactor":1,"legendFormat":" Free inodes","refId":"B"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Volume inodes Usage","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"none","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"none","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["rgba(50, 172, 45, 0.97)","rgba(237, 129, 40, 0.89)","rgba(245, 54, 54, 0.9)"],"datasource":"$datasource","format":"percent","gauge":{"maxValue":100,"minValue":0,"show":true,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{},"id":5,"interval":"1m","legend":{"alignAsTable":true,"rightSide":true},"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"span":3,"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"max without(instance,node) (\ntopk(1, kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n/\ntopk(1, kubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n* 100)\n","format":"time_series","intervalFactor":2,"legendFormat":"","refId":"A"}],"thresholds":"80, 90","title":"Volume inodes Usage","tooltip":{"shared":false},"type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Dashboard Row","titleSize":"h6","type":"row"}],"schemaVersion":14,"style":"dark","tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{},"datasource":"$datasource","hide":2,"includeAll":false,"label":"cluster","multi":false,"name":"cluster","options":[],"query":"label_values(kubelet_volume_stats_capacity_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}, cluster)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{},"datasource":"$datasource","hide":0,"includeAll":false,"label":"Namespace","multi":false,"name":"namespace","options":[],"query":"label_values(kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\"}, namespace)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{},"datasource":"$datasource","hide":0,"includeAll":false,"label":"PersistentVolumeClaim","multi":false,"name":"volume","options":[],"query":"label_values(kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\"}, persistentvolumeclaim)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-7d","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Kubernetes / Persistent Volumes","uid":"919b92a8e8041bd567af9edab12c840c","version":0} \ No newline at end of file diff --git a/monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-pod-total.yaml b/monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-pod-total.yaml new file mode 100644 index 0000000..76c8714 --- /dev/null +++ b/monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-pod-total.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/pod-total.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: prometheus-community-kube-pod-total + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +data: + pod-total.json: |- + {"__inputs":[],"__requires":[],"annotations":{"list":[{"builtIn":1,"datasource":"-- Grafana --","enable":true,"hide":true,"iconColor":"rgba(0, 211, 255, 1)","name":"Annotations & Alerts","type":"dashboard"}]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"id":null,"links":[],"panels":[{"collapse":false,"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":0},"id":2,"panels":[],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Current Bandwidth","titleSize":"h6","type":"row"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"$datasource","decimals":0,"format":"time_series","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":9,"w":12,"x":0,"y":1},"height":9,"id":3,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"minSpan":12,"nullPointMode":"connected","nullText":null,"options":{"fieldOptions":{"calcs":["last"],"defaults":{"max":10000000000,"min":0,"title":"$namespace: $pod","unit":"Bps"},"mappings":[],"override":{},"thresholds":[{"color":"dark-green","index":0,"value":null},{"color":"dark-yellow","index":1,"value":5000000000},{"color":"dark-red","index":2,"value":7000000000}],"values":false}},"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"span":12,"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution]))","format":"time_series","instant":null,"intervalFactor":1,"legendFormat":"","refId":"A"}],"thresholds":"","timeFrom":null,"timeShift":null,"title":"Current Rate of Bytes Received","type":"gauge","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"$datasource","decimals":0,"format":"time_series","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{"h":9,"w":12,"x":12,"y":1},"height":9,"id":4,"interval":null,"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"minSpan":12,"nullPointMode":"connected","nullText":null,"options":{"fieldOptions":{"calcs":["last"],"defaults":{"max":10000000000,"min":0,"title":"$namespace: $pod","unit":"Bps"},"mappings":[],"override":{},"thresholds":[{"color":"dark-green","index":0,"value":null},{"color":"dark-yellow","index":1,"value":5000000000},{"color":"dark-red","index":2,"value":7000000000}],"values":false}},"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"span":12,"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution]))","format":"time_series","instant":null,"intervalFactor":1,"legendFormat":"","refId":"A"}],"thresholds":"","timeFrom":null,"timeShift":null,"title":"Current Rate of Bytes Transmitted","type":"gauge","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"current"},{"collapse":false,"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":10},"id":5,"panels":[],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Bandwidth","titleSize":"h6","type":"row"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":0,"y":11},"id":6,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)","format":"time_series","intervalFactor":1,"legendFormat":"{{pod}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Receive Bandwidth","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":12,"y":11},"id":7,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)","format":"time_series","intervalFactor":1,"legendFormat":"{{pod}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Transmit Bandwidth","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"collapse":true,"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":20},"id":8,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":10,"w":12,"x":0,"y":21},"id":9,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)","format":"time_series","intervalFactor":1,"legendFormat":"{{pod}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Received Packets","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":10,"w":12,"x":12,"y":21},"id":10,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)","format":"time_series","intervalFactor":1,"legendFormat":"{{pod}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Transmitted Packets","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Packets","titleSize":"h6","type":"row"},{"collapse":true,"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":21},"id":11,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":10,"w":12,"x":0,"y":32},"id":12,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)","format":"time_series","intervalFactor":1,"legendFormat":"{{pod}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Received Packets Dropped","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":10,"w":12,"x":12,"y":32},"id":13,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)","format":"time_series","intervalFactor":1,"legendFormat":"{{pod}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Transmitted Packets Dropped","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Errors","titleSize":"h6","type":"row"}],"refresh":"10s","rows":[],"schemaVersion":18,"style":"dark","tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{},"datasource":"$datasource","hide":2,"includeAll":false,"label":null,"multi":false,"name":"cluster","options":[],"query":"label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)","refresh":2,"regex":"","sort":0,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":".+","auto":false,"auto_count":30,"auto_min":"10s","current":{"text":"kube-system","value":"kube-system"},"datasource":"$datasource","definition":"label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)","hide":0,"includeAll":true,"label":null,"multi":false,"name":"namespace","options":[],"query":"label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)","refresh":2,"regex":"","skipUrlSync":false,"sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":".+","auto":false,"auto_count":30,"auto_min":"10s","current":{"text":"","value":""},"datasource":"$datasource","definition":"label_values(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}, pod)","hide":0,"includeAll":false,"label":null,"multi":false,"name":"pod","options":[],"query":"label_values(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}, pod)","refresh":2,"regex":"","skipUrlSync":false,"sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"auto":false,"auto_count":30,"auto_min":"10s","current":{"text":"5m","value":"5m"},"datasource":"$datasource","hide":0,"includeAll":false,"label":null,"multi":false,"name":"resolution","options":[{"selected":false,"text":"30s","value":"30s"},{"selected":true,"text":"5m","value":"5m"},{"selected":false,"text":"1h","value":"1h"}],"query":"30s,5m,1h","refresh":2,"regex":"","skipUrlSync":false,"sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"interval","useTags":false},{"allValue":null,"auto":false,"auto_count":30,"auto_min":"10s","current":{"text":"5m","value":"5m"},"datasource":"$datasource","hide":2,"includeAll":false,"label":null,"multi":false,"name":"interval","options":[{"selected":true,"text":"4h","value":"4h"}],"query":"4h","refresh":2,"regex":"","skipUrlSync":false,"sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"interval","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Kubernetes / Networking / Pod","uid":"7a18067ce943a40ae25454675c19ff5c","version":0} \ No newline at end of file diff --git a/monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-workload-total.yaml b/monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-workload-total.yaml new file mode 100644 index 0000000..dcc71a4 --- /dev/null +++ b/monitor/dashboards-minimal/v1_ConfigMap_prometheus-community-kube-workload-total.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/workload-total.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: prometheus-community-kube-workload-total + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +data: + workload-total.json: |- + {"__inputs":[],"__requires":[],"annotations":{"list":[{"builtIn":1,"datasource":"-- Grafana --","enable":true,"hide":true,"iconColor":"rgba(0, 211, 255, 1)","name":"Annotations & Alerts","type":"dashboard"}]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"id":null,"links":[],"panels":[{"collapse":false,"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":0},"id":2,"panels":[],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Current Bandwidth","titleSize":"h6","type":"row"},{"aliasColors":{},"bars":true,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":0,"y":1},"id":3,"legend":{"alignAsTable":true,"avg":false,"current":true,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":false,"linewidth":1,"links":[],"minSpan":24,"nullPointMode":"null","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":24,"stack":false,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"time_series","intervalFactor":1,"legendFormat":"{{ pod }}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Current Rate of Bytes Received","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"series","name":null,"show":false,"values":["current"]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":true,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":12,"y":1},"id":4,"legend":{"alignAsTable":true,"avg":false,"current":true,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":false,"linewidth":1,"links":[],"minSpan":24,"nullPointMode":"null","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":24,"stack":false,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"time_series","intervalFactor":1,"legendFormat":"{{ pod }}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Current Rate of Bytes Transmitted","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"series","name":null,"show":false,"values":["current"]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"collapse":true,"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":10},"id":5,"panels":[{"aliasColors":{},"bars":true,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":0,"y":11},"id":6,"legend":{"alignAsTable":true,"avg":false,"current":true,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":false,"linewidth":1,"links":[],"minSpan":24,"nullPointMode":"null","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":24,"stack":false,"steppedLine":false,"targets":[{"expr":"sort_desc(avg(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"time_series","intervalFactor":1,"legendFormat":"{{ pod }}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Average Rate of Bytes Received","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"series","name":null,"show":false,"values":["current"]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":true,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":12,"y":11},"id":7,"legend":{"alignAsTable":true,"avg":false,"current":true,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"sort":"current","sortDesc":true,"total":false,"values":true},"lines":false,"linewidth":1,"links":[],"minSpan":24,"nullPointMode":"null","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":24,"stack":false,"steppedLine":false,"targets":[{"expr":"sort_desc(avg(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"time_series","intervalFactor":1,"legendFormat":"{{ pod }}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Average Rate of Bytes Transmitted","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"series","name":null,"show":false,"values":["current"]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Average Bandwidth","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"gridPos":{"h":1,"w":24,"x":0,"y":11},"id":8,"panels":[],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Bandwidth HIstory","titleSize":"h6","type":"row"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":0,"y":12},"id":9,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"time_series","intervalFactor":1,"legendFormat":"{{pod}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Receive Bandwidth","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":12,"y":12},"id":10,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"time_series","intervalFactor":1,"legendFormat":"{{pod}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Transmit Bandwidth","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"collapse":true,"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":21},"id":11,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":0,"y":22},"id":12,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"time_series","intervalFactor":1,"legendFormat":"{{pod}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Received Packets","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":12,"y":22},"id":13,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"time_series","intervalFactor":1,"legendFormat":"{{pod}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Transmitted Packets","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Packets","titleSize":"h6","type":"row"},{"collapse":true,"collapsed":true,"gridPos":{"h":1,"w":24,"x":0,"y":22},"id":14,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":0,"y":23},"id":15,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"time_series","intervalFactor":1,"legendFormat":"{{pod}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Received Packets Dropped","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":2,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":12,"y":23},"id":16,"legend":{"alignAsTable":false,"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"minSpan":12,"nullPointMode":"connected","paceLength":10,"percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sort_desc(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"time_series","intervalFactor":1,"legendFormat":"{{pod}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Transmitted Packets Dropped","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Errors","titleSize":"h6","type":"row"}],"refresh":"10s","rows":[],"schemaVersion":18,"style":"dark","tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{},"datasource":"$datasource","hide":2,"includeAll":false,"label":null,"multi":false,"name":"cluster","options":[],"query":"label_values(kube_pod_info{job=\"kube-state-metrics\"}, cluster)","refresh":2,"regex":"","sort":0,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":".+","auto":false,"auto_count":30,"auto_min":"10s","current":{"text":"kube-system","value":"kube-system"},"datasource":"$datasource","definition":"label_values(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\"}, namespace)","hide":0,"includeAll":true,"label":null,"multi":false,"name":"namespace","options":[],"query":"label_values(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\"}, namespace)","refresh":2,"regex":"","skipUrlSync":false,"sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"auto":false,"auto_count":30,"auto_min":"10s","current":{"text":"","value":""},"datasource":"$datasource","definition":"label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\"}, workload)","hide":0,"includeAll":false,"label":null,"multi":false,"name":"workload","options":[],"query":"label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\"}, workload)","refresh":2,"regex":"","skipUrlSync":false,"sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"auto":false,"auto_count":30,"auto_min":"10s","current":{"text":"","value":""},"datasource":"$datasource","definition":"label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\"}, workload_type)","hide":0,"includeAll":true,"label":null,"multi":false,"name":"type","options":[],"query":"label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\"}, workload_type)","refresh":2,"regex":"","skipUrlSync":false,"sort":0,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"auto":false,"auto_count":30,"auto_min":"10s","current":{"text":"5m","value":"5m"},"datasource":"$datasource","hide":0,"includeAll":false,"label":null,"multi":false,"name":"resolution","options":[{"selected":false,"text":"30s","value":"30s"},{"selected":true,"text":"5m","value":"5m"},{"selected":false,"text":"1h","value":"1h"}],"query":"30s,5m,1h","refresh":2,"regex":"","skipUrlSync":false,"sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"interval","useTags":false},{"allValue":null,"auto":false,"auto_count":30,"auto_min":"10s","current":{"text":"5m","value":"5m"},"datasource":"$datasource","hide":2,"includeAll":false,"label":null,"multi":false,"name":"interval","options":[{"selected":true,"text":"4h","value":"4h"}],"query":"4h","refresh":2,"regex":"","skipUrlSync":false,"sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"interval","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Kubernetes / Networking / Workload","uid":"728bf77cc1166d2f3133bf25846876cc","version":0} \ No newline at end of file diff --git a/monitor/dashboards-namespace/datas.tf b/monitor/dashboards-namespace/datas.tf new file mode 100644 index 0000000..9797980 --- /dev/null +++ b/monitor/dashboards-namespace/datas.tf @@ -0,0 +1,16 @@ +locals { + common-labels = { + "vynil.solidite.fr/owner-name" = var.instance + "vynil.solidite.fr/owner-namespace" = var.namespace + "vynil.solidite.fr/owner-category" = var.category + "vynil.solidite.fr/owner-component" = var.component + "app.kubernetes.io/managed-by" = "vynil" + "app.kubernetes.io/instance" = var.instance + } +} + +data "kustomization_overlay" "data" { + common_labels = local.common-labels + namespace = var.namespace + resources = [for file in fileset(path.module, "*.yaml"): file if file != "index.yaml"] +} diff --git a/monitor/dashboards-namespace/index.yaml b/monitor/dashboards-namespace/index.yaml new file mode 100644 index 0000000..18a9096 --- /dev/null +++ b/monitor/dashboards-namespace/index.yaml @@ -0,0 +1,24 @@ +--- +apiVersion: vinyl.solidite.fr/v1beta1 +kind: Component +category: monitor +metadata: + name: dashboards-namespace + description: null +options: + useless: + default: true + examples: + - true + type: boolean +dependencies: [] +providers: + kubernetes: true + authentik: null + kubectl: true + postgresql: null + mysql: null + restapi: null + http: null + gitea: null +tfaddtype: null diff --git a/monitor/dashboards-namespace/v1_ConfigMap_prometheus-community-kube-k8s-resources-namespace.yaml b/monitor/dashboards-namespace/v1_ConfigMap_prometheus-community-kube-k8s-resources-namespace.yaml new file mode 100644 index 0000000..529f8ec --- /dev/null +++ b/monitor/dashboards-namespace/v1_ConfigMap_prometheus-community-kube-k8s-resources-namespace.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-namespace.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: prometheus-community-kube-k8s-resources-namespace + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +data: + k8s-resources-namespace.json: |- + {"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"links":[],"refresh":"10s","rows":[{"collapse":false,"height":"100px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"format":"percentunit","id":1,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":3,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})","format":"time_series","instant":true,"refId":"A"}],"thresholds":"70,80","timeFrom":null,"timeShift":null,"title":"CPU Utilisation (from requests)","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"singlestat","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"format":"percentunit","id":2,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":3,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})","format":"time_series","instant":true,"refId":"A"}],"thresholds":"70,80","timeFrom":null,"timeShift":null,"title":"CPU Utilisation (from limits)","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"singlestat","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"format":"percentunit","id":3,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":3,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})","format":"time_series","instant":true,"refId":"A"}],"thresholds":"70,80","timeFrom":null,"timeShift":null,"title":"Memory Utilisation (from requests)","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"singlestat","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"format":"percentunit","id":4,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":3,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})","format":"time_series","instant":true,"refId":"A"}],"thresholds":"70,80","timeFrom":null,"timeShift":null,"title":"Memory Utilisation (from limits)","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"singlestat","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Headlines","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":5,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"quota - requests","color":"#F2495C","dashes":true,"fill":0,"hiddenSeries":true,"hideTooltip":true,"legend":true,"linewidth":2,"stack":false},{"alias":"quota - limits","color":"#FF9830","dashes":true,"fill":0,"hiddenSeries":true,"hideTooltip":true,"legend":true,"linewidth":2,"stack":false}],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"time_series","legendFormat":"{{pod}}","legendLink":null},{"expr":"scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.cpu\"})","format":"time_series","legendFormat":"quota - requests","legendLink":null},{"expr":"scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.cpu\"})","format":"time_series","legendFormat":"quota - limits","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Usage","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"CPU Usage","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":6,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"CPU Usage","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Requests","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Requests %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"CPU Limits","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Limits %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"Pod","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":true,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__value.text}","pattern":"pod","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"B"},{"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"C"},{"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"D"},{"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"E"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Quota","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"CPU Quota","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":7,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"quota - requests","color":"#F2495C","dashes":true,"fill":0,"hiddenSeries":true,"hideTooltip":true,"legend":true,"linewidth":2,"stack":false},{"alias":"quota - limits","color":"#FF9830","dashes":true,"fill":0,"hiddenSeries":true,"hideTooltip":true,"legend":true,"linewidth":2,"stack":false}],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}) by (pod)","format":"time_series","legendFormat":"{{pod}}","legendLink":null},{"expr":"scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"})","format":"time_series","legendFormat":"quota - requests","legendLink":null},{"expr":"scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})","format":"time_series","legendFormat":"quota - limits","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory Usage (w/o cache)","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Memory Usage","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":8,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"Memory Usage","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Requests","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Requests %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"Memory Limits","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Limits %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"Memory Usage (RSS)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #F","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Usage (Cache)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #G","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Usage (Swap)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #H","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Pod","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":true,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__value.text}","pattern":"pod","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"B"},{"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"C"},{"expr":"sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"D"},{"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"E"},{"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"F"},{"expr":"sum(container_memory_cache{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"G"},{"expr":"sum(container_memory_swap{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"H"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory Quota","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Memory Quota","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":9,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"Current Receive Bandwidth","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Current Transmit Bandwidth","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Rate of Received Packets","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"pps"},{"alias":"Rate of Transmitted Packets","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"pps"},{"alias":"Rate of Received Packets Dropped","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"pps"},{"alias":"Rate of Transmitted Packets Dropped","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #F","thresholds":[],"type":"number","unit":"pps"},{"alias":"Pod","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":true,"linkTargetBlank":false,"linkTooltip":"Drill down to pods","linkUrl":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__value.text}","pattern":"pod","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"B"},{"expr":"sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"C"},{"expr":"sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"D"},{"expr":"sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"E"},{"expr":"sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"F"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Current Network Usage","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Current Network Usage","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":10,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Receive Bandwidth","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":11,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Transmit Bandwidth","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Bandwidth","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":12,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Received Packets","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":13,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Transmitted Packets","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Rate of Packets","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":14,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Received Packets Dropped","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":15,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Transmitted Packets Dropped","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Rate of Packets Dropped","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","decimals":null,"fill":10,"id":16,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"ceil(sum by(pod) (rate(container_fs_reads_total{container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_total{container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])))","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"IOPS(Reads+Writes)","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":17,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by(pod) (rate(container_fs_reads_bytes_total{container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"ThroughPut(Read+Write)","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Storage IO","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":18,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"sort":{"col":4,"desc":true},"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"IOPS(Reads)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":3,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"number","unit":"iops"},{"alias":"IOPS(Writes)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":3,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"iops"},{"alias":"IOPS(Reads + Writes)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":3,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"iops"},{"alias":"Throughput(Read)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Throughput(Write)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Throughput(Read + Write)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #F","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Pod","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":true,"linkTargetBlank":false,"linkTooltip":"Drill down to pods","linkUrl":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__value.text}","pattern":"pod","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"sum by(pod) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"sum by(pod) (rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))","format":"table","instant":true,"legendFormat":"","refId":"B"},{"expr":"sum by(pod) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))","format":"table","instant":true,"legendFormat":"","refId":"C"},{"expr":"sum by(pod) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))","format":"table","instant":true,"legendFormat":"","refId":"D"},{"expr":"sum by(pod) (rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))","format":"table","instant":true,"legendFormat":"","refId":"E"},{"expr":"sum by(pod) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))","format":"table","instant":true,"legendFormat":"","refId":"F"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Current Storage IO","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Storage IO - Distribution","titleSize":"h6"}],"schemaVersion":14,"style":"dark","tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{"text":"","value":""},"datasource":"$datasource","hide":2,"includeAll":false,"label":null,"multi":false,"name":"cluster","options":[],"query":"label_values(up{job=\"kube-state-metrics\"}, cluster)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{"text":"","value":""},"datasource":"$datasource","hide":0,"includeAll":false,"label":null,"multi":false,"name":"namespace","options":[],"query":"label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Kubernetes / Compute Resources / Namespace (Pods)","uid":"85a562078cdf77779eaa1add43ccec1e","version":0} \ No newline at end of file diff --git a/monitor/dashboards-namespace/v1_ConfigMap_prometheus-community-kube-k8s-resources-workloads-namespace.yaml b/monitor/dashboards-namespace/v1_ConfigMap_prometheus-community-kube-k8s-resources-workloads-namespace.yaml new file mode 100644 index 0000000..95be31e --- /dev/null +++ b/monitor/dashboards-namespace/v1_ConfigMap_prometheus-community-kube-k8s-resources-workloads-namespace.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-workloads-namespace.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: prometheus-community-kube-k8s-resources-workloads-namespace + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +data: + k8s-resources-workloads-namespace.json: |- + {"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"links":[],"refresh":"10s","rows":[{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":1,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"quota - requests","color":"#F2495C","dashes":true,"fill":0,"hiddenSeries":true,"hideTooltip":true,"legend":true,"linewidth":2,"stack":false},{"alias":"quota - limits","color":"#FF9830","dashes":true,"fill":0,"hiddenSeries":true,"hideTooltip":true,"legend":true,"linewidth":2,"stack":false}],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"time_series","legendFormat":"{{workload}} - {{workload_type}}","legendLink":null},{"expr":"scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.cpu\"})","format":"time_series","legendFormat":"quota - requests","legendLink":null},{"expr":"scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.cpu\"})","format":"time_series","legendFormat":"quota - limits","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Usage","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"CPU Usage","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":2,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"Running Pods","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":0,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Usage","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Requests","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Requests %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"CPU Limits","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Limits %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #F","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"Workload","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":true,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"/d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=${__value.text}&var-type=${__data.fields.workload_type}","pattern":"workload","thresholds":[],"type":"number","unit":"short"},{"alias":"Workload Type","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"workload_type","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload, workload_type)","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true,"legendFormat":"","refId":"B"},{"expr":"sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true,"legendFormat":"","refId":"C"},{"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true,"legendFormat":"","refId":"D"},{"expr":"sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true,"legendFormat":"","refId":"E"},{"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true,"legendFormat":"","refId":"F"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Quota","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"CPU Quota","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":3,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"quota - requests","color":"#F2495C","dashes":true,"fill":0,"hiddenSeries":true,"hideTooltip":true,"legend":true,"linewidth":2,"stack":false},{"alias":"quota - limits","color":"#FF9830","dashes":true,"fill":0,"hiddenSeries":true,"hideTooltip":true,"legend":true,"linewidth":2,"stack":false}],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"time_series","legendFormat":"{{workload}} - {{workload_type}}","legendLink":null},{"expr":"scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"})","format":"time_series","legendFormat":"quota - requests","legendLink":null},{"expr":"scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})","format":"time_series","legendFormat":"quota - limits","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory Usage","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Memory Usage","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":4,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"Running Pods","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":0,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"number","unit":"short"},{"alias":"Memory Usage","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Requests","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Requests %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"Memory Limits","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Limits %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #F","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"Workload","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":true,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"/d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=${__value.text}&var-type=${__data.fields.workload_type}","pattern":"workload","thresholds":[],"type":"number","unit":"short"},{"alias":"Workload Type","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"workload_type","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload, workload_type)","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true,"legendFormat":"","refId":"B"},{"expr":"sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true,"legendFormat":"","refId":"C"},{"expr":"sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true,"legendFormat":"","refId":"D"},{"expr":"sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true,"legendFormat":"","refId":"E"},{"expr":"sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}\n) by (workload, workload_type)\n","format":"table","instant":true,"legendFormat":"","refId":"F"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory Quota","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Memory Quota","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":5,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"Current Receive Bandwidth","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Current Transmit Bandwidth","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Rate of Received Packets","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"pps"},{"alias":"Rate of Transmitted Packets","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"pps"},{"alias":"Rate of Received Packets Dropped","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"pps"},{"alias":"Rate of Transmitted Packets Dropped","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #F","thresholds":[],"type":"number","unit":"pps"},{"alias":"Workload","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":true,"linkTargetBlank":false,"linkTooltip":"Drill down to pods","linkUrl":"/d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=${__value.text}&var-type=$type","pattern":"workload","thresholds":[],"type":"number","unit":"short"},{"alias":"Workload Type","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"workload_type","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true,"legendFormat":"","refId":"B"},{"expr":"(sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true,"legendFormat":"","refId":"C"},{"expr":"(sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true,"legendFormat":"","refId":"D"},{"expr":"(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true,"legendFormat":"","refId":"E"},{"expr":"(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}) by (workload))\n","format":"table","instant":true,"legendFormat":"","refId":"F"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Current Network Usage","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Current Network Usage","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":6,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"time_series","legendFormat":"{{workload}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Receive Bandwidth","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":7,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"time_series","legendFormat":"{{workload}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Transmit Bandwidth","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Bandwidth","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":8,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"(avg(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"time_series","legendFormat":"{{workload}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Average Container Bandwidth by Workload: Received","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":9,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"(avg(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"time_series","legendFormat":"{{workload}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Average Container Bandwidth by Workload: Transmitted","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Average Container Bandwidth by Workload","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":10,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"(sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"time_series","legendFormat":"{{workload}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Received Packets","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":11,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"(sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"time_series","legendFormat":"{{workload}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Transmitted Packets","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Rate of Packets","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":12,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"time_series","legendFormat":"{{workload}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Received Packets Dropped","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":13,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=~\"$type\"}) by (workload))\n","format":"time_series","legendFormat":"{{workload}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Transmitted Packets Dropped","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Rate of Packets Dropped","titleSize":"h6"}],"schemaVersion":14,"style":"dark","tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{"text":"","value":""},"datasource":"$datasource","hide":2,"includeAll":false,"label":null,"multi":false,"name":"cluster","options":[],"query":"label_values(up{job=\"kube-state-metrics\"}, cluster)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{"text":"","value":""},"datasource":"$datasource","hide":0,"includeAll":false,"label":null,"multi":false,"name":"namespace","options":[],"query":"label_values(kube_pod_info{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"auto":false,"auto_count":30,"auto_min":"10s","current":{"text":"","value":""},"datasource":"$datasource","definition":"label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)","hide":0,"includeAll":true,"label":null,"multi":false,"name":"type","options":[],"query":"label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)","refresh":2,"regex":"","skipUrlSync":false,"sort":0,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Kubernetes / Compute Resources / Namespace (Workloads)","uid":"a87fb0d919ec0ea5f6543124e16c42a5","version":0} \ No newline at end of file diff --git a/monitor/dashboards-workload/datas.tf b/monitor/dashboards-workload/datas.tf new file mode 100644 index 0000000..9797980 --- /dev/null +++ b/monitor/dashboards-workload/datas.tf @@ -0,0 +1,16 @@ +locals { + common-labels = { + "vynil.solidite.fr/owner-name" = var.instance + "vynil.solidite.fr/owner-namespace" = var.namespace + "vynil.solidite.fr/owner-category" = var.category + "vynil.solidite.fr/owner-component" = var.component + "app.kubernetes.io/managed-by" = "vynil" + "app.kubernetes.io/instance" = var.instance + } +} + +data "kustomization_overlay" "data" { + common_labels = local.common-labels + namespace = var.namespace + resources = [for file in fileset(path.module, "*.yaml"): file if file != "index.yaml"] +} diff --git a/monitor/dashboards-workload/index.yaml b/monitor/dashboards-workload/index.yaml new file mode 100644 index 0000000..6fa8bcc --- /dev/null +++ b/monitor/dashboards-workload/index.yaml @@ -0,0 +1,24 @@ +--- +apiVersion: vinyl.solidite.fr/v1beta1 +kind: Component +category: monitor +metadata: + name: dashboards-workload + description: null +options: + useless: + default: true + examples: + - true + type: boolean +dependencies: [] +providers: + kubernetes: true + authentik: null + kubectl: true + postgresql: null + mysql: null + restapi: null + http: null + gitea: null +tfaddtype: null diff --git a/monitor/dashboards-workload/v1_ConfigMap_prometheus-community-kube-k8s-resources-node.yaml b/monitor/dashboards-workload/v1_ConfigMap_prometheus-community-kube-k8s-resources-node.yaml new file mode 100644 index 0000000..62ccd05 --- /dev/null +++ b/monitor/dashboards-workload/v1_ConfigMap_prometheus-community-kube-k8s-resources-node.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-node.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: prometheus-community-kube-k8s-resources-node + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +data: + k8s-resources-node.json: |- + {"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"links":[],"refresh":"10s","rows":[{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":1,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"max capacity","color":"#F2495C","dashes":true,"fill":0,"hiddenSeries":true,"hideTooltip":true,"legend":true,"linewidth":2,"stack":false}],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(kube_node_status_capacity{cluster=\"$cluster\", node=~\"$node\", resource=\"cpu\"})","format":"time_series","legendFormat":"max capacity","legendLink":null},{"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Usage","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"CPU Usage","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":2,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"CPU Usage","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Requests","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Requests %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"CPU Limits","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Limits %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"Pod","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"pod","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"B"},{"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"C"},{"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"D"},{"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"E"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Quota","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"CPU Quota","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":3,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"max capacity","color":"#F2495C","dashes":true,"fill":0,"hiddenSeries":true,"hideTooltip":true,"legend":true,"linewidth":2,"stack":false}],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(kube_node_status_capacity{cluster=\"$cluster\", node=~\"$node\", resource=\"memory\"})","format":"time_series","legendFormat":"max capacity","legendLink":null},{"expr":"sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\", container!=\"\"}) by (pod)","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory Usage (w/o cache)","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Memory Usage","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":4,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"Memory Usage","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Requests","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Requests %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"Memory Limits","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Limits %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"Memory Usage (RSS)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #F","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Usage (Cache)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #G","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Usage (Swap)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #H","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Pod","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"pod","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"B"},{"expr":"sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"C"},{"expr":"sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"D"},{"expr":"sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"E"},{"expr":"sum(node_namespace_pod_container:container_memory_rss{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"F"},{"expr":"sum(node_namespace_pod_container:container_memory_cache{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"G"},{"expr":"sum(node_namespace_pod_container:container_memory_swap{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)","format":"table","instant":true,"legendFormat":"","refId":"H"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory Quota","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Memory Quota","titleSize":"h6"}],"schemaVersion":14,"style":"dark","tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{"text":"","value":""},"datasource":"$datasource","hide":2,"includeAll":false,"label":null,"multi":false,"name":"cluster","options":[],"query":"label_values(up{job=\"kube-state-metrics\"}, cluster)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{"text":"","value":""},"datasource":"$datasource","hide":0,"includeAll":false,"label":null,"multi":true,"name":"node","options":[],"query":"label_values(kube_node_info{cluster=\"$cluster\"}, node)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Kubernetes / Compute Resources / Node (Pods)","uid":"200ac8fdbfbb74b39aff88118e4d1c2c","version":0} \ No newline at end of file diff --git a/monitor/dashboards-workload/v1_ConfigMap_prometheus-community-kube-k8s-resources-pod.yaml b/monitor/dashboards-workload/v1_ConfigMap_prometheus-community-kube-k8s-resources-pod.yaml new file mode 100644 index 0000000..81a9b03 --- /dev/null +++ b/monitor/dashboards-workload/v1_ConfigMap_prometheus-community-kube-k8s-resources-pod.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-pod.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: prometheus-community-kube-k8s-resources-pod + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +data: + k8s-resources-pod.json: |- + {"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"links":[],"refresh":"10s","rows":[{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":1,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"requests","color":"#F2495C","fill":0,"hideTooltip":true,"legend":true,"linewidth":2,"stack":false},{"alias":"limits","color":"#FF9830","fill":0,"hideTooltip":true,"legend":true,"linewidth":2,"stack":false}],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}) by (container)","format":"time_series","legendFormat":"{{container}}","legendLink":null},{"expr":"sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n","format":"time_series","legendFormat":"requests","legendLink":null},{"expr":"sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n","format":"time_series","legendFormat":"limits","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Usage","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"CPU Usage","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":2,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":true,"max":true,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(increase(container_cpu_cfs_throttled_periods_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval])) by (container) /sum(increase(container_cpu_cfs_periods_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval])) by (container)","format":"time_series","legendFormat":"{{container}}","legendLink":null}],"thresholds":[{"colorMode":"critical","fill":true,"line":true,"op":"gt","value":0.25,"yaxis":"left"}],"timeFrom":null,"timeShift":null,"title":"CPU Throttling","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":1,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"CPU Throttling","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":3,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"CPU Usage","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Requests","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Requests %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"CPU Limits","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Limits %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"Container","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"container","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)","format":"table","instant":true,"legendFormat":"","refId":"B"},{"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)","format":"table","instant":true,"legendFormat":"","refId":"C"},{"expr":"sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)","format":"table","instant":true,"legendFormat":"","refId":"D"},{"expr":"sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)","format":"table","instant":true,"legendFormat":"","refId":"E"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Quota","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"CPU Quota","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":4,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"requests","color":"#F2495C","dashes":true,"fill":0,"hideTooltip":true,"legend":true,"linewidth":2,"stack":false},{"alias":"limits","color":"#FF9830","dashes":true,"fill":0,"hideTooltip":true,"legend":true,"linewidth":2,"stack":false}],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container)","format":"time_series","legendFormat":"{{container}}","legendLink":null},{"expr":"sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}\n)\n","format":"time_series","legendFormat":"requests","legendLink":null},{"expr":"sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}\n)\n","format":"time_series","legendFormat":"limits","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory Usage (WSS)","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Memory Usage","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":5,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"Memory Usage (WSS)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Requests","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Requests %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"Memory Limits","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Limits %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"Memory Usage (RSS)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #F","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Usage (Cache)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #G","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Usage (Swap)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #H","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Container","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"container","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container)","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)","format":"table","instant":true,"legendFormat":"","refId":"B"},{"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", image!=\"\"}) by (container) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)","format":"table","instant":true,"legendFormat":"","refId":"C"},{"expr":"sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)","format":"table","instant":true,"legendFormat":"","refId":"D"},{"expr":"sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)","format":"table","instant":true,"legendFormat":"","refId":"E"},{"expr":"sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)","format":"table","instant":true,"legendFormat":"","refId":"F"},{"expr":"sum(container_memory_cache{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)","format":"table","instant":true,"legendFormat":"","refId":"G"},{"expr":"sum(container_memory_swap{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)","format":"table","instant":true,"legendFormat":"","refId":"H"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory Quota","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Memory Quota","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":6,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Receive Bandwidth","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":7,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Transmit Bandwidth","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Bandwidth","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":8,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Received Packets","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":9,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Transmitted Packets","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Rate of Packets","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":10,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Received Packets Dropped","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":11,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Transmitted Packets Dropped","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Rate of Packets Dropped","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","decimals":null,"fill":10,"id":12,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"ceil(sum by(pod) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])))","format":"time_series","legendFormat":"Reads","legendLink":null},{"expr":"ceil(sum by(pod) (rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])))","format":"time_series","legendFormat":"Writes","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"IOPS","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":13,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by(pod) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))","format":"time_series","legendFormat":"Reads","legendLink":null},{"expr":"sum by(pod) (rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))","format":"time_series","legendFormat":"Writes","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"ThroughPut","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Storage IO - Distribution(Pod - Read & Writes)","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","decimals":null,"fill":10,"id":14,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"ceil(sum by(container) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval])))","format":"time_series","legendFormat":"{{container}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"IOPS(Reads+Writes)","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":15,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by(container) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))","format":"time_series","legendFormat":"{{container}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"ThroughPut(Read+Write)","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Storage IO - Distribution(Containers)","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":16,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"sort":{"col":4,"desc":true},"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"IOPS(Reads)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":3,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"number","unit":"iops"},{"alias":"IOPS(Writes)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":3,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"iops"},{"alias":"IOPS(Reads + Writes)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":3,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"iops"},{"alias":"Throughput(Read)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Throughput(Write)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Throughput(Read + Write)","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #F","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Container","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"container","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"sum by(container) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"sum by(container) (rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\",device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))","format":"table","instant":true,"legendFormat":"","refId":"B"},{"expr":"sum by(container) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))","format":"table","instant":true,"legendFormat":"","refId":"C"},{"expr":"sum by(container) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))","format":"table","instant":true,"legendFormat":"","refId":"D"},{"expr":"sum by(container) (rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))","format":"table","instant":true,"legendFormat":"","refId":"E"},{"expr":"sum by(container) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))","format":"table","instant":true,"legendFormat":"","refId":"F"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Current Storage IO","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Storage IO - Distribution","titleSize":"h6"}],"schemaVersion":14,"style":"dark","tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{"text":"","value":""},"datasource":"$datasource","hide":2,"includeAll":false,"label":null,"multi":false,"name":"cluster","options":[],"query":"label_values(up{job=\"kube-state-metrics\"}, cluster)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{"text":"","value":""},"datasource":"$datasource","hide":0,"includeAll":false,"label":null,"multi":false,"name":"namespace","options":[],"query":"label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{"text":"","value":""},"datasource":"$datasource","hide":0,"includeAll":false,"label":null,"multi":false,"name":"pod","options":[],"query":"label_values(kube_pod_info{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\"}, pod)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Kubernetes / Compute Resources / Pod","uid":"6581e46e4e5c7ba40a07646395ef7b23","version":0} \ No newline at end of file diff --git a/monitor/dashboards-workload/v1_ConfigMap_prometheus-community-kube-k8s-resources-workload.yaml b/monitor/dashboards-workload/v1_ConfigMap_prometheus-community-kube-k8s-resources-workload.yaml new file mode 100644 index 0000000..3eb6155 --- /dev/null +++ b/monitor/dashboards-workload/v1_ConfigMap_prometheus-community-kube-k8s-resources-workload.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-resources-workload.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: prometheus-community-kube-k8s-resources-workload + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +data: + k8s-resources-workload.json: |- + {"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"links":[],"refresh":"10s","rows":[{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":1,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Usage","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"CPU Usage","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":2,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"CPU Usage","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Requests","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Requests %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"CPU Limits","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"short"},{"alias":"CPU Limits %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"Pod","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":true,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__value.text}","pattern":"pod","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true,"legendFormat":"","refId":"B"},{"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true,"legendFormat":"","refId":"C"},{"expr":"sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true,"legendFormat":"","refId":"D"},{"expr":"sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true,"legendFormat":"","refId":"E"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Quota","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"CPU Quota","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":3,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory Usage","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Memory Usage","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":4,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"Memory Usage","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Requests","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Requests %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"Memory Limits","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"bytes"},{"alias":"Memory Limits %","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"percentunit"},{"alias":"Pod","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":true,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__value.text}","pattern":"pod","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true,"legendFormat":"","refId":"B"},{"expr":"sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true,"legendFormat":"","refId":"C"},{"expr":"sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true,"legendFormat":"","refId":"D"},{"expr":"sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=~\"$type\"}\n) by (pod)\n","format":"table","instant":true,"legendFormat":"","refId":"E"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory Quota","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Memory Quota","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":5,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"Current Receive Bandwidth","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Current Transmit Bandwidth","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"Bps"},{"alias":"Rate of Received Packets","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #C","thresholds":[],"type":"number","unit":"pps"},{"alias":"Rate of Transmitted Packets","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #D","thresholds":[],"type":"number","unit":"pps"},{"alias":"Rate of Received Packets Dropped","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #E","thresholds":[],"type":"number","unit":"pps"},{"alias":"Rate of Transmitted Packets Dropped","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #F","thresholds":[],"type":"number","unit":"pps"},{"alias":"Pod","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":true,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=${__value.text}","pattern":"pod","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"table","instant":true,"legendFormat":"","refId":"B"},{"expr":"(sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"table","instant":true,"legendFormat":"","refId":"C"},{"expr":"(sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"table","instant":true,"legendFormat":"","refId":"D"},{"expr":"(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"table","instant":true,"legendFormat":"","refId":"E"},{"expr":"(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"table","instant":true,"legendFormat":"","refId":"F"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Current Network Usage","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Current Network Usage","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":6,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Receive Bandwidth","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":7,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Transmit Bandwidth","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Bandwidth","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":8,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"(avg(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Average Container Bandwidth by Pod: Received","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":9,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"(avg(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Average Container Bandwidth by Pod: Transmitted","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Average Container Bandwidth by Pod","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":10,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"(sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Received Packets","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":11,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"(sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Transmitted Packets","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Rate of Packets","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":12,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Received Packets Dropped","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":13,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=~\"$type\"}) by (pod))\n","format":"time_series","legendFormat":"{{pod}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rate of Transmitted Packets Dropped","tooltip":{"shared":false,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Rate of Packets Dropped","titleSize":"h6"}],"schemaVersion":14,"style":"dark","tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{"text":"","value":""},"datasource":"$datasource","hide":2,"includeAll":false,"label":null,"multi":false,"name":"cluster","options":[],"query":"label_values(up{job=\"kube-state-metrics\"}, cluster)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{"text":"","value":""},"datasource":"$datasource","hide":0,"includeAll":false,"label":null,"multi":false,"name":"namespace","options":[],"query":"label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{"text":"","value":""},"datasource":"$datasource","hide":0,"includeAll":true,"label":null,"multi":false,"name":"type","options":[],"query":"label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\"}, workload_type)","refresh":2,"regex":"","sort":0,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{"text":"","value":""},"datasource":"$datasource","hide":0,"includeAll":false,"label":null,"multi":false,"name":"workload","options":[],"query":"label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=~\"$type\"}, workload)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Kubernetes / Compute Resources / Workload","uid":"a164a7f0339f99e89cea5cb47e9be617","version":0} \ No newline at end of file diff --git a/monitor/grafana/apps_v1_Deployment_grafana.yaml b/monitor/grafana/apps_v1_Deployment_grafana.yaml new file mode 100644 index 0000000..63e0341 --- /dev/null +++ b/monitor/grafana/apps_v1_Deployment_grafana.yaml @@ -0,0 +1,298 @@ +# Source: grafana/templates/deployment.yaml +apiVersion: apps/v1 +kind: Deployment +metadata: + name: grafana + namespace: vynil-monitor + labels: + helm.sh/chart: grafana-7.2.5 + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: grafana + app.kubernetes.io/version: "10.2.3" + app.kubernetes.io/managed-by: Helm +spec: + replicas: 1 + revisionHistoryLimit: 10 + selector: + matchLabels: + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: grafana + strategy: + type: RollingUpdate + template: + metadata: + labels: + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: grafana + annotations: + checksum/config: 0e9cbd0ea8e24e32f7dfca5bab17a2ba05652642f0a09a4882833ae88e4cc4a3 + checksum/sc-dashboard-provider-config: 593c0a8778b83f11fe80ccb21dfb20bc46705e2be3178df1dc4c89d164c8cd9c + kubectl.kubernetes.io/default-container: grafana + spec: + + serviceAccountName: grafana + automountServiceAccountToken: true + securityContext: + fsGroup: 472 + runAsGroup: 472 + runAsNonRoot: true + runAsUser: 472 + initContainers: + - name: init-chown-data + image: "docker.io/library/busybox:1.31.1" + imagePullPolicy: IfNotPresent + securityContext: + capabilities: + add: + - CHOWN + runAsNonRoot: false + runAsUser: 0 + seccompProfile: + type: RuntimeDefault + command: + - chown + - -R + - 472:472 + - /var/lib/grafana + volumeMounts: + - name: storage + mountPath: "/var/lib/grafana" + enableServiceLinks: true + containers: + - name: grafana-sc-dashboard + image: "quay.io/kiwigrid/k8s-sidecar:1.25.2" + imagePullPolicy: IfNotPresent + env: + - name: METHOD + value: WATCH + - name: LABEL + value: "grafana_dashboard" + - name: FOLDER + value: "/tmp/dashboards" + - name: RESOURCE + value: "both" + - name: REQ_USERNAME + valueFrom: + secretKeyRef: + name: grafana-admin-user + key: username + - name: REQ_PASSWORD + valueFrom: + secretKeyRef: + name: grafana-admin-user + key: password + - name: REQ_URL + value: http://localhost:3000/api/admin/provisioning/dashboards/reload + - name: REQ_METHOD + value: POST + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + seccompProfile: + type: RuntimeDefault + volumeMounts: + - name: sc-dashboard-volume + mountPath: "/tmp/dashboards" + - name: grafana-sc-datasources + image: "quay.io/kiwigrid/k8s-sidecar:1.25.2" + imagePullPolicy: IfNotPresent + env: + - name: METHOD + value: WATCH + - name: LABEL + value: "grafana_datasource" + - name: FOLDER + value: "/etc/grafana/provisioning/datasources" + - name: RESOURCE + value: "both" + - name: REQ_USERNAME + valueFrom: + secretKeyRef: + name: grafana-admin-user + key: username + - name: REQ_PASSWORD + valueFrom: + secretKeyRef: + name: grafana-admin-user + key: password + - name: REQ_URL + value: http://localhost:3000/api/admin/provisioning/datasources/reload + - name: REQ_METHOD + value: POST + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + seccompProfile: + type: RuntimeDefault + volumeMounts: + - name: sc-datasources-volume + mountPath: "/etc/grafana/provisioning/datasources" + - name: grafana-sc-notifiers + image: "quay.io/kiwigrid/k8s-sidecar:1.25.2" + imagePullPolicy: IfNotPresent + env: + - name: METHOD + value: WATCH + - name: LABEL + value: "grafana_notifier" + - name: FOLDER + value: "/etc/grafana/provisioning/notifiers" + - name: RESOURCE + value: "both" + - name: REQ_USERNAME + valueFrom: + secretKeyRef: + name: grafana-admin-user + key: username + - name: REQ_PASSWORD + valueFrom: + secretKeyRef: + name: grafana-admin-user + key: password + - name: REQ_URL + value: http://localhost:3000/api/admin/provisioning/notifications/reload + - name: REQ_METHOD + value: POST + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + seccompProfile: + type: RuntimeDefault + volumeMounts: + - name: sc-notifiers-volume + mountPath: "/etc/grafana/provisioning/notifiers" + - name: grafana-sc-plugins + image: "quay.io/kiwigrid/k8s-sidecar:1.25.2" + imagePullPolicy: IfNotPresent + env: + - name: METHOD + value: WATCH + - name: LABEL + value: "grafana_plugin" + - name: FOLDER + value: "/etc/grafana/provisioning/plugins" + - name: RESOURCE + value: "both" + - name: REQ_USERNAME + valueFrom: + secretKeyRef: + name: grafana-admin-user + key: username + - name: REQ_PASSWORD + valueFrom: + secretKeyRef: + name: grafana-admin-user + key: password + - name: REQ_URL + value: http://localhost:3000/api/admin/provisioning/plugins/reload + - name: REQ_METHOD + value: POST + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + seccompProfile: + type: RuntimeDefault + volumeMounts: + - name: sc-plugins-volume + mountPath: "/etc/grafana/provisioning/plugins" + - name: grafana + image: "docker.io/grafana/grafana:10.2.3" + imagePullPolicy: IfNotPresent + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + seccompProfile: + type: RuntimeDefault + volumeMounts: + - name: config + mountPath: "/etc/grafana/grafana.ini" + subPath: grafana.ini + - name: storage + mountPath: "/var/lib/grafana" + - name: sc-dashboard-volume + mountPath: "/tmp/dashboards" + - name: sc-dashboard-provider + mountPath: "/etc/grafana/provisioning/dashboards/sc-dashboardproviders.yaml" + subPath: provider.yaml + - name: sc-datasources-volume + mountPath: "/etc/grafana/provisioning/datasources" + - name: sc-plugins-volume + mountPath: "/etc/grafana/provisioning/plugins" + - name: sc-notifiers-volume + mountPath: "/etc/grafana/provisioning/notifiers" + ports: + - name: grafana + containerPort: 3000 + protocol: TCP + - name: gossip-tcp + containerPort: 9094 + protocol: TCP + - name: gossip-udp + containerPort: 9094 + protocol: UDP + env: + - name: POD_IP + valueFrom: + fieldRef: + fieldPath: status.podIP + - name: GF_SECURITY_ADMIN_USER + valueFrom: + secretKeyRef: + name: grafana-admin-user + key: username + - name: GF_SECURITY_ADMIN_PASSWORD + valueFrom: + secretKeyRef: + name: grafana-admin-user + key: password + - name: GF_PATHS_DATA + value: /var/lib/grafana/ + - name: GF_PATHS_LOGS + value: /var/log/grafana + - name: GF_PATHS_PLUGINS + value: /var/lib/grafana/plugins + - name: GF_PATHS_PROVISIONING + value: /etc/grafana/provisioning + livenessProbe: + failureThreshold: 10 + httpGet: + path: /api/health + port: 3000 + initialDelaySeconds: 60 + timeoutSeconds: 30 + readinessProbe: + httpGet: + path: /api/health + port: 3000 + volumes: + - name: config + configMap: + name: grafana + - name: storage + persistentVolumeClaim: + claimName: grafana + - name: sc-dashboard-volume + emptyDir: + {} + - name: sc-dashboard-provider + configMap: + name: grafana-config-dashboards + - name: sc-datasources-volume + emptyDir: + {} + - name: sc-plugins-volume + emptyDir: + {} + - name: sc-notifiers-volume + emptyDir: + {} \ No newline at end of file diff --git a/monitor/grafana/config.tf b/monitor/grafana/config.tf new file mode 100644 index 0000000..d10de92 --- /dev/null +++ b/monitor/grafana/config.tf @@ -0,0 +1,43 @@ +resource "kubernetes_config_map_v1" "config" { + metadata { + name = "grafana" + namespace = var.namespace + labels = local.common-labels + } + data = { + "grafana.ini" = <<-EOF +[analytics] +check_for_updates = true +[grafana_net] +url = https://grafana.net +[log] +mode = console +[paths] +data = /var/lib/grafana/ +logs = /var/log/grafana +plugins = /var/lib/grafana/plugins +provisioning = /etc/grafana/provisioning +[server] +domain = '' +root_url = 'https://${local.dns_name}/' +[users] +auto_assign_org = true +auto_assign_org_id = 1 +[auth] +oauth_allow_insecure_email_lookup = true +signout_redirect_url = '${module.oauth2.sso_signout_url}' +oauth_auto_login = true +[auth.generic_oauth] +enabled = true +name = vynil +scopes = openid profile email +${var.issuer=="letsencrypt-prod"?";":""}tls_client_ca = /etc/local-certs/ca.crt +client_id = '${module.oauth2.client_id}' +client_secret = '${module.oauth2.client_secret}' +auth_url = '${module.oauth2.sso_authorize_url}' +api_url = '${module.oauth2.sso_userinfo_url}' +token_url = '${module.oauth2.sso_token_url}' +role_attribute_path = contains(groups, '${module.application.main_group}-admin') && 'Admin' || contains(groups, '${module.application.main_group}') && 'Editor' || 'Viewer' + EOF + } +} diff --git a/monitor/grafana/datas.tf b/monitor/grafana/datas.tf new file mode 100644 index 0000000..591b91d --- /dev/null +++ b/monitor/grafana/datas.tf @@ -0,0 +1,112 @@ +locals { + authentik_url = "http://authentik.${var.domain}-auth.svc" + authentik_token = data.kubernetes_secret_v1.authentik.data["AUTHENTIK_BOOTSTRAP_TOKEN"] + common-labels = { + "vynil.solidite.fr/owner-name" = var.instance + "vynil.solidite.fr/owner-namespace" = var.namespace + "vynil.solidite.fr/owner-category" = var.category + "vynil.solidite.fr/owner-component" = var.component + "app.kubernetes.io/managed-by" = "vynil" + "app.kubernetes.io/instance" = var.instance + } + pvc_spec = merge({ + "accessModes" = [var.storage.volume.accessMode] + "volumeMode" = var.storage.volume.type + "resources" = { + "requests" = { + "storage" = "${var.storage.volume.size}" + } + } + }, var.storage.volume.class != "" ?{ + "storageClassName" = var.storage.volume.class + }:{}) +} + + +data "kubernetes_secret_v1" "authentik" { + metadata { + name = "authentik" + namespace = "${var.domain}-auth" + } +} + +data "kubernetes_ingress_v1" "authentik" { + metadata { + name = "authentik" + namespace = "${var.domain}-auth" + } +} + +data "kustomization_overlay" "data" { + common_labels = local.common-labels + namespace = var.namespace + resources = [for file in fileset(path.module, "*.yaml"): file if file != "index.yaml" && length(regexall("ClusterRole",file))<1] + images { + name = "docker.io/grafana/grafana" + new_name = "${var.images.grafana.registry}/${var.images.grafana.repository}" + new_tag = "${var.images.grafana.tag}" + } + images { + name = "docker.io/library/busybox" + new_name = "${var.images.busybox.registry}/${var.images.busybox.repository}" + new_tag = "${var.images.busybox.tag}" + } + images { + name = "quay.io/kiwigrid/k8s-sidecar" + new_name = "${var.images.sidecar.registry}/${var.images.sidecar.repository}" + new_tag = "${var.images.sidecar.tag}" + } + patches { + target { + kind = "PersistentVolumeClaim" + name = "grafana" + } + patch = <<-EOF + kind: PersistentVolumeClaim + apiVersion: v1 + metadata: + name: grafana + annotations: + k8up.io/backup: "true" + spec: ${jsonencode(local.pvc_spec)} + EOF + } + patches { + target { + kind = "ServiceMonitor" + name = "grafana" + } + patch = <<-EOF + - op: replace + path: /spec/namespaceSelector/matchNames/0 + value: "${var.namespace}" + EOF + } + patches { + target { + kind = "Deployment" + name = "grafana" + } + patch = <<-EOF + apiVersion: apps/v1 + kind: Deployment + metadata: + name: grafana + annotations: + configmap.reloader.stakater.com/reload: "grafana" + spec: + template: + spec: + containers: + - name: grafana + volumeMounts: + - name: local-certs + mountPath: "/etc/local-certs" + volumes: + - name: local-certs + secret: + secretName: "${var.instance}-cert" + defaultMode: 0444 + EOF + } +} diff --git a/monitor/grafana/index.yaml b/monitor/grafana/index.yaml new file mode 100644 index 0000000..daab533 --- /dev/null +++ b/monitor/grafana/index.yaml @@ -0,0 +1,194 @@ +--- +apiVersion: vinyl.solidite.fr/v1beta1 +kind: Component +category: monitor +metadata: + name: grafana + description: null +options: + domain_name: + default: your_company.com + examples: + - your_company.com + type: string + storage: + default: + volume: + accessMode: ReadWriteOnce + class: '' + size: 10Gi + type: Filesystem + description: Configure this app storage + examples: + - volume: + accessMode: ReadWriteOnce + class: '' + size: 10Gi + type: Filesystem + properties: + volume: + default: + accessMode: ReadWriteOnce + class: '' + size: 10Gi + type: Filesystem + properties: + accessMode: + default: ReadWriteOnce + enum: + - ReadWriteOnce + - ReadOnlyMany + - ReadWriteMany + type: string + class: + default: '' + type: string + size: + default: 10Gi + type: string + type: + default: Filesystem + enum: + - Filesystem + - Block + type: string + type: object + type: object + ingress_class: + default: traefik + examples: + - traefik + type: string + sub_domain: + default: grafana + examples: + - grafana + type: string + issuer: + default: letsencrypt-prod + examples: + - letsencrypt-prod + type: string + domain: + default: your-company + examples: + - your-company + type: string + admin_name: + default: grafana_admin + examples: + - grafana_admin + type: string + app_group: + default: monitor + examples: + - monitor + type: string + images: + default: + busybox: + registry: docker.io + repository: library/busybox + tag: 1.31.1 + grafana: + pullPolicy: IfNotPresent + registry: docker.io + repository: grafana/grafana + tag: 10.2.3 + sidecar: + pullPolicy: IfNotPresent + registry: quay.io + repository: kiwigrid/k8s-sidecar + tag: 1.25.2 + examples: + - busybox: + registry: docker.io + repository: library/busybox + tag: 1.31.1 + grafana: + pullPolicy: IfNotPresent + registry: docker.io + repository: grafana/grafana + tag: 10.2.3 + sidecar: + pullPolicy: IfNotPresent + registry: quay.io + repository: kiwigrid/k8s-sidecar + tag: 1.25.2 + properties: + busybox: + default: + registry: docker.io + repository: library/busybox + tag: 1.31.1 + properties: + registry: + default: docker.io + type: string + repository: + default: library/busybox + type: string + tag: + default: 1.31.1 + type: string + type: object + grafana: + default: + pullPolicy: IfNotPresent + registry: docker.io + repository: grafana/grafana + tag: 10.2.3 + properties: + pullPolicy: + default: IfNotPresent + enum: + - Always + - Never + - IfNotPresent + type: string + registry: + default: docker.io + type: string + repository: + default: grafana/grafana + type: string + tag: + default: 10.2.3 + type: string + type: object + sidecar: + default: + pullPolicy: IfNotPresent + registry: quay.io + repository: kiwigrid/k8s-sidecar + tag: 1.25.2 + properties: + pullPolicy: + default: IfNotPresent + enum: + - Always + - Never + - IfNotPresent + type: string + registry: + default: quay.io + type: string + repository: + default: kiwigrid/k8s-sidecar + type: string + tag: + default: 1.25.2 + type: string + type: object + type: object +dependencies: [] +providers: + kubernetes: true + authentik: true + kubectl: true + postgresql: null + mysql: null + restapi: true + http: true + gitea: null +tfaddtype: null diff --git a/monitor/grafana/monitoring.coreos.com_v1_ServiceMonitor_grafana.yaml b/monitor/grafana/monitoring.coreos.com_v1_ServiceMonitor_grafana.yaml new file mode 100644 index 0000000..07dcc3b --- /dev/null +++ b/monitor/grafana/monitoring.coreos.com_v1_ServiceMonitor_grafana.yaml @@ -0,0 +1,28 @@ +# Source: grafana/templates/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: grafana + namespace: vynil-monitor + labels: + helm.sh/chart: grafana-7.2.5 + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: grafana + app.kubernetes.io/version: "10.2.3" + app.kubernetes.io/managed-by: Helm +spec: + endpoints: + - port: service + interval: 30s + scrapeTimeout: 30s + honorLabels: true + path: /metrics + scheme: http + jobLabel: "grafana" + selector: + matchLabels: + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: grafana + namespaceSelector: + matchNames: + - vynil-monitor \ No newline at end of file diff --git a/monitor/grafana/presentation.tf b/monitor/grafana/presentation.tf new file mode 100644 index 0000000..b38289f --- /dev/null +++ b/monitor/grafana/presentation.tf @@ -0,0 +1,72 @@ +locals { + dns_name = "${var.sub_domain}.${var.domain_name}" + dns_names = [local.dns_name] + app_name = var.component == var.instance ? var.instance : format("%s-%s", var.component, var.instance) + icon = "public/img/grafana_icon.svg" + request_headers = { + "Content-Type" = "application/json" + Authorization = "Bearer ${data.kubernetes_secret_v1.authentik.data["AUTHENTIK_BOOTSTRAP_TOKEN"]}" + } + service = { + "name" = "grafana" + "port" = { + "number" = 80 + } + } +} + +module "ingress" { + source = "git::https://git.solidite.fr/vynil/kydah-modules.git//ingress" + component = "" + instance = var.instance + namespace = var.namespace + issuer = var.issuer + ingress_class = var.ingress_class + labels = local.common-labels + dns_names = local.dns_names + middlewares = [] + services = [local.service] + providers = { + kubectl = kubectl + } +} + + module "application" { + source = "git::https://git.solidite.fr/vynil/kydah-modules.git//application" + component = var.component + instance = var.instance + app_group = var.app_group + dns_name = local.dns_name + icon = local.icon + sub_groups = ["admin"] + protocol_provider = module.oauth2.provider-id + providers = { + authentik = authentik + } +} + +module "oauth2" { + source = "git::https://git.solidite.fr/vynil/kydah-modules.git//oauth2" + component = var.component + instance = var.instance + namespace = var.namespace + domain = var.domain + labels = local.common-labels + dns_name = local.dns_name + redirect_path = "login/generic_oauth" + providers = { + kubernetes = kubernetes + kubectl = kubectl + authentik = authentik + } +} + +provider "restapi" { + uri = "http://authentik.${var.domain}-auth.svc/api/v3/" + headers = local.request_headers + create_method = "PATCH" + update_method = "PATCH" + destroy_method = "PATCH" + write_returns_object = true + id_attribute = "name" +} \ No newline at end of file diff --git a/monitor/grafana/rbac.authorization.k8s.io_v1_RoleBinding_grafana.yaml b/monitor/grafana/rbac.authorization.k8s.io_v1_RoleBinding_grafana.yaml new file mode 100644 index 0000000..61adf84 --- /dev/null +++ b/monitor/grafana/rbac.authorization.k8s.io_v1_RoleBinding_grafana.yaml @@ -0,0 +1,20 @@ +# Source: grafana/templates/rolebinding.yaml +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + name: grafana + namespace: vynil-monitor + labels: + helm.sh/chart: grafana-7.2.5 + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: grafana + app.kubernetes.io/version: "10.2.3" + app.kubernetes.io/managed-by: Helm +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: grafana +subjects: +- kind: ServiceAccount + name: grafana + namespace: vynil-monitor \ No newline at end of file diff --git a/monitor/grafana/rbac.authorization.k8s.io_v1_Role_grafana.yaml b/monitor/grafana/rbac.authorization.k8s.io_v1_Role_grafana.yaml new file mode 100644 index 0000000..c2ac368 --- /dev/null +++ b/monitor/grafana/rbac.authorization.k8s.io_v1_Role_grafana.yaml @@ -0,0 +1,16 @@ +# Source: grafana/templates/role.yaml +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + name: grafana + namespace: vynil-monitor + labels: + helm.sh/chart: grafana-7.2.5 + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: grafana + app.kubernetes.io/version: "10.2.3" + app.kubernetes.io/managed-by: Helm +rules: + - apiGroups: [""] # "" indicates the core API group + resources: ["configmaps", "secrets"] + verbs: ["get", "watch", "list"] \ No newline at end of file diff --git a/monitor/grafana/secret.tf b/monitor/grafana/secret.tf new file mode 100644 index 0000000..ee72b3e --- /dev/null +++ b/monitor/grafana/secret.tf @@ -0,0 +1,19 @@ + +resource "kubectl_manifest" "grafana_secret" { + ignore_fields = ["metadata.annotations"] + yaml_body = <<-EOF + apiVersion: "secretgenerator.mittwald.de/v1alpha1" + kind: "StringSecret" + metadata: + name: "grafana-admin-user" + namespace: "${var.namespace}" + labels: ${jsonencode(local.common-labels)} + spec: + forceRegenerate: false + data: + username: "${var.admin_name}" + fields: + - fieldName: "password" + length: "32" + EOF +} diff --git a/monitor/grafana/v1_ConfigMap_grafana-config-dashboards.yaml b/monitor/grafana/v1_ConfigMap_grafana-config-dashboards.yaml new file mode 100644 index 0000000..13f7717 --- /dev/null +++ b/monitor/grafana/v1_ConfigMap_grafana-config-dashboards.yaml @@ -0,0 +1,26 @@ +# Source: grafana/templates/configmap-dashboard-provider.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + labels: + helm.sh/chart: grafana-7.2.5 + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: grafana + app.kubernetes.io/version: "10.2.3" + app.kubernetes.io/managed-by: Helm + name: grafana-config-dashboards + namespace: vynil-monitor +data: + provider.yaml: |- + apiVersion: 1 + providers: + - name: 'sidecarProvider' + orgId: 1 + folder: '' + type: file + disableDeletion: false + allowUiUpdates: false + updateIntervalSeconds: 30 + options: + foldersFromFilesStructure: false + path: /tmp/dashboards \ No newline at end of file diff --git a/monitor/grafana/v1_PersistentVolumeClaim_grafana.yaml b/monitor/grafana/v1_PersistentVolumeClaim_grafana.yaml new file mode 100644 index 0000000..ce7919b --- /dev/null +++ b/monitor/grafana/v1_PersistentVolumeClaim_grafana.yaml @@ -0,0 +1,20 @@ +# Source: grafana/templates/pvc.yaml +apiVersion: v1 +kind: PersistentVolumeClaim +metadata: + name: grafana + namespace: vynil-monitor + labels: + helm.sh/chart: grafana-7.2.5 + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: grafana + app.kubernetes.io/version: "10.2.3" + app.kubernetes.io/managed-by: Helm + finalizers: + - kubernetes.io/pvc-protection +spec: + accessModes: + - "ReadWriteOnce" + resources: + requests: + storage: "10Gi" \ No newline at end of file diff --git a/monitor/grafana/v1_ServiceAccount_grafana.yaml b/monitor/grafana/v1_ServiceAccount_grafana.yaml new file mode 100644 index 0000000..fce3f04 --- /dev/null +++ b/monitor/grafana/v1_ServiceAccount_grafana.yaml @@ -0,0 +1,13 @@ +--- +# Source: grafana/templates/serviceaccount.yaml +apiVersion: v1 +kind: ServiceAccount +metadata: + labels: + helm.sh/chart: grafana-7.2.5 + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: grafana + app.kubernetes.io/version: "10.2.3" + app.kubernetes.io/managed-by: Helm + name: grafana + namespace: vynil-monitor \ No newline at end of file diff --git a/monitor/grafana/v1_Service_grafana.yaml b/monitor/grafana/v1_Service_grafana.yaml new file mode 100644 index 0000000..090cad6 --- /dev/null +++ b/monitor/grafana/v1_Service_grafana.yaml @@ -0,0 +1,22 @@ +# Source: grafana/templates/service.yaml +apiVersion: v1 +kind: Service +metadata: + name: grafana + namespace: vynil-monitor + labels: + helm.sh/chart: grafana-7.2.5 + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: grafana + app.kubernetes.io/version: "10.2.3" + app.kubernetes.io/managed-by: Helm +spec: + type: ClusterIP + ports: + - name: service + port: 80 + protocol: TCP + targetPort: 3000 + selector: + app.kubernetes.io/name: grafana + app.kubernetes.io/instance: grafana \ No newline at end of file diff --git a/monitor/kube-state-metrics/apps_v1_Deployment_kube-state-metrics.yaml b/monitor/kube-state-metrics/apps_v1_Deployment_kube-state-metrics.yaml new file mode 100644 index 0000000..2c580f9 --- /dev/null +++ b/monitor/kube-state-metrics/apps_v1_Deployment_kube-state-metrics.yaml @@ -0,0 +1,82 @@ +# Source: kube-prometheus-stack/charts/kube-state-metrics/templates/deployment.yaml +apiVersion: apps/v1 +kind: Deployment +metadata: + name: kube-state-metrics + namespace: vynil-monitor + labels: + helm.sh/chart: kube-state-metrics-5.16.0 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: kube-state-metrics + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/instance: kube-state-metrics + app.kubernetes.io/version: "2.10.1" + release: kube-state-metrics +spec: + selector: + matchLabels: + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/instance: kube-state-metrics + replicas: 1 + strategy: + type: RollingUpdate + revisionHistoryLimit: 10 + template: + metadata: + labels: + helm.sh/chart: kube-state-metrics-5.16.0 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: kube-state-metrics + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/instance: kube-state-metrics + app.kubernetes.io/version: "2.10.1" + release: kube-state-metrics + spec: + hostNetwork: false + serviceAccountName: kube-state-metrics + securityContext: + fsGroup: 65534 + runAsGroup: 65534 + runAsNonRoot: true + runAsUser: 65534 + seccompProfile: + type: RuntimeDefault + containers: + - name: kube-state-metrics + args: + - --port=8080 + - --resources=certificatesigningrequests,configmaps,cronjobs,daemonsets,deployments,endpoints,horizontalpodautoscalers,ingresses,jobs,leases,limitranges,mutatingwebhookconfigurations,namespaces,networkpolicies,nodes,persistentvolumeclaims,persistentvolumes,poddisruptionbudgets,pods,replicasets,replicationcontrollers,resourcequotas,secrets,services,statefulsets,storageclasses,validatingwebhookconfigurations,volumeattachments + imagePullPolicy: IfNotPresent + image: registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.10.1 + ports: + - containerPort: 8080 + name: "http" + livenessProbe: + failureThreshold: 3 + httpGet: + httpHeaders: + path: /healthz + port: 8080 + scheme: HTTP + initialDelaySeconds: 5 + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 5 + readinessProbe: + failureThreshold: 3 + httpGet: + httpHeaders: + path: / + port: 8080 + scheme: HTTP + initialDelaySeconds: 5 + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 5 + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL \ No newline at end of file diff --git a/monitor/kube-state-metrics/datas.tf b/monitor/kube-state-metrics/datas.tf new file mode 100644 index 0000000..f26ff7e --- /dev/null +++ b/monitor/kube-state-metrics/datas.tf @@ -0,0 +1,49 @@ +locals { + common-labels = { + "vynil.solidite.fr/owner-name" = var.instance + "vynil.solidite.fr/owner-namespace" = var.namespace + "vynil.solidite.fr/owner-category" = var.category + "vynil.solidite.fr/owner-component" = var.component + "app.kubernetes.io/managed-by" = "vynil" + "app.kubernetes.io/instance" = var.instance + } + rb-patch = <<-EOF + - op: replace + path: /subjects/0/namespace + value: "${var.namespace}" + EOF +} + +data "kustomization_overlay" "data" { + common_labels = local.common-labels + namespace = var.namespace + resources = [for file in fileset(path.module, "*.yaml"): file if file != "index.yaml" && length(regexall("ClusterRole",file))<1] + images { + name = "registry.k8s.io/kube-state-metrics/kube-state-metrics" + new_name = "${var.images.kube-state-metrics.registry}/${var.images.kube-state-metrics.repository}" + new_tag = "${var.images.kube-state-metrics.tag}" + } + patches { + target { + kind = "ServiceMonitor" + name = "kube-state-metrics" + } + patch = <<-EOF + - op: replace + path: /spec/selector/matchLabels/app.kubernetes.io~1instance + value: "${var.instance}" + EOF + } +} + +data "kustomization_overlay" "data_no_ns" { + common_labels = local.common-labels + resources = [for file in fileset(path.module, "*.yaml"): file if length(regexall("ClusterRole",file))>0] + patches { + target { + kind = "ClusterRoleBinding" + name = "kube-state-metrics" + } + patch = local.rb-patch + } +} diff --git a/monitor/kube-state-metrics/index.yaml b/monitor/kube-state-metrics/index.yaml new file mode 100644 index 0000000..08b74c3 --- /dev/null +++ b/monitor/kube-state-metrics/index.yaml @@ -0,0 +1,58 @@ +--- +apiVersion: vinyl.solidite.fr/v1beta1 +kind: Component +category: monitor +metadata: + name: kube-state-metrics + description: null +options: + images: + default: + kube-state-metrics: + pullPolicy: IfNotPresent + registry: registry.k8s.io + repository: kube-state-metrics/kube-state-metrics + tag: v2.10.1 + examples: + - kube-state-metrics: + pullPolicy: IfNotPresent + registry: registry.k8s.io + repository: kube-state-metrics/kube-state-metrics + tag: v2.10.1 + properties: + kube-state-metrics: + default: + pullPolicy: IfNotPresent + registry: registry.k8s.io + repository: kube-state-metrics/kube-state-metrics + tag: v2.10.1 + properties: + pullPolicy: + default: IfNotPresent + enum: + - Always + - Never + - IfNotPresent + type: string + registry: + default: registry.k8s.io + type: string + repository: + default: kube-state-metrics/kube-state-metrics + type: string + tag: + default: v2.10.1 + type: string + type: object + type: object +dependencies: [] +providers: + kubernetes: true + authentik: null + kubectl: true + postgresql: null + mysql: null + restapi: null + http: null + gitea: null +tfaddtype: null diff --git a/monitor/kube-state-metrics/monitoring.coreos.com_v1_PrometheusRule_kube-state-metrics-kube-pr-kube-state-metrics.yaml b/monitor/kube-state-metrics/monitoring.coreos.com_v1_PrometheusRule_kube-state-metrics-kube-pr-kube-state-metrics.yaml new file mode 100644 index 0000000..ef7b3f2 --- /dev/null +++ b/monitor/kube-state-metrics/monitoring.coreos.com_v1_PrometheusRule_kube-state-metrics-kube-pr-kube-state-metrics.yaml @@ -0,0 +1,68 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-state-metrics.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: kube-state-metrics-kube-pr-kube-state-metrics + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: kube-state-metrics + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "kube-state-metrics" + heritage: "Helm" +spec: + groups: + - name: kube-state-metrics + rules: + - alert: KubeStateMetricsListErrors + annotations: + description: kube-state-metrics is experiencing errors at an elevated rate in list operations. This is likely causing it to not be able to expose metrics about Kubernetes objects correctly or at all. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kube-state-metrics/kubestatemetricslisterrors + summary: kube-state-metrics is experiencing errors in list operations. + expr: |- + (sum(rate(kube_state_metrics_list_total{job="kube-state-metrics",result="error"}[5m])) by (cluster) + / + sum(rate(kube_state_metrics_list_total{job="kube-state-metrics"}[5m])) by (cluster)) + > 0.01 + for: 15m + labels: + severity: critical + - alert: KubeStateMetricsWatchErrors + annotations: + description: kube-state-metrics is experiencing errors at an elevated rate in watch operations. This is likely causing it to not be able to expose metrics about Kubernetes objects correctly or at all. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kube-state-metrics/kubestatemetricswatcherrors + summary: kube-state-metrics is experiencing errors in watch operations. + expr: |- + (sum(rate(kube_state_metrics_watch_total{job="kube-state-metrics",result="error"}[5m])) by (cluster) + / + sum(rate(kube_state_metrics_watch_total{job="kube-state-metrics"}[5m])) by (cluster)) + > 0.01 + for: 15m + labels: + severity: critical + - alert: KubeStateMetricsShardingMismatch + annotations: + description: kube-state-metrics pods are running with different --total-shards configuration, some Kubernetes objects may be exposed multiple times or not exposed at all. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kube-state-metrics/kubestatemetricsshardingmismatch + summary: kube-state-metrics sharding is misconfigured. + expr: stdvar (kube_state_metrics_total_shards{job="kube-state-metrics"}) by (cluster) != 0 + for: 15m + labels: + severity: critical + - alert: KubeStateMetricsShardsMissing + annotations: + description: kube-state-metrics shards are missing, some Kubernetes objects are not being exposed. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kube-state-metrics/kubestatemetricsshardsmissing + summary: kube-state-metrics shards are missing. + expr: |- + 2^max(kube_state_metrics_total_shards{job="kube-state-metrics"}) by (cluster) - 1 + - + sum( 2 ^ max by (cluster, shard_ordinal) (kube_state_metrics_shard_ordinal{job="kube-state-metrics"}) ) by (cluster) + != 0 + for: 15m + labels: + severity: critical \ No newline at end of file diff --git a/monitor/kube-state-metrics/monitoring.coreos.com_v1_ServiceMonitor_kube-state-metrics.yaml b/monitor/kube-state-metrics/monitoring.coreos.com_v1_ServiceMonitor_kube-state-metrics.yaml new file mode 100644 index 0000000..5034788 --- /dev/null +++ b/monitor/kube-state-metrics/monitoring.coreos.com_v1_ServiceMonitor_kube-state-metrics.yaml @@ -0,0 +1,24 @@ +# Source: kube-prometheus-stack/charts/kube-state-metrics/templates/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: kube-state-metrics + namespace: vynil-monitor + labels: + helm.sh/chart: kube-state-metrics-5.16.0 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: kube-state-metrics + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/instance: kube-state-metrics + app.kubernetes.io/version: "2.10.1" + release: kube-state-metrics +spec: + jobLabel: app.kubernetes.io/name + selector: + matchLabels: + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/instance: kube-state-metrics + endpoints: + - port: http + honorLabels: true \ No newline at end of file diff --git a/monitor/kube-state-metrics/rbac.authorization.k8s.io_v1_ClusterRoleBinding_kube-state-metrics.yaml b/monitor/kube-state-metrics/rbac.authorization.k8s.io_v1_ClusterRoleBinding_kube-state-metrics.yaml new file mode 100644 index 0000000..1b5d050 --- /dev/null +++ b/monitor/kube-state-metrics/rbac.authorization.k8s.io_v1_ClusterRoleBinding_kube-state-metrics.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/charts/kube-state-metrics/templates/clusterrolebinding.yaml +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + labels: + helm.sh/chart: kube-state-metrics-5.16.0 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: kube-state-metrics + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/instance: kube-state-metrics + app.kubernetes.io/version: "2.10.1" + release: kube-state-metrics + name: kube-state-metrics +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: kube-state-metrics +subjects: +- kind: ServiceAccount + name: kube-state-metrics + namespace: vynil-monitor \ No newline at end of file diff --git a/monitor/kube-state-metrics/rbac.authorization.k8s.io_v1_ClusterRole_kube-state-metrics.yaml b/monitor/kube-state-metrics/rbac.authorization.k8s.io_v1_ClusterRole_kube-state-metrics.yaml new file mode 100644 index 0000000..f335187 --- /dev/null +++ b/monitor/kube-state-metrics/rbac.authorization.k8s.io_v1_ClusterRole_kube-state-metrics.yaml @@ -0,0 +1,155 @@ +# Source: kube-prometheus-stack/charts/kube-state-metrics/templates/role.yaml +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + labels: + helm.sh/chart: kube-state-metrics-5.16.0 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: kube-state-metrics + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/instance: kube-state-metrics + app.kubernetes.io/version: "2.10.1" + release: kube-state-metrics + name: kube-state-metrics +rules: + +- apiGroups: ["certificates.k8s.io"] + resources: + - certificatesigningrequests + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - configmaps + verbs: ["list", "watch"] + +- apiGroups: ["batch"] + resources: + - cronjobs + verbs: ["list", "watch"] + +- apiGroups: ["extensions", "apps"] + resources: + - daemonsets + verbs: ["list", "watch"] + +- apiGroups: ["extensions", "apps"] + resources: + - deployments + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - endpoints + verbs: ["list", "watch"] + +- apiGroups: ["autoscaling"] + resources: + - horizontalpodautoscalers + verbs: ["list", "watch"] + +- apiGroups: ["extensions", "networking.k8s.io"] + resources: + - ingresses + verbs: ["list", "watch"] + +- apiGroups: ["batch"] + resources: + - jobs + verbs: ["list", "watch"] + +- apiGroups: ["coordination.k8s.io"] + resources: + - leases + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - limitranges + verbs: ["list", "watch"] + +- apiGroups: ["admissionregistration.k8s.io"] + resources: + - mutatingwebhookconfigurations + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - namespaces + verbs: ["list", "watch"] + +- apiGroups: ["networking.k8s.io"] + resources: + - networkpolicies + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - nodes + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - persistentvolumeclaims + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - persistentvolumes + verbs: ["list", "watch"] + +- apiGroups: ["policy"] + resources: + - poddisruptionbudgets + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - pods + verbs: ["list", "watch"] + +- apiGroups: ["extensions", "apps"] + resources: + - replicasets + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - replicationcontrollers + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - resourcequotas + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - secrets + verbs: ["list", "watch"] + +- apiGroups: [""] + resources: + - services + verbs: ["list", "watch"] + +- apiGroups: ["apps"] + resources: + - statefulsets + verbs: ["list", "watch"] + +- apiGroups: ["storage.k8s.io"] + resources: + - storageclasses + verbs: ["list", "watch"] + +- apiGroups: ["admissionregistration.k8s.io"] + resources: + - validatingwebhookconfigurations + verbs: ["list", "watch"] + +- apiGroups: ["storage.k8s.io"] + resources: + - volumeattachments + verbs: ["list", "watch"] \ No newline at end of file diff --git a/monitor/kube-state-metrics/ressources_no_ns.tf b/monitor/kube-state-metrics/ressources_no_ns.tf new file mode 100644 index 0000000..9fa58b7 --- /dev/null +++ b/monitor/kube-state-metrics/ressources_no_ns.tf @@ -0,0 +1,45 @@ + +# first loop through resources in ids_prio[0] +resource "kustomization_resource" "pre_no_ns" { + for_each = data.kustomization_overlay.data_no_ns.ids_prio[0] + + manifest = ( + contains(["_/Secret"], regex("(?P.*/.*)/.*/.*", each.value)["group_kind"]) + ? sensitive(data.kustomization_overlay.data_no_ns.manifests[each.value]) + : data.kustomization_overlay.data_no_ns.manifests[each.value] + ) +} + +# then loop through resources in ids_prio[1] +# and set an explicit depends_on on kustomization_resource.pre +# wait 2 minutes for any deployment or daemonset to become ready +resource "kustomization_resource" "main_no_ns" { + for_each = data.kustomization_overlay.data_no_ns.ids_prio[1] + + manifest = ( + contains(["_/Secret"], regex("(?P.*/.*)/.*/.*", each.value)["group_kind"]) + ? sensitive(data.kustomization_overlay.data_no_ns.manifests[each.value]) + : data.kustomization_overlay.data_no_ns.manifests[each.value] + ) + wait = true + timeouts { + create = "5m" + update = "5m" + } + + depends_on = [kustomization_resource.pre_no_ns] +} + +# finally, loop through resources in ids_prio[2] +# and set an explicit depends_on on kustomization_resource.main +resource "kustomization_resource" "post_no_ns" { + for_each = data.kustomization_overlay.data_no_ns.ids_prio[2] + + manifest = ( + contains(["_/Secret"], regex("(?P.*/.*)/.*/.*", each.value)["group_kind"]) + ? sensitive(data.kustomization_overlay.data_no_ns.manifests[each.value]) + : data.kustomization_overlay.data_no_ns.manifests[each.value] + ) + + depends_on = [kustomization_resource.main_no_ns] +} diff --git a/monitor/kube-state-metrics/v1_ServiceAccount_kube-state-metrics.yaml b/monitor/kube-state-metrics/v1_ServiceAccount_kube-state-metrics.yaml new file mode 100644 index 0000000..d275f41 --- /dev/null +++ b/monitor/kube-state-metrics/v1_ServiceAccount_kube-state-metrics.yaml @@ -0,0 +1,16 @@ +--- +# Source: kube-prometheus-stack/charts/kube-state-metrics/templates/serviceaccount.yaml +apiVersion: v1 +kind: ServiceAccount +metadata: + labels: + helm.sh/chart: kube-state-metrics-5.16.0 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: kube-state-metrics + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/instance: kube-state-metrics + app.kubernetes.io/version: "2.10.1" + release: kube-state-metrics + name: kube-state-metrics + namespace: vynil-monitor \ No newline at end of file diff --git a/monitor/kube-state-metrics/v1_Service_kube-state-metrics.yaml b/monitor/kube-state-metrics/v1_Service_kube-state-metrics.yaml new file mode 100644 index 0000000..56e2a69 --- /dev/null +++ b/monitor/kube-state-metrics/v1_Service_kube-state-metrics.yaml @@ -0,0 +1,28 @@ +# Source: kube-prometheus-stack/charts/kube-state-metrics/templates/service.yaml +apiVersion: v1 +kind: Service +metadata: + name: kube-state-metrics + namespace: vynil-monitor + labels: + helm.sh/chart: kube-state-metrics-5.16.0 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: kube-state-metrics + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/instance: kube-state-metrics + app.kubernetes.io/version: "2.10.1" + release: kube-state-metrics + annotations: + prometheus.io/scrape: 'true' +spec: + type: "ClusterIP" + ports: + - name: "http" + protocol: TCP + port: 8080 + targetPort: 8080 + + selector: + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/instance: kube-state-metrics \ No newline at end of file diff --git a/monitor/loki-dashboard/index.yaml b/monitor/loki-dashboard/index.yaml new file mode 100644 index 0000000..6c689a8 --- /dev/null +++ b/monitor/loki-dashboard/index.yaml @@ -0,0 +1,83 @@ +--- +apiVersion: vinyl.solidite.fr/v1beta1 +kind: Component +category: monitor +metadata: + name: loki-dashboard + description: null +options: + domain: + default: your-company + examples: + - your-company + type: string + ingress_class: + default: traefik + examples: + - traefik + type: string + images: + default: + operator: + pullPolicy: IfNotPresent + registry: docker.io + repository: to-be/defined + tag: v1.0.0 + examples: + - operator: + pullPolicy: IfNotPresent + registry: docker.io + repository: to-be/defined + tag: v1.0.0 + properties: + operator: + default: + pullPolicy: IfNotPresent + registry: docker.io + repository: to-be/defined + tag: v1.0.0 + properties: + pullPolicy: + default: IfNotPresent + enum: + - Always + - Never + - IfNotPresent + type: string + registry: + default: docker.io + type: string + repository: + default: to-be/defined + type: string + tag: + default: v1.0.0 + type: string + type: object + type: object + sub_domain: + default: to-be-set + examples: + - to-be-set + type: string + domain_name: + default: your_company.com + examples: + - your_company.com + type: string + issuer: + default: letsencrypt-prod + examples: + - letsencrypt-prod + type: string +dependencies: [] +providers: + kubernetes: true + authentik: true + kubectl: true + postgresql: null + mysql: null + restapi: null + http: null + gitea: null +tfaddtype: null diff --git a/monitor/loki-dashboard/v1_ConfigMap_loki-dashboards-1.yaml b/monitor/loki-dashboard/v1_ConfigMap_loki-dashboards-1.yaml new file mode 100644 index 0000000..5d9de03 --- /dev/null +++ b/monitor/loki-dashboard/v1_ConfigMap_loki-dashboards-1.yaml @@ -0,0 +1,24 @@ +# Source: loki/templates/monitoring/dashboards/configmap-1.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + name: loki-dashboards-1 + namespace: vynil-monitor + labels: + helm.sh/chart: loki-5.41.8 + app.kubernetes.io/name: loki + app.kubernetes.io/instance: loki + app.kubernetes.io/version: "2.9.3" + app.kubernetes.io/managed-by: Helm + grafana_dashboard: "1" +data: + "loki-chunks.json": | + {"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"links":[{"asDropdown":true,"icon":"external link","includeVars":true,"keepTime":true,"tags":["loki"],"targetBlank":false,"title":"Loki Dashboards","type":"dashboards"}],"refresh":"10s","rows":[{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":1,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(loki_ingester_memory_chunks{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"})","format":"time_series","intervalFactor":2,"legendFormat":"series","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Series","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":2,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(loki_ingester_memory_chunks{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}) / sum(loki_ingester_memory_streams{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"})","format":"time_series","intervalFactor":2,"legendFormat":"chunks","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Chunks per series","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Active Series / Chunks","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":3,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(loki_ingester_chunk_utilization_bucket{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[$__rate_interval])) by (le)) * 1","format":"time_series","intervalFactor":2,"legendFormat":"99th Percentile","refId":"A","step":10},{"expr":"histogram_quantile(0.50, sum(rate(loki_ingester_chunk_utilization_bucket{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[$__rate_interval])) by (le)) * 1","format":"time_series","intervalFactor":2,"legendFormat":"50th Percentile","refId":"B","step":10},{"expr":"sum(rate(loki_ingester_chunk_utilization_sum{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[$__rate_interval])) * 1 / sum(rate(loki_ingester_chunk_utilization_count{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"Average","refId":"C","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Utilization","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":4,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(loki_ingester_chunk_age_seconds_bucket{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[$__rate_interval])) by (le)) * 1e3","format":"time_series","intervalFactor":2,"legendFormat":"99th Percentile","refId":"A","step":10},{"expr":"histogram_quantile(0.50, sum(rate(loki_ingester_chunk_age_seconds_bucket{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[$__rate_interval])) by (le)) * 1e3","format":"time_series","intervalFactor":2,"legendFormat":"50th Percentile","refId":"B","step":10},{"expr":"sum(rate(loki_ingester_chunk_age_seconds_sum{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[$__rate_interval])) * 1e3 / sum(rate(loki_ingester_chunk_age_seconds_count{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"Average","refId":"C","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Age","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ms","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Flush Stats","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":5,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(loki_ingester_chunk_entries_bucket{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[$__rate_interval])) by (le)) * 1","format":"time_series","intervalFactor":2,"legendFormat":"99th Percentile","refId":"A","step":10},{"expr":"histogram_quantile(0.50, sum(rate(loki_ingester_chunk_entries_bucket{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[$__rate_interval])) by (le)) * 1","format":"time_series","intervalFactor":2,"legendFormat":"50th Percentile","refId":"B","step":10},{"expr":"sum(rate(loki_ingester_chunk_entries_sum{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[$__rate_interval])) * 1 / sum(rate(loki_ingester_chunk_entries_count{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"Average","refId":"C","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Log Entries Per Chunk","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":6,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_chunk_store_index_entries_per_chunk_sum{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[5m])) / sum(rate(loki_chunk_store_index_entries_per_chunk_count{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[5m]))","format":"time_series","intervalFactor":2,"legendFormat":"Index Entries","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Index Entries Per Chunk","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Flush Stats","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":7,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"loki_ingester_flush_queue_length{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"} or cortex_ingester_flush_queue_length{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}","format":"time_series","intervalFactor":2,"legendFormat":"{{pod}}","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Queue Length","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{"1xx":"#EAB839","2xx":"#7EB26D","3xx":"#6ED0E0","4xx":"#EF843C","5xx":"#E24D42","error":"#E24D42","success":"#7EB26D"},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":8,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by (status) (\n label_replace(label_replace(rate(loki_ingester_chunk_age_seconds_count{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n","format":"time_series","intervalFactor":2,"legendFormat":"{{status}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Flush Rate","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Flush Stats","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":9,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_ingester_chunks_flushed_total{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"{{pod}}","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Chunks Flushed/Second","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":10,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by (reason) (rate(loki_ingester_chunks_flushed_total{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[$__rate_interval])) / ignoring(reason) group_left sum(rate(loki_ingester_chunks_flushed_total{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"{{reason}}","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Chunk Flush Reason","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":1,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":1,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Flush Stats","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"cards":{"cardPadding":null,"cardRound":null},"color":{"cardColor":"#b4ff00","colorScale":"sqrt","colorScheme":"interpolateSpectral","exponent":0.5,"mode":"spectrum"},"dataFormat":"tsbuckets","datasource":"$datasource","heatmap":{},"hideZeroBuckets":false,"highlightCards":true,"id":11,"legend":{"show":true},"span":12,"targets":[{"expr":"sum by (le) (rate(loki_ingester_chunk_utilization_bucket{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[$__rate_interval]))","format":"heatmap","intervalFactor":2,"legendFormat":"{{le}}","refId":"A"}],"title":"Chunk Utilization","tooltip":{"show":true,"showHistogram":true},"type":"heatmap","xAxis":{"show":true},"xBucketNumber":null,"xBucketSize":null,"yAxis":{"decimals":0,"format":"percentunit","show":true,"splitFactor":null},"yBucketBound":"auto"}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Utilization","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"cards":{"cardPadding":null,"cardRound":null},"color":{"cardColor":"#b4ff00","colorScale":"sqrt","colorScheme":"interpolateSpectral","exponent":0.5,"mode":"spectrum"},"dataFormat":"tsbuckets","datasource":"$datasource","heatmap":{},"hideZeroBuckets":false,"highlightCards":true,"id":12,"legend":{"show":true},"span":12,"targets":[{"expr":"sum(rate(loki_ingester_chunk_size_bytes_bucket{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[$__rate_interval])) by (le)","format":"heatmap","intervalFactor":2,"legendFormat":"{{le}}","refId":"A"}],"title":"Chunk Size Bytes","tooltip":{"show":true,"showHistogram":true},"type":"heatmap","xAxis":{"show":true},"xBucketNumber":null,"xBucketSize":null,"yAxis":{"decimals":0,"format":"bytes","show":true,"splitFactor":null},"yBucketBound":"auto"}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Utilization","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":13,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(loki_ingester_chunk_size_bytes_bucket{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[1m])) by (le))","format":"time_series","intervalFactor":2,"legendFormat":"p99","legendLink":null,"step":10},{"expr":"histogram_quantile(0.90, sum(rate(loki_ingester_chunk_size_bytes_bucket{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[1m])) by (le))","format":"time_series","intervalFactor":2,"legendFormat":"p90","legendLink":null,"step":10},{"expr":"histogram_quantile(0.50, sum(rate(loki_ingester_chunk_size_bytes_bucket{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[1m])) by (le))","format":"time_series","intervalFactor":2,"legendFormat":"p50","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Chunk Size Quantiles","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Utilization","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":14,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.5, sum(rate(loki_ingester_chunk_bounds_hours_bucket{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[5m])) by (le))","format":"time_series","intervalFactor":2,"legendFormat":"p50","legendLink":null,"step":10},{"expr":"histogram_quantile(0.99, sum(rate(loki_ingester_chunk_bounds_hours_bucket{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[5m])) by (le))","format":"time_series","intervalFactor":2,"legendFormat":"p99","legendLink":null,"step":10},{"expr":"sum(rate(loki_ingester_chunk_bounds_hours_sum{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[5m])) / sum(rate(loki_ingester_chunk_bounds_hours_count{cluster=\"$cluster\", job=~\"$namespace/(loki|enterprise-logs)-write\"}[5m]))","format":"time_series","intervalFactor":2,"legendFormat":"avg","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Chunk Duration hours (end-start)","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Duration","titleSize":"h6"}],"schemaVersion":14,"style":"dark","tags":["loki"],"templating":{"list":[{"current":{"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{"text":"prod","value":"prod"},"datasource":"$datasource","hide":0,"includeAll":false,"label":"cluster","multi":false,"name":"cluster","options":[],"query":"label_values(loki_build_info, cluster)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{"text":"prod","value":"prod"},"datasource":"$datasource","hide":0,"includeAll":false,"label":"namespace","multi":false,"name":"namespace","options":[],"query":"label_values(loki_build_info{cluster=~\"$cluster\"}, namespace)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone":"utc","title":"Loki / Chunks","uid":"chunks","version":0} + "loki-deletion.json": | + {"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"links":[{"asDropdown":true,"icon":"external link","includeVars":true,"keepTime":true,"tags":["loki"],"targetBlank":false,"title":"Loki Dashboards","type":"dashboards"}],"refresh":"10s","rows":[{"collapse":false,"height":"100px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"format":"none","id":1,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(loki_compactor_pending_delete_requests_count{cluster=~\"$cluster\", namespace=~\"$namespace\"})","format":"time_series","instant":true,"intervalFactor":2,"refId":"A"}],"thresholds":"70,80","timeFrom":null,"timeShift":null,"title":"Number of Pending Requests","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"singlestat","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"format":"dtdurations","id":2,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"max(loki_compactor_oldest_pending_delete_request_age_seconds{cluster=~\"$cluster\", namespace=~\"$namespace\"})","format":"time_series","instant":true,"intervalFactor":2,"refId":"A"}],"thresholds":"70,80","timeFrom":null,"timeShift":null,"title":"Oldest Pending Request Age","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"singlestat","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Headlines","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":3,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(increase(loki_compactor_delete_requests_received_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[1d]))","format":"time_series","intervalFactor":2,"legendFormat":"received","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Delete Requests Received / Day","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":4,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(increase(loki_compactor_delete_requests_processed_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[1d]))","format":"time_series","intervalFactor":2,"legendFormat":"processed","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Delete Requests Processed / Day","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Churn","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":5,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(increase(loki_compactor_load_pending_requests_attempts_total{status=\"fail\", cluster=~\"$cluster\", namespace=~\"$namespace\"}[1h]))","format":"time_series","intervalFactor":2,"legendFormat":"failures","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Failures in Loading Delete Requests / Hour","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Failures","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":6,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_compactor_deleted_lines{cluster=~\"$cluster\",job=~\"$namespace/(loki|enterprise-logs)-read\"}[$__rate_interval])) by (user)","format":"time_series","intervalFactor":2,"legendFormat":"{{user}}","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Lines Deleted / Sec","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Deleted lines","titleSize":"h6"}],"schemaVersion":14,"style":"dark","tags":["loki"],"templating":{"list":[{"current":{"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{"text":"prod","value":"prod"},"datasource":"$datasource","hide":0,"includeAll":false,"label":"cluster","multi":false,"name":"cluster","options":[],"query":"label_values(loki_build_info, cluster)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{"text":"prod","value":"prod"},"datasource":"$datasource","hide":0,"includeAll":false,"label":"namespace","multi":false,"name":"namespace","options":[],"query":"label_values(loki_build_info{cluster=~\"$cluster\"}, namespace)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone":"utc","title":"Loki / Deletion","uid":"deletion","version":0} + "loki-logs.json": | + {"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"id":8,"iteration":1583185057230,"links":[{"asDropdown":true,"icon":"external link","includeVars":true,"keepTime":true,"tags":["loki"],"targetBlank":false,"title":"Loki Dashboards","type":"dashboards"}],"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":4,"w":3,"x":0,"y":0},"hiddenSeries":false,"id":35,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(go_goroutines{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\"})","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"goroutines","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"timeseries","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":4,"w":3,"x":3,"y":0},"hiddenSeries":false,"id":41,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(go_gc_duration_seconds{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\"}) by (quantile)","legendFormat":"{{quantile}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"gc duration","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"timeseries","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":4,"w":3,"x":6,"y":0},"hiddenSeries":false,"id":36,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(container_cpu_usage_seconds_total{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\"}[5m]))","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"cpu","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"timeseries","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":4,"w":3,"x":9,"y":0},"hiddenSeries":false,"id":40,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\"})","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"working set","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"timeseries","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":4,"w":3,"x":12,"y":0},"hiddenSeries":false,"id":38,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\"}[5m]))","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"tx","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"timeseries","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":4,"w":3,"x":15,"y":0},"hiddenSeries":false,"id":39,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\"}[5m]))","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"rx","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"timeseries","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"decbytes","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":4,"w":3,"x":18,"y":0},"hiddenSeries":false,"id":37,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"increase(kube_pod_container_status_last_terminated_reason{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\"}[30m]) \u003e 0","legendFormat":"{{reason}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"restarts","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"timeseries","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":4,"w":3,"x":21,"y":0},"hiddenSeries":false,"id":42,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(promtail_custom_bad_words_total{cluster=\"$cluster\", exported_namespace=\"$namespace\", exported_pod=~\"$deployment.*\", exported_pod=~\"$pod\", container=~\"$container\"}[5m])) by (level)","legendFormat":"{{level}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"bad words","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"timeseries","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$logs","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":24,"x":0,"y":4},"hiddenSeries":false,"id":31,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"warn","color":"#FF780A"},{"alias":"error","color":"#E02F44"},{"alias":"info","color":"#56A64B"},{"alias":"debug","color":"#3274D9"}],"spaceLength":10,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(rate({cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\" } |logfmt| level=~\"$level\" |= \"$filter\" [5m])) by (level)","intervalFactor":3,"legendFormat":"{{level}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Log Rate","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"timeseries","xaxis":{"buckets":null,"mode":"time","name":null,"show":false,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}],"yaxis":{"align":false,"alignLevel":null}},{"datasource":"$logs","gridPos":{"h":19,"w":24,"x":0,"y":6},"id":29,"maxDataPoints":"","options":{"showLabels":false,"showTime":true,"sortOrder":"Descending","wrapLogMessage":true},"targets":[{"expr":"{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\", pod=~\"$pod\", container=~\"$container\"} | logfmt | level=~\"$level\" |= \"$filter\"","refId":"A"}],"timeFrom":null,"timeShift":null,"title":"Logs","type":"logs"}],"refresh":"10s","rows":[],"schemaVersion":14,"style":"dark","tags":["loki"],"templating":{"list":[{"current":{"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{"text":"prod","value":"prod"},"datasource":"$datasource","hide":0,"includeAll":false,"label":"cluster","multi":false,"name":"cluster","options":[],"query":"label_values(loki_build_info, cluster)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{"text":"prod","value":"prod"},"datasource":"$datasource","hide":0,"includeAll":false,"label":"namespace","multi":false,"name":"namespace","options":[],"query":"label_values(loki_build_info{cluster=~\"$cluster\"}, namespace)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"hide":0,"label":null,"name":"logs","options":[],"query":"loki","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{},"datasource":"$datasource","hide":0,"includeAll":false,"label":null,"multi":false,"name":"deployment","options":[],"query":"label_values(kube_deployment_created{cluster=\"$cluster\", namespace=\"$namespace\"}, deployment)","refresh":0,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{},"datasource":"$datasource","hide":0,"includeAll":false,"label":null,"multi":false,"name":"pod","options":[],"query":"label_values(kube_pod_container_info{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$deployment.*\"}, pod)","refresh":0,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{},"datasource":"$datasource","hide":0,"includeAll":false,"label":null,"multi":false,"name":"container","options":[],"query":"label_values(kube_pod_container_info{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\", pod=~\"$deployment.*\"}, container)","refresh":0,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{"selected":true,"text":"","value":""},"hide":0,"includeAll":false,"label":"","multi":true,"name":"level","options":[{"selected":false,"text":"debug","value":"debug"},{"selected":false,"text":"info","value":"info"},{"selected":false,"text":"warn","value":"warn"},{"selected":false,"text":"error","value":"error"}],"query":"debug,info,warn,error","refresh":0,"type":"custom"},{"current":{"selected":false,"text":"","value":""},"label":"LogQL Filter","name":"filter","query":"","type":"textbox"}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone":"utc","title":"Loki / Logs","uid":"logs","version":0} + "loki-mixin-recording-rules.json": | + {"annotations":{"list":[{"builtIn":1,"datasource":"-- Grafana --","enable":true,"hide":true,"iconColor":"rgba(0, 211, 255, 1)","name":"Annotations \u0026 Alerts","target":{"limit":100,"matchAny":false,"tags":[],"type":"dashboard"},"type":"dashboard"},{"datasource":"${datasource}","enable":false,"expr":"sum by (tenant) (changes(loki_ruler_wal_prometheus_tsdb_wal_truncations_total{tenant=~\"${tenant}\"}[$__rate_interval]))","iconColor":"red","name":"WAL Truncations","target":{"queryType":"Azure Monitor","refId":"Anno"},"titleFormat":"{{tenant}}"}]},"editable":true,"fiscalYearStartMonth":0,"gnetId":null,"graphTooltip":0,"iteration":1635347545534,"links":[],"liveNow":false,"panels":[{"datasource":"${datasource}","fieldConfig":{"defaults":{"color":{"mode":"thresholds"},"mappings":[],"noValue":"0","thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":1}]}},"overrides":[]},"gridPos":{"h":10,"w":2,"x":0,"y":0},"id":2,"options":{"colorMode":"value","graphMode":"area","justifyMode":"auto","orientation":"auto","reduceOptions":{"calcs":["lastNotNull"],"fields":"","values":false},"textMode":"auto"},"pluginVersion":"8.3.0-38205pre","targets":[{"datasource":"${datasource}","exemplar":false,"expr":"sum(loki_ruler_wal_appender_ready) by (pod, tenant) == 0","instant":true,"interval":"","legendFormat":"","refId":"A"}],"title":"Appenders Not Ready","type":"stat"},{"datasource":"${datasource}","description":"","fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":0,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"lineInterpolation":"linear","lineWidth":1,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"auto","spanNulls":false,"stacking":{"group":"A","mode":"none"},"thresholdsStyle":{"mode":"off"}},"mappings":[],"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]}},"overrides":[]},"gridPos":{"h":10,"w":11,"x":2,"y":0},"id":4,"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom"},"tooltip":{"mode":"single"}},"targets":[{"datasource":"${datasource}","exemplar":true,"expr":"sum(rate(loki_ruler_wal_samples_appended_total{tenant=~\"${tenant}\"}[$__rate_interval])) by (tenant) \u003e 0","interval":"","legendFormat":"{{tenant}}","refId":"A"}],"title":"Samples Appended to WAL per Second","type":"timeseries"},{"datasource":"${datasource}","description":"Series are unique combinations of labels","fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":0,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"lineInterpolation":"linear","lineWidth":1,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"auto","spanNulls":false,"stacking":{"group":"A","mode":"none"},"thresholdsStyle":{"mode":"off"}},"mappings":[],"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]}},"overrides":[]},"gridPos":{"h":10,"w":11,"x":13,"y":0},"id":5,"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom"},"tooltip":{"mode":"single"}},"targets":[{"datasource":"${datasource}","exemplar":true,"expr":"sum(rate(loki_ruler_wal_storage_created_series_total{tenant=~\"${tenant}\"}[$__rate_interval])) by (tenant) \u003e 0","interval":"","legendFormat":"{{tenant}}","refId":"A"}],"title":"Series Created per Second","type":"timeseries"},{"datasource":"${datasource}","description":"Difference between highest timestamp appended to WAL and highest timestamp successfully written to remote storage","fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":0,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"lineInterpolation":"linear","lineWidth":1,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"auto","spanNulls":false,"stacking":{"group":"A","mode":"none"},"thresholdsStyle":{"mode":"off"}},"mappings":[],"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]}},"overrides":[]},"gridPos":{"h":10,"w":12,"x":0,"y":10},"id":6,"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom"},"tooltip":{"mode":"single"}},"targets":[{"datasource":"${datasource}","exemplar":true,"expr":"loki_ruler_wal_prometheus_remote_storage_highest_timestamp_in_seconds{tenant=~\"${tenant}\"}\n- on (tenant)\n (\n loki_ruler_wal_prometheus_remote_storage_queue_highest_sent_timestamp_seconds{tenant=~\"${tenant}\"}\n or vector(0)\n )","interval":"","legendFormat":"{{tenant}}","refId":"A"}],"title":"Write Behind","type":"timeseries"},{"datasource":"${datasource}","description":"","fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":0,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"lineInterpolation":"linear","lineWidth":1,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"auto","spanNulls":false,"stacking":{"group":"A","mode":"none"},"thresholdsStyle":{"mode":"off"}},"mappings":[],"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]}},"overrides":[]},"gridPos":{"h":10,"w":12,"x":12,"y":10},"id":7,"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom"},"tooltip":{"mode":"single"}},"targets":[{"datasource":"${datasource}","exemplar":true,"expr":"sum(rate(loki_ruler_wal_prometheus_remote_storage_samples_total{tenant=~\"${tenant}\"}[$__rate_interval])) by (tenant) \u003e 0","interval":"","legendFormat":"{{tenant}}","refId":"A"}],"title":"Samples Sent per Second","type":"timeseries"},{"datasource":"${datasource}","description":"\n","fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":0,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"lineInterpolation":"linear","lineWidth":1,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"auto","spanNulls":false,"stacking":{"group":"A","mode":"none"},"thresholdsStyle":{"mode":"off"}},"mappings":[],"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]},"unit":"bytes"},"overrides":[]},"gridPos":{"h":10,"w":12,"x":0,"y":20},"id":8,"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom"},"tooltip":{"mode":"single"}},"targets":[{"datasource":"${datasource}","exemplar":true,"expr":"sum by (tenant) (loki_ruler_wal_disk_size{tenant=~\"${tenant}\"})","interval":"","legendFormat":"{{tenant}}","refId":"A"}],"title":"WAL Disk Size","type":"timeseries"},{"datasource":"${datasource}","description":"Some number of pending samples is expected, but if remote-write is failing this value will remain high","fieldConfig":{"defaults":{"color":{"mode":"palette-classic"},"custom":{"axisLabel":"","axisPlacement":"auto","barAlignment":0,"drawStyle":"line","fillOpacity":0,"gradientMode":"none","hideFrom":{"legend":false,"tooltip":false,"viz":false},"lineInterpolation":"linear","lineWidth":1,"pointSize":5,"scaleDistribution":{"type":"linear"},"showPoints":"auto","spanNulls":false,"stacking":{"group":"A","mode":"none"},"thresholdsStyle":{"mode":"off"}},"mappings":[],"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]}},"overrides":[]},"gridPos":{"h":10,"w":12,"x":12,"y":20},"id":9,"options":{"legend":{"calcs":[],"displayMode":"list","placement":"bottom"},"tooltip":{"mode":"single"}},"targets":[{"datasource":"${datasource}","exemplar":true,"expr":"max(loki_ruler_wal_prometheus_remote_storage_samples_pending{tenant=~\"${tenant}\"}) by (tenant,pod) \u003e 0","interval":"","legendFormat":"{{tenant}}","refId":"A"}],"title":"Pending Samples","type":"timeseries"}],"schemaVersion":31,"style":"dark","tags":[],"templating":{"list":[{"description":null,"error":null,"hide":0,"includeAll":false,"label":"Datasource","multi":false,"name":"datasource","options":[],"query":"prometheus","queryValue":"","refresh":1,"regex":"","skipUrlSync":false,"type":"datasource"},{"allValue":null,"datasource":"${datasource}","definition":"label_values(loki_ruler_wal_samples_appended_total, tenant)","description":null,"error":null,"hide":0,"includeAll":true,"label":"Tenant","multi":true,"name":"tenant","options":[],"query":{"query":"label_values(loki_ruler_wal_samples_appended_total, tenant)","refId":"StandardVariableQuery"},"refresh":2,"regex":"","skipUrlSync":false,"sort":0,"type":"query"}]},"time":{"from":"now-6h","to":"now"},"timepicker":{},"timezone":"","title":"Recording Rules","uid":"2xKA_ZK7k","version":9,"weekStart":""} + "loki-operational.json": | + {"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"id":68,"iteration":1588704280892,"links":[{"asDropdown":true,"icon":"external link","includeVars":true,"keepTime":true,"tags":["loki"],"targetBlank":false,"title":"Loki Dashboards","type":"dashboards"}],"panels":[{"collapsed":false,"datasource":null,"gridPos":{"h":1,"w":24,"x":0,"y":0},"id":17,"panels":[],"targets":[],"title":"Main","type":"row"},{"aliasColors":{"5xx":"red"},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fieldConfig":{"defaults":{"custom":{}},"overrides":[]},"fill":1,"fillGradient":0,"gridPos":{"h":5,"w":4,"x":0,"y":1},"hiddenSeries":false,"id":6,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum by (status) (\nlabel_replace(\n label_replace(\n rate(loki_request_duration_seconds_count{cluster=\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\"}[5m]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n\"status\", \"${1}\", \"status_code\", \"([a-z]+)\")\n)","legendFormat":"{{status}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Queries/Second","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":10,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{"5xx":"red"},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fieldConfig":{"defaults":{"custom":{}},"overrides":[]},"fill":1,"fillGradient":0,"gridPos":{"h":5,"w":4,"x":4,"y":1},"hiddenSeries":false,"id":7,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum by (status) (\nlabel_replace(\n label_replace(\n rate(loki_request_duration_seconds_count{cluster=\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push\"}[5m]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n\"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))","legendFormat":"{{status}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Pushes/Second","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":10,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fieldConfig":{"defaults":{"custom":{}},"overrides":[]},"fill":1,"fillGradient":0,"gridPos":{"h":5,"w":4,"x":12,"y":1},"hiddenSeries":false,"id":2,"interval":"","legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"topk(10, sum(rate(loki_distributor_lines_received_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (tenant))","legendFormat":"{{tenant}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Lines Per Tenant (top 10)","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fieldConfig":{"defaults":{"custom":{}},"overrides":[]},"fill":1,"fillGradient":0,"gridPos":{"h":5,"w":4,"x":16,"y":1},"hiddenSeries":false,"id":4,"legend":{"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"topk(10, sum(rate(loki_distributor_bytes_received_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (tenant)) / 1024 / 1024","legendFormat":"{{tenant}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"MBs Per Tenant (Top 10)","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fieldConfig":{"defaults":{"custom":{}},"overrides":[]},"fill":1,"fillGradient":0,"gridPos":{"h":5,"w":4,"x":20,"y":1},"hiddenSeries":false,"id":24,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"increase(kube_pod_container_status_restarts_total{cluster=\"$cluster\", namespace=\"$namespace\"}[10m]) \u003e 0","hide":false,"interval":"","legendFormat":"{{container}}-{{pod}}","refId":"B"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Container Restarts","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fieldConfig":{"defaults":{"custom":{}},"overrides":[]},"fill":1,"fillGradient":0,"gridPos":{"h":10,"w":12,"x":0,"y":6},"hiddenSeries":false,"id":9,"legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push\", cluster=~\"$cluster\"})) * 1e3","legendFormat":".99","refId":"A"},{"expr":"histogram_quantile(0.75, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push\", cluster=~\"$cluster\"})) * 1e3","legendFormat":".9","refId":"B"},{"expr":"histogram_quantile(0.5, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push\", cluster=~\"$cluster\"})) * 1e3","legendFormat":".5","refId":"C"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Push Latency","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fieldConfig":{"defaults":{"custom":{}},"overrides":[]},"fill":1,"fillGradient":0,"gridPos":{"h":5,"w":6,"x":12,"y":6},"hiddenSeries":false,"id":12,"legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum by (le) (job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3","legendFormat":".99","refId":"A"},{"expr":"histogram_quantile(0.9, sum by (le) (job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3","legendFormat":".9","refId":"B"},{"expr":"histogram_quantile(0.5, sum by (le) (job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3","legendFormat":".5","refId":"C"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Distributor Latency","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fieldConfig":{"defaults":{"custom":{}},"overrides":[]},"fill":0,"fillGradient":0,"gridPos":{"h":5,"w":6,"x":18,"y":6},"hiddenSeries":false,"id":71,"legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\"}[5m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\"}[5m])) by (route)","interval":"","legendFormat":"{{route}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Distributor Success Rate","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"decimals":null,"format":"percentunit","label":"","logBase":1,"max":"1","min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fieldConfig":{"defaults":{"custom":{}},"overrides":[]},"fill":1,"fillGradient":0,"gridPos":{"h":5,"w":6,"x":12,"y":11},"hiddenSeries":false,"id":13,"legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\", cluster=~\"$cluster\"})) * 1e3","legendFormat":".99","refId":"A"},{"expr":"histogram_quantile(0.9, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\", cluster=~\"$cluster\"})) * 1e3","hide":false,"legendFormat":".9","refId":"B"},{"expr":"histogram_quantile(0.5, sum by (le) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\", cluster=~\"$cluster\"})) * 1e3","hide":false,"legendFormat":".5","refId":"C"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Ingester Latency Write","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fieldConfig":{"defaults":{"custom":{}},"overrides":[]},"fill":0,"fillGradient":0,"gridPos":{"h":5,"w":6,"x":18,"y":11},"hiddenSeries":false,"id":72,"legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\", route=\"/logproto.Pusher/Push\"}[5m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", route=\"/logproto.Pusher/Push\"}[5m])) by (route)","interval":"","legendFormat":"{{route}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Ingester Success Rate Write","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"decimals":null,"format":"percentunit","label":"","logBase":1,"max":"1","min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fieldConfig":{"defaults":{"custom":{}},"overrides":[]},"fill":1,"fillGradient":0,"gridPos":{"h":10,"w":12,"x":0,"y":16},"hiddenSeries":false,"id":10,"legend":{"alignAsTable":true,"avg":false,"current":false,"hideEmpty":true,"hideZero":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"}))","legendFormat":"{{route}}-.99","refId":"A"},{"expr":"histogram_quantile(0.9, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"}))","legendFormat":"{{route}}-.9","refId":"B"},{"expr":"histogram_quantile(0.5, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"}))","legendFormat":"{{route}}-.5","refId":"C"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Query Latency","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fieldConfig":{"defaults":{"custom":{}},"overrides":[]},"fill":1,"fillGradient":0,"gridPos":{"h":5,"w":6,"x":12,"y":16},"hiddenSeries":false,"id":14,"legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"})) * 1e3","legendFormat":".99-{{route}}","refId":"A"},{"expr":"histogram_quantile(0.9, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"})) * 1e3","legendFormat":".9-{{route}}","refId":"B"},{"expr":"histogram_quantile(0.5, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"api_prom_query|api_prom_labels|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_label|loki_api_v1_label_name_values\", cluster=\"$cluster\"})) * 1e3","legendFormat":".5-{{route}}","refId":"C"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Querier Latency","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fieldConfig":{"defaults":{"custom":{}},"overrides":[]},"fill":0,"fillGradient":0,"gridPos":{"h":5,"w":6,"x":18,"y":16},"hiddenSeries":false,"id":73,"legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\", status_code!~\"5[0-9]{2}\"}[5m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\"}[5m])) by (route)","interval":"","legendFormat":"{{route}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Querier Success Rate","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"decimals":null,"format":"percentunit","label":"","logBase":1,"max":"1","min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","description":"","fieldConfig":{"defaults":{"custom":{}},"overrides":[]},"fill":1,"fillGradient":0,"gridPos":{"h":5,"w":6,"x":12,"y":21},"hiddenSeries":false,"id":15,"legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\", cluster=\"$cluster\"})) * 1e3","legendFormat":".99-{{route}}","refId":"A"},{"expr":"histogram_quantile(0.9, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\", cluster=\"$cluster\"})) * 1e3","legendFormat":".9-{{route}}","refId":"B"},{"expr":"histogram_quantile(0.5, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\", cluster=\"$cluster\"})) * 1e3","legendFormat":".5-{{route}}","refId":"C"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Ingester Latency Read","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fieldConfig":{"defaults":{"custom":{}},"overrides":[]},"fill":0,"fillGradient":0,"gridPos":{"h":5,"w":6,"x":18,"y":21},"hiddenSeries":false,"id":74,"legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}[5m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"/logproto.Querier/Query|/logproto.Querier/Label|/logproto.Querier/Series|/logproto.Querier/QuerySample|/logproto.Querier/GetChunkIDs\"}[5m])) by (route)","interval":"","legendFormat":"{{route}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Ingester Success Rate Read","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"decimals":null,"format":"percentunit","label":"","logBase":1,"max":"1","min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"collapsed":true,"datasource":null,"gridPos":{"h":1,"w":24,"x":0,"y":26},"id":110,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":12,"x":0,"y":27},"hiddenSeries":false,"id":112,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"topk(10,sum by (tenant, reason) (rate(loki_discarded_samples_total{cluster=\"$cluster\",namespace=\"$namespace\"}[1m])))","interval":"","legendFormat":"{{ tenant }} - {{ reason }}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Discarded Lines","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"columns":[],"datasource":"$datasource","fontSize":"100%","gridPos":{"h":8,"w":12,"x":12,"y":27},"id":113,"pageSize":null,"panels":[],"showHeader":true,"sort":{"col":3,"desc":true},"styles":[{"alias":"Time","align":"auto","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"","align":"auto","colorMode":null,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"mappingType":1,"pattern":"tenant","thresholds":[],"type":"string","unit":"short"},{"alias":"","align":"auto","colorMode":null,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"mappingType":1,"pattern":"reason","thresholds":[],"type":"number","unit":"short"},{"alias":"","align":"right","colorMode":null,"colors":["rgba(245, 54, 54, 0.9)","rgba(237, 129, 40, 0.89)","rgba(50, 172, 45, 0.97)"],"decimals":2,"pattern":"/.*/","thresholds":[],"type":"number","unit":"short"}],"targets":[{"expr":"topk(10, sum by (tenant, reason) (sum_over_time(increase(loki_discarded_samples_total{cluster=\"$cluster\",namespace=\"$namespace\"}[1m])[$__range:1m])))","format":"table","instant":true,"interval":"","legendFormat":"{{ tenant }} - {{ reason }}","refId":"A"}],"timeFrom":null,"timeShift":null,"title":"Discarded Lines Per Interval","transform":"table","type":"table-old"}],"targets":[],"title":"Limits","type":"row"},{"collapsed":true,"datasource":null,"gridPos":{"h":1,"w":24,"x":0,"y":27},"id":23,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":6,"x":0,"y":28},"hiddenSeries":false,"id":26,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":false,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":true,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"(loki|enterprise-logs)-write.*\"}","intervalFactor":3,"legendFormat":"{{pod}}-{{container}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"CPU Usage","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":6,"x":6,"y":28},"hiddenSeries":false,"id":27,"legend":{"avg":false,"current":false,"hideEmpty":false,"hideZero":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":false,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":true,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"go_memstats_heap_inuse_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"(loki|enterprise-logs)-write.*\"}","instant":false,"intervalFactor":3,"legendFormat":"{{pod}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Memory Usage","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":true,"dashLength":10,"dashes":false,"datasource":"$logs","fill":1,"fillGradient":0,"gridPos":{"h":4,"w":12,"x":12,"y":28},"hiddenSeries":false,"id":31,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":false,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"{}","color":"#C4162A"}],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate({cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\"} | logfmt | level=\"error\"[1m]))","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Error Log Rate","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":false,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}],"yaxis":{"align":false,"alignLevel":null}},{"datasource":"$logs","gridPos":{"h":18,"w":12,"x":12,"y":32},"id":29,"options":{"showLabels":false,"showTime":false,"sortOrder":"Descending","wrapLogMessage":true},"panels":[],"targets":[{"expr":"{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\"} | logfmt | level=\"error\"","refId":"A"}],"timeFrom":null,"timeShift":null,"title":"Logs","type":"logs"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":0,"fillGradient":0,"gridPos":{"h":7,"w":6,"x":0,"y":35},"hiddenSeries":false,"id":33,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\", status_code!~\"5[0-9]{2}\"}[5m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-write\"}[5m])) by (route)","interval":"","intervalFactor":1,"legendFormat":"{{route}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Success Rate","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":6,"x":6,"y":35},"hiddenSeries":false,"id":32,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_distributor_ingester_append_failures_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (ingester)","intervalFactor":1,"legendFormat":"{{ingester}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Append Failures By Ingester","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":6,"x":0,"y":42},"hiddenSeries":false,"id":34,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_distributor_bytes_received_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (pod)","intervalFactor":1,"legendFormat":"{{pod}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Bytes Received/Second","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":6,"x":6,"y":42},"hiddenSeries":false,"id":35,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_distributor_lines_received_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (pod)","intervalFactor":1,"legendFormat":"{{pod}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Lines Received/Second","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}}],"targets":[],"title":"Write Path","type":"row"},{"collapsed":true,"datasource":null,"gridPos":{"h":1,"w":24,"x":0,"y":29},"id":104,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":12,"x":0,"y":30},"hiddenSeries":false,"id":106,"legend":{"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"topk(10,sum by (tenant) (loki_ingester_memory_streams{cluster=\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-write\"}))","interval":"","legendFormat":"{{ tenant }}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Active Streams","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":12,"x":12,"y":30},"hiddenSeries":false,"id":108,"legend":{"avg":false,"current":false,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"topk(10, sum by (tenant) (rate(loki_ingester_streams_created_total{cluster=\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-write\"}[1m]) \u003e 0))","interval":"","legendFormat":"{{ tenant }}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Streams Created/Sec","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}}],"targets":[],"title":"Streams","type":"row"},{"collapsed":true,"datasource":null,"gridPos":{"h":1,"w":24,"x":0,"y":30},"id":94,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":12,"x":0,"y":31},"hiddenSeries":false,"id":102,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"De-Dupe Ratio","yaxis":2}],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_ingester_chunks_flushed_total{cluster=\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-write\"}[1m]))","interval":"","legendFormat":"Chunks","refId":"A"},{"expr":"sum(increase(loki_chunk_store_deduped_chunks_total{cluster=\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\"}[1m]))/sum(increase(loki_ingester_chunks_flushed_total{cluster=\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\"}[1m])) \u003c 1","interval":"","legendFormat":"De-Dupe Ratio","refId":"B"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Chunks Flushed/Sec","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"cards":{"cardPadding":null,"cardRound":null},"color":{"cardColor":"#b4ff00","colorScale":"sqrt","colorScheme":"interpolateSpectral","exponent":0.5,"mode":"spectrum"},"dataFormat":"tsbuckets","datasource":"$datasource","gridPos":{"h":8,"w":12,"x":12,"y":31},"heatmap":{},"hideZeroBuckets":false,"highlightCards":true,"id":100,"legend":{"show":true},"panels":[],"reverseYBuckets":false,"targets":[{"expr":"sum(rate(loki_ingester_chunk_size_bytes_bucket{cluster=\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-write\"}[1m])) by (le)","format":"heatmap","instant":false,"interval":"","legendFormat":"{{ le }}","refId":"A"}],"timeFrom":null,"timeShift":null,"title":"Chunk Size Bytes","tooltip":{"show":true,"showHistogram":false},"type":"heatmap","xAxis":{"show":true},"xBucketNumber":null,"xBucketSize":null,"yAxis":{"decimals":0,"format":"bytes","logBase":1,"max":null,"min":null,"show":true,"splitFactor":null},"yBucketBound":"auto","yBucketNumber":null,"yBucketSize":null},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":7,"fillGradient":0,"gridPos":{"h":9,"w":12,"x":0,"y":39},"hiddenSeries":false,"id":96,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by(reason) (rate(loki_ingester_chunks_flushed_total{cluster=~\"$cluster\",job=~\"$namespace/ingester\", namespace=~\"$namespace\"}[$__rate_interval])) / ignoring(reason) group_left sum(rate(loki_ingester_chunks_flushed_total{cluster=~\"$cluster\",job=~\"$namespace/ingester\", namespace=~\"$namespace\"}[$__rate_interval]))","interval":"","legendFormat":"{{ reason }}"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Chunk Flush Reason %","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":"1","min":"0","show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"cards":{"cardPadding":null,"cardRound":null},"color":{"cardColor":"#b4ff00","colorScale":"sqrt","colorScheme":"interpolateSpectral","exponent":0.5,"max":null,"min":null,"mode":"spectrum"},"dataFormat":"tsbuckets","datasource":"$datasource","gridPos":{"h":9,"w":12,"x":12,"y":39},"heatmap":{},"hideZeroBuckets":true,"highlightCards":true,"id":98,"legend":{"show":true},"panels":[],"reverseYBuckets":false,"targets":[{"expr":"sum by (le) (rate(loki_ingester_chunk_utilization_bucket{cluster=\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\"}[1m]))","format":"heatmap","instant":false,"interval":"","legendFormat":"{{ le }}","refId":"A"}],"timeFrom":null,"timeShift":null,"title":"Chunk Utilization","tooltip":{"show":true,"showHistogram":false},"type":"heatmap","xAxis":{"show":true},"xBucketNumber":null,"xBucketSize":null,"yAxis":{"decimals":0,"format":"percentunit","logBase":1,"max":null,"min":null,"show":true,"splitFactor":null},"yBucketBound":"auto","yBucketNumber":null,"yBucketSize":null}],"targets":[],"title":"Chunks","type":"row"},{"collapsed":true,"datasource":null,"gridPos":{"h":1,"w":24,"x":0,"y":31},"id":64,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":6,"x":0,"y":32},"hiddenSeries":false,"id":68,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":false,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":true,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"(loki|enterprise-logs)-read.*\"}","intervalFactor":3,"legendFormat":"{{pod}}-{{container}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"CPU Usage","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":6,"x":0,"y":39},"hiddenSeries":false,"id":69,"legend":{"avg":false,"current":false,"hideEmpty":false,"hideZero":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":false,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":true,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"go_memstats_heap_inuse_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"(loki|enterprise-logs)-read.*\"}","instant":false,"intervalFactor":3,"legendFormat":"{{pod}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Memory Usage","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":true,"dashLength":10,"dashes":false,"datasource":"$logs","fill":1,"fillGradient":0,"gridPos":{"h":3,"w":18,"x":12,"y":32},"hiddenSeries":false,"id":65,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":false,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"{}","color":"#F2495C"}],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate({cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\"} | logfmt | level=\"error\"[1m]))","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Error Log Rate","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":false,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}],"yaxis":{"align":false,"alignLevel":null}},{"datasource":"$logs","gridPos":{"h":18,"w":18,"x":12,"y":35},"id":66,"options":{"showLabels":false,"showTime":false,"sortOrder":"Descending","wrapLogMessage":true},"panels":[],"targets":[{"expr":"{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\"} | logfmt | level=\"error\"","refId":"A"}],"timeFrom":null,"timeShift":null,"title":"Logs","type":"logs"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":0,"fillGradient":0,"gridPos":{"h":7,"w":6,"x":0,"y":46},"hiddenSeries":false,"id":70,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\", status_code!~\"5[0-9]{2}\"}[1m])) by (route)\n/\nsum(rate(loki_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", job=~\"($namespace)/(loki|enterprise-logs)-read\"}[1m])) by (route)","interval":"","intervalFactor":1,"legendFormat":"{{route}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Success Rate","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}}],"targets":[],"title":"Read Path","type":"row"},{"collapsed":true,"datasource":null,"gridPos":{"h":1,"w":24,"x":0,"y":32},"id":52,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":24,"x":0,"y":30},"hiddenSeries":false,"id":53,"interval":"","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(.99, sum(rate(loki_memcache_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (method, name, le, container))","intervalFactor":1,"legendFormat":"{{container}}: .99-{{method}}-{{name}}","refId":"A"},{"expr":"histogram_quantile(.9, sum(rate(loki_memcache_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (method, name, le, container))","hide":false,"legendFormat":"{{container}}: .9-{{method}}-{{name}}","refId":"B"},{"expr":"histogram_quantile(.5, sum(rate(loki_memcache_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (method, name, le, container))","hide":false,"legendFormat":"{{container}}: .5-{{method}}-{{name}}","refId":"C"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Latency By Method","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":24,"x":0,"y":38},"hiddenSeries":false,"id":54,"interval":"","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_memcache_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (status_code, method, name, container)","intervalFactor":1,"legendFormat":"{{container}}: {{status_code}}-{{method}}-{{name}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Status By Method","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}}],"targets":[],"title":"Memcached","type":"row"},{"collapsed":true,"datasource":null,"gridPos":{"h":1,"w":24,"x":0,"y":33},"id":57,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":24,"x":0,"y":31},"hiddenSeries":false,"id":55,"interval":"","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(.99, sum(rate(loki_consul_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))","intervalFactor":1,"legendFormat":".99-{{operation}}","refId":"A"},{"expr":"histogram_quantile(.9, sum(rate(loki_consul_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))","hide":false,"legendFormat":".9-{{operation}}","refId":"B"},{"expr":"histogram_quantile(.5, sum(rate(loki_consul_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))","hide":false,"legendFormat":".5-{{operation}}","refId":"C"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Latency By Operation","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":24,"x":0,"y":39},"hiddenSeries":false,"id":58,"interval":"","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_consul_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, status_code, method)","intervalFactor":1,"legendFormat":"{{status_code}}-{{operation}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Status By Operation","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}}],"targets":[],"title":"Consul","type":"row"},{"collapsed":true,"datasource":null,"gridPos":{"h":1,"w":24,"x":0,"y":34},"id":43,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":6,"x":0,"y":9},"hiddenSeries":false,"id":41,"interval":"","legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(.99, sum(rate(loki_bigtable_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\", operation=\"/google.bigtable.v2.Bigtable/MutateRows\"}[5m])) by (operation, le))","intervalFactor":1,"legendFormat":".9","refId":"A"},{"expr":"histogram_quantile(.9, sum(rate(loki_bigtable_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\", operation=\"/google.bigtable.v2.Bigtable/MutateRows\"}[5m])) by (operation, le))","refId":"B"},{"expr":"histogram_quantile(.5, sum(rate(loki_bigtable_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\", operation=\"/google.bigtable.v2.Bigtable/MutateRows\"}[5m])) by (operation, le))","refId":"C"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"MutateRows Latency","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":6,"x":6,"y":9},"hiddenSeries":false,"id":46,"interval":"","legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(.99, sum(rate(loki_bigtable_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\", operation=\"/google.bigtable.v2.Bigtable/ReadRows\"}[5m])) by (operation, le))","interval":"","intervalFactor":1,"legendFormat":"99%","refId":"A"},{"expr":"histogram_quantile(.9, sum(rate(loki_bigtable_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\", operation=\"/google.bigtable.v2.Bigtable/ReadRows\"}[5m])) by (operation, le))","interval":"","legendFormat":"90%","refId":"B"},{"expr":"histogram_quantile(.5, sum(rate(loki_bigtable_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\", operation=\"/google.bigtable.v2.Bigtable/ReadRows\"}[5m])) by (operation, le))","interval":"","legendFormat":"50%","refId":"C"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"ReadRows Latency","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":6,"x":12,"y":9},"hiddenSeries":false,"id":44,"interval":"","legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(.99, sum(rate(loki_bigtable_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\", operation=\"/google.bigtable.admin.v2.BigtableTableAdmin/GetTable\"}[5m])) by (operation, le))","interval":"","intervalFactor":1,"legendFormat":"99%","refId":"A"},{"expr":"histogram_quantile(.9, sum(rate(loki_bigtable_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\", operation=\"/google.bigtable.admin.v2.BigtableTableAdmin/GetTable\"}[5m])) by (operation, le))","interval":"","legendFormat":"90%","refId":"B"},{"expr":"histogram_quantile(.5, sum(rate(loki_bigtable_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\", operation=\"/google.bigtable.admin.v2.BigtableTableAdmin/GetTable\"}[5m])) by (operation, le))","interval":"","legendFormat":"50%","refId":"C"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"GetTable Latency","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":6,"x":18,"y":9},"hiddenSeries":false,"id":45,"interval":"","legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(.99, sum(rate(loki_bigtable_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\", operation=\"/google.bigtable.admin.v2.BigtableTableAdmin/ListTables\"}[5m])) by (operation, le))","intervalFactor":1,"legendFormat":".9","refId":"A"},{"expr":"histogram_quantile(.9, sum(rate(loki_bigtable_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\", operation=\"/google.bigtable.admin.v2.BigtableTableAdmin/ListTables\"}[5m])) by (operation, le))","refId":"B"},{"expr":"histogram_quantile(.5, sum(rate(loki_bigtable_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\", operation=\"/google.bigtable.admin.v2.BigtableTableAdmin/ListTables\"}[5m])) by (operation, le))","refId":"C"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"ListTables Latency","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":6,"x":0,"y":16},"hiddenSeries":false,"id":47,"interval":"","legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_bigtable_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", operation=\"/google.bigtable.v2.Bigtable/MutateRows\"}[5m])) by (status_code)","intervalFactor":1,"legendFormat":"{{status_code}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"MutateRows Status","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":6,"x":6,"y":16},"hiddenSeries":false,"id":50,"interval":"","legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_bigtable_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", operation=\"/google.bigtable.v2.Bigtable/ReadRows\"}[5m])) by (status_code)","intervalFactor":1,"legendFormat":"{{status_code}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"ReadRows Status","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":6,"x":12,"y":16},"hiddenSeries":false,"id":48,"interval":"","legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_bigtable_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", operation=\"/google.bigtable.admin.v2.BigtableTableAdmin/GetTable\"}[5m])) by (status_code)","intervalFactor":1,"legendFormat":"{{status_code}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"GetTable Status","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":6,"x":18,"y":16},"hiddenSeries":false,"id":49,"interval":"","legend":{"avg":false,"current":false,"max":false,"min":false,"show":false,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_bigtable_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\", operation=\"/google.bigtable.admin.v2.BigtableTableAdmin/ListTables\"}[5m])) by (status_code)","intervalFactor":1,"legendFormat":"{{status_code}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"ListTables Status","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}}],"targets":[],"title":"Big Table","type":"row"},{"collapsed":true,"datasource":null,"gridPos":{"h":1,"w":24,"x":0,"y":35},"id":60,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":24,"x":0,"y":33},"hiddenSeries":false,"id":61,"interval":"","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(.99, sum(rate(loki_gcs_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))","intervalFactor":1,"legendFormat":".99-{{operation}}","refId":"A"},{"expr":"histogram_quantile(.9, sum(rate(loki_gcs_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))","hide":false,"legendFormat":".9-{{operation}}","refId":"B"},{"expr":"histogram_quantile(.5, sum(rate(loki_gcs_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))","hide":false,"legendFormat":".5-{{operation}}","refId":"C"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Latency By Operation","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":24,"x":0,"y":41},"hiddenSeries":false,"id":62,"interval":"","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_gcs_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (status_code, operation)","intervalFactor":1,"legendFormat":"{{status_code}}-{{operation}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Status By Method","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}}],"targets":[],"title":"GCS","type":"row"},{"collapsed":true,"datasource":null,"gridPos":{"h":1,"w":24,"x":0,"y":36},"id":76,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":null,"fill":1,"fillGradient":0,"gridPos":{"h":6,"w":6,"x":0,"y":9},"id":82,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(cortex_dynamo_failures_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m]))","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Failure Rate","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":null,"fill":1,"fillGradient":0,"gridPos":{"h":6,"w":6,"x":6,"y":9},"id":83,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(cortex_dynamo_consumed_capacity_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m]))","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Consumed Capacity Rate","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":null,"fill":1,"fillGradient":0,"gridPos":{"h":6,"w":6,"x":12,"y":9},"id":84,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(cortex_dynamo_throttled_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m]))","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Throttled Rate","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":null,"fill":1,"fillGradient":0,"gridPos":{"h":6,"w":6,"x":18,"y":9},"id":85,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(cortex_dynamo_dropped_requests_total{cluster=\"$cluster\", namespace=\"$namespace\"}[5m]))","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Dropped Rate","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":null,"fill":1,"fillGradient":0,"gridPos":{"h":6,"w":6,"x":0,"y":15},"id":86,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":2,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(.99, sum(rate(cortex_dynamo_query_pages_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])))","legendFormat":".99","refId":"A"},{"expr":"histogram_quantile(.9, sum(rate(cortex_dynamo_query_pages_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])))","legendFormat":".9","refId":"B"},{"expr":"histogram_quantile(.5, sum(rate(cortex_dynamo_query_pages_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])))","legendFormat":".5","refId":"C"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Query Pages","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":6,"w":9,"x":6,"y":15},"id":87,"interval":"","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(.99, sum(rate(cortex_dynamo_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))","intervalFactor":1,"legendFormat":".99-{{operation}}","refId":"A"},{"expr":"histogram_quantile(.9, sum(rate(cortex_dynamo_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))","hide":false,"legendFormat":".9-{{operation}}","refId":"B"},{"expr":"histogram_quantile(.5, sum(rate(cortex_dynamo_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))","hide":false,"legendFormat":".5-{{operation}}","refId":"C"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Latency By Operation","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":6,"w":9,"x":15,"y":15},"id":88,"interval":"","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(cortex_dynamo_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (status_code, operation)","intervalFactor":1,"legendFormat":"{{status_code}}-{{operation}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Status By Method","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}}],"targets":[],"title":"Dynamo","type":"row"},{"collapsed":true,"datasource":null,"gridPos":{"h":1,"w":24,"x":0,"y":37},"id":78,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":24,"x":0,"y":10},"id":79,"interval":"","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(.99, sum(rate(loki_s3_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))","intervalFactor":1,"legendFormat":".99-{{operation}}","refId":"A"},{"expr":"histogram_quantile(.9, sum(rate(loki_s3_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))","hide":false,"legendFormat":".9-{{operation}}","refId":"B"},{"expr":"histogram_quantile(.5, sum(rate(loki_s3_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))","hide":false,"legendFormat":".5-{{operation}}","refId":"C"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Latency By Operation","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":24,"x":0,"y":18},"id":80,"interval":"","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_s3_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (status_code, operation)","intervalFactor":1,"legendFormat":"{{status_code}}-{{operation}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Status By Method","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}}],"targets":[],"title":"S3","type":"row"},{"collapsed":true,"datasource":null,"gridPos":{"h":1,"w":24,"x":0,"y":37},"id":78,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":24,"x":0,"y":10},"id":79,"interval":"","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(.99, sum(rate(loki_azure_blob_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))","intervalFactor":1,"legendFormat":".99-{{operation}}","refId":"A"},{"expr":"histogram_quantile(.9, sum(rate(loki_azure_blob_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))","hide":false,"legendFormat":".9-{{operation}}","refId":"B"},{"expr":"histogram_quantile(.5, sum(rate(loki_azure_blob_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))","hide":false,"legendFormat":".5-{{operation}}","refId":"C"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Latency By Operation","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":24,"x":0,"y":18},"id":80,"interval":"","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_azure_blob_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (status_code, operation)","intervalFactor":1,"legendFormat":"{{status_code}}-{{operation}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Status By Method","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}}],"targets":[],"title":"Azure Blob","type":"row"},{"collapsed":true,"datasource":null,"gridPos":{"h":1,"w":24,"x":0,"y":37},"id":114,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":24,"x":0,"y":10},"id":115,"interval":"","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(.99, sum(rate(loki_boltdb_shipper_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))","intervalFactor":1,"legendFormat":".99-{{operation}}","refId":"A"},{"expr":"histogram_quantile(.9, sum(rate(loki_boltdb_shipper_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))","hide":false,"legendFormat":".9-{{operation}}","refId":"B"},{"expr":"histogram_quantile(.5, sum(rate(loki_boltdb_shipper_request_duration_seconds_bucket{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (operation, le))","hide":false,"legendFormat":".5-{{operation}}","refId":"C"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Latency By Operation","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":8,"w":24,"x":0,"y":18},"id":116,"interval":"","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"nullPointMode":"null","options":{"dataLinks":[]},"panels":[],"percentage":false,"pointradius":1,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(loki_boltdb_shipper_request_duration_seconds_count{cluster=\"$cluster\", namespace=\"$namespace\"}[5m])) by (status_code, operation)","intervalFactor":1,"legendFormat":"{{status_code}}-{{operation}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Status By Method","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}}],"targets":[],"title":"BoltDB Shipper","type":"row"}],"refresh":"10s","rows":[],"schemaVersion":14,"style":"dark","tags":["loki"],"templating":{"list":[{"current":{"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"hide":0,"label":null,"name":"logs","options":[],"query":"loki","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{"text":"prod","value":"prod"},"datasource":"$datasource","hide":0,"includeAll":false,"label":"cluster","multi":false,"name":"cluster","options":[],"query":"label_values(loki_build_info, cluster)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{"text":"prod","value":"prod"},"datasource":"$datasource","hide":0,"includeAll":false,"label":"namespace","multi":false,"name":"namespace","options":[],"query":"label_values(loki_build_info{cluster=~\"$cluster\"}, namespace)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone":"utc","title":"Loki / Operational","uid":"operational","version":0} \ No newline at end of file diff --git a/monitor/loki-dashboard/v1_ConfigMap_loki-dashboards-2.yaml b/monitor/loki-dashboard/v1_ConfigMap_loki-dashboards-2.yaml new file mode 100644 index 0000000..1fd43eb --- /dev/null +++ b/monitor/loki-dashboard/v1_ConfigMap_loki-dashboards-2.yaml @@ -0,0 +1,24 @@ +# Source: loki/templates/monitoring/dashboards/configmap-2.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + name: loki-dashboards-2 + namespace: vynil-monitor + labels: + helm.sh/chart: loki-5.41.8 + app.kubernetes.io/name: loki + app.kubernetes.io/instance: loki + app.kubernetes.io/version: "2.9.3" + app.kubernetes.io/managed-by: Helm + grafana_dashboard: "1" +data: + "loki-reads-resources.json": | + {"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"links":[{"asDropdown":true,"icon":"external link","includeVars":true,"keepTime":true,"tags":["loki"],"targetBlank":false,"title":"Loki Dashboards","type":"dashboards"}],"refresh":"10s","rows":[{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"gridPos":{},"id":1,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"limit","color":"#E02F44","fill":0}],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"{{pod}}","legendLink":null,"step":10},{"expr":"min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\"})","format":"time_series","intervalFactor":2,"legendFormat":"limit","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU","tooltip":{"sort":2},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"gridPos":{},"id":2,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"limit","color":"#E02F44","fill":0}],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\"})","format":"time_series","intervalFactor":2,"legendFormat":"{{pod}}","legendLink":null,"step":10},{"expr":"min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\"} \u003e 0)","format":"time_series","intervalFactor":2,"legendFormat":"limit","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory (workingset)","tooltip":{"sort":2},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"gridPos":{},"id":3,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-read\"})","format":"time_series","intervalFactor":2,"legendFormat":"{{pod}}","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory (go heap inuse)","tooltip":{"sort":2},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"gridPos":{},"id":4,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by(instance, pod, device) (rate(node_disk_written_bytes_total[$__rate_interval])) + ignoring(pod) group_right() (label_replace(count by(instance, pod, device) (container_fs_writes_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n","format":"time_series","intervalFactor":2,"legendFormat":"{{pod}} - {{device}}","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Disk Writes","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"gridPos":{},"id":5,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by(instance, pod, device) (rate(node_disk_read_bytes_total[$__rate_interval])) + ignoring(pod) group_right() (label_replace(count by(instance, pod, device) (container_fs_writes_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n","format":"time_series","intervalFactor":2,"legendFormat":"{{pod}} - {{device}}","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Disk Reads","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"gridPos":{},"id":6,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"max by(persistentvolumeclaim) (kubelet_volume_stats_used_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"} / kubelet_volume_stats_capacity_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"}) and count by(persistentvolumeclaim) (kube_persistentvolumeclaim_labels{cluster=~\"$cluster\", namespace=~\"$namespace\",label_name=~\"(loki|enterprise-logs)-read.*\"})","format":"time_series","intervalFactor":2,"legendFormat":"{{persistentvolumeclaim}}","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Disk Space Utilization","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"gridPos":{},"id":7,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"loki_boltdb_shipper_query_readiness_duration_seconds{cluster=~\"$cluster\", namespace=~\"$namespace\"}","format":"time_series","intervalFactor":2,"legendFormat":"duration","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Query Readiness Duration","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Read path","titleSize":"h6","type":"row"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":8,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"limit","color":"#E02F44","fill":0}],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"{{pod}}","legendLink":null,"step":10},{"expr":"min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"})","format":"time_series","intervalFactor":2,"legendFormat":"limit","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU","tooltip":{"sort":2},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":9,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"limit","color":"#E02F44","fill":0}],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"})","format":"time_series","intervalFactor":2,"legendFormat":"{{pod}}","legendLink":null,"step":10},{"expr":"min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"} \u003e 0)","format":"time_series","intervalFactor":2,"legendFormat":"limit","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory (workingset)","tooltip":{"sort":2},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":10,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\"})","format":"time_series","intervalFactor":2,"legendFormat":"{{pod}}","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory (go heap inuse)","tooltip":{"sort":2},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Ingester","titleSize":"h6"}],"schemaVersion":14,"style":"dark","tags":["loki"],"templating":{"list":[{"current":{"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{"text":"prod","value":"prod"},"datasource":"$datasource","hide":0,"includeAll":false,"label":"cluster","multi":false,"name":"cluster","options":[],"query":"label_values(loki_build_info, cluster)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{"text":"prod","value":"prod"},"datasource":"$datasource","hide":0,"includeAll":false,"label":"namespace","multi":false,"name":"namespace","options":[],"query":"label_values(loki_build_info{cluster=~\"$cluster\"}, namespace)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone":"utc","title":"Loki / Reads Resources","uid":"reads-resources","version":0} + "loki-reads.json": | + {"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"links":[{"asDropdown":true,"icon":"external link","includeVars":true,"keepTime":true,"tags":["loki"],"targetBlank":false,"title":"Loki Dashboards","type":"dashboards"}],"refresh":"10s","rows":[{"collapse":false,"height":"250px","panels":[{"aliasColors":{"1xx":"#EAB839","2xx":"#7EB26D","3xx":"#6ED0E0","4xx":"#EF843C","5xx":"#E24D42","error":"#E24D42","success":"#7EB26D"},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":1,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by (status) (\n label_replace(label_replace(rate(loki_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n","format":"time_series","intervalFactor":2,"legendFormat":"{{status}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"QPS","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":2,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\", cluster=~\"$cluster\"})) * 1e3","format":"time_series","intervalFactor":2,"legendFormat":"{{ route }} 99th Percentile","refId":"A","step":10},{"expr":"histogram_quantile(0.50, sum by (le,route) (job_route:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\", cluster=~\"$cluster\"})) * 1e3","format":"time_series","intervalFactor":2,"legendFormat":"{{ route }} 50th Percentile","refId":"B","step":10},{"expr":"1e3 * sum(job_route:loki_request_duration_seconds_sum:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\", cluster=~\"$cluster\"}) by (route) / sum(job_route:loki_request_duration_seconds_count:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-read\", route=~\"loki_api_v1_series|api_prom_series|api_prom_query|api_prom_label|api_prom_label_name_values|loki_api_v1_query|loki_api_v1_query_range|loki_api_v1_labels|loki_api_v1_label_name_values\", cluster=~\"$cluster\"}) by (route) ","format":"time_series","intervalFactor":2,"legendFormat":"{{ route }} Average","refId":"C","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Latency","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ms","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Read Path","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{"1xx":"#EAB839","2xx":"#7EB26D","3xx":"#6ED0E0","4xx":"#EF843C","5xx":"#E24D42","error":"#E24D42","success":"#7EB26D"},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":3,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by (status) (\n label_replace(label_replace(rate(loki_boltdb_shipper_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", operation=\"Shipper.Query\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n","format":"time_series","intervalFactor":2,"legendFormat":"{{status}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"QPS","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":4,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(loki_boltdb_shipper_request_duration_seconds_bucket{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", operation=\"Shipper.Query\"}[$__rate_interval])) by (le)) * 1e3","format":"time_series","intervalFactor":2,"legendFormat":"99th Percentile","refId":"A","step":10},{"expr":"histogram_quantile(0.50, sum(rate(loki_boltdb_shipper_request_duration_seconds_bucket{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", operation=\"Shipper.Query\"}[$__rate_interval])) by (le)) * 1e3","format":"time_series","intervalFactor":2,"legendFormat":"50th Percentile","refId":"B","step":10},{"expr":"sum(rate(loki_boltdb_shipper_request_duration_seconds_sum{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", operation=\"Shipper.Query\"}[$__rate_interval])) * 1e3 / sum(rate(loki_boltdb_shipper_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-read\", operation=\"Shipper.Query\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"Average","refId":"C","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Latency","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ms","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"BoltDB Shipper","titleSize":"h6"}],"schemaVersion":14,"style":"dark","tags":["loki"],"templating":{"list":[{"current":{"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{"text":"prod","value":"prod"},"datasource":"$datasource","hide":0,"includeAll":false,"label":"cluster","multi":false,"name":"cluster","options":[],"query":"label_values(loki_build_info, cluster)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{"text":"prod","value":"prod"},"datasource":"$datasource","hide":0,"includeAll":false,"label":"namespace","multi":false,"name":"namespace","options":[],"query":"label_values(loki_build_info{cluster=~\"$cluster\"}, namespace)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone":"utc","title":"Loki / Reads","uid":"reads","version":0} + "loki-retention.json": | + {"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"links":[{"asDropdown":true,"icon":"external link","includeVars":true,"keepTime":true,"tags":["loki"],"targetBlank":false,"title":"Loki Dashboards","type":"dashboards"}],"refresh":"10s","rows":[{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":1,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"limit","color":"#E02F44","fill":0}],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"{{pod}}","legendLink":null,"step":10},{"expr":"min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\"})","format":"time_series","intervalFactor":2,"legendFormat":"limit","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU","tooltip":{"sort":2},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":2,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"limit","color":"#E02F44","fill":0}],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\"})","format":"time_series","intervalFactor":2,"legendFormat":"{{pod}}","legendLink":null,"step":10},{"expr":"min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-read.*\"} \u003e 0)","format":"time_series","intervalFactor":2,"legendFormat":"limit","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory (workingset)","tooltip":{"sort":2},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":3,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-read\"})","format":"time_series","intervalFactor":2,"legendFormat":"{{pod}}","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory (go heap inuse)","tooltip":{"sort":2},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Resource Usage","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fieldConfig":{"defaults":{"color":{"fixedColor":"blue","mode":"fixed"},"custom":{},"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null}]},"unit":"dateTimeFromNow"}},"fill":1,"id":4,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","options":{"colorMode":"value","graphMode":"area","justifyMode":"auto","orientation":"auto","reduceOptions":{"calcs":["lastNotNull"],"fields":"","values":false},"text":{},"textMode":"auto"},"percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"loki_boltdb_shipper_compact_tables_operation_last_successful_run_timestamp_seconds{cluster=~\"$cluster\", namespace=~\"$namespace\"} * 1e3","format":"time_series","instant":true,"refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Last Compact and Mark Operation Success","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"stat","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":5,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"loki_boltdb_shipper_compact_tables_operation_duration_seconds{cluster=~\"$cluster\", namespace=~\"$namespace\"}","format":"time_series","intervalFactor":2,"legendFormat":"duration","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Compact and Mark Operations Duration","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":6,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"sum by (status)(rate(loki_boltdb_shipper_compact_tables_operation_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"{{success}}","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Compact and Mark Operations Per Status","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Compact and Mark","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":7,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":4,"stack":true,"steppedLine":false,"targets":[{"expr":"count by(action)(loki_boltdb_shipper_retention_marker_table_processed_total{cluster=~\"$cluster\", namespace=~\"$namespace\"})","format":"time_series","intervalFactor":2,"legendFormat":"{{action}}","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Processed Tables Per Action","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":8,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":4,"stack":true,"steppedLine":false,"targets":[{"expr":"count by(table,action)(loki_boltdb_shipper_retention_marker_table_processed_total{cluster=~\"$cluster\", namespace=~\"$namespace\" , action=~\"modified|deleted\"})","format":"time_series","intervalFactor":2,"legendFormat":"{{table}}-{{action}}","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Modified Tables","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":9,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":4,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by (table)(rate(loki_boltdb_shipper_retention_marker_count_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) \u003e0","format":"time_series","intervalFactor":2,"legendFormat":"{{table}}","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Marks Creation Rate Per Table","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Per Table Marker","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"format":"short","id":10,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"sum (increase(loki_boltdb_shipper_retention_marker_count_total{cluster=~\"$cluster\", namespace=~\"$namespace\"}[24h]))","format":"time_series","instant":true,"intervalFactor":2,"refId":"A"}],"thresholds":"70,80","timeFrom":null,"timeShift":null,"title":"Marked Chunks (24h)","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"singlestat","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":11,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(loki_boltdb_shipper_retention_marker_table_processed_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (le)) * 1e3","format":"time_series","intervalFactor":2,"legendFormat":"99th Percentile","refId":"A","step":10},{"expr":"histogram_quantile(0.50, sum(rate(loki_boltdb_shipper_retention_marker_table_processed_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (le)) * 1e3","format":"time_series","intervalFactor":2,"legendFormat":"50th Percentile","refId":"B","step":10},{"expr":"sum(rate(loki_boltdb_shipper_retention_marker_table_processed_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) * 1e3 / sum(rate(loki_boltdb_shipper_retention_marker_table_processed_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"Average","refId":"C","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Mark Table Latency","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ms","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"format":"short","id":12,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"sum (increase(loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\"}[24h]))","format":"time_series","instant":true,"intervalFactor":2,"refId":"A"}],"thresholds":"70,80","timeFrom":null,"timeShift":null,"title":"Delete Chunks (24h)","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"singlestat","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":13,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (le)) * 1e3","format":"time_series","intervalFactor":2,"legendFormat":"99th Percentile","refId":"A","step":10},{"expr":"histogram_quantile(0.50, sum(rate(loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_bucket{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (le)) * 1e3","format":"time_series","intervalFactor":2,"legendFormat":"50th Percentile","refId":"B","step":10},{"expr":"sum(rate(loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_sum{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) * 1e3 / sum(rate(loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"Average","refId":"C","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Delete Latency","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ms","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Sweeper","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":14,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"time() - (loki_boltdb_shipper_retention_sweeper_marker_file_processing_current_time{cluster=~\"$cluster\", namespace=~\"$namespace\"} \u003e 0)","format":"time_series","intervalFactor":2,"legendFormat":"lag","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Sweeper Lag","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":15,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(loki_boltdb_shipper_retention_sweeper_marker_files_current{cluster=~\"$cluster\", namespace=~\"$namespace\"})","format":"time_series","intervalFactor":2,"legendFormat":"count","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Marks Files to Process","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":16,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"sum by (status)(rate(loki_boltdb_shipper_retention_sweeper_chunk_deleted_duration_seconds_count{cluster=~\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"{{status}}","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Delete Rate Per Status","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"datasource":"$logs","id":17,"span":12,"targets":[{"expr":"{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-read\"}","refId":"A"}],"title":"Compactor Logs","type":"logs"}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Logs","titleSize":"h6"}],"schemaVersion":14,"style":"dark","tags":["loki"],"templating":{"list":[{"current":{"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{"text":"prod","value":"prod"},"datasource":"$datasource","hide":0,"includeAll":false,"label":"cluster","multi":false,"name":"cluster","options":[],"query":"label_values(loki_build_info, cluster)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{"text":"prod","value":"prod"},"datasource":"$datasource","hide":0,"includeAll":false,"label":"namespace","multi":false,"name":"namespace","options":[],"query":"label_values(loki_build_info{cluster=~\"$cluster\"}, namespace)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"hide":0,"label":null,"name":"logs","options":[],"query":"loki","refresh":1,"regex":"","type":"datasource"}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone":"utc","title":"Loki / Retention","uid":"retention","version":0} + "loki-writes-resources.json": | + {"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"links":[{"asDropdown":true,"icon":"external link","includeVars":true,"keepTime":true,"tags":["loki"],"targetBlank":false,"title":"Loki Dashboards","type":"dashboards"}],"refresh":"10s","rows":[{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"gridPos":{},"id":1,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"sum by(pod) (loki_ingester_memory_streams{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\"})","format":"time_series","intervalFactor":2,"legendFormat":"{{pod}}","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"In-memory streams","tooltip":{"sort":2},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"gridPos":{},"id":2,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"limit","color":"#E02F44","fill":0}],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"sum by(pod) (rate(container_cpu_usage_seconds_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"{{pod}}","legendLink":null,"step":10},{"expr":"min(container_spec_cpu_quota{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"} / container_spec_cpu_period{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"})","format":"time_series","intervalFactor":2,"legendFormat":"limit","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU","tooltip":{"sort":2},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"gridPos":{},"id":3,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"limit","color":"#E02F44","fill":0}],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"max by(pod) (container_memory_working_set_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"})","format":"time_series","intervalFactor":2,"legendFormat":"{{pod}}","legendLink":null,"step":10},{"expr":"min(container_spec_memory_limit_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\"} \u003e 0)","format":"time_series","intervalFactor":2,"legendFormat":"limit","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory (workingset)","tooltip":{"sort":2},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"gridPos":{},"id":4,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"sum by(pod) (go_memstats_heap_inuse_bytes{cluster=~\"$cluster\", job=~\"($namespace)/(loki|enterprise-logs)-write\"})","format":"time_series","intervalFactor":2,"legendFormat":"{{pod}}","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory (go heap inuse)","tooltip":{"sort":2},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"gridPos":{},"id":5,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by(instance, pod, device) (rate(node_disk_written_bytes_total[$__rate_interval])) + ignoring(pod) group_right() (label_replace(count by(instance, pod, device) (container_fs_writes_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n","format":"time_series","intervalFactor":2,"legendFormat":"{{pod}} - {{device}}","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Disk Writes","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"gridPos":{},"id":6,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by(instance, pod, device) (rate(node_disk_read_bytes_total[$__rate_interval])) + ignoring(pod) group_right() (label_replace(count by(instance, pod, device) (container_fs_writes_bytes_total{cluster=~\"$cluster\", namespace=~\"$namespace\", container=\"loki\", pod=~\"(loki|enterprise-logs)-write.*\", device!~\".*sda.*\"}), \"device\", \"$1\", \"device\", \"/dev/(.*)\") * 0)\n","format":"time_series","intervalFactor":2,"legendFormat":"{{pod}} - {{device}}","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Disk Reads","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"gridPos":{},"id":7,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"max by(persistentvolumeclaim) (kubelet_volume_stats_used_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"} / kubelet_volume_stats_capacity_bytes{cluster=~\"$cluster\", namespace=~\"$namespace\"}) and count by(persistentvolumeclaim) (kube_persistentvolumeclaim_labels{cluster=~\"$cluster\", namespace=~\"$namespace\",label_name=~\"(loki|enterprise-logs)-write.*\"})","format":"time_series","intervalFactor":2,"legendFormat":"{{persistentvolumeclaim}}","legendLink":null,"step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Disk Space Utilization","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Write path","titleSize":"h6","type":"row"}],"schemaVersion":14,"style":"dark","tags":["loki"],"templating":{"list":[{"current":{"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{"text":"prod","value":"prod"},"datasource":"$datasource","hide":0,"includeAll":false,"label":"cluster","multi":false,"name":"cluster","options":[],"query":"label_values(loki_build_info, cluster)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{"text":"prod","value":"prod"},"datasource":"$datasource","hide":0,"includeAll":false,"label":"namespace","multi":false,"name":"namespace","options":[],"query":"label_values(loki_build_info{cluster=~\"$cluster\"}, namespace)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone":"utc","title":"Loki / Writes Resources","uid":"writes-resources","version":0} + "loki-writes.json": | + {"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"links":[{"asDropdown":true,"icon":"external link","includeVars":true,"keepTime":true,"tags":["loki"],"targetBlank":false,"title":"Loki Dashboards","type":"dashboards"}],"refresh":"10s","rows":[{"collapse":false,"height":"250px","panels":[{"aliasColors":{"1xx":"#EAB839","2xx":"#7EB26D","3xx":"#6ED0E0","4xx":"#EF843C","5xx":"#E24D42","error":"#E24D42","success":"#7EB26D"},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":1,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by (status) (\n label_replace(label_replace(rate(loki_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-write\", route=~\"api_prom_push|loki_api_v1_push|/httpgrpc.HTTP/Handle\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n","format":"time_series","intervalFactor":2,"legendFormat":"{{status}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"QPS","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":2,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum by (le) (job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3","format":"time_series","intervalFactor":2,"legendFormat":"99th Percentile","refId":"A","step":10},{"expr":"histogram_quantile(0.50, sum by (le) (job:loki_request_duration_seconds_bucket:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})) * 1e3","format":"time_series","intervalFactor":2,"legendFormat":"50th Percentile","refId":"B","step":10},{"expr":"1e3 * sum(job:loki_request_duration_seconds_sum:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"}) / sum(job:loki_request_duration_seconds_count:sum_rate{job=~\"($namespace)/(loki|enterprise-logs)-write\", cluster=~\"$cluster\"})","format":"time_series","intervalFactor":2,"legendFormat":"Average","refId":"C","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Latency","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ms","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Write Path","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{"1xx":"#EAB839","2xx":"#7EB26D","3xx":"#6ED0E0","4xx":"#EF843C","5xx":"#E24D42","error":"#E24D42","success":"#7EB26D"},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":3,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by (status) (\n label_replace(label_replace(rate(loki_boltdb_shipper_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-write\", operation=\"WRITE\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n","format":"time_series","intervalFactor":2,"legendFormat":"{{status}}","refId":"A","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"QPS","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":4,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(loki_boltdb_shipper_request_duration_seconds_bucket{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-write\", operation=\"WRITE\"}[$__rate_interval])) by (le)) * 1e3","format":"time_series","intervalFactor":2,"legendFormat":"99th Percentile","refId":"A","step":10},{"expr":"histogram_quantile(0.50, sum(rate(loki_boltdb_shipper_request_duration_seconds_bucket{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-write\", operation=\"WRITE\"}[$__rate_interval])) by (le)) * 1e3","format":"time_series","intervalFactor":2,"legendFormat":"50th Percentile","refId":"B","step":10},{"expr":"sum(rate(loki_boltdb_shipper_request_duration_seconds_sum{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-write\", operation=\"WRITE\"}[$__rate_interval])) * 1e3 / sum(rate(loki_boltdb_shipper_request_duration_seconds_count{cluster=~\"$cluster\",job=~\"($namespace)/(loki|enterprise-logs)-write\", operation=\"WRITE\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"Average","refId":"C","step":10}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Latency","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ms","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"BoltDB Shipper","titleSize":"h6"}],"schemaVersion":14,"style":"dark","tags":["loki"],"templating":{"list":[{"current":{"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{"text":"prod","value":"prod"},"datasource":"$datasource","hide":0,"includeAll":false,"label":"cluster","multi":false,"name":"cluster","options":[],"query":"label_values(loki_build_info, cluster)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{"text":"prod","value":"prod"},"datasource":"$datasource","hide":0,"includeAll":false,"label":"namespace","multi":false,"name":"namespace","options":[],"query":"label_values(loki_build_info{cluster=~\"$cluster\"}, namespace)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone":"utc","title":"Loki / Writes","uid":"writes","version":0} \ No newline at end of file diff --git a/monitor/loki/apps_v1_StatefulSet_loki.yaml b/monitor/loki/apps_v1_StatefulSet_loki.yaml new file mode 100644 index 0000000..7aafa68 --- /dev/null +++ b/monitor/loki/apps_v1_StatefulSet_loki.yaml @@ -0,0 +1,124 @@ +# Source: loki/templates/single-binary/statefulset.yaml +apiVersion: apps/v1 +kind: StatefulSet +metadata: + name: loki + namespace: vynil-monitor + labels: + helm.sh/chart: loki-5.42.0 + app.kubernetes.io/name: loki + app.kubernetes.io/instance: loki + app.kubernetes.io/version: "2.9.3" + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: single-binary + app.kubernetes.io/part-of: memberlist +spec: + replicas: 1 + podManagementPolicy: Parallel + updateStrategy: + rollingUpdate: + partition: 0 + serviceName: loki-headless + revisionHistoryLimit: 10 + + persistentVolumeClaimRetentionPolicy: + whenDeleted: Delete + whenScaled: Delete + selector: + matchLabels: + app.kubernetes.io/name: loki + app.kubernetes.io/instance: loki + app.kubernetes.io/component: single-binary + template: + metadata: + annotations: + checksum/config: 460436a92733ff5d408f5f9ce92c1b436dccb5d60e0b4040a9511a6e21252c53 + labels: + app.kubernetes.io/name: loki + app.kubernetes.io/instance: loki + app.kubernetes.io/component: single-binary + app.kubernetes.io/part-of: memberlist + spec: + serviceAccountName: loki + automountServiceAccountToken: true + enableServiceLinks: true + + securityContext: + fsGroup: 10001 + runAsGroup: 10001 + runAsNonRoot: true + runAsUser: 10001 + terminationGracePeriodSeconds: 30 + containers: + - name: loki + image: docker.io/grafana/loki:2.9.3 + imagePullPolicy: IfNotPresent + args: + - -config.file=/etc/loki/config/config.yaml + - -target=all + ports: + - name: http-metrics + containerPort: 3100 + protocol: TCP + - name: grpc + containerPort: 9095 + protocol: TCP + - name: http-memberlist + containerPort: 7946 + protocol: TCP + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + readinessProbe: + httpGet: + path: /ready + port: http-metrics + initialDelaySeconds: 30 + timeoutSeconds: 1 + volumeMounts: + - name: tmp + mountPath: /tmp + - name: config + mountPath: /etc/loki/config + - name: runtime-config + mountPath: /etc/loki/runtime-config + - name: storage + mountPath: /var/loki + resources: + {} + affinity: + podAntiAffinity: + requiredDuringSchedulingIgnoredDuringExecution: + - labelSelector: + matchLabels: + app.kubernetes.io/name: loki + app.kubernetes.io/instance: loki + app.kubernetes.io/component: single-binary + topologyKey: kubernetes.io/hostname + + volumes: + - name: tmp + emptyDir: {} + - name: config + configMap: + name: loki + items: + - key: "config.yaml" + path: "config.yaml" + - name: runtime-config + configMap: + name: loki-runtime + volumeClaimTemplates: + - apiVersion: v1 + kind: PersistentVolumeClaim + metadata: + name: storage + spec: + accessModes: + - ReadWriteOnce + resources: + requests: + storage: "17Gi" \ No newline at end of file diff --git a/monitor/loki/config.tf b/monitor/loki/config.tf new file mode 100644 index 0000000..de79b58 --- /dev/null +++ b/monitor/loki/config.tf @@ -0,0 +1,91 @@ +resource "kubectl_manifest" "datasource" { + yaml_body = <<-EOF + apiVersion: v1 + kind: ConfigMap + metadata: + name: loki-datasource + namespace: "${var.namespace}" + labels: ${jsonencode(merge(local.common-labels, {"grafana_datasource" = "1"}))} + data: + loki-datasource.yaml: |- + apiVersion: 1 + datasources: + - name: Loki + type: loki + access: proxy + url: "http://loki.${var.namespace}.svc:3100" + version: 1 + isDefault: false + jsonData: + {} + EOF +} +resource "kubectl_manifest" "config" { + yaml_body = <<-EOF + apiVersion: v1 + kind: ConfigMap + metadata: + name: loki + namespace: "${var.namespace}" + labels: ${jsonencode(local.common-labels)} + data: + config.yaml: | + auth_enabled: false + common: + compactor_address: 'loki' + path_prefix: /var/loki + replication_factor: 1 + storage: + filesystem: + chunks_directory: /var/loki/chunks + rules_directory: /var/loki/rules + frontend: + scheduler_address: "" + frontend_worker: + scheduler_address: "" + index_gateway: + mode: ring + limits_config: + max_cache_freshness_per_query: 10m + reject_old_samples: true + reject_old_samples_max_age: 168h + split_queries_by_interval: 15m + memberlist: + join_members: + - loki-memberlist + query_range: + align_queries_with_step: true + ruler: + storage: + type: local + local: + directory: /tmp/rules + rule_path: /tmp/scratch + alertmanager_url: http://${var.alertmanager}:9093 + ring: + kvstore: + store: inmemory + enable_api: true + runtime_config: + file: /etc/loki/runtime-config/runtime-config.yaml + schema_config: + configs: + - from: "2022-01-11" + index: + period: 24h + prefix: loki_index_ + object_store: filesystem + schema: v12 + store: boltdb-shipper + server: + grpc_listen_port: 9095 + http_listen_port: 3100 + storage_config: + hedging: + at: 250ms + max_per_second: 20 + up_to: 3 + tracing: + enabled: false + EOF +} diff --git a/monitor/loki/datas.tf b/monitor/loki/datas.tf new file mode 100644 index 0000000..32c9304 --- /dev/null +++ b/monitor/loki/datas.tf @@ -0,0 +1,77 @@ +locals { + common-labels = { + "vynil.solidite.fr/owner-name" = var.instance + "vynil.solidite.fr/owner-namespace" = var.namespace + "vynil.solidite.fr/owner-category" = var.category + "vynil.solidite.fr/owner-component" = var.component + "app.kubernetes.io/managed-by" = "vynil" + "app.kubernetes.io/instance" = var.instance + } + pvc_spec = merge({ + "accessModes" = [var.storage.volume.accessMode] + "volumeMode" = var.storage.volume.type + "resources" = { + "requests" = { + "storage" = "${var.storage.volume.size}" + } + } + }, var.storage.volume.class != "" ?{ + "storageClassName" = var.storage.volume.class + }:{}) + rb-patch = <<-EOF + - op: replace + path: /subjects/0/namespace + value: "${var.namespace}" + EOF +} + +data "kustomization_overlay" "data" { + common_labels = local.common-labels + namespace = var.namespace + resources = [for file in fileset(path.module, "*.yaml"): file if file != "index.yaml" && length(regexall("ClusterRole",file))<1] + images { + name = "docker.io/grafana/loki" + new_name = "${var.images.loki.registry}/${var.images.loki.repository}" + new_tag = "${var.images.loki.tag}" + } + patches { + target { + kind = "ServiceMonitor" + name = "loki" + } + patch = <<-EOF + - op: replace + path: /spec/endpoints/0/relabelings/0/replacement + value: "${var.namespace}/$1" + EOF + } + patches { + target { + kind = "StatefulSet" + name = "loki" + } + patch = <<-EOF + apiVersion: apps/v1 + kind: StatefulSet + metadata: + name: loki + spec: + replicas: 1 + template: + spec: + containers: + - name: loki + imagePullPolicy: ${var.images.loki.pullPolicy} + volumeClaimTemplates: + - apiVersion: v1 + kind: PersistentVolumeClaim + metadata: + name: storage + annotations: + k8up.io/backup: "true" + spec: ${jsonencode(local.pvc_spec)} + EOF + } +} + + diff --git a/monitor/loki/index.yaml b/monitor/loki/index.yaml new file mode 100644 index 0000000..74021bf --- /dev/null +++ b/monitor/loki/index.yaml @@ -0,0 +1,106 @@ +--- +apiVersion: vinyl.solidite.fr/v1beta1 +kind: Component +category: monitor +metadata: + name: loki + description: null +options: + storage: + default: + volume: + accessMode: ReadWriteOnce + class: '' + size: 10Gi + type: Filesystem + description: Configure this app storage + examples: + - volume: + accessMode: ReadWriteOnce + class: '' + size: 10Gi + type: Filesystem + properties: + volume: + default: + accessMode: ReadWriteOnce + class: '' + size: 10Gi + type: Filesystem + properties: + accessMode: + default: ReadWriteOnce + enum: + - ReadWriteOnce + - ReadOnlyMany + - ReadWriteMany + type: string + class: + default: '' + type: string + size: + default: 10Gi + type: string + type: + default: Filesystem + enum: + - Filesystem + - Block + type: string + type: object + type: object + alertmanager: + default: alertmanager-alertmanager + examples: + - alertmanager-alertmanager + type: string + images: + default: + loki: + pullPolicy: IfNotPresent + registry: docker.io + repository: grafana/loki + tag: 2.9.3 + examples: + - loki: + pullPolicy: IfNotPresent + registry: docker.io + repository: grafana/loki + tag: 2.9.3 + properties: + loki: + default: + pullPolicy: IfNotPresent + registry: docker.io + repository: grafana/loki + tag: 2.9.3 + properties: + pullPolicy: + default: IfNotPresent + enum: + - Always + - Never + - IfNotPresent + type: string + registry: + default: docker.io + type: string + repository: + default: grafana/loki + type: string + tag: + default: 2.9.3 + type: string + type: object + type: object +dependencies: [] +providers: + kubernetes: true + authentik: null + kubectl: true + postgresql: null + mysql: null + restapi: null + http: null + gitea: null +tfaddtype: null diff --git a/monitor/loki/monitoring.coreos.com_v1_PrometheusRule_loki-loki-alerts.yaml b/monitor/loki/monitoring.coreos.com_v1_PrometheusRule_loki-loki-alerts.yaml new file mode 100644 index 0000000..16b78ef --- /dev/null +++ b/monitor/loki/monitoring.coreos.com_v1_PrometheusRule_loki-loki-alerts.yaml @@ -0,0 +1,65 @@ +# Source: loki/templates/monitoring/loki-alerts.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + labels: + helm.sh/chart: loki-5.42.0 + app.kubernetes.io/name: loki + app.kubernetes.io/instance: loki + app.kubernetes.io/version: "2.9.3" + app.kubernetes.io/managed-by: Helm + name: loki-loki-alerts + namespace: vynil-monitor +spec: + groups: + - name: loki_alerts + rules: + - alert: LokiRequestErrors + annotations: + message: | + {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf "%.2f" $value }}% errors. + expr: | + 100 * sum(rate(loki_request_duration_seconds_count{status_code=~"5.."}[2m])) by (namespace, job, route) + / + sum(rate(loki_request_duration_seconds_count[2m])) by (namespace, job, route) + > 10 + for: 15m + labels: + severity: critical + - alert: LokiRequestPanics + annotations: + message: | + {{ $labels.job }} is experiencing {{ printf "%.2f" $value }}% increase of panics. + expr: | + sum(increase(loki_panic_total[10m])) by (namespace, job) > 0 + labels: + severity: critical + - alert: LokiRequestLatency + annotations: + message: | + {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf "%.2f" $value }}s 99th percentile latency. + expr: | + namespace_job_route:loki_request_duration_seconds:99quantile{route!~"(?i).*tail.*"} > 1 + for: 15m + labels: + severity: critical + - alert: LokiTooManyCompactorsRunning + annotations: + message: | + {{ $labels.cluster }} {{ $labels.namespace }} has had {{ printf "%.0f" $value }} compactors running for more than 5m. Only one compactor should run at a time. + expr: | + sum(loki_boltdb_shipper_compactor_running) by (namespace, cluster) > 1 + for: 5m + labels: + severity: warning + - name: loki_canaries_alerts + rules: + - alert: LokiCanaryLatency + annotations: + message: | + {{ $labels.job }} is experiencing {{ printf "%.2f" $value }}s 99th percentile latency. + expr: | + histogram_quantile(0.99, sum(rate(loki_canary_response_latency_seconds_bucket[5m])) by (le, namespace, job)) > 5 + for: 15m + labels: + severity: warning \ No newline at end of file diff --git a/monitor/loki/monitoring.coreos.com_v1_PrometheusRule_loki-loki-rules.yaml b/monitor/loki/monitoring.coreos.com_v1_PrometheusRule_loki-loki-rules.yaml new file mode 100644 index 0000000..2a5fd30 --- /dev/null +++ b/monitor/loki/monitoring.coreos.com_v1_PrometheusRule_loki-loki-rules.yaml @@ -0,0 +1,98 @@ +# Source: loki/templates/monitoring/loki-rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + labels: + helm.sh/chart: loki-5.42.0 + app.kubernetes.io/name: loki + app.kubernetes.io/instance: loki + app.kubernetes.io/version: "2.9.3" + app.kubernetes.io/managed-by: Helm + name: loki-loki-rules + namespace: vynil-monitor +spec: + groups: + - name: loki_rules + rules: + - expr: histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m])) + by (le, job)) + labels: + cluster: loki + record: job:loki_request_duration_seconds:99quantile + - expr: histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m])) + by (le, job)) + labels: + cluster: loki + record: job:loki_request_duration_seconds:50quantile + - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (job) / sum(rate(loki_request_duration_seconds_count[1m])) + by (job) + labels: + cluster: loki + record: job:loki_request_duration_seconds:avg + - expr: sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job) + labels: + cluster: loki + record: job:loki_request_duration_seconds_bucket:sum_rate + - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (job) + labels: + cluster: loki + record: job:loki_request_duration_seconds_sum:sum_rate + - expr: sum(rate(loki_request_duration_seconds_count[1m])) by (job) + labels: + cluster: loki + record: job:loki_request_duration_seconds_count:sum_rate + - expr: histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m])) + by (le, job, route)) + labels: + cluster: loki + record: job_route:loki_request_duration_seconds:99quantile + - expr: histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m])) + by (le, job, route)) + labels: + cluster: loki + record: job_route:loki_request_duration_seconds:50quantile + - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (job, route) / sum(rate(loki_request_duration_seconds_count[1m])) + by (job, route) + labels: + cluster: loki + record: job_route:loki_request_duration_seconds:avg + - expr: sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job, route) + labels: + cluster: loki + record: job_route:loki_request_duration_seconds_bucket:sum_rate + - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (job, route) + labels: + cluster: loki + record: job_route:loki_request_duration_seconds_sum:sum_rate + - expr: sum(rate(loki_request_duration_seconds_count[1m])) by (job, route) + labels: + cluster: loki + record: job_route:loki_request_duration_seconds_count:sum_rate + - expr: histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m])) + by (le, namespace, job, route)) + labels: + cluster: loki + record: namespace_job_route:loki_request_duration_seconds:99quantile + - expr: histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m])) + by (le, namespace, job, route)) + labels: + cluster: loki + record: namespace_job_route:loki_request_duration_seconds:50quantile + - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (namespace, job, route) + / sum(rate(loki_request_duration_seconds_count[1m])) by (namespace, job, route) + labels: + cluster: loki + record: namespace_job_route:loki_request_duration_seconds:avg + - expr: sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, namespace, job, + route) + labels: + cluster: loki + record: namespace_job_route:loki_request_duration_seconds_bucket:sum_rate + - expr: sum(rate(loki_request_duration_seconds_sum[1m])) by (namespace, job, route) + labels: + cluster: loki + record: namespace_job_route:loki_request_duration_seconds_sum:sum_rate + - expr: sum(rate(loki_request_duration_seconds_count[1m])) by (namespace, job, route) + labels: + cluster: loki + record: namespace_job_route:loki_request_duration_seconds_count:sum_rate \ No newline at end of file diff --git a/monitor/loki/monitoring.coreos.com_v1_ServiceMonitor_loki.yaml b/monitor/loki/monitoring.coreos.com_v1_ServiceMonitor_loki.yaml new file mode 100644 index 0000000..9d2ac58 --- /dev/null +++ b/monitor/loki/monitoring.coreos.com_v1_ServiceMonitor_loki.yaml @@ -0,0 +1,35 @@ +# Source: loki/templates/monitoring/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: loki + namespace: vynil-monitor + labels: + helm.sh/chart: loki-5.42.0 + app.kubernetes.io/name: loki + app.kubernetes.io/instance: loki + app.kubernetes.io/version: "2.9.3" + app.kubernetes.io/managed-by: Helm +spec: + selector: + matchLabels: + app.kubernetes.io/name: loki + app.kubernetes.io/instance: loki + matchExpressions: + - key: prometheus.io/service-monitor + operator: NotIn + values: + - "false" + endpoints: + - port: http-metrics + path: /metrics + interval: 15s + relabelings: + - sourceLabels: [job] + action: replace + replacement: "vynil-monitor/$1" + targetLabel: job + - action: replace + replacement: "loki" + targetLabel: cluster + scheme: http \ No newline at end of file diff --git a/monitor/loki/v1_ConfigMap_loki-runtime.yaml b/monitor/loki/v1_ConfigMap_loki-runtime.yaml new file mode 100644 index 0000000..eeffe70 --- /dev/null +++ b/monitor/loki/v1_ConfigMap_loki-runtime.yaml @@ -0,0 +1,15 @@ +# Source: loki/templates/runtime-configmap.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + name: loki-runtime + namespace: vynil-monitor + labels: + helm.sh/chart: loki-5.42.0 + app.kubernetes.io/name: loki + app.kubernetes.io/instance: loki + app.kubernetes.io/version: "2.9.3" + app.kubernetes.io/managed-by: Helm +data: + runtime-config.yaml: | + {} \ No newline at end of file diff --git a/monitor/loki/v1_ServiceAccount_loki.yaml b/monitor/loki/v1_ServiceAccount_loki.yaml new file mode 100644 index 0000000..2ca964e --- /dev/null +++ b/monitor/loki/v1_ServiceAccount_loki.yaml @@ -0,0 +1,14 @@ +--- +# Source: loki/templates/serviceaccount.yaml +apiVersion: v1 +kind: ServiceAccount +metadata: + name: loki + namespace: vynil-monitor + labels: + helm.sh/chart: loki-5.42.0 + app.kubernetes.io/name: loki + app.kubernetes.io/instance: loki + app.kubernetes.io/version: "2.9.3" + app.kubernetes.io/managed-by: Helm +automountServiceAccountToken: true \ No newline at end of file diff --git a/monitor/loki/v1_Service_loki-headless.yaml b/monitor/loki/v1_Service_loki-headless.yaml new file mode 100644 index 0000000..26d6d46 --- /dev/null +++ b/monitor/loki/v1_Service_loki-headless.yaml @@ -0,0 +1,25 @@ +# Source: loki/templates/single-binary/service-headless.yaml +apiVersion: v1 +kind: Service +metadata: + name: loki-headless + namespace: vynil-monitor + labels: + helm.sh/chart: loki-5.42.0 + app.kubernetes.io/name: loki + app.kubernetes.io/instance: loki + app.kubernetes.io/version: "2.9.3" + app.kubernetes.io/managed-by: Helm + variant: headless + prometheus.io/service-monitor: "false" + annotations: +spec: + clusterIP: None + ports: + - name: http-metrics + port: 3100 + targetPort: http-metrics + protocol: TCP + selector: + app.kubernetes.io/name: loki + app.kubernetes.io/instance: loki \ No newline at end of file diff --git a/monitor/loki/v1_Service_loki-memberlist.yaml b/monitor/loki/v1_Service_loki-memberlist.yaml new file mode 100644 index 0000000..3278c78 --- /dev/null +++ b/monitor/loki/v1_Service_loki-memberlist.yaml @@ -0,0 +1,24 @@ +# Source: loki/templates/service-memberlist.yaml +apiVersion: v1 +kind: Service +metadata: + name: loki-memberlist + namespace: vynil-monitor + labels: + helm.sh/chart: loki-5.42.0 + app.kubernetes.io/name: loki + app.kubernetes.io/instance: loki + app.kubernetes.io/version: "2.9.3" + app.kubernetes.io/managed-by: Helm +spec: + type: ClusterIP + clusterIP: None + ports: + - name: tcp + port: 7946 + targetPort: http-memberlist + protocol: TCP + selector: + app.kubernetes.io/name: loki + app.kubernetes.io/instance: loki + app.kubernetes.io/part-of: memberlist \ No newline at end of file diff --git a/monitor/loki/v1_Service_loki.yaml b/monitor/loki/v1_Service_loki.yaml new file mode 100644 index 0000000..71ac2b9 --- /dev/null +++ b/monitor/loki/v1_Service_loki.yaml @@ -0,0 +1,28 @@ +# Source: loki/templates/single-binary/service.yaml +apiVersion: v1 +kind: Service +metadata: + name: loki + namespace: vynil-monitor + labels: + helm.sh/chart: loki-5.42.0 + app.kubernetes.io/name: loki + app.kubernetes.io/instance: loki + app.kubernetes.io/version: "2.9.3" + app.kubernetes.io/managed-by: Helm + annotations: +spec: + type: ClusterIP + ports: + - name: http-metrics + port: 3100 + targetPort: http-metrics + protocol: TCP + - name: grpc + port: 9095 + targetPort: grpc + protocol: TCP + selector: + app.kubernetes.io/name: loki + app.kubernetes.io/instance: loki + app.kubernetes.io/component: single-binary \ No newline at end of file diff --git a/monitor/monitor-control-plan/datas.tf b/monitor/monitor-control-plan/datas.tf new file mode 100644 index 0000000..d850fcd --- /dev/null +++ b/monitor/monitor-control-plan/datas.tf @@ -0,0 +1,20 @@ +locals { + common-labels = { + "vynil.solidite.fr/owner-name" = var.instance + "vynil.solidite.fr/owner-namespace" = var.namespace + "vynil.solidite.fr/owner-category" = var.category + "vynil.solidite.fr/owner-component" = var.component + "app.kubernetes.io/managed-by" = "vynil" + "app.kubernetes.io/instance" = var.instance + } +} + +data "kustomization_overlay" "data" { + common_labels = local.common-labels + namespace = var.namespace + resources = [for file in fileset(path.module, "*.yaml"): file if file != "index.yaml" && length(regexall("v1_Service_prometheus",file))<1] +} + +data "kustomization_overlay" "data_no_ns" { + resources = [for file in fileset(path.module, "*.yaml"): file if length(regexall("v1_Service_prometheus",file))>0] +} diff --git a/monitor/monitor-control-plan/index.yaml b/monitor/monitor-control-plan/index.yaml new file mode 100644 index 0000000..ce4f6e4 --- /dev/null +++ b/monitor/monitor-control-plan/index.yaml @@ -0,0 +1,24 @@ +--- +apiVersion: vinyl.solidite.fr/v1beta1 +kind: Component +category: monitor +metadata: + name: monitor-control-plan + description: null +options: + useless: + default: true + examples: + - true + type: boolean +dependencies: [] +providers: + kubernetes: true + authentik: null + kubectl: true + postgresql: null + mysql: null + restapi: null + http: null + gitea: null +tfaddtype: null diff --git a/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-etcd.yaml b/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-etcd.yaml new file mode 100644 index 0000000..8a109a9 --- /dev/null +++ b/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-etcd.yaml @@ -0,0 +1,167 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/etcd.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-etcd + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: etcd + rules: + - alert: etcdMembersDown + annotations: + description: 'etcd cluster "{{ $labels.job }}": members are down ({{ $value }}).' + summary: etcd cluster members are down. + expr: |- + max without (endpoint) ( + sum without (instance) (up{job=~".*etcd.*"} == bool 0) + or + count without (To) ( + sum without (instance) (rate(etcd_network_peer_sent_failures_total{job=~".*etcd.*"}[120s])) > 0.01 + ) + ) + > 0 + for: 10m + labels: + severity: critical + - alert: etcdInsufficientMembers + annotations: + description: 'etcd cluster "{{ $labels.job }}": insufficient members ({{ $value }}).' + summary: etcd cluster has insufficient number of members. + expr: sum(up{job=~".*etcd.*"} == bool 1) without (instance) < ((count(up{job=~".*etcd.*"}) without (instance) + 1) / 2) + for: 3m + labels: + severity: critical + - alert: etcdNoLeader + annotations: + description: 'etcd cluster "{{ $labels.job }}": member {{ $labels.instance }} has no leader.' + summary: etcd cluster has no leader. + expr: etcd_server_has_leader{job=~".*etcd.*"} == 0 + for: 1m + labels: + severity: critical + - alert: etcdHighNumberOfLeaderChanges + annotations: + description: 'etcd cluster "{{ $labels.job }}": {{ $value }} leader changes within the last 15 minutes. Frequent elections may be a sign of insufficient resources, high network latency, or disruptions by other components and should be investigated.' + summary: etcd cluster has high number of leader changes. + expr: increase((max without (instance) (etcd_server_leader_changes_seen_total{job=~".*etcd.*"}) or 0*absent(etcd_server_leader_changes_seen_total{job=~".*etcd.*"}))[15m:1m]) >= 4 + for: 5m + labels: + severity: warning + - alert: etcdHighNumberOfFailedGRPCRequests + annotations: + description: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.' + summary: etcd cluster has high number of failed grpc requests. + expr: |- + 100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code=~"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded"}[5m])) without (grpc_type, grpc_code) + / + sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) without (grpc_type, grpc_code) + > 1 + for: 10m + labels: + severity: warning + - alert: etcdHighNumberOfFailedGRPCRequests + annotations: + description: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.' + summary: etcd cluster has high number of failed grpc requests. + expr: |- + 100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code=~"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded"}[5m])) without (grpc_type, grpc_code) + / + sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) without (grpc_type, grpc_code) + > 5 + for: 5m + labels: + severity: critical + - alert: etcdGRPCRequestsSlow + annotations: + description: 'etcd cluster "{{ $labels.job }}": 99th percentile of gRPC requests is {{ $value }}s on etcd instance {{ $labels.instance }} for {{ $labels.grpc_method }} method.' + summary: etcd grpc requests are slow + expr: |- + histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~".*etcd.*", grpc_method!="Defragment", grpc_type="unary"}[5m])) without(grpc_type)) + > 0.15 + for: 10m + labels: + severity: critical + - alert: etcdMemberCommunicationSlow + annotations: + description: 'etcd cluster "{{ $labels.job }}": member communication with {{ $labels.To }} is taking {{ $value }}s on etcd instance {{ $labels.instance }}.' + summary: etcd cluster member communication is slow. + expr: |- + histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket{job=~".*etcd.*"}[5m])) + > 0.15 + for: 10m + labels: + severity: warning + - alert: etcdHighNumberOfFailedProposals + annotations: + description: 'etcd cluster "{{ $labels.job }}": {{ $value }} proposal failures within the last 30 minutes on etcd instance {{ $labels.instance }}.' + summary: etcd cluster has high number of proposal failures. + expr: rate(etcd_server_proposals_failed_total{job=~".*etcd.*"}[15m]) > 5 + for: 15m + labels: + severity: warning + - alert: etcdHighFsyncDurations + annotations: + description: 'etcd cluster "{{ $labels.job }}": 99th percentile fsync durations are {{ $value }}s on etcd instance {{ $labels.instance }}.' + summary: etcd cluster 99th percentile fsync durations are too high. + expr: |- + histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~".*etcd.*"}[5m])) + > 0.5 + for: 10m + labels: + severity: warning + - alert: etcdHighFsyncDurations + annotations: + description: 'etcd cluster "{{ $labels.job }}": 99th percentile fsync durations are {{ $value }}s on etcd instance {{ $labels.instance }}.' + summary: etcd cluster 99th percentile fsync durations are too high. + expr: |- + histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~".*etcd.*"}[5m])) + > 1 + for: 10m + labels: + severity: critical + - alert: etcdHighCommitDurations + annotations: + description: 'etcd cluster "{{ $labels.job }}": 99th percentile commit durations {{ $value }}s on etcd instance {{ $labels.instance }}.' + summary: etcd cluster 99th percentile commit durations are too high. + expr: |- + histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket{job=~".*etcd.*"}[5m])) + > 0.25 + for: 10m + labels: + severity: warning + - alert: etcdDatabaseQuotaLowSpace + annotations: + description: 'etcd cluster "{{ $labels.job }}": database size exceeds the defined quota on etcd instance {{ $labels.instance }}, please defrag or increase the quota as the writes to etcd will be disabled when it is full.' + summary: etcd cluster database is running full. + expr: (last_over_time(etcd_mvcc_db_total_size_in_bytes{job=~".*etcd.*"}[5m]) / last_over_time(etcd_server_quota_backend_bytes{job=~".*etcd.*"}[5m]))*100 > 95 + for: 10m + labels: + severity: critical + - alert: etcdExcessiveDatabaseGrowth + annotations: + description: 'etcd cluster "{{ $labels.job }}": Predicting running out of disk space in the next four hours, based on write observations within the past four hours on etcd instance {{ $labels.instance }}, please check as it might be disruptive.' + summary: etcd cluster database growing very fast. + expr: predict_linear(etcd_mvcc_db_total_size_in_bytes{job=~".*etcd.*"}[4h], 4*60*60) > etcd_server_quota_backend_bytes{job=~".*etcd.*"} + for: 10m + labels: + severity: warning + - alert: etcdDatabaseHighFragmentationRatio + annotations: + description: 'etcd cluster "{{ $labels.job }}": database size in use on instance {{ $labels.instance }} is {{ $value | humanizePercentage }} of the actual allocated disk space, please run defragmentation (e.g. etcdctl defrag) to retrieve the unused fragmented disk space.' + runbook_url: https://etcd.io/docs/v3.5/op-guide/maintenance/#defragmentation + summary: etcd database size in use is less than 50% of the actual allocated storage. + expr: (last_over_time(etcd_mvcc_db_total_size_in_use_in_bytes{job=~".*etcd.*"}[5m]) / last_over_time(etcd_mvcc_db_total_size_in_bytes{job=~".*etcd.*"}[5m])) < 0.5 and etcd_mvcc_db_total_size_in_use_in_bytes{job=~".*etcd.*"} > 104857600 + for: 10m + labels: + severity: warning \ No newline at end of file diff --git a/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-apiserver-availability.rules.yaml b/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-apiserver-availability.rules.yaml new file mode 100644 index 0000000..dbf7787 --- /dev/null +++ b/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-apiserver-availability.rules.yaml @@ -0,0 +1,129 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-availability.rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-kube-apiserver-availability.rules + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - interval: 3m + name: kube-apiserver-availability.rules + rules: + - expr: avg_over_time(code_verb:apiserver_request_total:increase1h[30d]) * 24 * 30 + record: code_verb:apiserver_request_total:increase30d + - expr: sum by (cluster, code) (code_verb:apiserver_request_total:increase30d{verb=~"LIST|GET"}) + labels: + verb: read + record: code:apiserver_request_total:increase30d + - expr: sum by (cluster, code) (code_verb:apiserver_request_total:increase30d{verb=~"POST|PUT|PATCH|DELETE"}) + labels: + verb: write + record: code:apiserver_request_total:increase30d + - expr: sum by (cluster, verb, scope) (increase(apiserver_request_sli_duration_seconds_count{job="apiserver"}[1h])) + record: cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase1h + - expr: sum by (cluster, verb, scope) (avg_over_time(cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase1h[30d]) * 24 * 30) + record: cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d + - expr: sum by (cluster, verb, scope, le) (increase(apiserver_request_sli_duration_seconds_bucket[1h])) + record: cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase1h + - expr: sum by (cluster, verb, scope, le) (avg_over_time(cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase1h[30d]) * 24 * 30) + record: cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d + - expr: |- + 1 - ( + ( + # write too slow + sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~"POST|PUT|PATCH|DELETE"}) + - + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"POST|PUT|PATCH|DELETE",le="1"}) + ) + + ( + # read too slow + sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~"LIST|GET"}) + - + ( + ( + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope=~"resource|",le="1"}) + or + vector(0) + ) + + + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="namespace",le="5"}) + + + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="cluster",le="30"}) + ) + ) + + # errors + sum by (cluster) (code:apiserver_request_total:increase30d{code=~"5.."} or vector(0)) + ) + / + sum by (cluster) (code:apiserver_request_total:increase30d) + labels: + verb: all + record: apiserver_request:availability30d + - expr: |- + 1 - ( + sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~"LIST|GET"}) + - + ( + # too slow + ( + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope=~"resource|",le="1"}) + or + vector(0) + ) + + + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="namespace",le="5"}) + + + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="cluster",le="30"}) + ) + + + # errors + sum by (cluster) (code:apiserver_request_total:increase30d{verb="read",code=~"5.."} or vector(0)) + ) + / + sum by (cluster) (code:apiserver_request_total:increase30d{verb="read"}) + labels: + verb: read + record: apiserver_request:availability30d + - expr: |- + 1 - ( + ( + # too slow + sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~"POST|PUT|PATCH|DELETE"}) + - + sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~"POST|PUT|PATCH|DELETE",le="1"}) + ) + + + # errors + sum by (cluster) (code:apiserver_request_total:increase30d{verb="write",code=~"5.."} or vector(0)) + ) + / + sum by (cluster) (code:apiserver_request_total:increase30d{verb="write"}) + labels: + verb: write + record: apiserver_request:availability30d + - expr: sum by (cluster,code,resource) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m])) + labels: + verb: read + record: code_resource:apiserver_request_total:rate5m + - expr: sum by (cluster,code,resource) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m])) + labels: + verb: write + record: code_resource:apiserver_request_total:rate5m + - expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"2.."}[1h])) + record: code_verb:apiserver_request_total:increase1h + - expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"3.."}[1h])) + record: code_verb:apiserver_request_total:increase1h + - expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"4.."}[1h])) + record: code_verb:apiserver_request_total:increase1h + - expr: sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"5.."}[1h])) + record: code_verb:apiserver_request_total:increase1h \ No newline at end of file diff --git a/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-apiserver-burnrate.rules.yaml b/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-apiserver-burnrate.rules.yaml new file mode 100644 index 0000000..30df7c0 --- /dev/null +++ b/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-apiserver-burnrate.rules.yaml @@ -0,0 +1,321 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-burnrate.rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-kube-apiserver-burnrate.rules + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: kube-apiserver-burnrate.rules + rules: + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[1d])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[1d])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[1d])) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[1d])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[1d])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1d])) + labels: + verb: read + record: apiserver_request:burnrate1d + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[1h])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[1h])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[1h])) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[1h])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[1h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1h])) + labels: + verb: read + record: apiserver_request:burnrate1h + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[2h])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[2h])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[2h])) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[2h])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[2h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[2h])) + labels: + verb: read + record: apiserver_request:burnrate2h + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[30m])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[30m])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[30m])) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[30m])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[30m])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[30m])) + labels: + verb: read + record: apiserver_request:burnrate30m + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[3d])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[3d])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[3d])) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[3d])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[3d])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[3d])) + labels: + verb: read + record: apiserver_request:burnrate3d + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[5m])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[5m])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[5m])) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[5m])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[5m])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m])) + labels: + verb: read + record: apiserver_request:burnrate5m + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[6h])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[6h])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[6h])) + + + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[6h])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[6h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[6h])) + labels: + verb: read + record: apiserver_request:burnrate6h + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[1d])) + - + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[1d])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1d])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1d])) + labels: + verb: write + record: apiserver_request:burnrate1d + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[1h])) + - + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[1h])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1h])) + labels: + verb: write + record: apiserver_request:burnrate1h + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[2h])) + - + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[2h])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[2h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[2h])) + labels: + verb: write + record: apiserver_request:burnrate2h + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[30m])) + - + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[30m])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[30m])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30m])) + labels: + verb: write + record: apiserver_request:burnrate30m + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[3d])) + - + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[3d])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[3d])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[3d])) + labels: + verb: write + record: apiserver_request:burnrate3d + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[5m])) + - + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[5m])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[5m])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m])) + labels: + verb: write + record: apiserver_request:burnrate5m + - expr: |- + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[6h])) + - + sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[6h])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[6h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[6h])) + labels: + verb: write + record: apiserver_request:burnrate6h \ No newline at end of file diff --git a/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-apiserver-histogram.rules.yaml b/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-apiserver-histogram.rules.yaml new file mode 100644 index 0000000..7f9aaa9 --- /dev/null +++ b/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-apiserver-histogram.rules.yaml @@ -0,0 +1,30 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-histogram.rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-kube-apiserver-histogram.rules + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: kube-apiserver-histogram.rules + rules: + - expr: histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[5m]))) > 0 + labels: + quantile: '0.99' + verb: read + record: cluster_quantile:apiserver_request_sli_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[5m]))) > 0 + labels: + quantile: '0.99' + verb: write + record: cluster_quantile:apiserver_request_sli_duration_seconds:histogram_quantile \ No newline at end of file diff --git a/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-apiserver-slos.yaml b/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-apiserver-slos.yaml new file mode 100644 index 0000000..75e977c --- /dev/null +++ b/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-apiserver-slos.yaml @@ -0,0 +1,76 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-slos.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-kube-apiserver-slos + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: kube-apiserver-slos + rules: + - alert: KubeAPIErrorBudgetBurn + annotations: + description: The API server is burning too much error budget. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn + summary: The API server is burning too much error budget. + expr: |- + sum(apiserver_request:burnrate1h) > (14.40 * 0.01000) + and + sum(apiserver_request:burnrate5m) > (14.40 * 0.01000) + for: 2m + labels: + long: 1h + severity: critical + short: 5m + - alert: KubeAPIErrorBudgetBurn + annotations: + description: The API server is burning too much error budget. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn + summary: The API server is burning too much error budget. + expr: |- + sum(apiserver_request:burnrate6h) > (6.00 * 0.01000) + and + sum(apiserver_request:burnrate30m) > (6.00 * 0.01000) + for: 15m + labels: + long: 6h + severity: critical + short: 30m + - alert: KubeAPIErrorBudgetBurn + annotations: + description: The API server is burning too much error budget. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn + summary: The API server is burning too much error budget. + expr: |- + sum(apiserver_request:burnrate1d) > (3.00 * 0.01000) + and + sum(apiserver_request:burnrate2h) > (3.00 * 0.01000) + for: 1h + labels: + long: 1d + severity: warning + short: 2h + - alert: KubeAPIErrorBudgetBurn + annotations: + description: The API server is burning too much error budget. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn + summary: The API server is burning too much error budget. + expr: |- + sum(apiserver_request:burnrate3d) > (1.00 * 0.01000) + and + sum(apiserver_request:burnrate6h) > (1.00 * 0.01000) + for: 3h + labels: + long: 3d + severity: warning + short: 6h \ No newline at end of file diff --git a/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-scheduler.rules.yaml b/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-scheduler.rules.yaml new file mode 100644 index 0000000..39187da --- /dev/null +++ b/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kube-scheduler.rules.yaml @@ -0,0 +1,56 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kube-scheduler.rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-kube-scheduler.rules + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: kube-scheduler.rules + rules: + - expr: histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.99' + record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.99' + record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.99' + record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.9, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.9' + record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.9, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.9' + record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.9, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.9' + record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.5, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.5' + record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.5, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.5' + record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.5, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: '0.5' + record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile \ No newline at end of file diff --git a/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-system-controller-manager.yaml b/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-system-controller-manager.yaml new file mode 100644 index 0000000..2743844 --- /dev/null +++ b/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-system-controller-manager.yaml @@ -0,0 +1,29 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-controller-manager.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-kubernetes-system-controller-manager + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: kubernetes-system-controller-manager + rules: + - alert: KubeControllerManagerDown + annotations: + description: KubeControllerManager has disappeared from Prometheus target discovery. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecontrollermanagerdown + summary: Target disappeared from Prometheus target discovery. + expr: absent(up{job="kube-controller-manager"} == 1) + for: 15m + labels: + severity: critical \ No newline at end of file diff --git a/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-system-scheduler.yaml b/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-system-scheduler.yaml new file mode 100644 index 0000000..96c513b --- /dev/null +++ b/monitor/monitor-control-plan/monitoring.coreos.com_v1_PrometheusRule_prometheus-community-kube-kubernetes-system-scheduler.yaml @@ -0,0 +1,29 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-scheduler.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-community-kube-kubernetes-system-scheduler + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + groups: + - name: kubernetes-system-scheduler + rules: + - alert: KubeSchedulerDown + annotations: + description: KubeScheduler has disappeared from Prometheus target discovery. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeschedulerdown + summary: Target disappeared from Prometheus target discovery. + expr: absent(up{job="kube-scheduler"} == 1) + for: 15m + labels: + severity: critical \ No newline at end of file diff --git a/monitor/monitor-control-plan/monitoring.coreos.com_v1_ServiceMonitor_prometheus-community-kube-apiserver.yaml b/monitor/monitor-control-plan/monitoring.coreos.com_v1_ServiceMonitor_prometheus-community-kube-apiserver.yaml new file mode 100644 index 0000000..de6f764 --- /dev/null +++ b/monitor/monitor-control-plan/monitoring.coreos.com_v1_ServiceMonitor_prometheus-community-kube-apiserver.yaml @@ -0,0 +1,40 @@ +# Source: kube-prometheus-stack/templates/exporters/kube-api-server/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: prometheus-community-kube-apiserver + namespace: vynil-monitor + labels: + app: kube-prometheus-stack-apiserver + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + + endpoints: + - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + port: https + scheme: https + metricRelabelings: + - action: drop + regex: apiserver_request_duration_seconds_bucket;(0.15|0.2|0.3|0.35|0.4|0.45|0.6|0.7|0.8|0.9|1.25|1.5|1.75|2|3|3.5|4|4.5|6|7|8|9|15|25|40|50) + sourceLabels: + - __name__ + - le + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + serverName: kubernetes + insecureSkipVerify: false + jobLabel: component + namespaceSelector: + matchNames: + - default + selector: + matchLabels: + component: apiserver + provider: kubernetes \ No newline at end of file diff --git a/monitor/monitor-control-plan/monitoring.coreos.com_v1_ServiceMonitor_prometheus-community-kube-kube-controller-manager.yaml b/monitor/monitor-control-plan/monitoring.coreos.com_v1_ServiceMonitor_prometheus-community-kube-kube-controller-manager.yaml new file mode 100644 index 0000000..43630e8 --- /dev/null +++ b/monitor/monitor-control-plan/monitoring.coreos.com_v1_ServiceMonitor_prometheus-community-kube-kube-controller-manager.yaml @@ -0,0 +1,33 @@ +# Source: kube-prometheus-stack/templates/exporters/kube-controller-manager/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: prometheus-community-kube-kube-controller-manager + namespace: vynil-monitor + labels: + app: kube-prometheus-stack-kube-controller-manager + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + jobLabel: jobLabel + + selector: + matchLabels: + app: kube-prometheus-stack-kube-controller-manager + release: "prometheus-community" + namespaceSelector: + matchNames: + - "kube-system" + endpoints: + - port: http-metrics + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + scheme: https + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + insecureSkipVerify: true \ No newline at end of file diff --git a/monitor/monitor-control-plan/monitoring.coreos.com_v1_ServiceMonitor_prometheus-community-kube-kube-etcd.yaml b/monitor/monitor-control-plan/monitoring.coreos.com_v1_ServiceMonitor_prometheus-community-kube-kube-etcd.yaml new file mode 100644 index 0000000..989dcef --- /dev/null +++ b/monitor/monitor-control-plan/monitoring.coreos.com_v1_ServiceMonitor_prometheus-community-kube-kube-etcd.yaml @@ -0,0 +1,29 @@ +# Source: kube-prometheus-stack/templates/exporters/kube-etcd/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: prometheus-community-kube-kube-etcd + namespace: vynil-monitor + labels: + app: kube-prometheus-stack-kube-etcd + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + jobLabel: jobLabel + + selector: + matchLabels: + app: kube-prometheus-stack-kube-etcd + release: "prometheus-community" + namespaceSelector: + matchNames: + - "kube-system" + endpoints: + - port: http-metrics + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token \ No newline at end of file diff --git a/monitor/monitor-control-plan/monitoring.coreos.com_v1_ServiceMonitor_prometheus-community-kube-kube-scheduler.yaml b/monitor/monitor-control-plan/monitoring.coreos.com_v1_ServiceMonitor_prometheus-community-kube-kube-scheduler.yaml new file mode 100644 index 0000000..d882d09 --- /dev/null +++ b/monitor/monitor-control-plan/monitoring.coreos.com_v1_ServiceMonitor_prometheus-community-kube-kube-scheduler.yaml @@ -0,0 +1,33 @@ +# Source: kube-prometheus-stack/templates/exporters/kube-scheduler/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: prometheus-community-kube-kube-scheduler + namespace: vynil-monitor + labels: + app: kube-prometheus-stack-kube-scheduler + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +spec: + jobLabel: jobLabel + + selector: + matchLabels: + app: kube-prometheus-stack-kube-scheduler + release: "prometheus-community" + namespaceSelector: + matchNames: + - "kube-system" + endpoints: + - port: http-metrics + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + scheme: https + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + insecureSkipVerify: true \ No newline at end of file diff --git a/monitor/monitor-control-plan/ressources_no_ns.tf b/monitor/monitor-control-plan/ressources_no_ns.tf new file mode 100644 index 0000000..9fa58b7 --- /dev/null +++ b/monitor/monitor-control-plan/ressources_no_ns.tf @@ -0,0 +1,45 @@ + +# first loop through resources in ids_prio[0] +resource "kustomization_resource" "pre_no_ns" { + for_each = data.kustomization_overlay.data_no_ns.ids_prio[0] + + manifest = ( + contains(["_/Secret"], regex("(?P.*/.*)/.*/.*", each.value)["group_kind"]) + ? sensitive(data.kustomization_overlay.data_no_ns.manifests[each.value]) + : data.kustomization_overlay.data_no_ns.manifests[each.value] + ) +} + +# then loop through resources in ids_prio[1] +# and set an explicit depends_on on kustomization_resource.pre +# wait 2 minutes for any deployment or daemonset to become ready +resource "kustomization_resource" "main_no_ns" { + for_each = data.kustomization_overlay.data_no_ns.ids_prio[1] + + manifest = ( + contains(["_/Secret"], regex("(?P.*/.*)/.*/.*", each.value)["group_kind"]) + ? sensitive(data.kustomization_overlay.data_no_ns.manifests[each.value]) + : data.kustomization_overlay.data_no_ns.manifests[each.value] + ) + wait = true + timeouts { + create = "5m" + update = "5m" + } + + depends_on = [kustomization_resource.pre_no_ns] +} + +# finally, loop through resources in ids_prio[2] +# and set an explicit depends_on on kustomization_resource.main +resource "kustomization_resource" "post_no_ns" { + for_each = data.kustomization_overlay.data_no_ns.ids_prio[2] + + manifest = ( + contains(["_/Secret"], regex("(?P.*/.*)/.*/.*", each.value)["group_kind"]) + ? sensitive(data.kustomization_overlay.data_no_ns.manifests[each.value]) + : data.kustomization_overlay.data_no_ns.manifests[each.value] + ) + + depends_on = [kustomization_resource.main_no_ns] +} diff --git a/monitor/monitor-control-plan/v1_ConfigMap_prometheus-community-kube-apiserver.yaml b/monitor/monitor-control-plan/v1_ConfigMap_prometheus-community-kube-apiserver.yaml new file mode 100644 index 0000000..882d9fe --- /dev/null +++ b/monitor/monitor-control-plan/v1_ConfigMap_prometheus-community-kube-apiserver.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/apiserver.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: prometheus-community-kube-apiserver + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +data: + apiserver.json: |- + {"__inputs":[],"__requires":[],"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"id":null,"links":[],"panels":[{"content":"The SLO (service level objective) and other metrics displayed on this dashboard are for informational purposes only.","datasource":null,"description":"The SLO (service level objective) and other metrics displayed on this dashboard are for informational purposes only.","gridPos":{"h":2,"w":24,"x":0,"y":0},"id":2,"mode":"markdown","span":12,"title":"Notice","type":"text"}],"refresh":"10s","rows":[{"collapse":false,"collapsed":false,"panels":[{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"$datasource","decimals":3,"description":"How many percent of requests (both read and write) in 30 days have been answered successfully and fast enough?","format":"percentunit","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{},"id":3,"interval":"1m","legend":{"alignAsTable":true,"rightSide":true},"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"span":4,"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"apiserver_request:availability30d{verb=\"all\", cluster=\"$cluster\"}","format":"time_series","intervalFactor":2,"legendFormat":"","refId":"A"}],"thresholds":"","title":"Availability (30d) > 99.000%","tooltip":{"shared":false},"type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","decimals":3,"description":"How much error budget is left looking at our 0.990% availability guarantees?","fill":10,"fillGradient":0,"gridPos":{},"id":4,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":8,"stack":false,"steppedLine":false,"targets":[{"expr":"100 * (apiserver_request:availability30d{verb=\"all\", cluster=\"$cluster\"} - 0.990000)","format":"time_series","intervalFactor":2,"legendFormat":"errorbudget","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"ErrorBudget (30d) > 99.000%","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"decimals":3,"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true},{"decimals":3,"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Dashboard Row","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"$datasource","decimals":3,"description":"How many percent of read requests (LIST,GET) in 30 days have been answered successfully and fast enough?","format":"percentunit","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{},"id":5,"interval":"1m","legend":{"alignAsTable":true,"rightSide":true},"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"span":3,"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"apiserver_request:availability30d{verb=\"read\", cluster=\"$cluster\"}","format":"time_series","intervalFactor":2,"legendFormat":"","refId":"A"}],"thresholds":"","title":"Read Availability (30d)","tooltip":{"shared":false},"type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","description":"How many read requests (LIST,GET) per second do the apiservers get by code?","fill":10,"fillGradient":0,"gridPos":{},"id":6,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[{"alias":"/2../i","color":"#56A64B"},{"alias":"/3../i","color":"#F2CC0C"},{"alias":"/4../i","color":"#3274D9"},{"alias":"/5../i","color":"#E02F44"}],"spaceLength":10,"span":3,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by (code) (code_resource:apiserver_request_total:rate5m{verb=\"read\", cluster=\"$cluster\"})","format":"time_series","intervalFactor":2,"legendFormat":"{{ code }}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Read SLI - Requests","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"reqps","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"reqps","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","description":"How many percent of read requests (LIST,GET) per second are returned with errors (5xx)?","fill":1,"fillGradient":0,"gridPos":{},"id":7,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":3,"stack":false,"steppedLine":false,"targets":[{"expr":"sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"read\",code=~\"5..\", cluster=\"$cluster\"}) / sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"read\", cluster=\"$cluster\"})","format":"time_series","intervalFactor":2,"legendFormat":"{{ resource }}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Read SLI - Errors","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"percentunit","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","description":"How many seconds is the 99th percentile for reading (LIST|GET) a given resource?","fill":1,"fillGradient":0,"gridPos":{},"id":8,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":3,"stack":false,"steppedLine":false,"targets":[{"expr":"cluster_quantile:apiserver_request_sli_duration_seconds:histogram_quantile{verb=\"read\", cluster=\"$cluster\"}","format":"time_series","intervalFactor":2,"legendFormat":"{{ resource }}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Read SLI - Duration","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Dashboard Row","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"$datasource","decimals":3,"description":"How many percent of write requests (POST|PUT|PATCH|DELETE) in 30 days have been answered successfully and fast enough?","format":"percentunit","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{},"id":9,"interval":"1m","legend":{"alignAsTable":true,"rightSide":true},"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"span":3,"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"apiserver_request:availability30d{verb=\"write\", cluster=\"$cluster\"}","format":"time_series","intervalFactor":2,"legendFormat":"","refId":"A"}],"thresholds":"","title":"Write Availability (30d)","tooltip":{"shared":false},"type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"avg"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","description":"How many write requests (POST|PUT|PATCH|DELETE) per second do the apiservers get by code?","fill":10,"fillGradient":0,"gridPos":{},"id":10,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[{"alias":"/2../i","color":"#56A64B"},{"alias":"/3../i","color":"#F2CC0C"},{"alias":"/4../i","color":"#3274D9"},{"alias":"/5../i","color":"#E02F44"}],"spaceLength":10,"span":3,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by (code) (code_resource:apiserver_request_total:rate5m{verb=\"write\", cluster=\"$cluster\"})","format":"time_series","intervalFactor":2,"legendFormat":"{{ code }}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Write SLI - Requests","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"reqps","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"reqps","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","description":"How many percent of write requests (POST|PUT|PATCH|DELETE) per second are returned with errors (5xx)?","fill":1,"fillGradient":0,"gridPos":{},"id":11,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":3,"stack":false,"steppedLine":false,"targets":[{"expr":"sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"write\",code=~\"5..\", cluster=\"$cluster\"}) / sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"write\", cluster=\"$cluster\"})","format":"time_series","intervalFactor":2,"legendFormat":"{{ resource }}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Write SLI - Errors","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"percentunit","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","description":"How many seconds is the 99th percentile for writing (POST|PUT|PATCH|DELETE) a given resource?","fill":1,"fillGradient":0,"gridPos":{},"id":12,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":3,"stack":false,"steppedLine":false,"targets":[{"expr":"cluster_quantile:apiserver_request_sli_duration_seconds:histogram_quantile{verb=\"write\", cluster=\"$cluster\"}","format":"time_series","intervalFactor":2,"legendFormat":"{{ resource }}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Write SLI - Duration","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Dashboard Row","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":13,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(workqueue_adds_total{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])) by (instance, name)","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} {{name}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Work Queue Add Rate","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ops","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"ops","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":14,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(workqueue_depth{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])) by (instance, name)","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} {{name}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Work Queue Depth","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":15,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])) by (instance, name, le))","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} {{name}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Work Queue Latency","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Dashboard Row","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":16,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"process_resident_memory_bytes{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":17,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"rate(process_cpu_seconds_total{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU usage","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":18,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"go_goroutines{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Goroutines","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Dashboard Row","titleSize":"h6","type":"row"}],"schemaVersion":14,"style":"dark","tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{},"datasource":"$datasource","hide":2,"includeAll":false,"label":"cluster","multi":false,"name":"cluster","options":[],"query":"label_values(up{job=\"apiserver\"}, cluster)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{},"datasource":"$datasource","hide":0,"includeAll":true,"label":null,"multi":false,"name":"instance","options":[],"query":"label_values(up{job=\"apiserver\", cluster=\"$cluster\"}, instance)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Kubernetes / API server","uid":"09ec8aa1e996d6ffcd6817bbaff4db1b","version":0} \ No newline at end of file diff --git a/monitor/monitor-control-plan/v1_ConfigMap_prometheus-community-kube-controller-manager.yaml b/monitor/monitor-control-plan/v1_ConfigMap_prometheus-community-kube-controller-manager.yaml new file mode 100644 index 0000000..1ff7805 --- /dev/null +++ b/monitor/monitor-control-plan/v1_ConfigMap_prometheus-community-kube-controller-manager.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/controller-manager.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: prometheus-community-kube-controller-manager + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +data: + controller-manager.json: |- + {"__inputs":[],"__requires":[],"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"id":null,"links":[],"refresh":"10s","rows":[{"collapse":false,"collapsed":false,"panels":[{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"$datasource","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{},"id":2,"interval":"1m","legend":{"alignAsTable":true,"rightSide":true},"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"span":2,"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"sum(up{cluster=\"$cluster\", job=\"kube-controller-manager\"})","format":"time_series","intervalFactor":2,"legendFormat":"","refId":"A"}],"thresholds":"","title":"Up","tooltip":{"shared":false},"type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"min"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":3,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(workqueue_adds_total{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, name)","format":"time_series","intervalFactor":2,"legendFormat":"{{cluster}} {{instance}} {{name}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Work Queue Add Rate","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Dashboard Row","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":4,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(workqueue_depth{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, name)","format":"time_series","intervalFactor":2,"legendFormat":"{{cluster}} {{instance}} {{name}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Work Queue Depth","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Dashboard Row","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":5,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, name, le))","format":"time_series","intervalFactor":2,"legendFormat":"{{cluster}} {{instance}} {{name}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Work Queue Latency","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Dashboard Row","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":6,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"2xx","refId":"A"},{"expr":"sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"3xx","refId":"B"},{"expr":"sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"4xx","refId":"C"},{"expr":"sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"5xx","refId":"D"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Kube API Request Rate","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":7,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":8,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"POST\"}[$__rate_interval])) by (verb, url, le))","format":"time_series","intervalFactor":2,"legendFormat":"{{verb}} {{url}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Post Request Latency 99th Quantile","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"s","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Dashboard Row","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":8,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, url, le))","format":"time_series","intervalFactor":2,"legendFormat":"{{verb}} {{url}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Get Request Latency 99th Quantile","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"s","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Dashboard Row","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":9,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"process_resident_memory_bytes{cluster=\"$cluster\", job=\"kube-controller-manager\",instance=~\"$instance\"}","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":10,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-controller-manager\",instance=~\"$instance\"}[$__rate_interval])","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU usage","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":11,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"go_goroutines{cluster=\"$cluster\", job=\"kube-controller-manager\",instance=~\"$instance\"}","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Goroutines","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Dashboard Row","titleSize":"h6","type":"row"}],"schemaVersion":14,"style":"dark","tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{},"datasource":"$datasource","hide":2,"includeAll":false,"label":"cluster","multi":false,"name":"cluster","options":[],"query":"label_values(up{job=\"kube-controller-manager\"}, cluster)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{},"datasource":"$datasource","hide":0,"includeAll":true,"label":null,"multi":false,"name":"instance","options":[],"query":"label_values(up{cluster=\"$cluster\", job=\"kube-controller-manager\"}, instance)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Kubernetes / Controller Manager","uid":"72e0e05bef5099e5f049b05fdc429ed4","version":0} \ No newline at end of file diff --git a/monitor/monitor-control-plan/v1_ConfigMap_prometheus-community-kube-etcd.yaml b/monitor/monitor-control-plan/v1_ConfigMap_prometheus-community-kube-etcd.yaml new file mode 100644 index 0000000..43a6281 --- /dev/null +++ b/monitor/monitor-control-plan/v1_ConfigMap_prometheus-community-kube-etcd.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/etcd.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: prometheus-community-kube-etcd + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +data: + etcd.json: |- + {"description":"etcd sample Grafana dashboard with Prometheus","panels":[{"datasource":{"type":"datasource","uid":"-- Mixed --"},"gridPos":{"h":7,"w":6,"x":0,"y":0},"id":1,"interval":"1m","options":{"colorMode":"none","graphMode":"none","reduceOptions":{"calcs":["lastNotNull"]}},"pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(etcd_server_has_leader{job=~\".*etcd.*\", job=\"$cluster\"})","legendFormat":"{{cluster}} - {{namespace}}\n"}],"title":"Up","type":"stat"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"ops"}},"gridPos":{"h":7,"w":10,"x":6,"y":0},"id":2,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(grpc_server_started_total{job=~\".*etcd.*\", job=\"$cluster\",grpc_type=\"unary\"}[$__rate_interval]))","legendFormat":"RPC rate"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(grpc_server_handled_total{job=~\".*etcd.*\", job=\"$cluster\",grpc_type=\"unary\",grpc_code=~\"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded\"}[$__rate_interval]))","legendFormat":"RPC failed rate"}],"title":"RPC rate","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"}}},"gridPos":{"h":7,"w":8,"x":16,"y":0},"id":3,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(grpc_server_started_total{job=~\".*etcd.*\",job=\"$cluster\",grpc_service=\"etcdserverpb.Watch\",grpc_type=\"bidi_stream\"}) - sum(grpc_server_handled_total{job=\"$cluster\",grpc_service=\"etcdserverpb.Watch\",grpc_type=\"bidi_stream\"})","legendFormat":"Watch streams"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(grpc_server_started_total{job=~\".*etcd.*\",job=\"$cluster\",grpc_service=\"etcdserverpb.Lease\",grpc_type=\"bidi_stream\"}) - sum(grpc_server_handled_total{job=\"$cluster\",grpc_service=\"etcdserverpb.Lease\",grpc_type=\"bidi_stream\"})","legendFormat":"Lease streams"}],"title":"Active streams","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"bytes"}},"gridPos":{"h":7,"w":8,"x":0,"y":25},"id":4,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"etcd_mvcc_db_total_size_in_bytes{job=~\".*etcd.*\", job=\"$cluster\"}","legendFormat":"{{instance}} DB size"}],"title":"DB size","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"s"}},"gridPos":{"h":7,"w":8,"x":8,"y":25},"id":5,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"histogram_quantile(0.99, sum(rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~\".*etcd.*\", job=\"$cluster\"}[$__rate_interval])) by (instance, le))","legendFormat":"{{instance}} WAL fsync"},{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"histogram_quantile(0.99, sum(rate(etcd_disk_backend_commit_duration_seconds_bucket{job=~\".*etcd.*\", job=\"$cluster\"}[$__rate_interval])) by (instance, le))","legendFormat":"{{instance}} DB fsync"}],"title":"Disk sync duration","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"bytes"}},"gridPos":{"h":7,"w":8,"x":16,"y":25},"id":6,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"process_resident_memory_bytes{job=~\".*etcd.*\", job=\"$cluster\"}","legendFormat":"{{instance}} resident memory"}],"title":"Memory","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"Bps"}},"gridPos":{"h":7,"w":6,"x":0,"y":50},"id":7,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(etcd_network_client_grpc_received_bytes_total{job=~\".*etcd.*\", job=\"$cluster\"}[$__rate_interval])","legendFormat":"{{instance}} client traffic in"}],"title":"Client traffic in","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"Bps"}},"gridPos":{"h":7,"w":6,"x":6,"y":50},"id":8,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"rate(etcd_network_client_grpc_sent_bytes_total{job=~\".*etcd.*\", job=\"$cluster\"}[$__rate_interval])","legendFormat":"{{instance}} client traffic out"}],"title":"Client traffic out","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"Bps"}},"gridPos":{"h":7,"w":6,"x":12,"y":50},"id":9,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(etcd_network_peer_received_bytes_total{job=~\".*etcd.*\", job=\"$cluster\"}[$__rate_interval])) by (instance)","legendFormat":"{{instance}} peer traffic in"}],"title":"Peer traffic in","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"Bps"}},"gridPos":{"h":7,"w":6,"x":18,"y":50},"id":10,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"sum(rate(etcd_network_peer_sent_bytes_total{job=~\".*etcd.*\", job=\"$cluster\"}[$__rate_interval])) by (instance)","legendFormat":"{{instance}} peer traffic out"}],"title":"Peer traffic out","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"}}},"gridPos":{"h":7,"w":8,"x":0,"y":75},"id":11,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"changes(etcd_server_leader_changes_seen_total{job=~\".*etcd.*\", job=\"$cluster\"}[1d])","legendFormat":"{{instance}} total leader elections per day"}],"title":"Raft proposals","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"}}},"gridPos":{"h":7,"w":8,"x":8,"y":75},"id":12,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"changes(etcd_server_leader_changes_seen_total{job=~\".*etcd.*\", job=\"$cluster\"}[1d])","legendFormat":"{{instance}} total leader elections per day"}],"title":"Total leader elections per day","type":"timeseries"},{"datasource":{"type":"datasource","uid":"-- Mixed --"},"fieldConfig":{"defaults":{"custom":{"fillOpacity":0,"lineWidth":2,"showPoints":"never"},"unit":"s"}},"gridPos":{"h":7,"w":8,"x":16,"y":75},"id":13,"interval":"1m","pluginVersion":"v10.0.0","targets":[{"datasource":{"type":"prometheus","uid":"$datasource"},"expr":"histogram_quantile(0.99, sum by (instance, le) (rate(etcd_network_peer_round_trip_time_seconds_bucket{job=~\".*etcd.*\", job=\"$cluster\"}[$__rate_interval])))","legendFormat":"{{instance}} peer round trip time"}],"title":"Peer round trip time","type":"timeseries"}],"refresh":"10s","schemaVersion":36,"tags":["etcd-mixin"],"templating":{"list":[{"label":"Data Source","name":"datasource","query":"prometheus","type":"datasource"},{"datasource":{"type":"prometheus","uid":"${datasource}"},"label":"cluster","name":"cluster","query":"label_values(etcd_server_has_leader{job=~\".*etcd.*\"}, job)","refresh":2,"type":"query","hide":2}]},"time":{"from":"now-15m","to":"now"},"timezone": "Europe/Paris","title":"etcd","uid":"c2f4e12cdf69feb95caa41a5a1b423d9"} \ No newline at end of file diff --git a/monitor/monitor-control-plan/v1_ConfigMap_prometheus-community-kube-scheduler.yaml b/monitor/monitor-control-plan/v1_ConfigMap_prometheus-community-kube-scheduler.yaml new file mode 100644 index 0000000..ac8bd35 --- /dev/null +++ b/monitor/monitor-control-plan/v1_ConfigMap_prometheus-community-kube-scheduler.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/scheduler.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: prometheus-community-kube-scheduler + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" +data: + scheduler.json: |- + {"__inputs":[],"__requires":[],"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"id":null,"links":[],"refresh":"10s","rows":[{"collapse":false,"collapsed":false,"panels":[{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"$datasource","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{},"id":2,"interval":"1m","legend":{"alignAsTable":true,"rightSide":true},"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"span":2,"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"sum(up{cluster=\"$cluster\", job=\"kube-scheduler\"})","format":"time_series","intervalFactor":2,"legendFormat":"","refId":"A"}],"thresholds":"","title":"Up","tooltip":{"shared":false},"type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"min"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":3,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":5,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(scheduler_e2e_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)","format":"time_series","intervalFactor":2,"legendFormat":"{{cluster}} {{instance}} e2e","refId":"A"},{"expr":"sum(rate(scheduler_binding_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)","format":"time_series","intervalFactor":2,"legendFormat":"{{cluster}} {{instance}} binding","refId":"B"},{"expr":"sum(rate(scheduler_scheduling_algorithm_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)","format":"time_series","intervalFactor":2,"legendFormat":"{{cluster}} {{instance}} scheduling algorithm","refId":"C"},{"expr":"sum(rate(scheduler_volume_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)","format":"time_series","intervalFactor":2,"legendFormat":"{{cluster}} {{instance}} volume","refId":"D"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Scheduling Rate","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ops","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"ops","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":4,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":5,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))","format":"time_series","intervalFactor":2,"legendFormat":"{{cluster}} {{instance}} e2e","refId":"A"},{"expr":"histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))","format":"time_series","intervalFactor":2,"legendFormat":"{{cluster}} {{instance}} binding","refId":"B"},{"expr":"histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))","format":"time_series","intervalFactor":2,"legendFormat":"{{cluster}} {{instance}} scheduling algorithm","refId":"C"},{"expr":"histogram_quantile(0.99, sum(rate(scheduler_volume_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))","format":"time_series","intervalFactor":2,"legendFormat":"{{cluster}} {{instance}} volume","refId":"D"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Scheduling latency 99th Quantile","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"s","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Dashboard Row","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":5,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"2xx","refId":"A"},{"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"3xx","refId":"B"},{"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"4xx","refId":"C"},{"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"5xx","refId":"D"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Kube API Request Rate","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ops","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"ops","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":6,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":8,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"POST\"}[$__rate_interval])) by (verb, url, le))","format":"time_series","intervalFactor":2,"legendFormat":"{{verb}} {{url}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Post Request Latency 99th Quantile","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"s","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Dashboard Row","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":7,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, url, le))","format":"time_series","intervalFactor":2,"legendFormat":"{{verb}} {{url}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Get Request Latency 99th Quantile","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"s","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Dashboard Row","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":8,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"process_resident_memory_bytes{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":9,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU usage","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":10,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"go_goroutines{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Goroutines","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Dashboard Row","titleSize":"h6","type":"row"}],"schemaVersion":14,"style":"dark","tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{},"datasource":"$datasource","hide":2,"includeAll":false,"label":"cluster","multi":false,"name":"cluster","options":[],"query":"label_values(up{job=\"kube-scheduler\"}, cluster)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{},"datasource":"$datasource","hide":0,"includeAll":true,"label":null,"multi":false,"name":"instance","options":[],"query":"label_values(up{job=\"kube-scheduler\", cluster=\"$cluster\"}, instance)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Kubernetes / Scheduler","uid":"2e6b6a3b4bddf1427b3a55aa1311c656","version":0} \ No newline at end of file diff --git a/monitor/monitor-control-plan/v1_Service_prometheus-community-kube-kube-controller-manager.yaml b/monitor/monitor-control-plan/v1_Service_prometheus-community-kube-kube-controller-manager.yaml new file mode 100644 index 0000000..5f2917d --- /dev/null +++ b/monitor/monitor-control-plan/v1_Service_prometheus-community-kube-kube-controller-manager.yaml @@ -0,0 +1,27 @@ +# Source: kube-prometheus-stack/templates/exporters/kube-controller-manager/service.yaml +apiVersion: v1 +kind: Service +metadata: + name: prometheus-community-kube-kube-controller-manager + labels: + app: kube-prometheus-stack-kube-controller-manager + jobLabel: kube-controller-manager + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" + namespace: kube-system +spec: + clusterIP: None + ports: + - name: http-metrics + port: 10257 + protocol: TCP + targetPort: 10257 + selector: + component: kube-controller-manager + type: ClusterIP \ No newline at end of file diff --git a/monitor/monitor-control-plan/v1_Service_prometheus-community-kube-kube-etcd.yaml b/monitor/monitor-control-plan/v1_Service_prometheus-community-kube-kube-etcd.yaml new file mode 100644 index 0000000..34e0301 --- /dev/null +++ b/monitor/monitor-control-plan/v1_Service_prometheus-community-kube-kube-etcd.yaml @@ -0,0 +1,27 @@ +# Source: kube-prometheus-stack/templates/exporters/kube-etcd/service.yaml +apiVersion: v1 +kind: Service +metadata: + name: prometheus-community-kube-kube-etcd + labels: + app: kube-prometheus-stack-kube-etcd + jobLabel: kube-etcd + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" + namespace: kube-system +spec: + clusterIP: None + ports: + - name: http-metrics + port: 2381 + protocol: TCP + targetPort: 2381 + selector: + component: etcd + type: ClusterIP \ No newline at end of file diff --git a/monitor/monitor-control-plan/v1_Service_prometheus-community-kube-kube-scheduler.yaml b/monitor/monitor-control-plan/v1_Service_prometheus-community-kube-kube-scheduler.yaml new file mode 100644 index 0000000..671288a --- /dev/null +++ b/monitor/monitor-control-plan/v1_Service_prometheus-community-kube-kube-scheduler.yaml @@ -0,0 +1,27 @@ +# Source: kube-prometheus-stack/templates/exporters/kube-scheduler/service.yaml +apiVersion: v1 +kind: Service +metadata: + name: prometheus-community-kube-kube-scheduler + labels: + app: kube-prometheus-stack-kube-scheduler + jobLabel: kube-scheduler + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus-community + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus-community" + heritage: "Helm" + namespace: kube-system +spec: + clusterIP: None + ports: + - name: http-metrics + port: 10259 + protocol: TCP + targetPort: 10259 + selector: + component: kube-scheduler + type: ClusterIP \ No newline at end of file diff --git a/monitor/node-exporter/apps_v1_DaemonSet_node-exporter-prometheus-node-exporter.yaml b/monitor/node-exporter/apps_v1_DaemonSet_node-exporter-prometheus-node-exporter.yaml new file mode 100644 index 0000000..d919580 --- /dev/null +++ b/monitor/node-exporter/apps_v1_DaemonSet_node-exporter-prometheus-node-exporter.yaml @@ -0,0 +1,119 @@ +# Source: kube-prometheus-stack/charts/prometheus-node-exporter/templates/daemonset.yaml +apiVersion: apps/v1 +kind: DaemonSet +metadata: + name: node-exporter-prometheus-node-exporter + namespace: vynil-monitor + labels: + helm.sh/chart: prometheus-node-exporter-4.26.0 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: prometheus-node-exporter + app.kubernetes.io/name: prometheus-node-exporter + app.kubernetes.io/instance: node-exporter + app.kubernetes.io/version: "1.7.0" + jobLabel: node-exporter + release: node-exporter +spec: + selector: + matchLabels: + app.kubernetes.io/name: prometheus-node-exporter + app.kubernetes.io/instance: node-exporter + revisionHistoryLimit: 10 + updateStrategy: + rollingUpdate: + maxUnavailable: 1 + type: RollingUpdate + template: + metadata: + annotations: + cluster-autoscaler.kubernetes.io/safe-to-evict: "true" + labels: + helm.sh/chart: prometheus-node-exporter-4.26.0 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: prometheus-node-exporter + app.kubernetes.io/name: prometheus-node-exporter + app.kubernetes.io/instance: node-exporter + app.kubernetes.io/version: "1.7.0" + jobLabel: node-exporter + release: node-exporter + spec: + automountServiceAccountToken: false + securityContext: + fsGroup: 65534 + runAsGroup: 65534 + runAsNonRoot: true + runAsUser: 65534 + serviceAccountName: node-exporter-prometheus-node-exporter + containers: + - name: node-exporter + image: quay.io/prometheus/node-exporter:v1.7.0 + imagePullPolicy: IfNotPresent + args: + - --path.procfs=/host/proc + - --path.sysfs=/host/sys + - --path.rootfs=/host/root + - --path.udev.data=/host/root/run/udev/data + - --web.listen-address=[$(HOST_IP)]:9100 + - --collector.filesystem.mount-points-exclude=^/(dev|proc|sys|var/lib/docker/.+|var/lib/kubelet/.+)($|/) + - --collector.filesystem.fs-types-exclude=^(autofs|binfmt_misc|bpf|cgroup2?|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|iso9660|mqueue|nsfs|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|selinuxfs|squashfs|sysfs|tracefs)$ + securityContext: + readOnlyRootFilesystem: true + env: + - name: HOST_IP + value: 0.0.0.0 + ports: + - name: http-metrics + containerPort: 9100 + protocol: TCP + livenessProbe: + failureThreshold: 3 + httpGet: + httpHeaders: + path: / + port: 9100 + scheme: HTTP + initialDelaySeconds: 0 + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 1 + readinessProbe: + failureThreshold: 3 + httpGet: + httpHeaders: + path: / + port: 9100 + scheme: HTTP + initialDelaySeconds: 0 + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 1 + volumeMounts: + - name: proc + mountPath: /host/proc + readOnly: true + - name: sys + mountPath: /host/sys + readOnly: true + - name: root + mountPath: /host/root + mountPropagation: HostToContainer + readOnly: true + hostNetwork: true + hostPID: true + nodeSelector: + kubernetes.io/os: linux + tolerations: + - effect: NoSchedule + operator: Exists + volumes: + - name: proc + hostPath: + path: /proc + - name: sys + hostPath: + path: /sys + - name: root + hostPath: + path: / \ No newline at end of file diff --git a/monitor/node-exporter/datas.tf b/monitor/node-exporter/datas.tf new file mode 100644 index 0000000..7068eea --- /dev/null +++ b/monitor/node-exporter/datas.tf @@ -0,0 +1,34 @@ +locals { + common-labels = { + "vynil.solidite.fr/owner-name" = var.instance + "vynil.solidite.fr/owner-namespace" = var.namespace + "vynil.solidite.fr/owner-category" = var.category + "vynil.solidite.fr/owner-component" = var.component + "app.kubernetes.io/managed-by" = "vynil" + "app.kubernetes.io/instance" = var.instance + } +} + +data "kustomization_overlay" "data" { + common_labels = local.common-labels + namespace = var.namespace + resources = [for file in fileset(path.module, "*.yaml"): file if file != "index.yaml"] + images { + name = "quay.io/prometheus/node-exporter" + new_name = "${var.images.node-exporter.registry}/${var.images.node-exporter.repository}" + new_tag = "${var.images.node-exporter.tag}" + } + patches { + target { + kind = "ServiceMonitor" + name = "node-exporter-prometheus-node-exporter" + } + patch = <<-EOF + - op: replace + path: /spec/selector/matchLabels/app.kubernetes.io~1instance + value: "${var.instance}" + EOF + } +} + + diff --git a/monitor/node-exporter/index.yaml b/monitor/node-exporter/index.yaml new file mode 100644 index 0000000..fa0b2ef --- /dev/null +++ b/monitor/node-exporter/index.yaml @@ -0,0 +1,58 @@ +--- +apiVersion: vinyl.solidite.fr/v1beta1 +kind: Component +category: monitor +metadata: + name: node-exporter + description: null +options: + images: + default: + node-exporter: + pullPolicy: IfNotPresent + registry: quay.io + repository: prometheus/node-exporter + tag: v1.7.0 + examples: + - node-exporter: + pullPolicy: IfNotPresent + registry: quay.io + repository: prometheus/node-exporter + tag: v1.7.0 + properties: + node-exporter: + default: + pullPolicy: IfNotPresent + registry: quay.io + repository: prometheus/node-exporter + tag: v1.7.0 + properties: + pullPolicy: + default: IfNotPresent + enum: + - Always + - Never + - IfNotPresent + type: string + registry: + default: quay.io + type: string + repository: + default: prometheus/node-exporter + type: string + tag: + default: v1.7.0 + type: string + type: object + type: object +dependencies: [] +providers: + kubernetes: true + authentik: null + kubectl: true + postgresql: null + mysql: null + restapi: null + http: null + gitea: null +tfaddtype: null diff --git a/monitor/node-exporter/monitoring.coreos.com_v1_PrometheusRule_node-exporter-kube-prometh-node-exporter.rules.yaml b/monitor/node-exporter/monitoring.coreos.com_v1_PrometheusRule_node-exporter-kube-prometh-node-exporter.rules.yaml new file mode 100644 index 0000000..2840838 --- /dev/null +++ b/monitor/node-exporter/monitoring.coreos.com_v1_PrometheusRule_node-exporter-kube-prometh-node-exporter.rules.yaml @@ -0,0 +1,82 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: node-exporter-kube-prometh-node-exporter.rules + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: node-exporter + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "node-exporter" + heritage: "Helm" +spec: + groups: + - name: node-exporter.rules + rules: + - expr: |- + count without (cpu, mode) ( + node_cpu_seconds_total{job="node-exporter",mode="idle"} + ) + record: instance:node_num_cpu:sum + - expr: |- + 1 - avg without (cpu) ( + sum without (mode) (rate(node_cpu_seconds_total{job="node-exporter", mode=~"idle|iowait|steal"}[5m])) + ) + record: instance:node_cpu_utilisation:rate5m + - expr: |- + ( + node_load1{job="node-exporter"} + / + instance:node_num_cpu:sum{job="node-exporter"} + ) + record: instance:node_load1_per_cpu:ratio + - expr: |- + 1 - ( + ( + node_memory_MemAvailable_bytes{job="node-exporter"} + or + ( + node_memory_Buffers_bytes{job="node-exporter"} + + + node_memory_Cached_bytes{job="node-exporter"} + + + node_memory_MemFree_bytes{job="node-exporter"} + + + node_memory_Slab_bytes{job="node-exporter"} + ) + ) + / + node_memory_MemTotal_bytes{job="node-exporter"} + ) + record: instance:node_memory_utilisation:ratio + - expr: rate(node_vmstat_pgmajfault{job="node-exporter"}[5m]) + record: instance:node_vmstat_pgmajfault:rate5m + - expr: rate(node_disk_io_time_seconds_total{job="node-exporter", device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m]) + record: instance_device:node_disk_io_time_seconds:rate5m + - expr: rate(node_disk_io_time_weighted_seconds_total{job="node-exporter", device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m]) + record: instance_device:node_disk_io_time_weighted_seconds:rate5m + - expr: |- + sum without (device) ( + rate(node_network_receive_bytes_total{job="node-exporter", device!="lo"}[5m]) + ) + record: instance:node_network_receive_bytes_excluding_lo:rate5m + - expr: |- + sum without (device) ( + rate(node_network_transmit_bytes_total{job="node-exporter", device!="lo"}[5m]) + ) + record: instance:node_network_transmit_bytes_excluding_lo:rate5m + - expr: |- + sum without (device) ( + rate(node_network_receive_drop_total{job="node-exporter", device!="lo"}[5m]) + ) + record: instance:node_network_receive_drop_excluding_lo:rate5m + - expr: |- + sum without (device) ( + rate(node_network_transmit_drop_total{job="node-exporter", device!="lo"}[5m]) + ) + record: instance:node_network_transmit_drop_excluding_lo:rate5m \ No newline at end of file diff --git a/monitor/node-exporter/monitoring.coreos.com_v1_PrometheusRule_node-exporter-kube-prometh-node-exporter.yaml b/monitor/node-exporter/monitoring.coreos.com_v1_PrometheusRule_node-exporter-kube-prometh-node-exporter.yaml new file mode 100644 index 0000000..6954439 --- /dev/null +++ b/monitor/node-exporter/monitoring.coreos.com_v1_PrometheusRule_node-exporter-kube-prometh-node-exporter.yaml @@ -0,0 +1,328 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: node-exporter-kube-prometh-node-exporter + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: node-exporter + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "node-exporter" + heritage: "Helm" +spec: + groups: + - name: node-exporter + rules: + - alert: NodeFilesystemSpaceFillingUp + annotations: + description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left and is filling up. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemspacefillingup + summary: Filesystem is predicted to run out of space within the next 24 hours. + expr: |- + ( + node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 15 + and + predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""}[6h], 24*60*60) < 0 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 1h + labels: + severity: warning + - alert: NodeFilesystemSpaceFillingUp + annotations: + description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left and is filling up fast. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemspacefillingup + summary: Filesystem is predicted to run out of space within the next 4 hours. + expr: |- + ( + node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 10 + and + predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""}[6h], 4*60*60) < 0 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 1h + labels: + severity: critical + - alert: NodeFilesystemAlmostOutOfSpace + annotations: + description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutofspace + summary: Filesystem has less than 5% space left. + expr: |- + ( + node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 5 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 30m + labels: + severity: warning + - alert: NodeFilesystemAlmostOutOfSpace + annotations: + description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutofspace + summary: Filesystem has less than 3% space left. + expr: |- + ( + node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 3 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 30m + labels: + severity: critical + - alert: NodeFilesystemFilesFillingUp + annotations: + description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left and is filling up. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemfilesfillingup + summary: Filesystem is predicted to run out of inodes within the next 24 hours. + expr: |- + ( + node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_files{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 40 + and + predict_linear(node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""}[6h], 24*60*60) < 0 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 1h + labels: + severity: warning + - alert: NodeFilesystemFilesFillingUp + annotations: + description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left and is filling up fast. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemfilesfillingup + summary: Filesystem is predicted to run out of inodes within the next 4 hours. + expr: |- + ( + node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_files{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 20 + and + predict_linear(node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""}[6h], 4*60*60) < 0 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 1h + labels: + severity: critical + - alert: NodeFilesystemAlmostOutOfFiles + annotations: + description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutoffiles + summary: Filesystem has less than 5% inodes left. + expr: |- + ( + node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_files{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 5 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 1h + labels: + severity: warning + - alert: NodeFilesystemAlmostOutOfFiles + annotations: + description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutoffiles + summary: Filesystem has less than 3% inodes left. + expr: |- + ( + node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_files{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 3 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 1h + labels: + severity: critical + - alert: NodeNetworkReceiveErrs + annotations: + description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} receive errors in the last two minutes.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodenetworkreceiveerrs + summary: Network interface is reporting many receive errors. + expr: rate(node_network_receive_errs_total{job="node-exporter"}[2m]) / rate(node_network_receive_packets_total{job="node-exporter"}[2m]) > 0.01 + for: 1h + labels: + severity: warning + - alert: NodeNetworkTransmitErrs + annotations: + description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} transmit errors in the last two minutes.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodenetworktransmiterrs + summary: Network interface is reporting many transmit errors. + expr: rate(node_network_transmit_errs_total{job="node-exporter"}[2m]) / rate(node_network_transmit_packets_total{job="node-exporter"}[2m]) > 0.01 + for: 1h + labels: + severity: warning + - alert: NodeHighNumberConntrackEntriesUsed + annotations: + description: '{{ $value | humanizePercentage }} of conntrack entries are used.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodehighnumberconntrackentriesused + summary: Number of conntrack are getting close to the limit. + expr: (node_nf_conntrack_entries{job="node-exporter"} / node_nf_conntrack_entries_limit) > 0.75 + labels: + severity: warning + - alert: NodeTextFileCollectorScrapeError + annotations: + description: Node Exporter text file collector on {{ $labels.instance }} failed to scrape. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodetextfilecollectorscrapeerror + summary: Node Exporter text file collector failed to scrape. + expr: node_textfile_scrape_error{job="node-exporter"} == 1 + labels: + severity: warning + - alert: NodeClockSkewDetected + annotations: + description: Clock at {{ $labels.instance }} is out of sync by more than 0.05s. Ensure NTP is configured correctly on this host. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodeclockskewdetected + summary: Clock skew detected. + expr: |- + ( + node_timex_offset_seconds{job="node-exporter"} > 0.05 + and + deriv(node_timex_offset_seconds{job="node-exporter"}[5m]) >= 0 + ) + or + ( + node_timex_offset_seconds{job="node-exporter"} < -0.05 + and + deriv(node_timex_offset_seconds{job="node-exporter"}[5m]) <= 0 + ) + for: 10m + labels: + severity: warning + - alert: NodeClockNotSynchronising + annotations: + description: Clock at {{ $labels.instance }} is not synchronising. Ensure NTP is configured on this host. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodeclocknotsynchronising + summary: Clock not synchronising. + expr: |- + min_over_time(node_timex_sync_status{job="node-exporter"}[5m]) == 0 + and + node_timex_maxerror_seconds{job="node-exporter"} >= 16 + for: 10m + labels: + severity: warning + - alert: NodeRAIDDegraded + annotations: + description: RAID array '{{ $labels.device }}' at {{ $labels.instance }} is in degraded state due to one or more disks failures. Number of spare drives is insufficient to fix issue automatically. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/noderaiddegraded + summary: RAID Array is degraded. + expr: node_md_disks_required{job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"} - ignoring (state) (node_md_disks{state="active",job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}) > 0 + for: 15m + labels: + severity: critical + - alert: NodeRAIDDiskFailure + annotations: + description: At least one device in RAID array at {{ $labels.instance }} failed. Array '{{ $labels.device }}' needs attention and possibly a disk swap. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/noderaiddiskfailure + summary: Failed device in RAID array. + expr: node_md_disks{state="failed",job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"} > 0 + labels: + severity: warning + - alert: NodeFileDescriptorLimit + annotations: + description: File descriptors limit at {{ $labels.instance }} is currently at {{ printf "%.2f" $value }}%. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefiledescriptorlimit + summary: Kernel is predicted to exhaust file descriptors limit soon. + expr: |- + ( + node_filefd_allocated{job="node-exporter"} * 100 / node_filefd_maximum{job="node-exporter"} > 70 + ) + for: 15m + labels: + severity: warning + - alert: NodeFileDescriptorLimit + annotations: + description: File descriptors limit at {{ $labels.instance }} is currently at {{ printf "%.2f" $value }}%. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefiledescriptorlimit + summary: Kernel is predicted to exhaust file descriptors limit soon. + expr: |- + ( + node_filefd_allocated{job="node-exporter"} * 100 / node_filefd_maximum{job="node-exporter"} > 90 + ) + for: 15m + labels: + severity: critical + - alert: NodeCPUHighUsage + annotations: + description: 'CPU usage at {{ $labels.instance }} has been above 90% for the last 15 minutes, is currently at {{ printf "%.2f" $value }}%. + + ' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodecpuhighusage + summary: High CPU usage. + expr: sum without(mode) (avg without (cpu) (rate(node_cpu_seconds_total{job="node-exporter", mode!="idle"}[2m]))) * 100 > 90 + for: 15m + labels: + severity: info + - alert: NodeSystemSaturation + annotations: + description: 'System load per core at {{ $labels.instance }} has been above 2 for the last 15 minutes, is currently at {{ printf "%.2f" $value }}. + + This might indicate this instance resources saturation and can cause it becoming unresponsive. + + ' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodesystemsaturation + summary: System saturated, load per core is very high. + expr: |- + node_load1{job="node-exporter"} + / count without (cpu, mode) (node_cpu_seconds_total{job="node-exporter", mode="idle"}) > 2 + for: 15m + labels: + severity: warning + - alert: NodeMemoryMajorPagesFaults + annotations: + description: 'Memory major pages are occurring at very high rate at {{ $labels.instance }}, 500 major page faults per second for the last 15 minutes, is currently at {{ printf "%.2f" $value }}. + + Please check that there is enough memory available at this instance. + + ' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodememorymajorpagesfaults + summary: Memory major page faults are occurring at very high rate. + expr: rate(node_vmstat_pgmajfault{job="node-exporter"}[5m]) > 500 + for: 15m + labels: + severity: warning + - alert: NodeMemoryHighUtilization + annotations: + description: 'Memory is filling up at {{ $labels.instance }}, has been above 90% for the last 15 minutes, is currently at {{ printf "%.2f" $value }}%. + + ' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodememoryhighutilization + summary: Host is running out of memory. + expr: 100 - (node_memory_MemAvailable_bytes{job="node-exporter"} / node_memory_MemTotal_bytes{job="node-exporter"} * 100) > 90 + for: 15m + labels: + severity: warning + - alert: NodeDiskIOSaturation + annotations: + description: 'Disk IO queue (aqu-sq) is high on {{ $labels.device }} at {{ $labels.instance }}, has been above 10 for the last 15 minutes, is currently at {{ printf "%.2f" $value }}. + + This symptom might indicate disk saturation. + + ' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodediskiosaturation + summary: Disk IO queue is high. + expr: rate(node_disk_io_time_weighted_seconds_total{job="node-exporter", device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m]) > 10 + for: 30m + labels: + severity: warning + - alert: NodeSystemdServiceFailed + annotations: + description: Systemd service {{ $labels.name }} has entered failed state at {{ $labels.instance }} + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodesystemdservicefailed + summary: Systemd service has entered failed state. + expr: node_systemd_unit_state{job="node-exporter", state="failed"} == 1 + for: 5m + labels: + severity: warning + - alert: NodeBondingDegraded + annotations: + description: Bonding interface {{ $labels.master }} on {{ $labels.instance }} is in degraded state due to one or more slave failures. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodebondingdegraded + summary: Bonding interface is degraded + expr: (node_bonding_slaves - node_bonding_active) != 0 + for: 5m + labels: + severity: warning \ No newline at end of file diff --git a/monitor/node-exporter/monitoring.coreos.com_v1_PrometheusRule_node-exporter-kube-prometh-node-network.yaml b/monitor/node-exporter/monitoring.coreos.com_v1_PrometheusRule_node-exporter-kube-prometh-node-network.yaml new file mode 100644 index 0000000..b2a73b8 --- /dev/null +++ b/monitor/node-exporter/monitoring.coreos.com_v1_PrometheusRule_node-exporter-kube-prometh-node-network.yaml @@ -0,0 +1,29 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/node-network.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: node-exporter-kube-prometh-node-network + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: node-exporter + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "node-exporter" + heritage: "Helm" +spec: + groups: + - name: node-network + rules: + - alert: NodeNetworkInterfaceFlapping + annotations: + description: Network interface "{{ $labels.device }}" changing its up status often on node-exporter {{ $labels.namespace }}/{{ $labels.pod }} + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/nodenetworkinterfaceflapping + summary: Network interface is often changing its status + expr: changes(node_network_up{job="node-exporter",device!~"veth.+"}[2m]) > 2 + for: 2m + labels: + severity: warning \ No newline at end of file diff --git a/monitor/node-exporter/monitoring.coreos.com_v1_PrometheusRule_node-exporter-kube-prometh-node.rules.yaml b/monitor/node-exporter/monitoring.coreos.com_v1_PrometheusRule_node-exporter-kube-prometh-node.rules.yaml new file mode 100644 index 0000000..9f54155 --- /dev/null +++ b/monitor/node-exporter/monitoring.coreos.com_v1_PrometheusRule_node-exporter-kube-prometh-node.rules.yaml @@ -0,0 +1,56 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/node.rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: node-exporter-kube-prometh-node.rules + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: node-exporter + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "node-exporter" + heritage: "Helm" +spec: + groups: + - name: node.rules + rules: + - expr: |- + topk by (cluster, namespace, pod) (1, + max by (cluster, node, namespace, pod) ( + label_replace(kube_pod_info{job="kube-state-metrics",node!=""}, "pod", "$1", "pod", "(.*)") + )) + record: 'node_namespace_pod:kube_pod_info:' + - expr: |- + count by (cluster, node) ( + node_cpu_seconds_total{mode="idle",job="node-exporter"} + * on (cluster, namespace, pod) group_left(node) + topk by (cluster, namespace, pod) (1, node_namespace_pod:kube_pod_info:) + ) + record: node:node_num_cpu:sum + - expr: |- + sum( + node_memory_MemAvailable_bytes{job="node-exporter"} or + ( + node_memory_Buffers_bytes{job="node-exporter"} + + node_memory_Cached_bytes{job="node-exporter"} + + node_memory_MemFree_bytes{job="node-exporter"} + + node_memory_Slab_bytes{job="node-exporter"} + ) + ) by (cluster) + record: :node_memory_MemAvailable_bytes:sum + - expr: |- + avg by (cluster, node) ( + sum without (mode) ( + rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal",job="node-exporter"}[5m]) + ) + ) + record: node:node_cpu_utilization:ratio_rate5m + - expr: |- + avg by (cluster) ( + node:node_cpu_utilization:ratio_rate5m + ) + record: cluster:node_cpu:ratio_rate5m \ No newline at end of file diff --git a/monitor/node-exporter/monitoring.coreos.com_v1_ServiceMonitor_node-exporter-prometheus-node-exporter.yaml b/monitor/node-exporter/monitoring.coreos.com_v1_ServiceMonitor_node-exporter-prometheus-node-exporter.yaml new file mode 100644 index 0000000..890da43 --- /dev/null +++ b/monitor/node-exporter/monitoring.coreos.com_v1_ServiceMonitor_node-exporter-prometheus-node-exporter.yaml @@ -0,0 +1,28 @@ +# Source: kube-prometheus-stack/charts/prometheus-node-exporter/templates/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: node-exporter-prometheus-node-exporter + namespace: vynil-monitor + labels: + helm.sh/chart: prometheus-node-exporter-4.26.0 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: prometheus-node-exporter + app.kubernetes.io/name: prometheus-node-exporter + app.kubernetes.io/instance: node-exporter + app.kubernetes.io/version: "1.7.0" + jobLabel: node-exporter + release: node-exporter +spec: + jobLabel: jobLabel + + selector: + matchLabels: + app.kubernetes.io/name: prometheus-node-exporter + app.kubernetes.io/instance: node-exporter + attachMetadata: + node: false + endpoints: + - port: http-metrics + scheme: http \ No newline at end of file diff --git a/monitor/node-exporter/v1_ConfigMap_node-exporter-kube-prometh-node-cluster-rsrc-use.yaml b/monitor/node-exporter/v1_ConfigMap_node-exporter-kube-prometh-node-cluster-rsrc-use.yaml new file mode 100644 index 0000000..71b828f --- /dev/null +++ b/monitor/node-exporter/v1_ConfigMap_node-exporter-kube-prometh-node-cluster-rsrc-use.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/node-cluster-rsrc-use.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: node-exporter-kube-prometh-node-cluster-rsrc-use + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: node-exporter + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "node-exporter" + heritage: "Helm" +data: + node-cluster-rsrc-use.json: |- + {"__inputs":[],"__requires":[],"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":1,"hideControls":false,"id":null,"links":[],"refresh":"30s","rows":[{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"fillGradient":0,"gridPos":{},"id":2,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"((\n instance:node_cpu_utilisation:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}\n *\n instance:node_num_cpu:sum{job=\"node-exporter\", cluster=\"$cluster\"}\n) != 0 )\n/ scalar(sum(instance:node_num_cpu:sum{job=\"node-exporter\", cluster=\"$cluster\"}))\n","format":"time_series","intervalFactor":2,"legendFormat":"{{ instance }}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Utilisation","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"fillGradient":0,"gridPos":{},"id":3,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"(\n instance:node_load1_per_cpu:ratio{job=\"node-exporter\", cluster=\"$cluster\"}\n / scalar(count(instance:node_load1_per_cpu:ratio{job=\"node-exporter\", cluster=\"$cluster\"}))\n) != 0\n","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Saturation (Load1 per CPU)","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"CPU","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"fillGradient":0,"gridPos":{},"id":4,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"(\n instance:node_memory_utilisation:ratio{job=\"node-exporter\", cluster=\"$cluster\"}\n / scalar(count(instance:node_memory_utilisation:ratio{job=\"node-exporter\", cluster=\"$cluster\"}))\n) != 0\n","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory Utilisation","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"fillGradient":0,"gridPos":{},"id":5,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"instance:node_vmstat_pgmajfault:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory Saturation (Major Page Faults)","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"rds","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"rds","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Memory","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"fillGradient":0,"gridPos":{},"id":6,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[{"alias":"/Receive/","stack":"A"},{"alias":"/Transmit/","stack":"B","transform":"negative-Y"}],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"instance:node_network_receive_bytes_excluding_lo:rate5m{job=\"node-exporter\", cluster=\"$cluster\"} != 0","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} Receive","refId":"A"},{"expr":"instance:node_network_transmit_bytes_excluding_lo:rate5m{job=\"node-exporter\", cluster=\"$cluster\"} != 0","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} Transmit","refId":"B"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Network Utilisation (Bytes Receive/Transmit)","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"fillGradient":0,"gridPos":{},"id":7,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[{"alias":"/ Receive/","stack":"A"},{"alias":"/ Transmit/","stack":"B","transform":"negative-Y"}],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"instance:node_network_receive_drop_excluding_lo:rate5m{job=\"node-exporter\", cluster=\"$cluster\"} != 0","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} Receive","refId":"A"},{"expr":"instance:node_network_transmit_drop_excluding_lo:rate5m{job=\"node-exporter\", cluster=\"$cluster\"} != 0","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} Transmit","refId":"B"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Network Saturation (Drops Receive/Transmit)","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Network","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"fillGradient":0,"gridPos":{},"id":8,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"(\n instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}\n / scalar(count(instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}))\n) != 0\n","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} {{device}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Disk IO Utilisation","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"fillGradient":0,"gridPos":{},"id":9,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"(\n instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}\n / scalar(count(instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}))\n) != 0\n","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} {{device}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Disk IO Saturation","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Disk IO","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"fillGradient":0,"gridPos":{},"id":10,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sum without (device) (\n max without (fstype, mountpoint) ((\n node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\", mountpoint!=\"\", cluster=\"$cluster\"}\n -\n node_filesystem_avail_bytes{job=\"node-exporter\", fstype!=\"\", mountpoint!=\"\", cluster=\"$cluster\"}\n ) != 0)\n)\n/ scalar(sum(max without (fstype, mountpoint) (node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\", mountpoint!=\"\", cluster=\"$cluster\"})))\n","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Disk Space Utilisation","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Disk Space","titleSize":"h6","type":"row"}],"schemaVersion":14,"style":"dark","tags":["node-exporter-mixin"],"templating":{"list":[{"current":{"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{"text":"","value":""},"datasource":"$datasource","hide":2,"includeAll":false,"label":null,"multi":false,"name":"cluster","options":[],"query":"label_values(node_time_seconds, cluster)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Node Exporter / USE Method / Cluster","version":0} \ No newline at end of file diff --git a/monitor/node-exporter/v1_ConfigMap_node-exporter-kube-prometh-node-rsrc-use.yaml b/monitor/node-exporter/v1_ConfigMap_node-exporter-kube-prometh-node-rsrc-use.yaml new file mode 100644 index 0000000..164c2f0 --- /dev/null +++ b/monitor/node-exporter/v1_ConfigMap_node-exporter-kube-prometh-node-rsrc-use.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/node-rsrc-use.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: node-exporter-kube-prometh-node-rsrc-use + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: node-exporter + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "node-exporter" + heritage: "Helm" +data: + node-rsrc-use.json: |- + {"__inputs":[],"__requires":[],"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":1,"hideControls":false,"id":null,"links":[],"refresh":"30s","rows":[{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"fillGradient":0,"gridPos":{},"id":2,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"instance:node_cpu_utilisation:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","format":"time_series","intervalFactor":2,"legendFormat":"Utilisation","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Utilisation","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"fillGradient":0,"gridPos":{},"id":3,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"instance:node_load1_per_cpu:ratio{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","format":"time_series","intervalFactor":2,"legendFormat":"Saturation","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Saturation (Load1 per CPU)","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"CPU","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"fillGradient":0,"gridPos":{},"id":4,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"instance:node_memory_utilisation:ratio{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","format":"time_series","intervalFactor":2,"legendFormat":"Utilisation","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory Utilisation","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"fillGradient":0,"gridPos":{},"id":5,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"instance:node_vmstat_pgmajfault:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","format":"time_series","intervalFactor":2,"legendFormat":"Major page Faults","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory Saturation (Major Page Faults)","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"rds","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"rds","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Memory","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"fillGradient":0,"gridPos":{},"id":6,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[{"alias":"/Receive/","stack":"A"},{"alias":"/Transmit/","stack":"B","transform":"negative-Y"}],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"instance:node_network_receive_bytes_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","format":"time_series","intervalFactor":2,"legendFormat":"Receive","refId":"A"},{"expr":"instance:node_network_transmit_bytes_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","format":"time_series","intervalFactor":2,"legendFormat":"Transmit","refId":"B"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Network Utilisation (Bytes Receive/Transmit)","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"fillGradient":0,"gridPos":{},"id":7,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[{"alias":"/ Receive/","stack":"A"},{"alias":"/ Transmit/","stack":"B","transform":"negative-Y"}],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"instance:node_network_receive_drop_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","format":"time_series","intervalFactor":2,"legendFormat":"Receive","refId":"A"},{"expr":"instance:node_network_transmit_drop_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","format":"time_series","intervalFactor":2,"legendFormat":"Transmit","refId":"B"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Network Saturation (Drops Receive/Transmit)","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"Bps","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Network","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"fillGradient":0,"gridPos":{},"id":8,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","format":"time_series","intervalFactor":2,"legendFormat":"{{device}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Disk IO Utilisation","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"fillGradient":0,"gridPos":{},"id":9,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0","format":"time_series","intervalFactor":2,"legendFormat":"{{device}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Disk IO Saturation","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Disk IO","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"fillGradient":0,"gridPos":{},"id":10,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":false,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":true,"steppedLine":false,"targets":[{"expr":"sort_desc(1 -\n (\n max without (mountpoint, fstype) (node_filesystem_avail_bytes{job=\"node-exporter\", fstype!=\"\", instance=\"$instance\", cluster=\"$cluster\"})\n /\n max without (mountpoint, fstype) (node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\", instance=\"$instance\", cluster=\"$cluster\"})\n ) != 0\n)\n","format":"time_series","intervalFactor":2,"legendFormat":"{{device}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Disk Space Utilisation","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Disk Space","titleSize":"h6","type":"row"}],"schemaVersion":14,"style":"dark","tags":["node-exporter-mixin"],"templating":{"list":[{"current":{"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{"text":"","value":""},"datasource":"$datasource","hide":2,"includeAll":false,"label":null,"multi":false,"name":"cluster","options":[],"query":"label_values(node_time_seconds, cluster)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{},"datasource":"$datasource","hide":0,"includeAll":false,"label":null,"multi":false,"name":"instance","options":[],"query":"label_values(node_exporter_build_info{job=\"node-exporter\", cluster=\"$cluster\"}, instance)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Node Exporter / USE Method / Node","version":0} \ No newline at end of file diff --git a/monitor/node-exporter/v1_ConfigMap_node-exporter-kube-prometh-nodes-darwin.yaml b/monitor/node-exporter/v1_ConfigMap_node-exporter-kube-prometh-nodes-darwin.yaml new file mode 100644 index 0000000..fff2e39 --- /dev/null +++ b/monitor/node-exporter/v1_ConfigMap_node-exporter-kube-prometh-nodes-darwin.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/nodes-darwin.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: node-exporter-kube-prometh-nodes-darwin + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: node-exporter + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "node-exporter" + heritage: "Helm" +data: + nodes-darwin.json: |- + {"__inputs":[],"__requires":[],"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":1,"hideControls":false,"id":null,"links":[],"refresh":"30s","rows":[{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":2,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"(\n (1 - sum without (mode) (rate(node_cpu_seconds_total{job=\"node-exporter\", mode=~\"idle|iowait|steal\", instance=\"$instance\"}[$__rate_interval])))\n/ ignoring(cpu) group_left\n count without (cpu, mode) (node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\"})\n)\n","format":"time_series","intervalFactor":5,"legendFormat":"{{cpu}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Usage","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":1,"min":0,"show":true},{"format":"percentunit","label":null,"logBase":1,"max":1,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":0,"fillGradient":0,"gridPos":{},"id":3,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"node_load1{job=\"node-exporter\", instance=\"$instance\"}","format":"time_series","intervalFactor":2,"legendFormat":"1m load average","refId":"A"},{"expr":"node_load5{job=\"node-exporter\", instance=\"$instance\"}","format":"time_series","intervalFactor":2,"legendFormat":"5m load average","refId":"B"},{"expr":"node_load15{job=\"node-exporter\", instance=\"$instance\"}","format":"time_series","intervalFactor":2,"legendFormat":"15m load average","refId":"C"},{"expr":"count(node_cpu_seconds_total{job=\"node-exporter\", instance=\"$instance\", mode=\"idle\"})","format":"time_series","intervalFactor":2,"legendFormat":"logical cores","refId":"D"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Load Average","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"CPU","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":4,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":9,"stack":false,"steppedLine":false,"targets":[{"expr":"node_memory_total_bytes{job=\"node-exporter\", instance=\"$instance\"}","format":"time_series","intervalFactor":2,"legendFormat":"Physical Memory","refId":"A"},{"expr":"(\n node_memory_internal_bytes{job=\"node-exporter\", instance=\"$instance\"} -\n node_memory_purgeable_bytes{job=\"node-exporter\", instance=\"$instance\"} +\n node_memory_wired_bytes{job=\"node-exporter\", instance=\"$instance\"} +\n node_memory_compressed_bytes{job=\"node-exporter\", instance=\"$instance\"}\n)\n","format":"time_series","intervalFactor":2,"legendFormat":"Memory Used","refId":"B"},{"expr":"(\n node_memory_internal_bytes{job=\"node-exporter\", instance=\"$instance\"} -\n node_memory_purgeable_bytes{job=\"node-exporter\", instance=\"$instance\"}\n)\n","format":"time_series","intervalFactor":2,"legendFormat":"App Memory","refId":"C"},{"expr":"node_memory_wired_bytes{job=\"node-exporter\", instance=\"$instance\"}","format":"time_series","intervalFactor":2,"legendFormat":"Wired Memory","refId":"D"},{"expr":"node_memory_compressed_bytes{job=\"node-exporter\", instance=\"$instance\"}","format":"time_series","intervalFactor":2,"legendFormat":"Compressed","refId":"E"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory Usage","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"datasource":"$datasource","fieldConfig":{"defaults":{"max":100,"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"rgba(50, 172, 45, 0.97)"},{"color":"rgba(237, 129, 40, 0.89)","value":80},{"color":"rgba(245, 54, 54, 0.9)","value":90}]},"unit":"percent"}},"gridPos":{},"id":5,"span":3,"targets":[{"expr":"(\n (\n avg(node_memory_internal_bytes{job=\"node-exporter\", instance=\"$instance\"}) -\n avg(node_memory_purgeable_bytes{job=\"node-exporter\", instance=\"$instance\"}) +\n avg(node_memory_wired_bytes{job=\"node-exporter\", instance=\"$instance\"}) +\n avg(node_memory_compressed_bytes{job=\"node-exporter\", instance=\"$instance\"})\n ) /\n avg(node_memory_total_bytes{job=\"node-exporter\", instance=\"$instance\"})\n)\n*\n100\n","format":"time_series","intervalFactor":2,"legendFormat":""}],"title":"Memory Usage","transparent":false,"type":"gauge"}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Memory","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":0,"fillGradient":0,"gridPos":{},"id":6,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[{"alias":"/ read| written/","yaxis":1},{"alias":"/ io time/","yaxis":2}],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"rate(node_disk_read_bytes_total{job=\"node-exporter\", instance=\"$instance\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","format":"time_series","intervalFactor":1,"legendFormat":"{{device}} read","refId":"A"},{"expr":"rate(node_disk_written_bytes_total{job=\"node-exporter\", instance=\"$instance\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","format":"time_series","intervalFactor":1,"legendFormat":"{{device}} written","refId":"B"},{"expr":"rate(node_disk_io_time_seconds_total{job=\"node-exporter\", instance=\"$instance\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","format":"time_series","intervalFactor":1,"legendFormat":"{{device}} io time","refId":"C"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Disk I/O","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"datasource":"$datasource","fieldConfig":{"defaults":{"custom":{},"thresholds":{"mode":"absolute","steps":[{"color":"green"},{"color":"yellow","value":0.8},{"color":"red","value":0.9}]},"unit":"decbytes"},"overrides":[{"matcher":{"id":"byName","options":"Mounted on"},"properties":[{"id":"custom.width","value":260}]},{"matcher":{"id":"byName","options":"Size"},"properties":[{"id":"custom.width","value":93}]},{"matcher":{"id":"byName","options":"Used"},"properties":[{"id":"custom.width","value":72}]},{"matcher":{"id":"byName","options":"Available"},"properties":[{"id":"custom.width","value":88}]},{"matcher":{"id":"byName","options":"Used, %"},"properties":[{"id":"unit","value":"percentunit"},{"id":"custom.displayMode","value":"gradient-gauge"},{"id":"max","value":1},{"id":"min","value":0}]}]},"gridPos":{},"id":7,"span":6,"targets":[{"expr":"max by (mountpoint) (node_filesystem_size_bytes{job=\"node-exporter\", instance=\"$instance\", fstype!=\"\", mountpoint!=\"\"})\n","format":"table","instant":true,"intervalFactor":2,"legendFormat":""},{"expr":"max by (mountpoint) (node_filesystem_avail_bytes{job=\"node-exporter\", instance=\"$instance\", fstype!=\"\", mountpoint!=\"\"})\n","format":"table","instant":true,"intervalFactor":2,"legendFormat":""}],"title":"Disk Space Usage","transformations":[{"id":"groupBy","options":{"fields":{"Value #A":{"aggregations":["lastNotNull"],"operation":"aggregate"},"Value #B":{"aggregations":["lastNotNull"],"operation":"aggregate"},"mountpoint":{"aggregations":[],"operation":"groupby"}}}},{"id":"merge","options":{}},{"id":"calculateField","options":{"alias":"Used","binary":{"left":"Value #A (lastNotNull)","operator":"-","reducer":"sum","right":"Value #B (lastNotNull)"},"mode":"binary","reduce":{"reducer":"sum"}}},{"id":"calculateField","options":{"alias":"Used, %","binary":{"left":"Used","operator":"/","reducer":"sum","right":"Value #A (lastNotNull)"},"mode":"binary","reduce":{"reducer":"sum"}}},{"id":"organize","options":{"excludeByName":{},"indexByName":{},"renameByName":{"Value #A (lastNotNull)":"Size","Value #B (lastNotNull)":"Available","mountpoint":"Mounted on"}}},{"id":"sortBy","options":{"fields":{},"sort":[{"field":"Mounted on"}]}}],"transparent":false,"type":"table"}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Disk","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","description":"Network received (bits/s)","fill":0,"fillGradient":0,"gridPos":{},"id":8,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"rate(node_network_receive_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__rate_interval]) * 8","format":"time_series","intervalFactor":1,"legendFormat":"{{device}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Network Received","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","description":"Network transmitted (bits/s)","fill":0,"fillGradient":0,"gridPos":{},"id":9,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"rate(node_network_transmit_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__rate_interval]) * 8","format":"time_series","intervalFactor":1,"legendFormat":"{{device}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Network Transmitted","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Network","titleSize":"h6","type":"row"}],"schemaVersion":14,"style":"dark","tags":["node-exporter-mixin"],"templating":{"list":[{"current":{"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{},"datasource":"$datasource","hide":0,"includeAll":false,"label":"Instance","multi":false,"name":"instance","options":[],"query":"label_values(node_uname_info{job=\"node-exporter\", sysname=\"Darwin\"}, instance)","refresh":2,"regex":"","sort":0,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Node Exporter / MacOS","version":0} \ No newline at end of file diff --git a/monitor/node-exporter/v1_ConfigMap_node-exporter-kube-prometh-nodes.yaml b/monitor/node-exporter/v1_ConfigMap_node-exporter-kube-prometh-nodes.yaml new file mode 100644 index 0000000..dcb230c --- /dev/null +++ b/monitor/node-exporter/v1_ConfigMap_node-exporter-kube-prometh-nodes.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/nodes.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: node-exporter-kube-prometh-nodes + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: node-exporter + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "node-exporter" + heritage: "Helm" +data: + nodes.json: |- + {"__inputs":[],"__requires":[],"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":1,"hideControls":false,"id":null,"links":[],"refresh":"30s","rows":[{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":2,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"(\n (1 - sum without (mode) (rate(node_cpu_seconds_total{job=\"node-exporter\", mode=~\"idle|iowait|steal\", instance=\"$instance\"}[$__rate_interval])))\n/ ignoring(cpu) group_left\n count without (cpu, mode) (node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\"})\n)\n","format":"time_series","intervalFactor":5,"legendFormat":"{{cpu}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU Usage","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"percentunit","label":null,"logBase":1,"max":1,"min":0,"show":true},{"format":"percentunit","label":null,"logBase":1,"max":1,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":0,"fillGradient":0,"gridPos":{},"id":3,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"node_load1{job=\"node-exporter\", instance=\"$instance\"}","format":"time_series","intervalFactor":2,"legendFormat":"1m load average","refId":"A"},{"expr":"node_load5{job=\"node-exporter\", instance=\"$instance\"}","format":"time_series","intervalFactor":2,"legendFormat":"5m load average","refId":"B"},{"expr":"node_load15{job=\"node-exporter\", instance=\"$instance\"}","format":"time_series","intervalFactor":2,"legendFormat":"15m load average","refId":"C"},{"expr":"count(node_cpu_seconds_total{job=\"node-exporter\", instance=\"$instance\", mode=\"idle\"})","format":"time_series","intervalFactor":2,"legendFormat":"logical cores","refId":"D"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Load Average","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"CPU","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":4,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":9,"stack":true,"steppedLine":false,"targets":[{"expr":"(\n node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\"}\n-\n node_memory_MemFree_bytes{job=\"node-exporter\", instance=\"$instance\"}\n-\n node_memory_Buffers_bytes{job=\"node-exporter\", instance=\"$instance\"}\n-\n node_memory_Cached_bytes{job=\"node-exporter\", instance=\"$instance\"}\n)\n","format":"time_series","intervalFactor":2,"legendFormat":"memory used","refId":"A"},{"expr":"node_memory_Buffers_bytes{job=\"node-exporter\", instance=\"$instance\"}","format":"time_series","intervalFactor":2,"legendFormat":"memory buffers","refId":"B"},{"expr":"node_memory_Cached_bytes{job=\"node-exporter\", instance=\"$instance\"}","format":"time_series","intervalFactor":2,"legendFormat":"memory cached","refId":"C"},{"expr":"node_memory_MemFree_bytes{job=\"node-exporter\", instance=\"$instance\"}","format":"time_series","intervalFactor":2,"legendFormat":"memory free","refId":"D"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory Usage","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"bytes","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"datasource":"$datasource","fieldConfig":{"defaults":{"max":100,"min":0,"thresholds":{"mode":"absolute","steps":[{"color":"rgba(50, 172, 45, 0.97)"},{"color":"rgba(237, 129, 40, 0.89)","value":80},{"color":"rgba(245, 54, 54, 0.9)","value":90}]},"unit":"percent"}},"gridPos":{},"id":5,"span":3,"targets":[{"expr":"100 -\n(\n avg(node_memory_MemAvailable_bytes{job=\"node-exporter\", instance=\"$instance\"}) /\n avg(node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\"})\n* 100\n)\n","format":"time_series","intervalFactor":2,"legendFormat":""}],"title":"Memory Usage","transparent":false,"type":"gauge"}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Memory","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":0,"fillGradient":0,"gridPos":{},"id":6,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[{"alias":"/ read| written/","yaxis":1},{"alias":"/ io time/","yaxis":2}],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"rate(node_disk_read_bytes_total{job=\"node-exporter\", instance=\"$instance\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","format":"time_series","intervalFactor":1,"legendFormat":"{{device}} read","refId":"A"},{"expr":"rate(node_disk_written_bytes_total{job=\"node-exporter\", instance=\"$instance\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","format":"time_series","intervalFactor":1,"legendFormat":"{{device}} written","refId":"B"},{"expr":"rate(node_disk_io_time_seconds_total{job=\"node-exporter\", instance=\"$instance\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])","format":"time_series","intervalFactor":1,"legendFormat":"{{device}} io time","refId":"C"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Disk I/O","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"Bps","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"percentunit","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"datasource":"$datasource","fieldConfig":{"defaults":{"custom":{},"thresholds":{"mode":"absolute","steps":[{"color":"green"},{"color":"yellow","value":0.8},{"color":"red","value":0.9}]},"unit":"decbytes"},"overrides":[{"matcher":{"id":"byName","options":"Mounted on"},"properties":[{"id":"custom.width","value":260}]},{"matcher":{"id":"byName","options":"Size"},"properties":[{"id":"custom.width","value":93}]},{"matcher":{"id":"byName","options":"Used"},"properties":[{"id":"custom.width","value":72}]},{"matcher":{"id":"byName","options":"Available"},"properties":[{"id":"custom.width","value":88}]},{"matcher":{"id":"byName","options":"Used, %"},"properties":[{"id":"unit","value":"percentunit"},{"id":"custom.displayMode","value":"gradient-gauge"},{"id":"max","value":1},{"id":"min","value":0}]}]},"gridPos":{},"id":7,"span":6,"targets":[{"expr":"max by (mountpoint) (node_filesystem_size_bytes{job=\"node-exporter\", instance=\"$instance\", fstype!=\"\", mountpoint!=\"\"})\n","format":"table","instant":true,"intervalFactor":2,"legendFormat":""},{"expr":"max by (mountpoint) (node_filesystem_avail_bytes{job=\"node-exporter\", instance=\"$instance\", fstype!=\"\", mountpoint!=\"\"})\n","format":"table","instant":true,"intervalFactor":2,"legendFormat":""}],"title":"Disk Space Usage","transformations":[{"id":"groupBy","options":{"fields":{"Value #A":{"aggregations":["lastNotNull"],"operation":"aggregate"},"Value #B":{"aggregations":["lastNotNull"],"operation":"aggregate"},"mountpoint":{"aggregations":[],"operation":"groupby"}}}},{"id":"merge","options":{}},{"id":"calculateField","options":{"alias":"Used","binary":{"left":"Value #A (lastNotNull)","operator":"-","reducer":"sum","right":"Value #B (lastNotNull)"},"mode":"binary","reduce":{"reducer":"sum"}}},{"id":"calculateField","options":{"alias":"Used, %","binary":{"left":"Used","operator":"/","reducer":"sum","right":"Value #A (lastNotNull)"},"mode":"binary","reduce":{"reducer":"sum"}}},{"id":"organize","options":{"excludeByName":{},"indexByName":{},"renameByName":{"Value #A (lastNotNull)":"Size","Value #B (lastNotNull)":"Available","mountpoint":"Mounted on"}}},{"id":"sortBy","options":{"fields":{},"sort":[{"field":"Mounted on"}]}}],"transparent":false,"type":"table"}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Disk","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","description":"Network received (bits/s)","fill":0,"fillGradient":0,"gridPos":{},"id":8,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"rate(node_network_receive_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__rate_interval]) * 8","format":"time_series","intervalFactor":1,"legendFormat":"{{device}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Network Received","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","description":"Network transmitted (bits/s)","fill":0,"fillGradient":0,"gridPos":{},"id":9,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"rate(node_network_transmit_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__rate_interval]) * 8","format":"time_series","intervalFactor":1,"legendFormat":"{{device}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Network Transmitted","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bps","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"bps","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Network","titleSize":"h6","type":"row"}],"schemaVersion":14,"style":"dark","tags":["node-exporter-mixin"],"templating":{"list":[{"current":{"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{},"datasource":"$datasource","hide":0,"includeAll":false,"label":"Instance","multi":false,"name":"instance","options":[],"query":"label_values(node_uname_info{job=\"node-exporter\", sysname!=\"Darwin\"}, instance)","refresh":2,"regex":"","sort":0,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Node Exporter / Nodes","version":0} \ No newline at end of file diff --git a/monitor/node-exporter/v1_ServiceAccount_node-exporter-prometheus-node-exporter.yaml b/monitor/node-exporter/v1_ServiceAccount_node-exporter-prometheus-node-exporter.yaml new file mode 100644 index 0000000..2bb87ea --- /dev/null +++ b/monitor/node-exporter/v1_ServiceAccount_node-exporter-prometheus-node-exporter.yaml @@ -0,0 +1,17 @@ +--- +# Source: kube-prometheus-stack/charts/prometheus-node-exporter/templates/serviceaccount.yaml +apiVersion: v1 +kind: ServiceAccount +metadata: + name: node-exporter-prometheus-node-exporter + namespace: vynil-monitor + labels: + helm.sh/chart: prometheus-node-exporter-4.26.0 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: prometheus-node-exporter + app.kubernetes.io/name: prometheus-node-exporter + app.kubernetes.io/instance: node-exporter + app.kubernetes.io/version: "1.7.0" + jobLabel: node-exporter + release: node-exporter \ No newline at end of file diff --git a/monitor/node-exporter/v1_Service_node-exporter-prometheus-node-exporter.yaml b/monitor/node-exporter/v1_Service_node-exporter-prometheus-node-exporter.yaml new file mode 100644 index 0000000..e06580c --- /dev/null +++ b/monitor/node-exporter/v1_Service_node-exporter-prometheus-node-exporter.yaml @@ -0,0 +1,28 @@ +# Source: kube-prometheus-stack/charts/prometheus-node-exporter/templates/service.yaml +apiVersion: v1 +kind: Service +metadata: + name: node-exporter-prometheus-node-exporter + namespace: vynil-monitor + labels: + helm.sh/chart: prometheus-node-exporter-4.26.0 + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/component: metrics + app.kubernetes.io/part-of: prometheus-node-exporter + app.kubernetes.io/name: prometheus-node-exporter + app.kubernetes.io/instance: node-exporter + app.kubernetes.io/version: "1.7.0" + jobLabel: node-exporter + release: node-exporter + annotations: + prometheus.io/scrape: "true" +spec: + type: ClusterIP + ports: + - port: 9100 + targetPort: 9100 + protocol: TCP + name: http-metrics + selector: + app.kubernetes.io/name: prometheus-node-exporter + app.kubernetes.io/instance: node-exporter \ No newline at end of file diff --git a/monitor/prometheus/datas.tf b/monitor/prometheus/datas.tf new file mode 100644 index 0000000..0bb6ac9 --- /dev/null +++ b/monitor/prometheus/datas.tf @@ -0,0 +1,212 @@ +locals { + authentik_url = "http://authentik.${var.domain}-auth.svc" + authentik_token = data.kubernetes_secret_v1.authentik.data["AUTHENTIK_BOOTSTRAP_TOKEN"] + common-labels = { + "vynil.solidite.fr/owner-name" = var.instance + "vynil.solidite.fr/owner-namespace" = var.namespace + "vynil.solidite.fr/owner-category" = var.category + "vynil.solidite.fr/owner-component" = var.component + "app.kubernetes.io/managed-by" = "vynil" + "app.kubernetes.io/instance" = var.instance + } + rb-patch = <<-EOF + - op: replace + path: /subjects/0/namespace + value: "${var.namespace}" + EOF +} + +data "kubernetes_secret_v1" "authentik" { + metadata { + name = "authentik" + namespace = "${var.domain}-auth" + } +} + +data "kustomization_overlay" "data" { + common_labels = local.common-labels + namespace = var.namespace + resources = [for file in fileset(path.module, "*.yaml"): file if file != "index.yaml" && length(regexall("ClusterRole",file))<1 && length(regexall("Service_prometheus",file))<1] + patches { + target { + kind = "ConfigMap" + name = "prometheus-kube-prometheus-grafana-datasource" + } + patch = <<-EOF + apiVersion: v1 + kind: ConfigMap + metadata: + name: prometheus-kube-prometheus-grafana-datasource + data: + datasource.yaml: |- + apiVersion: 1 + datasources: + - name: Prometheus + type: prometheus + uid: prometheus + url: http://${var.component}-${var.instance}.${var.namespace}:9090/ + access: proxy + isDefault: false + jsonData: + httpMethod: POST + timeInterval: 30s + EOF + } + patches { + target { + kind = "ServiceMonitor" + name = "prometheus-kube-prometheus-prometheus" + } + patch = <<-EOF + - op: replace + path: /spec/namespaceSelector/matchNames/0 + value: "${var.namespace}" + EOF + } + + patches { + target { + kind = "PrometheusRule" + name = "prometheus-kube-prometheus-prometheus" + } + patch = <<-EOF + apiVersion: monitoring.coreos.com/v1 + kind: PrometheusRule + metadata: + name: prometheus-kube-prometheus-prometheus + spec: + groups: + - name: prometheus + rules: + - alert: PrometheusBadConfig + expr: |- + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + max_over_time(prometheus_config_last_reload_successful{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) == 0 + - alert: PrometheusSDRefreshFailure + expr: increase(prometheus_sd_refresh_failures_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[10m]) > 0 + - alert: PrometheusNotificationQueueRunningFull + expr: |- + # Without min_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + ( + predict_linear(prometheus_notifications_queue_length{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m], 60 * 30) + > + min_over_time(prometheus_notifications_queue_capacity{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) + ) + - alert: PrometheusErrorSendingAlertsToSomeAlertmanagers + expr: |- + ( + rate(prometheus_notifications_errors_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) + / + rate(prometheus_notifications_sent_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) + ) + * 100 + > 1 + - alert: PrometheusNotConnectedToAlertmanagers + expr: |- + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + max_over_time(prometheus_notifications_alertmanagers_discovered{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) < 1 + - alert: PrometheusTSDBReloadsFailing + expr: increase(prometheus_tsdb_reloads_failures_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[3h]) > 0 + - alert: PrometheusTSDBCompactionsFailing + expr: increase(prometheus_tsdb_compactions_failed_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[3h]) > 0 + - alert: PrometheusNotIngestingSamples + expr: |- + ( + rate(prometheus_tsdb_head_samples_appended_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) <= 0 + and + ( + sum without(scrape_job) (prometheus_target_metadata_cache_entries{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}) > 0 + or + sum without(rule_group) (prometheus_rule_group_rules{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}) > 0 + ) + ) + - alert: PrometheusDuplicateTimestamps + expr: rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) > 0 + - alert: PrometheusOutOfOrderTimestamps + expr: rate(prometheus_target_scrapes_sample_out_of_order_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) > 0 + - alert: PrometheusRemoteStorageFailures + expr: |- + ( + (rate(prometheus_remote_storage_failed_samples_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m])) + / + ( + (rate(prometheus_remote_storage_failed_samples_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m])) + + + (rate(prometheus_remote_storage_succeeded_samples_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) or rate(prometheus_remote_storage_samples_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m])) + ) + ) + * 100 + > 1 + - alert: PrometheusRemoteWriteBehind + expr: |- + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + ( + max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) + - ignoring(remote_name, url) group_right + max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) + ) + > 120 + - alert: PrometheusRemoteWriteDesiredShards + expr: |- + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + ( + max_over_time(prometheus_remote_storage_shards_desired{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) + > + max_over_time(prometheus_remote_storage_shards_max{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) + ) + - alert: PrometheusRuleFailures + expr: increase(prometheus_rule_evaluation_failures_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) > 0 + - alert: PrometheusMissingRuleEvaluations + expr: increase(prometheus_rule_group_iterations_missed_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) > 0 + - alert: PrometheusTargetLimitHit + expr: increase(prometheus_target_scrape_pool_exceeded_target_limit_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) > 0 + - alert: PrometheusLabelLimitHit + expr: increase(prometheus_target_scrape_pool_exceeded_label_limits_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) > 0 + - alert: PrometheusScrapeBodySizeLimitHit + expr: increase(prometheus_target_scrapes_exceeded_body_size_limit_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) > 0 + - alert: PrometheusScrapeSampleLimitHit + expr: increase(prometheus_target_scrapes_exceeded_sample_limit_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) > 0 + - alert: PrometheusTargetSyncFailure + expr: increase(prometheus_target_sync_failed_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[30m]) > 0 + - alert: PrometheusHighQueryLoad + expr: avg_over_time(prometheus_engine_queries{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) / max_over_time(prometheus_engine_queries_concurrent_max{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}"}[5m]) > 0.8 + - alert: PrometheusErrorSendingAlertsToAnyAlertmanager + expr: |- + min without (alertmanager) ( + rate(prometheus_notifications_errors_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}",alertmanager!~``}[5m]) + / + rate(prometheus_notifications_sent_total{job="prometheus-kube-prometheus-prometheus",namespace="${var.namespace}",alertmanager!~``}[5m]) + ) + * 100 + > 3 + EOF + } + patches { + target { + kind = "ServiceMonitor" + name = "prometheus-community-prometheus-node-exporter" + } + patch = <<-EOF + - op: replace + path: /spec/selector/matchLabels/app.kubernetes.io~1instance + value: "${var.instance}" + EOF + } +} + +data "kustomization_overlay" "data_no_ns" { + resources = [for file in fileset(path.module, "*.yaml"): file if (length(regexall("ClusterRole",file))>0 || length(regexall("Service_prometheus",file))>0)] + + patches { + target { + kind = "ClusterRoleBinding" + name = "prometheus-kube-prometheus-prometheus" + } + patch = local.rb-patch + } +} diff --git a/monitor/prometheus/index.yaml b/monitor/prometheus/index.yaml new file mode 100644 index 0000000..d3024c9 --- /dev/null +++ b/monitor/prometheus/index.yaml @@ -0,0 +1,126 @@ +--- +apiVersion: vinyl.solidite.fr/v1beta1 +kind: Component +category: monitor +metadata: + name: prometheus + description: null +options: + app_group: + default: monitor + examples: + - monitor + type: string + logLevel: + default: info + examples: + - info + type: string + listenLocal: + default: false + examples: + - false + type: boolean + shards: + default: 1 + examples: + - 1 + type: integer + retention: + default: 10d + examples: + - 10d + type: string + enableAdminAPI: + default: false + examples: + - false + type: boolean + domain: + default: your-company + examples: + - your-company + type: string + issuer: + default: letsencrypt-prod + examples: + - letsencrypt-prod + type: string + replicas: + default: 1 + examples: + - 1 + type: integer + domain_name: + default: your_company.com + examples: + - your_company.com + type: string + sub_domain: + default: prometheus + examples: + - prometheus + type: string + ingress_class: + default: traefik + examples: + - traefik + type: string + images: + default: + prometheus: + pullPolicy: IfNotPresent + registry: quay.io + repository: prometheus/prometheus + tag: v2.49.1 + examples: + - prometheus: + pullPolicy: IfNotPresent + registry: quay.io + repository: prometheus/prometheus + tag: v2.49.1 + properties: + prometheus: + default: + pullPolicy: IfNotPresent + registry: quay.io + repository: prometheus/prometheus + tag: v2.49.1 + properties: + pullPolicy: + default: IfNotPresent + enum: + - Always + - Never + - IfNotPresent + type: string + registry: + default: quay.io + type: string + repository: + default: prometheus/prometheus + type: string + tag: + default: v2.49.1 + type: string + type: object + type: object + alertmanager: + default: alertmanager-alertmanager + examples: + - alertmanager-alertmanager + type: string +dependencies: +- dist: null + category: share + component: authentik-forward +providers: + kubernetes: true + authentik: true + kubectl: true + postgresql: null + mysql: null + restapi: true + http: true + gitea: null +tfaddtype: null diff --git a/monitor/prometheus/monitoring.coreos.com_v1_PrometheusRule_prometheus-kube-prometheus-kubelet.rules.yaml b/monitor/prometheus/monitoring.coreos.com_v1_PrometheusRule_prometheus-kube-prometheus-kubelet.rules.yaml new file mode 100644 index 0000000..21d7dd2 --- /dev/null +++ b/monitor/prometheus/monitoring.coreos.com_v1_PrometheusRule_prometheus-kube-prometheus-kubelet.rules.yaml @@ -0,0 +1,32 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubelet.rules.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-kube-prometheus-kubelet.rules + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus" + heritage: "Helm" +spec: + groups: + - name: kubelet.rules + rules: + - expr: histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le) * on (cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"}) + labels: + quantile: '0.99' + record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.9, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le) * on (cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"}) + labels: + quantile: '0.9' + record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile + - expr: histogram_quantile(0.5, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le) * on (cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"}) + labels: + quantile: '0.5' + record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile \ No newline at end of file diff --git a/monitor/prometheus/monitoring.coreos.com_v1_PrometheusRule_prometheus-kube-prometheus-kubernetes-system-kube-proxy.yaml b/monitor/prometheus/monitoring.coreos.com_v1_PrometheusRule_prometheus-kube-prometheus-kubernetes-system-kube-proxy.yaml new file mode 100644 index 0000000..da6588b --- /dev/null +++ b/monitor/prometheus/monitoring.coreos.com_v1_PrometheusRule_prometheus-kube-prometheus-kubernetes-system-kube-proxy.yaml @@ -0,0 +1,29 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/kubernetes-system-kube-proxy.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-kube-prometheus-kubernetes-system-kube-proxy + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus" + heritage: "Helm" +spec: + groups: + - name: kubernetes-system-kube-proxy + rules: + - alert: KubeProxyDown + annotations: + description: KubeProxy has disappeared from Prometheus target discovery. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeproxydown + summary: Target disappeared from Prometheus target discovery. + expr: absent(up{job="kube-proxy"} == 1) + for: 15m + labels: + severity: critical \ No newline at end of file diff --git a/monitor/prometheus/monitoring.coreos.com_v1_PrometheusRule_prometheus-kube-prometheus-prometheus.yaml b/monitor/prometheus/monitoring.coreos.com_v1_PrometheusRule_prometheus-kube-prometheus-prometheus.yaml new file mode 100644 index 0000000..22c148e --- /dev/null +++ b/monitor/prometheus/monitoring.coreos.com_v1_PrometheusRule_prometheus-kube-prometheus-prometheus.yaml @@ -0,0 +1,280 @@ +# Source: kube-prometheus-stack/templates/prometheus/rules-1.14/prometheus.yaml +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: prometheus-kube-prometheus-prometheus + namespace: vynil-monitor + labels: + app: kube-prometheus-stack + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus" + heritage: "Helm" +spec: + groups: + - name: prometheus + rules: + - alert: PrometheusBadConfig + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to reload its configuration. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusbadconfig + summary: Failed Prometheus configuration reload. + expr: |- + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + max_over_time(prometheus_config_last_reload_successful{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) == 0 + for: 10m + labels: + severity: critical + - alert: PrometheusSDRefreshFailure + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to refresh SD with mechanism {{$labels.mechanism}}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheussdrefreshfailure + summary: Failed Prometheus SD refresh. + expr: increase(prometheus_sd_refresh_failures_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[10m]) > 0 + for: 20m + labels: + severity: warning + - alert: PrometheusNotificationQueueRunningFull + annotations: + description: Alert notification queue of Prometheus {{$labels.namespace}}/{{$labels.pod}} is running full. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusnotificationqueuerunningfull + summary: Prometheus alert notification queue predicted to run full in less than 30m. + expr: |- + # Without min_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + ( + predict_linear(prometheus_notifications_queue_length{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m], 60 * 30) + > + min_over_time(prometheus_notifications_queue_capacity{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) + ) + for: 15m + labels: + severity: warning + - alert: PrometheusErrorSendingAlertsToSomeAlertmanagers + annotations: + description: '{{ printf "%.1f" $value }}% errors while sending alerts from Prometheus {{$labels.namespace}}/{{$labels.pod}} to Alertmanager {{$labels.alertmanager}}.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheuserrorsendingalertstosomealertmanagers + summary: Prometheus has encountered more than 1% errors sending alerts to a specific Alertmanager. + expr: |- + ( + rate(prometheus_notifications_errors_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) + / + rate(prometheus_notifications_sent_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) + ) + * 100 + > 1 + for: 15m + labels: + severity: warning + - alert: PrometheusNotConnectedToAlertmanagers + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not connected to any Alertmanagers. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusnotconnectedtoalertmanagers + summary: Prometheus is not connected to any Alertmanagers. + expr: |- + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + max_over_time(prometheus_notifications_alertmanagers_discovered{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) < 1 + for: 10m + labels: + severity: warning + - alert: PrometheusTSDBReloadsFailing + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected {{$value | humanize}} reload failures over the last 3h. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustsdbreloadsfailing + summary: Prometheus has issues reloading blocks from disk. + expr: increase(prometheus_tsdb_reloads_failures_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[3h]) > 0 + for: 4h + labels: + severity: warning + - alert: PrometheusTSDBCompactionsFailing + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected {{$value | humanize}} compaction failures over the last 3h. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustsdbcompactionsfailing + summary: Prometheus has issues compacting blocks. + expr: increase(prometheus_tsdb_compactions_failed_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[3h]) > 0 + for: 4h + labels: + severity: warning + - alert: PrometheusNotIngestingSamples + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not ingesting samples. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusnotingestingsamples + summary: Prometheus is not ingesting samples. + expr: |- + ( + rate(prometheus_tsdb_head_samples_appended_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) <= 0 + and + ( + sum without(scrape_job) (prometheus_target_metadata_cache_entries{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}) > 0 + or + sum without(rule_group) (prometheus_rule_group_rules{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}) > 0 + ) + ) + for: 10m + labels: + severity: warning + - alert: PrometheusDuplicateTimestamps + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping {{ printf "%.4g" $value }} samples/s with different values but duplicated timestamp. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusduplicatetimestamps + summary: Prometheus is dropping samples with duplicate timestamps. + expr: rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) > 0 + for: 10m + labels: + severity: warning + - alert: PrometheusOutOfOrderTimestamps + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping {{ printf "%.4g" $value }} samples/s with timestamps arriving out of order. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusoutofordertimestamps + summary: Prometheus drops samples with out-of-order timestamps. + expr: rate(prometheus_target_scrapes_sample_out_of_order_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) > 0 + for: 10m + labels: + severity: warning + - alert: PrometheusRemoteStorageFailures + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} failed to send {{ printf "%.1f" $value }}% of the samples to {{ $labels.remote_name}}:{{ $labels.url }} + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotestoragefailures + summary: Prometheus fails to send samples to remote storage. + expr: |- + ( + (rate(prometheus_remote_storage_failed_samples_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m])) + / + ( + (rate(prometheus_remote_storage_failed_samples_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m])) + + + (rate(prometheus_remote_storage_succeeded_samples_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) or rate(prometheus_remote_storage_samples_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m])) + ) + ) + * 100 + > 1 + for: 15m + labels: + severity: critical + - alert: PrometheusRemoteWriteBehind + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write is {{ printf "%.1f" $value }}s behind for {{ $labels.remote_name}}:{{ $labels.url }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotewritebehind + summary: Prometheus remote write is behind. + expr: |- + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + ( + max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) + - ignoring(remote_name, url) group_right + max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) + ) + > 120 + for: 15m + labels: + severity: critical + - alert: PrometheusRemoteWriteDesiredShards + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write desired shards calculation wants to run {{ $value }} shards for queue {{ $labels.remote_name}}:{{ $labels.url }}, which is more than the max of {{ printf `prometheus_remote_storage_shards_max{instance="%s",job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}` $labels.instance | query | first | value }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotewritedesiredshards + summary: Prometheus remote write desired shards calculation wants to run more than configured max shards. + expr: |- + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + ( + max_over_time(prometheus_remote_storage_shards_desired{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) + > + max_over_time(prometheus_remote_storage_shards_max{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) + ) + for: 15m + labels: + severity: warning + - alert: PrometheusRuleFailures + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to evaluate {{ printf "%.0f" $value }} rules in the last 5m. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusrulefailures + summary: Prometheus is failing rule evaluations. + expr: increase(prometheus_rule_evaluation_failures_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) > 0 + for: 15m + labels: + severity: critical + - alert: PrometheusMissingRuleEvaluations + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has missed {{ printf "%.0f" $value }} rule group evaluations in the last 5m. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusmissingruleevaluations + summary: Prometheus is missing rule evaluations due to slow rule group evaluation. + expr: increase(prometheus_rule_group_iterations_missed_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) > 0 + for: 15m + labels: + severity: warning + - alert: PrometheusTargetLimitHit + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has dropped {{ printf "%.0f" $value }} targets because the number of targets exceeded the configured target_limit. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustargetlimithit + summary: Prometheus has dropped targets because some scrape configs have exceeded the targets limit. + expr: increase(prometheus_target_scrape_pool_exceeded_target_limit_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) > 0 + for: 15m + labels: + severity: warning + - alert: PrometheusLabelLimitHit + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has dropped {{ printf "%.0f" $value }} targets because some samples exceeded the configured label_limit, label_name_length_limit or label_value_length_limit. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheuslabellimithit + summary: Prometheus has dropped targets because some scrape configs have exceeded the labels limit. + expr: increase(prometheus_target_scrape_pool_exceeded_label_limits_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) > 0 + for: 15m + labels: + severity: warning + - alert: PrometheusScrapeBodySizeLimitHit + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed {{ printf "%.0f" $value }} scrapes in the last 5m because some targets exceeded the configured body_size_limit. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusscrapebodysizelimithit + summary: Prometheus has dropped some targets that exceeded body size limit. + expr: increase(prometheus_target_scrapes_exceeded_body_size_limit_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) > 0 + for: 15m + labels: + severity: warning + - alert: PrometheusScrapeSampleLimitHit + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed {{ printf "%.0f" $value }} scrapes in the last 5m because some targets exceeded the configured sample_limit. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusscrapesamplelimithit + summary: Prometheus has failed scrapes that have exceeded the configured sample limit. + expr: increase(prometheus_target_scrapes_exceeded_sample_limit_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) > 0 + for: 15m + labels: + severity: warning + - alert: PrometheusTargetSyncFailure + annotations: + description: '{{ printf "%.0f" $value }} targets in Prometheus {{$labels.namespace}}/{{$labels.pod}} have failed to sync because invalid configuration was supplied.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustargetsyncfailure + summary: Prometheus has failed to sync targets. + expr: increase(prometheus_target_sync_failed_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[30m]) > 0 + for: 5m + labels: + severity: critical + - alert: PrometheusHighQueryLoad + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} query API has less than 20% available capacity in its query engine for the last 15 minutes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheushighqueryload + summary: Prometheus is reaching its maximum capacity serving concurrent requests. + expr: avg_over_time(prometheus_engine_queries{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) / max_over_time(prometheus_engine_queries_concurrent_max{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor"}[5m]) > 0.8 + for: 15m + labels: + severity: warning + - alert: PrometheusErrorSendingAlertsToAnyAlertmanager + annotations: + description: '{{ printf "%.1f" $value }}% minimum errors while sending alerts from Prometheus {{$labels.namespace}}/{{$labels.pod}} to any Alertmanager.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheuserrorsendingalertstoanyalertmanager + summary: Prometheus encounters more than 3% errors sending alerts to any Alertmanager. + expr: |- + min without (alertmanager) ( + rate(prometheus_notifications_errors_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor",alertmanager!~``}[5m]) + / + rate(prometheus_notifications_sent_total{job="prometheus-kube-prometheus-prometheus",namespace="vynil-monitor",alertmanager!~``}[5m]) + ) + * 100 + > 3 + for: 15m + labels: + severity: critical \ No newline at end of file diff --git a/monitor/prometheus/monitoring.coreos.com_v1_ServiceMonitor_prometheus-kube-prometheus-coredns.yaml b/monitor/prometheus/monitoring.coreos.com_v1_ServiceMonitor_prometheus-kube-prometheus-coredns.yaml new file mode 100644 index 0000000..f3f664d --- /dev/null +++ b/monitor/prometheus/monitoring.coreos.com_v1_ServiceMonitor_prometheus-kube-prometheus-coredns.yaml @@ -0,0 +1,29 @@ +# Source: kube-prometheus-stack/templates/exporters/core-dns/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: prometheus-kube-prometheus-coredns + namespace: vynil-monitor + labels: + app: kube-prometheus-stack-coredns + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus" + heritage: "Helm" +spec: + jobLabel: jobLabel + + selector: + matchLabels: + app: kube-prometheus-stack-coredns + release: "prometheus" + namespaceSelector: + matchNames: + - "kube-system" + endpoints: + - port: http-metrics + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token \ No newline at end of file diff --git a/monitor/prometheus/monitoring.coreos.com_v1_ServiceMonitor_prometheus-kube-prometheus-kube-proxy.yaml b/monitor/prometheus/monitoring.coreos.com_v1_ServiceMonitor_prometheus-kube-prometheus-kube-proxy.yaml new file mode 100644 index 0000000..af7db6a --- /dev/null +++ b/monitor/prometheus/monitoring.coreos.com_v1_ServiceMonitor_prometheus-kube-prometheus-kube-proxy.yaml @@ -0,0 +1,29 @@ +# Source: kube-prometheus-stack/templates/exporters/kube-proxy/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: prometheus-kube-prometheus-kube-proxy + namespace: vynil-monitor + labels: + app: kube-prometheus-stack-kube-proxy + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus" + heritage: "Helm" +spec: + jobLabel: jobLabel + + selector: + matchLabels: + app: kube-prometheus-stack-kube-proxy + release: "prometheus" + namespaceSelector: + matchNames: + - "kube-system" + endpoints: + - port: http-metrics + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token \ No newline at end of file diff --git a/monitor/prometheus/monitoring.coreos.com_v1_ServiceMonitor_prometheus-kube-prometheus-kubelet.yaml b/monitor/prometheus/monitoring.coreos.com_v1_ServiceMonitor_prometheus-kube-prometheus-kubelet.yaml new file mode 100644 index 0000000..63b06c1 --- /dev/null +++ b/monitor/prometheus/monitoring.coreos.com_v1_ServiceMonitor_prometheus-kube-prometheus-kubelet.yaml @@ -0,0 +1,95 @@ +# Source: kube-prometheus-stack/templates/exporters/kubelet/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: prometheus-kube-prometheus-kubelet + namespace: vynil-monitor + labels: + app: kube-prometheus-stack-kubelet + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus" + heritage: "Helm" +spec: + + attachMetadata: + node: false + endpoints: + - port: https-metrics + scheme: https + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + insecureSkipVerify: true + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + honorLabels: true + honorTimestamps: true + relabelings: + - action: replace + sourceLabels: + - __metrics_path__ + targetLabel: metrics_path + - port: https-metrics + scheme: https + path: /metrics/cadvisor + honorLabels: true + honorTimestamps: true + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + insecureSkipVerify: true + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + metricRelabelings: + - action: drop + regex: container_cpu_(cfs_throttled_seconds_total|load_average_10s|system_seconds_total|user_seconds_total) + sourceLabels: + - __name__ + - action: drop + regex: container_fs_(io_current|io_time_seconds_total|io_time_weighted_seconds_total|reads_merged_total|sector_reads_total|sector_writes_total|writes_merged_total) + sourceLabels: + - __name__ + - action: drop + regex: container_memory_(mapped_file|swap) + sourceLabels: + - __name__ + - action: drop + regex: container_(file_descriptors|tasks_state|threads_max) + sourceLabels: + - __name__ + - action: drop + regex: container_spec.* + sourceLabels: + - __name__ + - action: drop + regex: .+; + sourceLabels: + - id + - pod + relabelings: + - action: replace + sourceLabels: + - __metrics_path__ + targetLabel: metrics_path + - port: https-metrics + scheme: https + path: /metrics/probes + honorLabels: true + honorTimestamps: true + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + insecureSkipVerify: true + bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + relabelings: + - action: replace + sourceLabels: + - __metrics_path__ + targetLabel: metrics_path + jobLabel: k8s-app + namespaceSelector: + matchNames: + - kube-system + selector: + matchLabels: + app.kubernetes.io/name: kubelet + k8s-app: kubelet \ No newline at end of file diff --git a/monitor/prometheus/monitoring.coreos.com_v1_ServiceMonitor_prometheus-kube-prometheus-prometheus.yaml b/monitor/prometheus/monitoring.coreos.com_v1_ServiceMonitor_prometheus-kube-prometheus-prometheus.yaml new file mode 100644 index 0000000..d5977c5 --- /dev/null +++ b/monitor/prometheus/monitoring.coreos.com_v1_ServiceMonitor_prometheus-kube-prometheus-prometheus.yaml @@ -0,0 +1,32 @@ +# Source: kube-prometheus-stack/templates/prometheus/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: prometheus-kube-prometheus-prometheus + namespace: vynil-monitor + labels: + app: kube-prometheus-stack-prometheus + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus" + heritage: "Helm" +spec: + + selector: + matchLabels: + app: kube-prometheus-stack-prometheus + release: "prometheus" + self-monitor: "true" + namespaceSelector: + matchNames: + - "vynil-monitor" + endpoints: + - port: http-web + path: "/metrics" + - port: reloader-web + scheme: http + path: "/metrics" \ No newline at end of file diff --git a/monitor/prometheus/presentation.tf b/monitor/prometheus/presentation.tf new file mode 100644 index 0000000..2f42d6e --- /dev/null +++ b/monitor/prometheus/presentation.tf @@ -0,0 +1,75 @@ +locals { + dns_name = "${var.sub_domain}.${var.domain_name}" + dns_names = [local.dns_name] + app_name = var.component == var.instance ? var.instance : format("%s-%s", var.component, var.instance) + icon = "favicon.ico" + request_headers = { + "Content-Type" = "application/json" + Authorization = "Bearer ${data.kubernetes_secret_v1.authentik.data["AUTHENTIK_BOOTSTRAP_TOKEN"]}" + } + service = { + "name" = "prometheus-operated" + "port" = { + "number" = 9090 + } + } +} + +module "ingress" { + source = "git::https://git.solidite.fr/vynil/kydah-modules.git//ingress" + component = "" + instance = var.instance + namespace = var.namespace + issuer = var.issuer + ingress_class = var.ingress_class + labels = local.common-labels + dns_names = local.dns_names + middlewares = [module.forward.middleware] + services = [local.service] + providers = { + kubectl = kubectl + } +} + +module "application" { + source = "git::https://git.solidite.fr/vynil/kydah-modules.git//application" + component = var.component + instance = var.instance + app_group = var.app_group + dns_name = local.dns_name + icon = local.icon + protocol_provider = module.forward.provider-id + providers = { + authentik = authentik + } +} + +provider "restapi" { + uri = "http://authentik.${var.domain}-auth.svc/api/v3/" + headers = local.request_headers + create_method = "PATCH" + update_method = "PATCH" + destroy_method = "PATCH" + write_returns_object = true + id_attribute = "name" +} + +module "forward" { + source = "git::https://git.solidite.fr/vynil/kydah-modules.git//forward" + component = var.component + instance = var.instance + domain = var.domain + namespace = var.namespace + ingress_class = var.ingress_class + labels = local.common-labels + dns_names = local.dns_names + service = local.service + icon = local.icon + request_headers = local.request_headers + providers = { + restapi = restapi + http = http + kubectl = kubectl + authentik = authentik + } +} diff --git a/monitor/prometheus/prometheus.tf b/monitor/prometheus/prometheus.tf new file mode 100644 index 0000000..2e1ecdb --- /dev/null +++ b/monitor/prometheus/prometheus.tf @@ -0,0 +1,62 @@ +resource "kubectl_manifest" "prometheus" { + yaml_body = <<-EOF + apiVersion: monitoring.coreos.com/v1 + kind: Prometheus + metadata: + name: prometheus + namespace: "${var.namespace}" + labels: ${jsonencode(local.common-labels)} + spec: + image: "${var.images.prometheus.registry}/${var.images.prometheus.repository}:${var.images.prometheus.tag}" + version: ${var.images.prometheus.tag} + externalUrl: http://${var.component}-${var.instance}.${var.namespace}:9090 + replicas: ${var.replicas} + shards: ${var.shards} + logLevel: ${var.logLevel} + listenLocal: ${var.listenLocal} + enableAdminAPI: ${var.enableAdminAPI} + retention: "${var.retention}" + tsdb: + outOfOrderTimeWindow: 0s + walCompression: true + routePrefix: "/" + alerting: + alertmanagers: + - namespace: ${var.namespace} + name: ${var.alertmanager} + port: http-web + pathPrefix: "/" + apiVersion: v2 + scrapeConfigNamespaceSelector: {} + scrapeConfigSelector: + matchLabels: + app.kubernetes.io/managed-by: vynil + serviceMonitorNamespaceSelector: {} + serviceMonitorSelector: + matchLabels: + app.kubernetes.io/managed-by: vynil + podMonitorNamespaceSelector: {} + podMonitorSelector: + matchLabels: + app.kubernetes.io/managed-by: vynil + probeNamespaceSelector: {} + probeSelector: + matchLabels: + app.kubernetes.io/managed-by: vynil + ruleNamespaceSelector: {} + ruleSelector: + matchLabels: + app.kubernetes.io/managed-by: vynil + serviceAccountName: prometheus-kube-prometheus-prometheus + securityContext: + fsGroup: 2000 + runAsGroup: 2000 + runAsNonRoot: true + runAsUser: 1000 + seccompProfile: + type: RuntimeDefault + + portName: http-web + hostNetwork: false + EOF +} diff --git a/monitor/prometheus/rbac.authorization.k8s.io_v1_ClusterRoleBinding_prometheus-kube-prometheus-prometheus.yaml b/monitor/prometheus/rbac.authorization.k8s.io_v1_ClusterRoleBinding_prometheus-kube-prometheus-prometheus.yaml new file mode 100644 index 0000000..de46174 --- /dev/null +++ b/monitor/prometheus/rbac.authorization.k8s.io_v1_ClusterRoleBinding_prometheus-kube-prometheus-prometheus.yaml @@ -0,0 +1,23 @@ +# Source: kube-prometheus-stack/templates/prometheus/clusterrolebinding.yaml +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + name: prometheus-kube-prometheus-prometheus + labels: + app: kube-prometheus-stack-prometheus + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus" + heritage: "Helm" +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: prometheus-kube-prometheus-prometheus +subjects: + - kind: ServiceAccount + name: prometheus-kube-prometheus-prometheus + namespace: vynil-monitor \ No newline at end of file diff --git a/monitor/prometheus/rbac.authorization.k8s.io_v1_ClusterRole_prometheus-kube-prometheus-prometheus.yaml b/monitor/prometheus/rbac.authorization.k8s.io_v1_ClusterRole_prometheus-kube-prometheus-prometheus.yaml new file mode 100644 index 0000000..cb0e92a --- /dev/null +++ b/monitor/prometheus/rbac.authorization.k8s.io_v1_ClusterRole_prometheus-kube-prometheus-prometheus.yaml @@ -0,0 +1,33 @@ +# Source: kube-prometheus-stack/templates/prometheus/clusterrole.yaml +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: prometheus-kube-prometheus-prometheus + labels: + app: kube-prometheus-stack-prometheus + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus" + heritage: "Helm" +rules: +# This permission are not in the kube-prometheus repo +# they're grabbed from https://github.com/prometheus/prometheus/blob/master/documentation/examples/rbac-setup.yml +- apiGroups: [""] + resources: + - nodes + - nodes/metrics + - services + - endpoints + - pods + verbs: ["get", "list", "watch"] +- apiGroups: + - "networking.k8s.io" + resources: + - ingresses + verbs: ["get", "list", "watch"] +- nonResourceURLs: ["/metrics", "/metrics/cadvisor"] + verbs: ["get"] \ No newline at end of file diff --git a/monitor/prometheus/ressources_no_ns.tf b/monitor/prometheus/ressources_no_ns.tf new file mode 100644 index 0000000..9fa58b7 --- /dev/null +++ b/monitor/prometheus/ressources_no_ns.tf @@ -0,0 +1,45 @@ + +# first loop through resources in ids_prio[0] +resource "kustomization_resource" "pre_no_ns" { + for_each = data.kustomization_overlay.data_no_ns.ids_prio[0] + + manifest = ( + contains(["_/Secret"], regex("(?P.*/.*)/.*/.*", each.value)["group_kind"]) + ? sensitive(data.kustomization_overlay.data_no_ns.manifests[each.value]) + : data.kustomization_overlay.data_no_ns.manifests[each.value] + ) +} + +# then loop through resources in ids_prio[1] +# and set an explicit depends_on on kustomization_resource.pre +# wait 2 minutes for any deployment or daemonset to become ready +resource "kustomization_resource" "main_no_ns" { + for_each = data.kustomization_overlay.data_no_ns.ids_prio[1] + + manifest = ( + contains(["_/Secret"], regex("(?P.*/.*)/.*/.*", each.value)["group_kind"]) + ? sensitive(data.kustomization_overlay.data_no_ns.manifests[each.value]) + : data.kustomization_overlay.data_no_ns.manifests[each.value] + ) + wait = true + timeouts { + create = "5m" + update = "5m" + } + + depends_on = [kustomization_resource.pre_no_ns] +} + +# finally, loop through resources in ids_prio[2] +# and set an explicit depends_on on kustomization_resource.main +resource "kustomization_resource" "post_no_ns" { + for_each = data.kustomization_overlay.data_no_ns.ids_prio[2] + + manifest = ( + contains(["_/Secret"], regex("(?P.*/.*)/.*/.*", each.value)["group_kind"]) + ? sensitive(data.kustomization_overlay.data_no_ns.manifests[each.value]) + : data.kustomization_overlay.data_no_ns.manifests[each.value] + ) + + depends_on = [kustomization_resource.main_no_ns] +} diff --git a/monitor/prometheus/svc.tf b/monitor/prometheus/svc.tf new file mode 100644 index 0000000..3b6bab6 --- /dev/null +++ b/monitor/prometheus/svc.tf @@ -0,0 +1,33 @@ +locals { + svc-label = merge(local.common-labels, { + "app" = "kube-prometheus-stack-prometheus" + "release" = "prometheus" + "self-monitor" = "true" + + }) +} +resource "kubectl_manifest" "svc" { + yaml_body = <<-EOF + apiVersion: v1 + kind: Service + metadata: + name: "${var.component}-${var.instance}" + namespace: "${var.namespace}" + labels: ${jsonencode(local.svc-label)} + spec: + ports: + - name: http-web + port: 9090 + targetPort: 9090 + - name: reloader-web + appProtocol: http + port: 8080 + targetPort: reloader-web + publishNotReadyAddresses: false + selector: + app.kubernetes.io/name: prometheus + operator.prometheus.io/name: ${kubectl_manifest.prometheus.name} + sessionAffinity: None + type: "ClusterIP" + EOF +} diff --git a/monitor/prometheus/v1_ConfigMap_prometheus-kube-prometheus-grafana-datasource.yaml b/monitor/prometheus/v1_ConfigMap_prometheus-kube-prometheus-grafana-datasource.yaml new file mode 100644 index 0000000..dff3f55 --- /dev/null +++ b/monitor/prometheus/v1_ConfigMap_prometheus-kube-prometheus-grafana-datasource.yaml @@ -0,0 +1,38 @@ +# Source: kube-prometheus-stack/templates/grafana/configmaps-datasources.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + name: prometheus-kube-prometheus-grafana-datasource + namespace: vynil-monitor + labels: + grafana_datasource: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus" + heritage: "Helm" +data: + datasource.yaml: |- + apiVersion: 1 + datasources: + - name: Prometheus + type: prometheus + uid: prometheus + url: http://prometheus-kube-prometheus-prometheus.vynil-monitor:9090/ + access: proxy + isDefault: true + jsonData: + httpMethod: POST + timeInterval: 30s + - name: Alertmanager + type: alertmanager + uid: alertmanager + url: http://prometheus-kube-prometheus-alertmanager.vynil-monitor:9093/ + access: proxy + jsonData: + handleGrafanaManagedAlerts: false + implementation: prometheus \ No newline at end of file diff --git a/monitor/prometheus/v1_ConfigMap_prometheus-kube-prometheus-k8s-coredns.yaml b/monitor/prometheus/v1_ConfigMap_prometheus-kube-prometheus-k8s-coredns.yaml new file mode 100644 index 0000000..1745662 --- /dev/null +++ b/monitor/prometheus/v1_ConfigMap_prometheus-kube-prometheus-k8s-coredns.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/k8s-coredns.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: prometheus-kube-prometheus-k8s-coredns + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus" + heritage: "Helm" +data: + k8s-coredns.json: |- + {"annotations":{"list":[{"builtIn":1,"datasource":"-- Grafana --","enable":true,"hide":true,"iconColor":"rgba(0, 211, 255, 1)","name":"Annotations & Alerts","type":"dashboard"}]},"description":"A dashboard for the CoreDNS DNS server with updated metrics for version 1.7.0+. Based on the CoreDNS dashboard by buhay.","editable":true,"gnetId":12539,"graphTooltip":0,"iteration":1603798405693,"links":[{"icon":"external link","tags":[],"targetBlank":true,"title":"CoreDNS.io","type":"link","url":"https://coredns.io"}],"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","editable":true,"error":false,"fieldConfig":{"defaults":{"custom":{},"links":[],"mappings":[],"thresholds":{"mode":"absolute","steps":[{"color":"green","value":null},{"color":"red","value":80}]}},"overrides":[]},"fill":1,"fillGradient":0,"grid":{},"gridPos":{"h":7,"w":8,"x":0,"y":0},"hiddenSeries":false,"id":2,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"7.2.0","pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"total","yaxis":2}],"spaceLength":10,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(rate(coredns_dns_request_count_total{job=~\"$job\",instance=~\"$instance\"}[5m])) by (proto) or\nsum(rate(coredns_dns_requests_total{job=~\"$job\",instance=~\"$instance\"}[5m])) by (proto)","format":"time_series","interval":"","intervalFactor":2,"legendFormat":"{{ proto }}","refId":"A","step":60}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Requests (total)","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","logBase":1,"max":null,"min":0,"show":true},{"format":"pps","logBase":1,"max":null,"min":0,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","editable":true,"error":false,"fieldConfig":{"defaults":{"custom":{},"links":[]},"overrides":[]},"fill":1,"fillGradient":0,"grid":{},"gridPos":{"h":7,"w":8,"x":8,"y":0},"hiddenSeries":false,"id":4,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"7.2.0","pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"total","yaxis":2},{"alias":"other","yaxis":2}],"spaceLength":10,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(rate(coredns_dns_request_type_count_total{job=~\"$job\",instance=~\"$instance\"}[5m])) by (type) or \nsum(rate(coredns_dns_requests_total{job=~\"$job\",instance=~\"$instance\"}[5m])) by (type)","interval":"","intervalFactor":2,"legendFormat":"{{ type }}","refId":"A","step":60}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Requests (by qtype)","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","logBase":1,"max":null,"min":0,"show":true},{"format":"pps","logBase":1,"max":null,"min":0,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","editable":true,"error":false,"fieldConfig":{"defaults":{"custom":{},"links":[]},"overrides":[]},"fill":1,"fillGradient":0,"grid":{},"gridPos":{"h":7,"w":8,"x":16,"y":0},"hiddenSeries":false,"id":6,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"7.2.0","pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"total","yaxis":2}],"spaceLength":10,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(rate(coredns_dns_request_count_total{job=~\"$job\",instance=~\"$instance\"}[5m])) by (zone) or\nsum(rate(coredns_dns_requests_total{job=~\"$job\",instance=~\"$instance\"}[5m])) by (zone)","interval":"","intervalFactor":2,"legendFormat":"{{ zone }}","refId":"A","step":60}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Requests (by zone)","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","logBase":1,"max":null,"min":0,"show":true},{"format":"pps","logBase":1,"max":null,"min":0,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","editable":true,"error":false,"fieldConfig":{"defaults":{"custom":{},"links":[]},"overrides":[]},"fill":1,"fillGradient":0,"grid":{},"gridPos":{"h":7,"w":12,"x":0,"y":7},"hiddenSeries":false,"id":8,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"7.2.0","pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"total","yaxis":2}],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(coredns_dns_request_do_count_total{job=~\"$job\",instance=~\"$instance\"}[5m])) or\nsum(rate(coredns_dns_do_requests_total{job=~\"$job\",instance=~\"$instance\"}[5m]))","interval":"","intervalFactor":2,"legendFormat":"DO","refId":"A","step":40},{"expr":"sum(rate(coredns_dns_request_count_total{job=~\"$job\",instance=~\"$instance\"}[5m])) or\nsum(rate(coredns_dns_requests_total{job=~\"$job\",instance=~\"$instance\"}[5m]))","interval":"","intervalFactor":2,"legendFormat":"total","refId":"B","step":40}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Requests (DO bit)","tooltip":{"shared":true,"sort":2,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","logBase":1,"max":null,"min":0,"show":true},{"format":"pps","logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","editable":true,"error":false,"fieldConfig":{"defaults":{"custom":{},"links":[]},"overrides":[]},"fill":1,"fillGradient":0,"grid":{},"gridPos":{"h":7,"w":6,"x":12,"y":7},"hiddenSeries":false,"id":10,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"7.2.0","pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"tcp:90","yaxis":2},{"alias":"tcp:99 ","yaxis":2},{"alias":"tcp:50","yaxis":2}],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(coredns_dns_request_size_bytes_bucket{job=~\"$job\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto))","interval":"","intervalFactor":2,"legendFormat":"{{ proto }}:99 ","refId":"A","step":60},{"expr":"histogram_quantile(0.90, sum(rate(coredns_dns_request_size_bytes_bucket{job=~\"$job\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto))","intervalFactor":2,"legendFormat":"{{ proto }}:90","refId":"B","step":60},{"expr":"histogram_quantile(0.50, sum(rate(coredns_dns_request_size_bytes_bucket{job=~\"$job\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto))","intervalFactor":2,"legendFormat":"{{ proto }}:50","refId":"C","step":60}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Requests (size, udp)","tooltip":{"shared":true,"sort":0,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","logBase":1,"max":null,"min":0,"show":true},{"format":"short","logBase":1,"max":null,"min":0,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","editable":true,"error":false,"fieldConfig":{"defaults":{"custom":{},"links":[]},"overrides":[]},"fill":1,"fillGradient":0,"grid":{},"gridPos":{"h":7,"w":6,"x":18,"y":7},"hiddenSeries":false,"id":12,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"7.2.0","pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"tcp:90","yaxis":1},{"alias":"tcp:99 ","yaxis":1},{"alias":"tcp:50","yaxis":1}],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(coredns_dns_request_size_bytes_bucket{job=~\"$job\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto))","format":"time_series","interval":"","intervalFactor":2,"legendFormat":"{{ proto }}:99 ","refId":"A","step":60},{"expr":"histogram_quantile(0.90, sum(rate(coredns_dns_request_size_bytes_bucket{job=~\"$job\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto))","format":"time_series","interval":"","intervalFactor":2,"legendFormat":"{{ proto }}:90","refId":"B","step":60},{"expr":"histogram_quantile(0.50, sum(rate(coredns_dns_request_size_bytes_bucket{job=~\"$job\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto))","format":"time_series","interval":"","intervalFactor":2,"legendFormat":"{{ proto }}:50","refId":"C","step":60}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Requests (size,tcp)","tooltip":{"shared":true,"sort":0,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","logBase":1,"max":null,"min":0,"show":true},{"format":"short","logBase":1,"max":null,"min":0,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","editable":true,"error":false,"fieldConfig":{"defaults":{"custom":{},"links":[]},"overrides":[]},"fill":1,"fillGradient":0,"grid":{},"gridPos":{"h":7,"w":12,"x":0,"y":14},"hiddenSeries":false,"id":14,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"7.2.0","pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(rate(coredns_dns_response_rcode_count_total{job=~\"$job\",instance=~\"$instance\"}[5m])) by (rcode) or\nsum(rate(coredns_dns_responses_total{job=~\"$job\",instance=~\"$instance\"}[5m])) by (rcode)","interval":"","intervalFactor":2,"legendFormat":"{{ rcode }}","refId":"A","step":40}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Responses (by rcode)","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","logBase":1,"max":null,"min":0,"show":true},{"format":"short","logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","editable":true,"error":false,"fieldConfig":{"defaults":{"custom":{},"links":[]},"overrides":[]},"fill":1,"fillGradient":0,"grid":{},"gridPos":{"h":7,"w":12,"x":12,"y":14},"hiddenSeries":false,"id":32,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"7.2.0","pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(coredns_dns_request_duration_seconds_bucket{job=~\"$job\",instance=~\"$instance\"}[5m])) by (le, job))","format":"time_series","intervalFactor":2,"legendFormat":"99%","refId":"A","step":40},{"expr":"histogram_quantile(0.90, sum(rate(coredns_dns_request_duration_seconds_bucket{job=~\"$job\",instance=~\"$instance\"}[5m])) by (le))","format":"time_series","intervalFactor":2,"legendFormat":"90%","refId":"B","step":40},{"expr":"histogram_quantile(0.50, sum(rate(coredns_dns_request_duration_seconds_bucket{job=~\"$job\",instance=~\"$instance\"}[5m])) by (le))","format":"time_series","intervalFactor":2,"legendFormat":"50%","refId":"C","step":40}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Responses (duration)","tooltip":{"shared":true,"sort":0,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","logBase":1,"max":null,"min":0,"show":true},{"format":"short","logBase":1,"max":null,"min":null,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","editable":true,"error":false,"fieldConfig":{"defaults":{"custom":{},"links":[]},"overrides":[]},"fill":1,"fillGradient":0,"grid":{},"gridPos":{"h":7,"w":12,"x":0,"y":21},"hiddenSeries":false,"id":18,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"7.2.0","pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"udp:50%","yaxis":1},{"alias":"tcp:50%","yaxis":2},{"alias":"tcp:90%","yaxis":2},{"alias":"tcp:99%","yaxis":2}],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(coredns_dns_response_size_bytes_bucket{job=~\"$job\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto)) ","interval":"","intervalFactor":2,"legendFormat":"{{ proto }}:99%","refId":"A","step":40},{"expr":"histogram_quantile(0.90, sum(rate(coredns_dns_response_size_bytes_bucket{job=~\"$job\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto)) ","interval":"","intervalFactor":2,"legendFormat":"{{ proto }}:90%","refId":"B","step":40},{"expr":"histogram_quantile(0.50, sum(rate(coredns_dns_response_size_bytes_bucket{job=~\"$job\",instance=~\"$instance\",proto=\"udp\"}[5m])) by (le,proto)) ","hide":false,"intervalFactor":2,"legendFormat":"{{ proto }}:50%","metric":"","refId":"C","step":40}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Responses (size, udp)","tooltip":{"shared":true,"sort":0,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","logBase":1,"max":null,"min":0,"show":true},{"format":"short","logBase":1,"max":null,"min":0,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","editable":true,"error":false,"fieldConfig":{"defaults":{"custom":{},"links":[]},"overrides":[]},"fill":1,"fillGradient":0,"grid":{},"gridPos":{"h":7,"w":12,"x":12,"y":21},"hiddenSeries":false,"id":20,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"7.2.0","pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"udp:50%","yaxis":1},{"alias":"tcp:50%","yaxis":1},{"alias":"tcp:90%","yaxis":1},{"alias":"tcp:99%","yaxis":1}],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(coredns_dns_response_size_bytes_bucket{job=~\"$job\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto)) ","format":"time_series","intervalFactor":2,"legendFormat":"{{ proto }}:99%","refId":"A","step":40},{"expr":"histogram_quantile(0.90, sum(rate(coredns_dns_response_size_bytes_bucket{job=~\"$job\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le,proto)) ","format":"time_series","intervalFactor":2,"legendFormat":"{{ proto }}:90%","refId":"B","step":40},{"expr":"histogram_quantile(0.50, sum(rate(coredns_dns_response_size_bytes_bucket{job=~\"$job\",instance=~\"$instance\",proto=\"tcp\"}[5m])) by (le, proto)) ","format":"time_series","intervalFactor":2,"legendFormat":"{{ proto }}:50%","metric":"","refId":"C","step":40}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Responses (size, tcp)","tooltip":{"shared":true,"sort":0,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","logBase":1,"max":null,"min":0,"show":true},{"format":"short","logBase":1,"max":null,"min":0,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","editable":true,"error":false,"fieldConfig":{"defaults":{"custom":{},"links":[]},"overrides":[]},"fill":1,"fillGradient":0,"grid":{},"gridPos":{"h":7,"w":12,"x":0,"y":28},"hiddenSeries":false,"id":22,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"7.2.0","pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(coredns_cache_size{job=~\"$job\",instance=~\"$instance\"}) by (type) or\nsum(coredns_cache_entries{job=~\"$job\",instance=~\"$instance\"}) by (type)","interval":"","intervalFactor":2,"legendFormat":"{{ type }}","refId":"A","step":40}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Cache (size)","tooltip":{"shared":true,"sort":2,"value_type":"cumulative"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"decbytes","logBase":1,"max":null,"min":0,"show":true},{"format":"short","logBase":1,"max":null,"min":0,"show":true}],"yaxis":{"align":false,"alignLevel":null}},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","editable":true,"error":false,"fieldConfig":{"defaults":{"custom":{},"links":[]},"overrides":[]},"fill":1,"fillGradient":0,"grid":{},"gridPos":{"h":7,"w":12,"x":12,"y":28},"hiddenSeries":false,"id":24,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":2,"links":[],"nullPointMode":"connected","options":{"alertThreshold":true},"percentage":false,"pluginVersion":"7.2.0","pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[{"alias":"misses","yaxis":2}],"spaceLength":10,"stack":true,"steppedLine":false,"targets":[{"expr":"sum(rate(coredns_cache_hits_total{job=~\"$job\",instance=~\"$instance\"}[5m])) by (type)","hide":false,"intervalFactor":2,"legendFormat":"hits:{{ type }}","refId":"A","step":40},{"expr":"sum(rate(coredns_cache_misses_total{job=~\"$job\",instance=~\"$instance\"}[5m])) by (type)","hide":false,"intervalFactor":2,"legendFormat":"misses","refId":"B","step":40}],"thresholds":[],"timeFrom":null,"timeRegions":[],"timeShift":null,"title":"Cache (hitrate)","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"pps","logBase":1,"max":null,"min":0,"show":true},{"format":"pps","logBase":1,"max":null,"min":0,"show":true}],"yaxis":{"align":false,"alignLevel":null}}],"refresh":"10s","schemaVersion":26,"style":"dark","tags":["dns","coredns"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"includeAll":false,"label":null,"multi":false,"name":"datasource","options":[],"query":"prometheus","queryValue":"","refresh":1,"regex":"","skipUrlSync":false,"type":"datasource"},{"allValue":".*","current":{"selected":false,"text":"coredns","value":"coredns"},"datasource":{"type":"prometheus","uid":"${datasource}"},"definition":"label_values(coredns_dns_requests_total, job)","hide":0,"includeAll":true,"label":"Job","multi":false,"name":"job","options":[],"query":{"query":"label_values(coredns_dns_requests_total, job)","refId":"StandardVariableQuery"},"refresh":1,"regex":"","skipUrlSync":false,"sort":1,"type":"query"},{"allValue":".*","current":{"selected":true,"text":"All","value":"$__all"},"datasource":"$datasource","definition":"label_values(coredns_dns_requests_total{job=~\"$job\"}, instance)","hide":0,"includeAll":true,"label":"Instance","multi":false,"name":"instance","options":[],"query":"label_values(coredns_dns_requests_total{job=~\"$job\"}, instance)","refresh":1,"regex":"","skipUrlSync":false,"sort":3,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-3h","to":"now"},"timepicker":{"refresh_intervals":["10s","30s","1m","5m","15m","30m","1h","2h","1d"]},"timezone":"Europe/Paris","title":"CoreDNS","uid":"vkQ0UHxik","version":3} \ No newline at end of file diff --git a/monitor/prometheus/v1_ConfigMap_prometheus-kube-prometheus-kubelet.yaml b/monitor/prometheus/v1_ConfigMap_prometheus-kube-prometheus-kubelet.yaml new file mode 100644 index 0000000..0a09015 --- /dev/null +++ b/monitor/prometheus/v1_ConfigMap_prometheus-kube-prometheus-kubelet.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/kubelet.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: prometheus-kube-prometheus-kubelet + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus" + heritage: "Helm" +data: + kubelet.json: |- + {"__inputs":[],"__requires":[],"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"id":null,"links":[],"panels":[{"datasource":"$datasource","fieldConfig":{"defaults":{"links":[],"mappings":[],"thresholds":{"mode":"absolute","steps":[]},"unit":"none"}},"gridPos":{"h":7,"w":4,"x":0,"y":0},"id":2,"links":[],"options":{"colorMode":"value","graphMode":"area","justifyMode":"auto","orientation":"auto","reduceOptions":{"calcs":["lastNotNull"],"fields":"","values":false},"textMode":"auto"},"pluginVersion":"7","targets":[{"expr":"sum(kubelet_node_name{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\"})","format":"time_series","intervalFactor":2,"legendFormat":"","refId":"A"}],"title":"Running Kubelets","transparent":false,"type":"stat"},{"datasource":"$datasource","fieldConfig":{"defaults":{"links":[],"mappings":[],"thresholds":{"mode":"absolute","steps":[]},"unit":"none"}},"gridPos":{"h":7,"w":4,"x":4,"y":0},"id":3,"links":[],"options":{"colorMode":"value","graphMode":"area","justifyMode":"auto","orientation":"auto","reduceOptions":{"calcs":["lastNotNull"],"fields":"","values":false},"textMode":"auto"},"pluginVersion":"7","targets":[{"expr":"sum(kubelet_running_pods{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}) OR sum(kubelet_running_pod_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"})","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"title":"Running Pods","transparent":false,"type":"stat"},{"datasource":"$datasource","fieldConfig":{"defaults":{"links":[],"mappings":[],"thresholds":{"mode":"absolute","steps":[]},"unit":"none"}},"gridPos":{"h":7,"w":4,"x":8,"y":0},"id":4,"links":[],"options":{"colorMode":"value","graphMode":"area","justifyMode":"auto","orientation":"auto","reduceOptions":{"calcs":["lastNotNull"],"fields":"","values":false},"textMode":"auto"},"pluginVersion":"7","targets":[{"expr":"sum(kubelet_running_containers{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}) OR sum(kubelet_running_container_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"})","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"title":"Running Containers","transparent":false,"type":"stat"},{"datasource":"$datasource","fieldConfig":{"defaults":{"links":[],"mappings":[],"thresholds":{"mode":"absolute","steps":[]},"unit":"none"}},"gridPos":{"h":7,"w":4,"x":12,"y":0},"id":5,"links":[],"options":{"colorMode":"value","graphMode":"area","justifyMode":"auto","orientation":"auto","reduceOptions":{"calcs":["lastNotNull"],"fields":"","values":false},"textMode":"auto"},"pluginVersion":"7","targets":[{"expr":"sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\", state=\"actual_state_of_world\"})","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"title":"Actual Volume Count","transparent":false,"type":"stat"},{"datasource":"$datasource","fieldConfig":{"defaults":{"links":[],"mappings":[],"thresholds":{"mode":"absolute","steps":[]},"unit":"none"}},"gridPos":{"h":7,"w":4,"x":16,"y":0},"id":6,"links":[],"options":{"colorMode":"value","graphMode":"area","justifyMode":"auto","orientation":"auto","reduceOptions":{"calcs":["lastNotNull"],"fields":"","values":false},"textMode":"auto"},"pluginVersion":"7","targets":[{"expr":"sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",state=\"desired_state_of_world\"})","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"title":"Desired Volume Count","transparent":false,"type":"stat"},{"datasource":"$datasource","fieldConfig":{"defaults":{"links":[],"mappings":[],"thresholds":{"mode":"absolute","steps":[]},"unit":"none"}},"gridPos":{"h":7,"w":4,"x":20,"y":0},"id":7,"links":[],"options":{"colorMode":"value","graphMode":"area","justifyMode":"auto","orientation":"auto","reduceOptions":{"calcs":["lastNotNull"],"fields":"","values":false},"textMode":"auto"},"pluginVersion":"7","targets":[{"expr":"sum(rate(kubelet_node_config_error{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"title":"Config Error Count","transparent":false,"type":"stat"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":12,"x":0,"y":7},"id":8,"legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(kubelet_runtime_operations_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (operation_type, instance)","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} {{operation_type}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Operation Rate","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":12,"x":12,"y":7},"id":9,"legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(kubelet_runtime_operations_errors_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type)","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} {{operation_type}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Operation Error Rate","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":24,"x":0,"y":14},"id":10,"legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(kubelet_runtime_operations_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type, le))","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} {{operation_type}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Operation duration 99th quantile","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":12,"x":0,"y":21},"id":11,"legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance)","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} pod","refId":"A"},{"expr":"sum(rate(kubelet_pod_worker_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance)","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} worker","refId":"B"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Pod Start Rate","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":12,"x":12,"y":21},"id":12,"legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(kubelet_pod_start_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} pod","refId":"A"},{"expr":"histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} worker","refId":"B"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Pod Start Duration","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":12,"x":0,"y":28},"id":13,"legend":{"alignAsTable":true,"avg":false,"current":true,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(storage_operation_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_name, volume_plugin)","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} {{operation_name}} {{volume_plugin}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Storage Operation Rate","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":12,"x":12,"y":28},"id":14,"legend":{"alignAsTable":true,"avg":false,"current":true,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(storage_operation_errors_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_name, volume_plugin)","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} {{operation_name}} {{volume_plugin}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Storage Operation Error Rate","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":24,"x":0,"y":35},"id":15,"legend":{"alignAsTable":true,"avg":false,"current":true,"hideEmpty":true,"hideZero":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(storage_operation_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_name, volume_plugin, le))","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} {{operation_name}} {{volume_plugin}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Storage Operation Duration 99th quantile","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":12,"x":0,"y":42},"id":16,"legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(kubelet_cgroup_manager_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type)","format":"time_series","intervalFactor":2,"legendFormat":"{{operation_type}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Cgroup manager operation rate","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":12,"x":12,"y":42},"id":17,"legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(kubelet_cgroup_manager_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type, le))","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} {{operation_type}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Cgroup manager 99th quantile","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","description":"Pod lifecycle event generator","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":12,"x":0,"y":49},"id":18,"legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(kubelet_pleg_relist_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) by (instance)","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"PLEG relist rate","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":12,"x":12,"y":49},"id":19,"legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_interval_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"PLEG relist interval","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":24,"x":0,"y":56},"id":20,"legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"PLEG relist duration","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":24,"x":0,"y":63},"id":21,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"2xx","refId":"A"},{"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"3xx","refId":"B"},{"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"4xx","refId":"C"},{"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"5xx","refId":"D"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"RPC Rate","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":24,"x":0,"y":70},"id":22,"legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) by (instance, verb, url, le))","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}} {{verb}} {{url}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Request duration 99th quantile","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"s","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":8,"x":0,"y":77},"id":23,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"process_resident_memory_bytes{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":8,"x":8,"y":77},"id":24,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"rate(process_cpu_seconds_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU usage","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{"h":7,"w":8,"x":16,"y":77},"id":25,"legend":{"alignAsTable":false,"avg":false,"current":false,"max":false,"min":false,"rightSide":false,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"stack":false,"steppedLine":false,"targets":[{"expr":"go_goroutines{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Goroutines","tooltip":{"shared":true,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"refresh":"10s","rows":[],"schemaVersion":14,"style":"dark","tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{},"datasource":"$datasource","hide":2,"includeAll":false,"label":"cluster","multi":false,"name":"cluster","options":[],"query":"label_values(up{job=\"kubelet\", metrics_path=\"/metrics\"}, cluster)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{},"datasource":"$datasource","hide":0,"includeAll":true,"label":"instance","multi":false,"name":"instance","options":[],"query":"label_values(up{job=\"kubelet\", metrics_path=\"/metrics\",cluster=\"$cluster\"}, instance)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Kubernetes / Kubelet","uid":"3138fa155d5915769fbded898ac09fd9","version":0} \ No newline at end of file diff --git a/monitor/prometheus/v1_ConfigMap_prometheus-kube-prometheus-prometheus.yaml b/monitor/prometheus/v1_ConfigMap_prometheus-kube-prometheus-prometheus.yaml new file mode 100644 index 0000000..2dc8311 --- /dev/null +++ b/monitor/prometheus/v1_ConfigMap_prometheus-kube-prometheus-prometheus.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/prometheus.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: prometheus-kube-prometheus-prometheus + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus" + heritage: "Helm" +data: + prometheus.json: |- + {"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"links":[],"refresh":"60s","rows":[{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":1,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"styles":[{"alias":"Time","dateFormat":"YYYY-MM-DD HH:mm:ss","pattern":"Time","type":"hidden"},{"alias":"Count","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #A","thresholds":[],"type":"hidden","unit":"short"},{"alias":"Uptime","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"Value #B","thresholds":[],"type":"number","unit":"s"},{"alias":"Cluster","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"cluster","thresholds":[],"type":"number","unit":"short"},{"alias":"Instance","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"instance","thresholds":[],"type":"number","unit":"short"},{"alias":"Job","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"job","thresholds":[],"type":"number","unit":"short"},{"alias":"Version","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"link":false,"linkTargetBlank":false,"linkTooltip":"Drill down","linkUrl":"","pattern":"version","thresholds":[],"type":"number","unit":"short"},{"alias":"","colorMode":null,"colors":[],"dateFormat":"YYYY-MM-DD HH:mm:ss","decimals":2,"pattern":"/.*/","thresholds":[],"type":"string","unit":"short"}],"targets":[{"expr":"count by (cluster, job, instance, version) (prometheus_build_info{cluster=~\"$cluster\", job=~\"$job\", instance=~\"$instance\"})","format":"table","instant":true,"legendFormat":"","refId":"A"},{"expr":"max by (cluster, job, instance) (time() - process_start_time_seconds{cluster=~\"$cluster\", job=~\"$job\", instance=~\"$instance\"})","format":"table","instant":true,"legendFormat":"","refId":"B"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Prometheus Stats","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"transform":"table","type":"table","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Prometheus Stats","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":2,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(prometheus_target_sync_length_seconds_sum{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}[5m])) by (cluster, job, scrape_job, instance) * 1e3","format":"time_series","legendFormat":"{{cluster}}:{{job}}:{{instance}}:{{scrape_job}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Target Sync","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ms","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":3,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by (cluster, job, instance) (prometheus_sd_discovered_targets{cluster=~\"$cluster\", job=~\"$job\",instance=~\"$instance\"})","format":"time_series","legendFormat":"{{cluster}}:{{job}}:{{instance}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Targets","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Discovery","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"id":4,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"rate(prometheus_target_interval_length_seconds_sum{cluster=~\"$cluster\", job=~\"$job\",instance=~\"$instance\"}[5m]) / rate(prometheus_target_interval_length_seconds_count{cluster=~\"$cluster\", job=~\"$job\",instance=~\"$instance\"}[5m]) * 1e3","format":"time_series","legendFormat":"{{cluster}}:{{job}}:{{instance}} {{interval}} configured","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Average Scrape Interval Duration","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ms","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":5,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":4,"stack":true,"steppedLine":false,"targets":[{"expr":"sum by (cluster, job, instance) (rate(prometheus_target_scrapes_exceeded_body_size_limit_total{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}[1m]))","format":"time_series","legendFormat":"exceeded body size limit: {{cluster}} {{job}} {{instance}}","legendLink":null},{"expr":"sum by (cluster, job, instance) (rate(prometheus_target_scrapes_exceeded_sample_limit_total{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}[1m]))","format":"time_series","legendFormat":"exceeded sample limit: {{cluster}} {{job}} {{instance}}","legendLink":null},{"expr":"sum by (cluster, job, instance) (rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}[1m]))","format":"time_series","legendFormat":"duplicate timestamp: {{cluster}} {{job}} {{instance}}","legendLink":null},{"expr":"sum by (cluster, job, instance) (rate(prometheus_target_scrapes_sample_out_of_bounds_total{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}[1m]))","format":"time_series","legendFormat":"out of bounds: {{cluster}} {{job}} {{instance}}","legendLink":null},{"expr":"sum by (cluster, job, instance) (rate(prometheus_target_scrapes_sample_out_of_order_total{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}[1m]))","format":"time_series","legendFormat":"out of order: {{cluster}} {{job}} {{instance}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Scrape failures","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":6,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":4,"stack":true,"steppedLine":false,"targets":[{"expr":"rate(prometheus_tsdb_head_samples_appended_total{cluster=~\"$cluster\", job=~\"$job\",instance=~\"$instance\"}[5m])","format":"time_series","legendFormat":"{{cluster}} {{job}} {{instance}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Appended Samples","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Retrieval","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":7,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"prometheus_tsdb_head_series{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}","format":"time_series","legendFormat":"{{cluster}} {{job}} {{instance}} head series","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Head Series","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":8,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"prometheus_tsdb_head_chunks{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\"}","format":"time_series","legendFormat":"{{cluster}} {{job}} {{instance}} head chunks","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Head Chunks","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Storage","titleSize":"h6"},{"collapse":false,"height":"250px","panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":9,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"rate(prometheus_engine_query_duration_seconds_count{cluster=~\"$cluster\",job=~\"$job\",instance=~\"$instance\",slice=\"inner_eval\"}[5m])","format":"time_series","legendFormat":"{{cluster}} {{job}} {{instance}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Query Rate","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":10,"id":10,"legend":{"avg":false,"current":false,"max":false,"min":false,"show":true,"total":false,"values":false},"lines":true,"linewidth":0,"links":[],"nullPointMode":"null as zero","percentage":false,"pointradius":5,"points":false,"renderer":"flot","seriesOverrides":[],"spaceLength":10,"span":6,"stack":true,"steppedLine":false,"targets":[{"expr":"max by (slice) (prometheus_engine_query_duration_seconds{quantile=\"0.9\",cluster=~\"$cluster\", job=~\"$job\",instance=~\"$instance\"}) * 1e3","format":"time_series","legendFormat":"{{slice}}","legendLink":null}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Stage Duration","tooltip":{"shared":true,"sort":2,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ms","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":false}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":true,"title":"Query","titleSize":"h6"}],"schemaVersion":14,"style":"dark","tags":["prometheus-mixin"],"templating":{"list":[{"current":{"text":"default","value":"default"},"hide":0,"label":"Data source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":".+","current":{"selected":true,"text":"All","value":"$__all"},"datasource":"$datasource","hide":2,"includeAll":true,"label":"cluster","multi":true,"name":"cluster","options":[],"query":"label_values(prometheus_build_info{job=\"prometheus-k8s\",namespace=\"monitoring\"}, cluster)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":".+","current":{"selected":true,"text":"All","value":"$__all"},"datasource":"$datasource","hide":0,"includeAll":true,"label":"job","multi":true,"name":"job","options":[],"query":"label_values(prometheus_build_info{cluster=~\"$cluster\"}, job)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":".+","current":{"selected":true,"text":"All","value":"$__all"},"datasource":"$datasource","hide":0,"includeAll":true,"label":"instance","multi":true,"name":"instance","options":[],"query":"label_values(prometheus_build_info{cluster=~\"$cluster\", job=~\"$job\"}, instance)","refresh":1,"regex":"","sort":2,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Prometheus / Overview","uid":"","version":0} \ No newline at end of file diff --git a/monitor/prometheus/v1_ConfigMap_prometheus-kube-prometheus-proxy.yaml b/monitor/prometheus/v1_ConfigMap_prometheus-kube-prometheus-proxy.yaml new file mode 100644 index 0000000..1dedc53 --- /dev/null +++ b/monitor/prometheus/v1_ConfigMap_prometheus-kube-prometheus-proxy.yaml @@ -0,0 +1,22 @@ +# Source: kube-prometheus-stack/templates/grafana/dashboards-1.14/proxy.yaml +apiVersion: v1 +kind: ConfigMap +metadata: + namespace: vynil-monitor + name: prometheus-kube-prometheus-proxy + annotations: + {} + labels: + grafana_dashboard: "1" + app: kube-prometheus-stack-grafana + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus" + heritage: "Helm" +data: + proxy.json: |- + {"__inputs":[],"__requires":[],"annotations":{"list":[]},"editable":true,"gnetId":null,"graphTooltip":0,"hideControls":false,"id":null,"links":[],"refresh":"10s","rows":[{"collapse":false,"collapsed":false,"panels":[{"cacheTimeout":null,"colorBackground":false,"colorValue":false,"colors":["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource":"$datasource","format":"none","gauge":{"maxValue":100,"minValue":0,"show":false,"thresholdLabels":false,"thresholdMarkers":true},"gridPos":{},"id":2,"interval":"1m","legend":{"alignAsTable":true,"rightSide":true},"links":[],"mappingType":1,"mappingTypes":[{"name":"value to text","value":1},{"name":"range to text","value":2}],"maxDataPoints":100,"nullPointMode":"connected","nullText":null,"postfix":"","postfixFontSize":"50%","prefix":"","prefixFontSize":"50%","rangeMaps":[{"from":"null","text":"N/A","to":"null"}],"span":2,"sparkline":{"fillColor":"rgba(31, 118, 189, 0.18)","full":false,"lineColor":"rgb(31, 120, 193)","show":false},"tableColumn":"","targets":[{"expr":"sum(up{cluster=\"$cluster\", job=\"kube-proxy\"})","format":"time_series","intervalFactor":2,"legendFormat":"","refId":"A"}],"thresholds":"","title":"Up","tooltip":{"shared":false},"type":"singlestat","valueFontSize":"80%","valueMaps":[{"op":"=","text":"N/A","value":"null"}],"valueName":"min"},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":3,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":5,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(kubeproxy_sync_proxy_rules_duration_seconds_count{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"rate","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rules Sync Rate","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ops","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"ops","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":4,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":5,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99,rate(kubeproxy_sync_proxy_rules_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Rule Sync Latency 99th Quantile","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"s","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Dashboard Row","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":5,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(kubeproxy_network_programming_duration_seconds_count{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"rate","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Network Programming Rate","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ops","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"ops","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":6,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":6,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(kubeproxy_network_programming_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval])) by (instance, le))","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Network Programming Latency 99th Quantile","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"s","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Dashboard Row","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":7,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"2xx","refId":"A"},{"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"3xx","refId":"B"},{"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"4xx","refId":"C"},{"expr":"sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))","format":"time_series","intervalFactor":2,"legendFormat":"5xx","refId":"D"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Kube API Request Rate","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"ops","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":8,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":8,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\",verb=\"POST\"}[$__rate_interval])) by (verb, url, le))","format":"time_series","intervalFactor":2,"legendFormat":"{{verb}} {{url}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Post Request Latency 99th Quantile","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"s","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Dashboard Row","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":9,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":true,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":true},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":12,"stack":false,"steppedLine":false,"targets":[{"expr":"histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, url, le))","format":"time_series","intervalFactor":2,"legendFormat":"{{verb}} {{url}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Get Request Latency 99th Quantile","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"s","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"s","label":null,"logBase":1,"max":null,"min":0,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Dashboard Row","titleSize":"h6","type":"row"},{"collapse":false,"collapsed":false,"panels":[{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":10,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"process_resident_memory_bytes{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Memory","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"bytes","label":null,"logBase":1,"max":null,"min":null,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":11,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}[$__rate_interval])","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"CPU usage","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":0,"show":true}]},{"aliasColors":{},"bars":false,"dashLength":10,"dashes":false,"datasource":"$datasource","fill":1,"fillGradient":0,"gridPos":{},"id":12,"interval":"1m","legend":{"alignAsTable":true,"avg":false,"current":false,"max":false,"min":false,"rightSide":true,"show":true,"sideWidth":null,"total":false,"values":false},"lines":true,"linewidth":1,"links":[],"nullPointMode":"null","percentage":false,"pointradius":5,"points":false,"renderer":"flot","repeat":null,"seriesOverrides":[],"spaceLength":10,"span":4,"stack":false,"steppedLine":false,"targets":[{"expr":"go_goroutines{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}","format":"time_series","intervalFactor":2,"legendFormat":"{{instance}}","refId":"A"}],"thresholds":[],"timeFrom":null,"timeShift":null,"title":"Goroutines","tooltip":{"shared":false,"sort":0,"value_type":"individual"},"type":"graph","xaxis":{"buckets":null,"mode":"time","name":null,"show":true,"values":[]},"yaxes":[{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true},{"format":"short","label":null,"logBase":1,"max":null,"min":null,"show":true}]}],"repeat":null,"repeatIteration":null,"repeatRowId":null,"showTitle":false,"title":"Dashboard Row","titleSize":"h6","type":"row"}],"schemaVersion":14,"style":"dark","tags":["kubernetes-mixin"],"templating":{"list":[{"current":{"selected":true,"text":"default","value":"default"},"hide":0,"label":"Data Source","name":"datasource","options":[],"query":"prometheus","refresh":1,"regex":"","type":"datasource"},{"allValue":null,"current":{},"datasource":"$datasource","hide":2,"includeAll":false,"label":"cluster","multi":false,"name":"cluster","options":[],"query":"label_values(up{job=\"kube-proxy\"}, cluster)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false},{"allValue":null,"current":{},"datasource":"$datasource","hide":0,"includeAll":true,"label":null,"multi":false,"name":"instance","options":[],"query":"label_values(up{job=\"kube-proxy\", cluster=\"$cluster\", job=\"kube-proxy\"}, instance)","refresh":2,"regex":"","sort":1,"tagValuesQuery":"","tags":[],"tagsQuery":"","type":"query","useTags":false}]},"time":{"from":"now-1h","to":"now"},"timepicker":{"refresh_intervals":["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options":["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "Europe/Paris","title":"Kubernetes / Proxy","uid":"632e265de029684c40b21cb76bca4f94","version":0} \ No newline at end of file diff --git a/monitor/prometheus/v1_Secret_prometheus-kube-prometheus-prometheus.yaml b/monitor/prometheus/v1_Secret_prometheus-kube-prometheus-prometheus.yaml new file mode 100644 index 0000000..ae80320 --- /dev/null +++ b/monitor/prometheus/v1_Secret_prometheus-kube-prometheus-prometheus.yaml @@ -0,0 +1,18 @@ +# Source: kube-prometheus-stack/templates/prometheus/secret.yaml +apiVersion: v1 +kind: Secret +metadata: + name: prometheus-kube-prometheus-prometheus + namespace: vynil-monitor + labels: + app: kube-prometheus-stack-prometheus + app.kubernetes.io/component: prometheus + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus" + heritage: "Helm" +data: \ No newline at end of file diff --git a/monitor/prometheus/v1_ServiceAccount_prometheus-kube-prometheus-prometheus.yaml b/monitor/prometheus/v1_ServiceAccount_prometheus-kube-prometheus-prometheus.yaml new file mode 100644 index 0000000..4348607 --- /dev/null +++ b/monitor/prometheus/v1_ServiceAccount_prometheus-kube-prometheus-prometheus.yaml @@ -0,0 +1,19 @@ +--- +# Source: kube-prometheus-stack/templates/prometheus/serviceaccount.yaml +apiVersion: v1 +kind: ServiceAccount +metadata: + name: prometheus-kube-prometheus-prometheus + namespace: vynil-monitor + labels: + app: kube-prometheus-stack-prometheus + app.kubernetes.io/name: kube-prometheus-stack-prometheus + app.kubernetes.io/component: prometheus + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus" + heritage: "Helm" \ No newline at end of file diff --git a/monitor/prometheus/v1_Service_prometheus-kube-prometheus-coredns.yaml b/monitor/prometheus/v1_Service_prometheus-kube-prometheus-coredns.yaml new file mode 100644 index 0000000..1e00daf --- /dev/null +++ b/monitor/prometheus/v1_Service_prometheus-kube-prometheus-coredns.yaml @@ -0,0 +1,26 @@ +# Source: kube-prometheus-stack/templates/exporters/core-dns/service.yaml +apiVersion: v1 +kind: Service +metadata: + name: prometheus-kube-prometheus-coredns + labels: + app: kube-prometheus-stack-coredns + jobLabel: coredns + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus" + heritage: "Helm" + namespace: kube-system +spec: + clusterIP: None + ports: + - name: http-metrics + port: 9153 + protocol: TCP + targetPort: 9153 + selector: + k8s-app: kube-dns \ No newline at end of file diff --git a/monitor/prometheus/v1_Service_prometheus-kube-prometheus-kube-proxy.yaml b/monitor/prometheus/v1_Service_prometheus-kube-prometheus-kube-proxy.yaml new file mode 100644 index 0000000..c603167 --- /dev/null +++ b/monitor/prometheus/v1_Service_prometheus-kube-prometheus-kube-proxy.yaml @@ -0,0 +1,27 @@ +# Source: kube-prometheus-stack/templates/exporters/kube-proxy/service.yaml +apiVersion: v1 +kind: Service +metadata: + name: prometheus-kube-prometheus-kube-proxy + labels: + app: kube-prometheus-stack-kube-proxy + jobLabel: kube-proxy + + app.kubernetes.io/managed-by: Helm + app.kubernetes.io/instance: prometheus + app.kubernetes.io/version: "56.2.0" + app.kubernetes.io/part-of: kube-prometheus-stack + chart: kube-prometheus-stack-56.2.0 + release: "prometheus" + heritage: "Helm" + namespace: kube-system +spec: + clusterIP: None + ports: + - name: http-metrics + port: 10249 + protocol: TCP + targetPort: 10249 + selector: + k8s-app: kube-proxy + type: ClusterIP \ No newline at end of file diff --git a/monitor/promtail/apps_v1_DaemonSet_promtail.yaml b/monitor/promtail/apps_v1_DaemonSet_promtail.yaml new file mode 100644 index 0000000..45085c7 --- /dev/null +++ b/monitor/promtail/apps_v1_DaemonSet_promtail.yaml @@ -0,0 +1,95 @@ +# Source: promtail/templates/daemonset.yaml +apiVersion: apps/v1 +kind: DaemonSet +metadata: + name: promtail + namespace: vynil-monitor + labels: + helm.sh/chart: promtail-6.15.4 + app.kubernetes.io/name: promtail + app.kubernetes.io/instance: promtail + app.kubernetes.io/version: "2.9.3" + app.kubernetes.io/managed-by: Helm + annotations: + configmap.reloader.stakater.com/reload: promtail +spec: + selector: + matchLabels: + app.kubernetes.io/name: promtail + app.kubernetes.io/instance: promtail + updateStrategy: + {} + template: + metadata: + labels: + app.kubernetes.io/name: promtail + app.kubernetes.io/instance: promtail + annotations: + checksum/config: 00064144e25aa9a0c6068578ba972e5af7d36ef6c203575fa021e9986a3194c3 + spec: + serviceAccountName: promtail + enableServiceLinks: true + securityContext: + runAsGroup: 0 + runAsUser: 0 + containers: + - name: promtail + image: "docker.io/grafana/promtail:2.9.3" + imagePullPolicy: IfNotPresent + args: + - "-config.file=/etc/promtail/promtail.yaml" + volumeMounts: + - name: config + mountPath: /etc/promtail + - mountPath: /run/promtail + name: run + - mountPath: /var/lib/docker/containers + name: containers + readOnly: true + - mountPath: /var/log/pods + name: pods + readOnly: true + env: + - name: HOSTNAME + valueFrom: + fieldRef: + fieldPath: spec.nodeName + ports: + - name: http-metrics + containerPort: 3101 + protocol: TCP + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + readinessProbe: + failureThreshold: 5 + httpGet: + path: '/ready' + port: http-metrics + initialDelaySeconds: 10 + periodSeconds: 10 + successThreshold: 1 + timeoutSeconds: 1 + tolerations: + - effect: NoSchedule + key: node-role.kubernetes.io/master + operator: Exists + - effect: NoSchedule + key: node-role.kubernetes.io/control-plane + operator: Exists + volumes: + - name: config + configMap: + name: promtail + - hostPath: + path: /run/promtail + name: run + - hostPath: + path: /var/lib/docker/containers + name: containers + - hostPath: + path: /var/log/pods + name: pods \ No newline at end of file diff --git a/monitor/promtail/config.tf b/monitor/promtail/config.tf new file mode 100644 index 0000000..0cbf1a6 --- /dev/null +++ b/monitor/promtail/config.tf @@ -0,0 +1,94 @@ +resource "kubectl_manifest" "config" { + yaml_body = <<-EOF + apiVersion: v1 + kind: ConfigMap + metadata: + name: promtail + namespace: "${var.namespace}" + labels: ${jsonencode(local.common-labels)} + data: + promtail.yaml: | + server: + log_level: ${var.log_level} + log_format: ${var.log_format} + http_listen_port: 3101 + clients: + - url: http://${var.loki-url}:3100/loki/api/v1/push + positions: + filename: /run/promtail/positions.yaml + scrape_configs: + - job_name: kubernetes-pods + pipeline_stages: + - cri: {} + kubernetes_sd_configs: + - role: pod + relabel_configs: + - source_labels: + - __meta_kubernetes_pod_controller_name + regex: ([0-9a-z-.]+?)(-[0-9a-f]{8,10})? + action: replace + target_label: __tmp_controller_name + - source_labels: + - __meta_kubernetes_pod_label_app_kubernetes_io_name + - __meta_kubernetes_pod_label_app + - __tmp_controller_name + - __meta_kubernetes_pod_name + regex: ^;*([^;]+)(;.*)?$ + action: replace + target_label: app + - source_labels: + - __meta_kubernetes_pod_label_app_kubernetes_io_instance + - __meta_kubernetes_pod_label_instance + regex: ^;*([^;]+)(;.*)?$ + action: replace + target_label: instance + - source_labels: + - __meta_kubernetes_pod_label_app_kubernetes_io_component + - __meta_kubernetes_pod_label_component + regex: ^;*([^;]+)(;.*)?$ + action: replace + target_label: component + - action: replace + source_labels: + - __meta_kubernetes_pod_node_name + target_label: node_name + - action: replace + source_labels: + - __meta_kubernetes_namespace + target_label: namespace + - action: replace + replacement: $1 + separator: / + source_labels: + - namespace + - app + target_label: job + - action: replace + source_labels: + - __meta_kubernetes_pod_name + target_label: pod + - action: replace + source_labels: + - __meta_kubernetes_pod_container_name + target_label: container + - action: replace + replacement: /var/log/pods/*$1/*.log + separator: / + source_labels: + - __meta_kubernetes_pod_uid + - __meta_kubernetes_pod_container_name + target_label: __path__ + - action: replace + regex: true/(.*) + replacement: /var/log/pods/*$1/*.log + separator: / + source_labels: + - __meta_kubernetes_pod_annotationpresent_kubernetes_io_config_hash + - __meta_kubernetes_pod_annotation_kubernetes_io_config_hash + - __meta_kubernetes_pod_container_name + target_label: __path__ + limits_config: + tracing: + enabled: false + EOF +} diff --git a/monitor/promtail/datas.tf b/monitor/promtail/datas.tf new file mode 100644 index 0000000..977a334 --- /dev/null +++ b/monitor/promtail/datas.tf @@ -0,0 +1,38 @@ +locals { + common-labels = { + "vynil.solidite.fr/owner-name" = var.instance + "vynil.solidite.fr/owner-namespace" = var.namespace + "vynil.solidite.fr/owner-category" = var.category + "vynil.solidite.fr/owner-component" = var.component + "app.kubernetes.io/managed-by" = "vynil" + "app.kubernetes.io/instance" = var.instance + } + rb-patch = <<-EOF + - op: replace + path: /subjects/0/namespace + value: "${var.namespace}" + EOF +} + +data "kustomization_overlay" "data" { + common_labels = local.common-labels + namespace = var.namespace + resources = [for file in fileset(path.module, "*.yaml"): file if file != "index.yaml" && length(regexall("ClusterRole",file))<1] + images { + name = "docker.io/grafana/promtail" + new_name = "${var.images.promtail.registry}/${var.images.promtail.repository}" + new_tag = "${var.images.promtail.tag}" + } +} +data "kustomization_overlay" "data_no_ns" { + common_labels = local.common-labels + resources = [for file in fileset(path.module, "*.yaml"): file if length(regexall("ClusterRole",file))>0] + + patches { + target { + kind = "ClusterRoleBinding" + name = "promtail" + } + patch = local.rb-patch + } +} diff --git a/monitor/promtail/index.yaml b/monitor/promtail/index.yaml new file mode 100644 index 0000000..691bdec --- /dev/null +++ b/monitor/promtail/index.yaml @@ -0,0 +1,73 @@ +--- +apiVersion: vinyl.solidite.fr/v1beta1 +kind: Component +category: monitor +metadata: + name: promtail + description: null +options: + images: + default: + promtail: + pullPolicy: IfNotPresent + registry: docker.io + repository: grafana/promtail + tag: 2.9.2 + examples: + - promtail: + pullPolicy: IfNotPresent + registry: docker.io + repository: grafana/promtail + tag: 2.9.2 + properties: + promtail: + default: + pullPolicy: IfNotPresent + registry: docker.io + repository: grafana/promtail + tag: 2.9.2 + properties: + pullPolicy: + default: IfNotPresent + enum: + - Always + - Never + - IfNotPresent + type: string + registry: + default: docker.io + type: string + repository: + default: grafana/promtail + type: string + tag: + default: 2.9.2 + type: string + type: object + type: object + log_format: + default: logfmt + examples: + - logfmt + type: string + loki-url: + default: loki + examples: + - loki + type: string + log_level: + default: info + examples: + - info + type: string +dependencies: [] +providers: + kubernetes: true + authentik: null + kubectl: true + postgresql: null + mysql: null + restapi: null + http: null + gitea: null +tfaddtype: null diff --git a/monitor/promtail/monitoring.coreos.com_v1_ServiceMonitor_promtail.yaml b/monitor/promtail/monitoring.coreos.com_v1_ServiceMonitor_promtail.yaml new file mode 100644 index 0000000..cd83030 --- /dev/null +++ b/monitor/promtail/monitoring.coreos.com_v1_ServiceMonitor_promtail.yaml @@ -0,0 +1,19 @@ +# Source: promtail/templates/servicemonitor.yaml +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + name: promtail + labels: + helm.sh/chart: promtail-6.15.4 + app.kubernetes.io/name: promtail + app.kubernetes.io/instance: promtail + app.kubernetes.io/version: "2.9.3" + app.kubernetes.io/managed-by: Helm +spec: + selector: + matchLabels: + app.kubernetes.io/name: promtail + app.kubernetes.io/instance: promtail + endpoints: + - port: http-metrics + scheme: http \ No newline at end of file diff --git a/monitor/promtail/rbac.authorization.k8s.io_v1_ClusterRoleBinding_promtail.yaml b/monitor/promtail/rbac.authorization.k8s.io_v1_ClusterRoleBinding_promtail.yaml new file mode 100644 index 0000000..98ecc74 --- /dev/null +++ b/monitor/promtail/rbac.authorization.k8s.io_v1_ClusterRoleBinding_promtail.yaml @@ -0,0 +1,19 @@ +# Source: promtail/templates/clusterrolebinding.yaml +kind: ClusterRoleBinding +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + name: promtail + labels: + helm.sh/chart: promtail-6.15.4 + app.kubernetes.io/name: promtail + app.kubernetes.io/instance: promtail + app.kubernetes.io/version: "2.9.3" + app.kubernetes.io/managed-by: Helm +subjects: + - kind: ServiceAccount + name: promtail + namespace: vynil-monitor +roleRef: + kind: ClusterRole + name: promtail + apiGroup: rbac.authorization.k8s.io \ No newline at end of file diff --git a/monitor/promtail/rbac.authorization.k8s.io_v1_ClusterRole_promtail.yaml b/monitor/promtail/rbac.authorization.k8s.io_v1_ClusterRole_promtail.yaml new file mode 100644 index 0000000..5870614 --- /dev/null +++ b/monitor/promtail/rbac.authorization.k8s.io_v1_ClusterRole_promtail.yaml @@ -0,0 +1,24 @@ +# Source: promtail/templates/clusterrole.yaml +kind: ClusterRole +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + name: promtail + labels: + helm.sh/chart: promtail-6.15.4 + app.kubernetes.io/name: promtail + app.kubernetes.io/instance: promtail + app.kubernetes.io/version: "2.9.3" + app.kubernetes.io/managed-by: Helm +rules: + - apiGroups: + - "" + resources: + - nodes + - nodes/proxy + - services + - endpoints + - pods + verbs: + - get + - watch + - list \ No newline at end of file diff --git a/monitor/promtail/ressources_no_ns.tf b/monitor/promtail/ressources_no_ns.tf new file mode 100644 index 0000000..9fa58b7 --- /dev/null +++ b/monitor/promtail/ressources_no_ns.tf @@ -0,0 +1,45 @@ + +# first loop through resources in ids_prio[0] +resource "kustomization_resource" "pre_no_ns" { + for_each = data.kustomization_overlay.data_no_ns.ids_prio[0] + + manifest = ( + contains(["_/Secret"], regex("(?P.*/.*)/.*/.*", each.value)["group_kind"]) + ? sensitive(data.kustomization_overlay.data_no_ns.manifests[each.value]) + : data.kustomization_overlay.data_no_ns.manifests[each.value] + ) +} + +# then loop through resources in ids_prio[1] +# and set an explicit depends_on on kustomization_resource.pre +# wait 2 minutes for any deployment or daemonset to become ready +resource "kustomization_resource" "main_no_ns" { + for_each = data.kustomization_overlay.data_no_ns.ids_prio[1] + + manifest = ( + contains(["_/Secret"], regex("(?P.*/.*)/.*/.*", each.value)["group_kind"]) + ? sensitive(data.kustomization_overlay.data_no_ns.manifests[each.value]) + : data.kustomization_overlay.data_no_ns.manifests[each.value] + ) + wait = true + timeouts { + create = "5m" + update = "5m" + } + + depends_on = [kustomization_resource.pre_no_ns] +} + +# finally, loop through resources in ids_prio[2] +# and set an explicit depends_on on kustomization_resource.main +resource "kustomization_resource" "post_no_ns" { + for_each = data.kustomization_overlay.data_no_ns.ids_prio[2] + + manifest = ( + contains(["_/Secret"], regex("(?P.*/.*)/.*/.*", each.value)["group_kind"]) + ? sensitive(data.kustomization_overlay.data_no_ns.manifests[each.value]) + : data.kustomization_overlay.data_no_ns.manifests[each.value] + ) + + depends_on = [kustomization_resource.main_no_ns] +} diff --git a/monitor/promtail/v1_ServiceAccount_promtail.yaml b/monitor/promtail/v1_ServiceAccount_promtail.yaml new file mode 100644 index 0000000..0adb061 --- /dev/null +++ b/monitor/promtail/v1_ServiceAccount_promtail.yaml @@ -0,0 +1,13 @@ +--- +# Source: promtail/templates/serviceaccount.yaml +apiVersion: v1 +kind: ServiceAccount +metadata: + name: promtail + namespace: vynil-monitor + labels: + helm.sh/chart: promtail-6.15.4 + app.kubernetes.io/name: promtail + app.kubernetes.io/instance: promtail + app.kubernetes.io/version: "2.9.3" + app.kubernetes.io/managed-by: Helm \ No newline at end of file diff --git a/monitor/promtail/v1_Service_promtail-metrics.yaml b/monitor/promtail/v1_Service_promtail-metrics.yaml new file mode 100644 index 0000000..e591249 --- /dev/null +++ b/monitor/promtail/v1_Service_promtail-metrics.yaml @@ -0,0 +1,22 @@ +# Source: promtail/templates/service-metrics.yaml +apiVersion: v1 +kind: Service +metadata: + name: promtail-metrics + namespace: vynil-monitor + labels: + helm.sh/chart: promtail-6.15.4 + app.kubernetes.io/name: promtail + app.kubernetes.io/instance: promtail + app.kubernetes.io/version: "2.9.3" + app.kubernetes.io/managed-by: Helm +spec: + clusterIP: None + ports: + - name: http-metrics + port: 3101 + targetPort: http-metrics + protocol: TCP + selector: + app.kubernetes.io/name: promtail + app.kubernetes.io/instance: promtail \ No newline at end of file