fix

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"]
+}

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

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

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

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

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

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

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