feat(kube-prom-stack): added some extra rules

[thiagoalmeidasa]

No description provided.

[github-actions]

--- kubernetes/apps/monitoring/kube-prometheus-stack/app Kustomization: flux-system/cluster-apps-kube-prometheus-stack HelmRelease: monitoring/kube-prometheus-stack

+++ kubernetes/apps/monitoring/kube-prometheus-stack/app Kustomization: flux-system/cluster-apps-kube-prometheus-stack HelmRelease: monitoring/kube-prometheus-stack

@@ -35,20 +35,12 @@

                 requests:
                   storage: 1Gi
               storageClassName: longhorn
       config:
         global:
           resolve_timeout: 5m
-        inhibit_rules:
-        - equal:
-          - alertname
-          - namespace
-          source_match:
-            severity: critical
-          target_match:
-            severity: warning
         receivers:
         - name: 'null'
         - name: pagerduty
           pagerduty_configs:
           - service_key: ${PAGERDUTY_KEY}
         - name: dead-mans-switch
@@ -69,13 +61,12 @@

               alertname: Watchdog
             receiver: dead-mans-switch
             repeat_interval: 6m
           - continue: true
             matchers:
             - severity=~"critical|page"
-            - alertname!="KubeAPIErrorBudgetBurn"
             receiver: pagerduty
       fullnameOverride: alertmanager
       ingress:
         annotations:
           hajimari.io/appName: Alert Manager
           hajimari.io/enable: 'true'
--- kubernetes/apps/monitoring/kube-prometheus-stack/app Kustomization: flux-system/cluster-apps-kube-prometheus-stack PrometheusRule: monitoring/miscellaneous-rules

+++ kubernetes/apps/monitoring/kube-prometheus-stack/app Kustomization: flux-system/cluster-apps-kube-prometheus-stack PrometheusRule: monitoring/miscellaneous-rules

@@ -0,0 +1,86 @@

+---
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  labels:
+    kustomize.toolkit.fluxcd.io/name: cluster-apps-kube-prometheus-stack
+    kustomize.toolkit.fluxcd.io/namespace: flux-system
+  name: miscellaneous-rules
+  namespace: monitoring
+spec:
+  groups:
+  - name: k8s.rules
+    rules:
+    - alert: KubernetesContainerOomKiller
+      annotations:
+        description: |-
+          Container {{ $labels.container }} in pod {{ $labels.namespace }}/{{ $labels.pod }} has been OOMKilled {{ $value }} times in the last 10 minutes.
+            VALUE = {{ $value }}
+            LABELS = {{ $labels }}
+        summary: Kubernetes Container oom killer (instance {{ $labels.instance }})
+      expr: (kube_pod_container_status_restarts_total - kube_pod_container_status_restarts_total
+        offset 10m >= 1) and ignoring (reason) min_over_time(kube_pod_container_status_last_terminated_reason{reason="OOMKilled"}[10m])
+        == 1
+      for: 0m
+      labels:
+        severity: critical
+    - alert: KubernetesPodCrashLooping
+      annotations:
+        description: |-
+          Pod {{ $labels.namespace }}/{{ $labels.pod }} is crash looping
+            VALUE = {{ $value }}
+            LABELS = {{ $labels }}
+        summary: Kubernetes pod crash looping (instance {{ $labels.instance }})
+      expr: increase(kube_pod_container_status_restarts_total[1m]) > 3
+      for: 2m
+      labels:
+        severity: critical
+    - alert: KubernetesNodeMemoryPressure
+      annotations:
+        description: |-
+          Node {{ $labels.node }} has MemoryPressure condition
+            VALUE = {{ $value }}
+            LABELS = {{ $labels }}
+        summary: Kubernetes Node memory pressure (instance {{ $labels.instance }})
+      expr: kube_node_status_condition{condition="MemoryPressure",status="true"} ==
+        1
+      for: 2m
+      labels:
+        severity: critical
+    - alert: KubernetesNodeDiskPressure
+      annotations:
+        description: |-
+          Node {{ $labels.node }} has DiskPressure condition
+            VALUE = {{ $value }}
+            LABELS = {{ $labels }}
+        summary: Kubernetes Node disk pressure (instance {{ $labels.instance }})
+      expr: kube_node_status_condition{condition="DiskPressure",status="true"} ==
+        1
+      for: 2m
+      labels:
+        severity: critical
+    - alert: KubernetesNodeNotReady
+      annotations:
+        description: |-
+          Node {{ $labels.node }} has been unready for a long time
+            VALUE = {{ $value }}
+            LABELS = {{ $labels }}
+        summary: Kubernetes Node not ready (instance {{ $labels.instance }})
+      expr: kube_node_status_condition{condition="Ready",status="true"} == 0
+      for: 10m
+      labels:
+        severity: critical
+    - alert: KubernetesVolumeFullInFourDays
+      annotations:
+        description: |-
+          Volume under {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is expected to fill up within four days. Currently {{ $value | humanize }}% is available.
+            VALUE = {{ $value }}
+            LABELS = {{ $labels }}
+        summary: Kubernetes Volume full in four days (instance {{ $labels.instance
+          }})
+      expr: predict_linear(kubelet_volume_stats_available_bytes[6h:5m], 4 * 24 * 3600)
+        < 0
+      for: 0m
+      labels:
+        severity: critical
+