prometheus-k8s-pod-rules.yaml

apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  labels:
    prometheus: k8s
    role: alert-rules
  name: prometheus-k8s-pod-rules
  namespace: monitoring
spec:
  groups:
  - name: KubePodCrashLooping
    rules:
    - alert: KubePodCrashLooping
      annotations:
        detail:  'Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container}}) is restarting {{ printf "%.2f" $value }} times / 5 minutes.'
        summary: "POD五分钟内发生重启次数"
      expr: |
        rate(kube_pod_container_status_restarts_total{job="kube-state-metrics"}[15m]) * 60 * 5 > 0
      for: 1h
      labels:
        severity: 严重
  - name: KubePodNotReadyMonitoring
    rules:
    - alert: KubePodNotReady
      annotations:
        detail:  "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready state for longer than an hour."
        summary: "POD状态异常，或者没有准备，在一小时内"
      expr: |
        sum by (namespace, pod) (kube_pod_status_phase{job="kube-state-metrics", phase=~"Pending|Unknown"}) > 0
      for: 1h
      labels:
        severity: 严重