groups:
- name: pods
  rules:
  - alert: kubernetes/pod-not-healthy
    expr: min_over_time(sum by (namespace, pod) (kube_pod_status_phase{phase=~"Pending|Unknown|Failed"})[3m:1m]) > 0
    for: 3m
    labels:
      severity: page
    annotations:
      summary: "Kubernetes Pod not healthy: {{ $labels.namespace }}/{{ $labels.pod }}"
      description: "Pod has been in a non-ready state for longer than 3 minutes."

  - alert: kubernetes/pod-crash-looping
    expr: increase(kube_pod_container_status_restarts_total[5m]) > 3
    for: 1m
    labels:
      severity: warning
    annotations:
      summary: "Kubernetes pod crash looping: {{ $labels.kubernetes_namespace }}/{{ $labels.pod }}"
      description: "Pod {{ $labels.pod }} is crash looping"