apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-rules
  namespace: default
data:
  kubernetes-alerts.yml: |
    groups:
    - name: kubernetes-alerts
      rules:
      - alert: PodCrashLooping
        expr: rate(kube_pod_container_status_restarts_total[15m]) * 60 * 15 > 0
        for: 0m
        labels:
          severity: warning
        annotations:
          summary: "Pod {{ $labels.namespace }}/{{ $labels.pod }} is crash looping"
          description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} is restarting {{ printf \"%.2f\" $value }} times / 15 minutes."

      - alert: PodNotReady
        expr: kube_pod_status_phase{phase=~"Pending|Unknown"} > 0
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Pod {{ $labels.namespace }}/{{ $labels.pod }} is not ready"
          description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready state for more than 5 minutes."

      - alert: NodeNotReady
        expr: kube_node_status_condition{condition="Ready",status="true"} == 0
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "Node {{ $labels.node }} is not ready"
          description: "Node {{ $labels.node }} has been unready for more than 5 minutes."

    - name: prometheus-alerts
      rules:
      - alert: PrometheusDown
        expr: up{job="prometheus"} == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Prometheus is down"
          description: "Prometheus has been down for more than 1 minute."

      - alert: PrometheusConfigReloadFailed
        expr: prometheus_config_last_reload_successful == 0
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Prometheus configuration reload failed"
          description: "Prometheus configuration reload has been failing for more than 5 minutes."

    - name: aserver-alerts
      rules:
      - alert: AServerOffline
        expr: absent(up{kubernetes_pod_name=~"aserver.*"}) or up{kubernetes_pod_name=~"aserver.*"} == 0
        for: 1m
        labels:
          severity: critical
          service: aserver
          alert_type: offline
        annotations:
          summary: "AServer 服务离线"
          description: "AServer Pod 不存在或已离线超过1分钟"
          action: "请检查 Pod 状态和日志"