groups:
  - name: region_health
    rules:
      - alert: RegionUnhealthy
        expr: up{region=~".+"} == 0
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "Region {{ $labels.region }} is unhealthy"
          description: "Region {{ $labels.region }} has been unhealthy for more than 5 minutes"
      
      - alert: RegionHighLatency
        expr: avg(region_latency_seconds) > 1
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: "High latency in region {{ $labels.region }}"
          description: "Average latency in region {{ $labels.region }} is {{ $value }}s"
      
      - alert: RegionNodeFailure
        expr: count(kube_node_status_condition{condition="Ready",status="true"}) < 3
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "Multiple node failures in region {{ $labels.region }}"
          description: "Less than 3 nodes are ready in region {{ $labels.region }}"
      
      - alert: RegionPodFailure
        expr: count(kube_pod_status_phase{phase="Running"}) < count(kube_pod_status_phase{}) * 0.8
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High pod failure rate in region {{ $labels.region }}"
          description: "Less than 80% of pods are running in region {{ $labels.region }}"