Prometheus Alerting Rules

groups:
  - name: infrastructure
    rules:
      - alert: HighCPU
        expr: 100 - (avg by(instance)(rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 85
        for: 5m
        labels: { severity: warning }
        annotations:
          summary: High CPU detected
      - alert: DiskAlmostFull
        expr: (node_filesystem_avail_bytes / node_filesystem_size_bytes) * 100 < 15
        for: 10m
        labels: { severity: critical }