groups:
  - name: service
    rules:
      - alert: service_down
        expr: up == 0
        for: 10m
        labels:
          severity: critical
        annotations:
          summary: "Instance {{ $labels.job }} down"
          description: "{{ $labels.job }} has been down for more than 10 minutes."

  - name: infrastructure
    rules:
      - alert: high_load
        expr: node_load1 > 8
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: "Instance {{ $labels.job }} under high load"
          description: "{{ $labels.job }} is under high load."

  - name: disk_space
    rules:
      - alert: disk_will_fill
        expr: predict_linear(node_filesystem_free_bytes{job="host-ps03fd"}[4h], 4 * 3600) < 0
        for: 5m
        labels:
          severity: critical

      - alert: disk_10_percent_free
        expr: node_exporter:node_filesystem_free_bytes:fs_used_percents >= 90
        labels:
          severity: critical
        annotations:
          summary: "Instance {{ $labels.instance }} is low on disk space"
          description: "{{ $labels.instance }} has only {{ $value }}% free."