alert.rules

groups:
- name: example
  rules:

  - alert: service_down
    expr: up == 0
    for: 30s
    labels:
      severity: page
    annotations:
      summary: "Instance {{ $labels.instance }} down"
      description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 30 seconds."

  - alert: high_load
    expr: node_load1 > 0.8
    for: 30s
    labels:
      severity: page
    annotations:
      summary: "Instance {{ $labels.instance }} under high load"
      description: "{{ $labels.instance }} of job {{ $labels.job }} is under high load."

  - alert: site_down
    expr: probe_success < 1
    for: 30s
    labels:
      severity: page
    annotations:
      summary: "Site Down: {{$labels.instance}}"
      description: "Site Down: {{$labels.instance}} for more than 30 seconds"