prometheus.rules

groups:
- name: prometheus.rules
  rules:
  - alert: InstanceDown
    expr: up == 0
    for: 5m
    labels:
      severity: high-priority
    annotations:
      description: '{{ $labels.host }} of job {{ $labels.job }} has been down for
        more than 5 minutes.'
      summary: Instance {{ $labels.host }} down
  - alert: InstanceLowDisk
    expr: 100 - (node_filesystem_avail{device=~"^(?:/.*)$",mountpoint!~"^(?:/var/lib/mesos/slave/.*)$"}
      / node_filesystem_size * 100) > 90
    for: 5m
    labels:
      severity: high-priority
    annotations:
      description: '{{$labels.host}} has less than 10% free disk space'
      summary: 'Instance {{$labels.host}}: low disk space'
  - alert: InstanceHighCpu
    expr: 100 - (avg(irate(node_cpu{job="node",mode="idle"}[5m])) BY (instance) *
      100) > 99
    for: 6h
    labels:
      severity: low-priority
    annotations:
      description: '{{$labels.host}} has high CPU activity'
      summary: 'Instance {{$labels.host}}: CPU high'
  - alert: InstanceLowMemory
    expr: node_memory_MemAvailable < 268435456
    for: 10m
    labels:
      severity: low-priority
    annotations:
      description: '{{$labels.host}} has less than 256M memory available'
      summary: 'Instance {{$labels.host}}: memory low'