Alerts


/etc/prometheus/alert.rules > example
high_load (0 active)
alert: high_load
expr: node_load1 > 0.5
for: 2m
labels:
  severity: page
annotations:
  description: '{{ $labels.instance }} of job {{ $labels.job }} is under high load.'
  summary: Instance {{ $labels.instance }} under high load
service_down (0 active)
alert: service_down
expr: up == 0
for: 2m
labels:
  severity: page
annotations:
  description: '{{ $labels.instance }} of job {{ $labels.job }} has been down for
    more than 2 minutes.'
  summary: Instance {{ $labels.instance }} down