2018-02-01 06:54:56 +00:00
|
|
|
groups:
|
|
|
|
|
- name: example
|
|
|
|
|
rules:
|
|
|
|
|
|
|
|
|
|
# Alert for any instance that is unreachable for >5 minutes.
|
|
|
|
|
- alert: service_down
|
|
|
|
|
expr: up == 0
|
|
|
|
|
for: 2m
|
|
|
|
|
labels:
|
|
|
|
|
severity: page
|
|
|
|
|
annotations:
|
|
|
|
|
summary: "Instance {{ $labels.instance }} down"
|
|
|
|
|
description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 2 minutes."
|
|
|
|
|
|
|
|
|
|
- alert: high_load
|
|
|
|
|
expr: node_load1 > 0.5
|
|
|
|
|
for: 2m
|
|
|
|
|
labels:
|
|
|
|
|
severity: page
|
|
|
|
|
annotations:
|
|
|
|
|
summary: "Instance {{ $labels.instance }} under high load"
|
|
|
|
|
description: "{{ $labels.instance }} of job {{ $labels.job }} is under high load."
|
