groups:
- name: example
rules:
# Alert for any instance that is unreachable for >5 minutes.
- alert: InstanceDown
expr: up == 0
for: 5m
labels:
severity: page
annotations:
summary: "Instance {{ $labels.instance }} down"
description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 5 minutes."
# Alert for any instance that has a median request latency >1s.
- alert: APIHighRequestLatency
expr: api_http_request_latencies_second{quantile="0.5"} > 1
for: 10m
annotations:
summary: "High request latency on {{ $labels.instance }}"
description: "{{ $labels.instance }} has a median request latency above 1s (current value: {{ $value }}s)"