自定义Prometheus告警规则
Last updated
rule_files:
[ - <filepath_glob> ... ]global:
[ evaluation_interval: <duration> | default = 1m ]# To insert a firing element's label values:
{{ $labels.<labelname> }}
# To insert the numeric expression value of the firing element:
{{ $value }}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)"ALERTS{alertname="<alert name>", alertstate="pending|firing", <additional alert labels>}rule_files:
- /etc/prometheus/rules/*.rulesgroups:
- name: hostStatsAlert
rules:
- alert: hostCpuUsageAlert
expr: sum(avg without (cpu)(irate(node_cpu{mode!='idle'}[5m]))) by (instance) > 0.85
for: 1m
labels:
severity: page
annotations:
summary: "Instance {{ $labels.instance }} CPU usgae high"
description: "{{ $labels.instance }} CPU usage above 85% (current value: {{ $value }})"
- alert: hostMemUsageAlert
expr: (node_memory_MemTotal - node_memory_MemAvailable)/node_memory_MemTotal > 0.85
for: 1m
labels:
severity: page
annotations:
summary: "Instance {{ $labels.instance }} MEM usgae high"
description: "{{ $labels.instance }} MEM usage above 85% (current value: {{ $value }})"cat /dev/zero>/dev/null