04常用告警规则
1.cpu告警规则
groups:
- name: hostStatsAlert
rules:
- alert: hostCpuUsageAlert
# 正则匹配job中的node_exporter值,这里.匹配了单个数字
expr: (1-(avg(irate(node_cpu_seconds_total{job=~"node_exporter.",mode="idle"}[5m])) by (instance)))*100 > 0.55
for: 100s
labels:
severity: page
annotations:
# {$..}调用prometheus ui界面的变量
summary: "Instance {{ $labels.instance }} CPU usgae high"
description: "{{ $labels.instance }} CPU usage above 55% (current value: {{ $value }})"
触发命令
cat /dev/zero > /dev/null

浙公网安备 33010602011771号