Prometheus告警规则示例：欢迎大家分享 #89
Description
这个网站有很多Prometheus告警规则样例: https://awesome-prometheus-alerts.grep.to/
# centos6和7的内存空闲量计算
node_memory_MemAvailable_bytes or (node_memory_Buffers_bytes + node_memory_Cached_bytes + node_memory_MemFree_bytes + node_memory_Slab_bytes)
一个prometheus rules的示例，level用作区分告警方式，level, kind用作告警抑制方式。
groups:
- name: node-cpu
rules:
# cpu核数
- record: instance:node_cpus:count
expr: count without (cpu, mode) (node_cpu_seconds_total{mode="idle"})
# 每个cpu使用率
- record: instance_cpu:node_cpu_seconds_not_idle:rate1m
expr: sum without (mode) (1 - rate(node_cpu_seconds_total{mode="idle"}[1m]))
# 总cpu使用率
- record: instance:node_cpu_utilization:ratio
expr: avg without (cpu) (instance_cpu:node_cpu_seconds_not_idle:rate1m)
- alert: cpu使用率大于88%
expr: instance:node_cpu_utilization:ratio * 100 > 88
for: 5m
labels:
severity: critical
level: 3
annotations:
summary: "cpu使用率大于85%"
description: "主机 {{ $labels.hostname }} 的cpu使用率为 {{ $value | humanize }}"
- alert: cpu使用率大于93%
expr: instance:node_cpu_utilization:ratio * 100 > 93
for: 2m
labels:
severity: emergency
level: 4
annotations:
summary: "cpu使用率大于93%"
description: "主机 {{ $labels.hostname }} 的cpu使用率为 {{ $value | humanize }}"
wxurl: "webhook1, webhook2"
mobile: "13xxx, 15xxx"
- alert: cpu负载大于Cores
expr: node_load5 > instance:node_cpus:count
for: 5m
labels:
severity: warning
level: 2
annotations:
summary: "cpu负载大于Cores"
description: "主机 {{ $labels.hostname }} 的cpu负载为 {{ $value }}"
- alert: cpu负载大于2Cores
expr: node_load1 > (instance:node_cpus:count * 2)
for: 4m
labels:
severity: critical
level: 3
annotations:
summary: "cpu负载大于2Cores"
description: "主机 {{ $labels.hostname }} 的cpu负载为 {{ $value }}"
alertgroup: ops在特定时间触发/不触发告警，参考: https://www.robustperception.io/combining-alert-conditions
groups:
- name: 指定特定时间范围
rules:
- alert: 凌晨0点到6点不触发告警
# prometheus默认是utc时间，请注意
expr: promQL表达式 and ON() (hour() < 16 > 22)