Prometheus Alerting: Alertmanager Routing
Routing Tree Structure
route:
receiver: default
group_by: [alertname, instance]
group_wait: 30s
group_interval: 5m
repeat_interval: 4h
routes:
- match:
severity: critical
receiver: pagerduty
repeat_interval: 30m
- match:
severity: warning
receiver: wechat
repeat_interval: 24h
Common Alert Rules
groups:
- name: host
rules:
- alert: HighCpu
expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
for: 5m
labels:
severity: warning
annotations:
summary: "CPU > 80% for 5m"
Note: Placeholder version.