55 lines
1.5 KiB
YAML
55 lines
1.5 KiB
YAML
groups:
|
|
- name: configcenter
|
|
rules:
|
|
- alert: ConfigCenterDown
|
|
expr: up{job="configcenter"} == 0
|
|
for: 2m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Config Center is unavailable
|
|
|
|
- alert: ConfigCenterOutboxBacklog
|
|
expr: configcenter_outbox_pending > 100
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Config Center outbox backlog is growing
|
|
|
|
- alert: ConfigCenterOutboxFailed
|
|
expr: configcenter_outbox_failed > 0
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Config Center has terminally failed releases
|
|
|
|
- alert: ConfigCenterHighHTTPErrorRate
|
|
expr: |
|
|
sum(rate(configcenter_http_requests_total{status=~"5.."}[5m]))
|
|
/
|
|
clamp_min(sum(rate(configcenter_http_requests_total[5m])), 0.001)
|
|
> 0.01
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Config Center 5xx rate exceeds 1%
|
|
|
|
- alert: EtcdDown
|
|
expr: up{job="etcd"} == 0
|
|
for: 2m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Config Center etcd is unavailable
|
|
|
|
- alert: EtcdNoLeader
|
|
expr: etcd_server_has_leader{job="etcd"} == 0
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Config Center etcd member has no leader
|