Files
ljwx-deploy/apps/ljwx-health-operations/alertmanager-config.yaml
T
BrunoGao 477eea302f feat(ops): close LJWX Health alert edge and PITR loops (#285)
Add the Feishu alert relay, dedicated in-cluster Cloudflare Tunnel, pgBackRest WAL/PITR operations, supporting Argo applications, and reproducible production drills.
2026-07-10 22:59:40 +08:00

71 lines
1.8 KiB
YAML

apiVersion: v1
kind: Secret
metadata:
name: alertmanager-monitoring-kube-prometheus-alertmanager
labels:
app.kubernetes.io/name: alertmanager
app.kubernetes.io/component: configuration
type: Opaque
stringData:
alertmanager.yaml: |
global:
resolve_timeout: 5m
inhibit_rules:
- source_matchers:
- severity="critical"
target_matchers:
- severity="warning"
equal:
- alertname
- cluster
- service
receivers:
- name: "null"
- name: critical-notifications
webhook_configs:
- url: http://ljwx-health-alert-relay.openclaw.svc.cluster.local:8080/alerts
send_resolved: true
max_alerts: 50
- name: warning-notifications
webhook_configs:
- url: http://ljwx-health-alert-relay.openclaw.svc.cluster.local:8080/alerts
send_resolved: true
max_alerts: 50
route:
receiver: "null"
group_by:
- alertname
- cluster
- service
- severity
group_wait: 30s
group_interval: 5m
repeat_interval: 12h
routes:
- matchers:
- alertname="Watchdog"
receiver: "null"
- matchers:
- alertname="InfoInhibitor"
receiver: "null"
- matchers:
- alertname=~"KubeSchedulerDown|KubeProxyDown|KubeControllerManagerDown"
receiver: "null"
- matchers:
- severity="critical"
receiver: critical-notifications
group_wait: 10s
group_interval: 30s
repeat_interval: 1h
- matchers:
- severity="warning"
receiver: warning-notifications
group_interval: 30s
repeat_interval: 4h
templates:
- /etc/alertmanager/config/*.tmpl