- Loki log aggregation (MinIO backed, 10-day retention) - Promtail daemonset (pod + talos journal logs) - Prometheus + kube-state-metrics - Grafana dashboards (6-row template per service)
24 lines
671 B
YAML
24 lines
671 B
YAML
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: forgejo-rules
|
|
namespace: forgejo
|
|
spec:
|
|
groups:
|
|
- name: forgejo.rules
|
|
interval: 15s
|
|
rules:
|
|
- alert: ForgejoHighErrorRate
|
|
expr: |
|
|
(
|
|
sum(rate(forgejo_http_request_total{status=~"5.."}[5m]))
|
|
/
|
|
sum(rate(forgejo_http_request_total[5m]))
|
|
) > 0.05
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "High error rate on Forgejo"
|
|
description: "5xx error rate exceeded 5% for 10 minutes. Value: {{ $value | humanizePercentage }}"
|