Files
homelab/k8s/infra/monitoring/alerts/svc-grafana-rules.yaml
T

24 lines
671 B
YAML

apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
name: grafana-rules
namespace: logging
spec:
groups:
- name: grafana.rules
interval: 15s
rules:
- alert: GrafanaHighErrorRate
expr: |
(
sum(rate(grafana_http_request_total{status=~"5.."}[5m]))
/
sum(rate(grafana_http_request_total[5m]))
) > 0.05
for: 10m
labels:
severity: warning
annotations:
summary: "High error rate on Grafana"
description: "5xx error rate exceeded 5% for 10 minutes. Value: {{ $value | humanizePercentage }}"