- 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)
36 lines
789 B
YAML
36 lines
789 B
YAML
service: grafana
|
|
display_name: "Grafana"
|
|
namespace: logging
|
|
service_type: web-app
|
|
folder: "Grafana"
|
|
jobs: [grafana]
|
|
metrics:
|
|
prefix: grafana
|
|
up_selector: 'job="grafana"'
|
|
rate:
|
|
metric: grafana_http_request_total
|
|
labels: [handler, status]
|
|
duration:
|
|
metric: grafana_http_request_duration_seconds
|
|
type: histogram
|
|
unit: s
|
|
error:
|
|
metric: grafana_http_request_total
|
|
filter: 'status=~"5.."'
|
|
domain:
|
|
- metric: grafana_dashboard_total
|
|
kind: gauge
|
|
- metric: grafana_user_total
|
|
kind: gauge
|
|
- metric: grafana_alerts_total
|
|
kind: gauge
|
|
correlation_ids: []
|
|
logs:
|
|
loki_namespace_selector: 'namespace="logging"'
|
|
alerts:
|
|
- name: HighErrorRate
|
|
expr_template: rate_error_ratio
|
|
threshold: 0.05
|
|
for: 10m
|
|
severity: warning
|