051c957347
- Add ServiceMonitors for Traefik, ArgoCD, and Longhorn - Enable cert-manager ServiceMonitor via helm values - Deploy Grafana Tempo for distributed tracing (single-binary, Longhorn PVC) - Add Tempo datasource with trace-to-logs and trace-to-metrics correlation - Instrument API with OpenTelemetry SDK (Prometheus metrics + OTLP traces) - Replace console.log with pino structured logging + pino-http middleware - Add Grafana dashboards for Traefik, API overview, and PostgreSQL (CNPG)
90 lines
2.7 KiB
YAML
90 lines
2.7 KiB
YAML
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: traefik-dashboard
|
|
namespace: observability
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
data:
|
|
traefik.json: |
|
|
{
|
|
"annotations": { "list": [] },
|
|
"editable": true,
|
|
"graphTooltip": 1,
|
|
"id": null,
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"title": "Request Rate",
|
|
"type": "timeseries",
|
|
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 0 },
|
|
"targets": [
|
|
{
|
|
"expr": "sum(rate(traefik_entrypoint_requests_total[5m])) by (entrypoint)",
|
|
"legendFormat": "{{ entrypoint }}"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": { "unit": "reqps" }
|
|
}
|
|
},
|
|
{
|
|
"title": "Error Rate (4xx/5xx)",
|
|
"type": "timeseries",
|
|
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 0 },
|
|
"targets": [
|
|
{
|
|
"expr": "sum(rate(traefik_entrypoint_requests_total{code=~\"4..\"}[5m]))",
|
|
"legendFormat": "4xx"
|
|
},
|
|
{
|
|
"expr": "sum(rate(traefik_entrypoint_requests_total{code=~\"5..\"}[5m]))",
|
|
"legendFormat": "5xx"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": { "unit": "reqps" }
|
|
}
|
|
},
|
|
{
|
|
"title": "Request Duration (p50 / p95 / p99)",
|
|
"type": "timeseries",
|
|
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 8 },
|
|
"targets": [
|
|
{
|
|
"expr": "histogram_quantile(0.50, sum(rate(traefik_entrypoint_request_duration_seconds_bucket[5m])) by (le))",
|
|
"legendFormat": "p50"
|
|
},
|
|
{
|
|
"expr": "histogram_quantile(0.95, sum(rate(traefik_entrypoint_request_duration_seconds_bucket[5m])) by (le))",
|
|
"legendFormat": "p95"
|
|
},
|
|
{
|
|
"expr": "histogram_quantile(0.99, sum(rate(traefik_entrypoint_request_duration_seconds_bucket[5m])) by (le))",
|
|
"legendFormat": "p99"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": { "unit": "s" }
|
|
}
|
|
},
|
|
{
|
|
"title": "Open Connections",
|
|
"type": "timeseries",
|
|
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 8 },
|
|
"targets": [
|
|
{
|
|
"expr": "sum(traefik_entrypoint_open_connections) by (entrypoint)",
|
|
"legendFormat": "{{ entrypoint }}"
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"schemaVersion": 39,
|
|
"tags": ["homelab", "traefik", "ingress"],
|
|
"templating": { "list": [] },
|
|
"time": { "from": "now-6h", "to": "now" },
|
|
"title": "Traefik",
|
|
"uid": "traefik"
|
|
}
|