2214 lines
63 KiB
YAML
2214 lines
63 KiB
YAML
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: traefik-grafana-dashboard
|
|
namespace: kube-mon
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
release: "kube-prometheus-stack-1761819498"
|
|
data:
|
|
traefik-overview.json: |-
|
|
{
|
|
"annotations": {
|
|
"list": [
|
|
{
|
|
"builtIn": 1,
|
|
"datasource": "-- Grafana --",
|
|
"enable": true,
|
|
"hide": true,
|
|
"iconColor": "rgba(0, 211, 255, 1)",
|
|
"name": "Annotations & Alerts",
|
|
"target": {
|
|
"limit": 100,
|
|
"matchAny": false,
|
|
"tags": [],
|
|
"type": "dashboard"
|
|
},
|
|
"type": "dashboard"
|
|
}
|
|
]
|
|
},
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 0,
|
|
"id": null,
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"id": 30,
|
|
"panels": [],
|
|
"title": "Overview",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 5
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 20
|
|
}
|
|
]
|
|
},
|
|
"unit": "reqps"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 0,
|
|
"y": 1
|
|
},
|
|
"id": 1,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "sum(rate(traefik_entrypoint_requests_total{entrypoint=~\"$entrypoint\"}[5m]))",
|
|
"legendFormat": "",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Requests/s",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 1
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 5
|
|
}
|
|
]
|
|
},
|
|
"unit": "reqps"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 6,
|
|
"y": 1
|
|
},
|
|
"id": 2,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "sum(rate(traefik_entrypoint_requests_total{entrypoint=~\"$entrypoint\",code=~\"4..\"}[5m]))",
|
|
"legendFormat": "",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "4xx/s",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 0.5
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 2
|
|
}
|
|
]
|
|
},
|
|
"unit": "reqps"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 12,
|
|
"y": 1
|
|
},
|
|
"id": 3,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "sum(rate(traefik_entrypoint_requests_total{entrypoint=~\"$entrypoint\",code=~\"5..\"}[5m]))",
|
|
"legendFormat": "",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "5xx/s",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 250
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 1000
|
|
}
|
|
]
|
|
},
|
|
"unit": "ms"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 18,
|
|
"y": 1
|
|
},
|
|
"id": 4,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "1000 * histogram_quantile(0.95, sum by (le) (rate(traefik_entrypoint_request_duration_seconds_bucket{entrypoint=~\"$entrypoint\"}[$__rate_interval])))",
|
|
"legendFormat": "",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "P95 Latency",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 5
|
|
},
|
|
"id": 31,
|
|
"panels": [],
|
|
"title": "Traffic, Latency & Routing",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "reqps"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 6
|
|
},
|
|
"id": 5,
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "sum by (entrypoint) (rate(traefik_entrypoint_requests_total{entrypoint=~\"$entrypoint\"}[$__rate_interval]))",
|
|
"legendFormat": "{{entrypoint}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Requests by Entrypoint",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "reqps"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 6
|
|
},
|
|
"id": 6,
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "sum by (code) (rate(traefik_entrypoint_requests_total{entrypoint=~\"$entrypoint\",code=~\"[2345]..\"}[$__rate_interval]))",
|
|
"legendFormat": "{{code}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Status Codes",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 14
|
|
},
|
|
"id": 7,
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "1000 * histogram_quantile(0.50, sum by (le) (rate(traefik_entrypoint_request_duration_seconds_bucket{entrypoint=~\"$entrypoint\"}[$__rate_interval])))",
|
|
"legendFormat": "p50",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "1000 * histogram_quantile(0.95, sum by (le) (rate(traefik_entrypoint_request_duration_seconds_bucket{entrypoint=~\"$entrypoint\"}[$__rate_interval])))",
|
|
"legendFormat": "p95",
|
|
"refId": "B"
|
|
},
|
|
{
|
|
"expr": "1000 * histogram_quantile(0.99, sum by (le) (rate(traefik_entrypoint_request_duration_seconds_bucket{entrypoint=~\"$entrypoint\"}[$__rate_interval])))",
|
|
"legendFormat": "p99",
|
|
"refId": "C"
|
|
}
|
|
],
|
|
"title": "Latency Percentiles",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "reqps"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 14
|
|
},
|
|
"id": 8,
|
|
"options": {
|
|
"displayMode": "gradient",
|
|
"legend": {
|
|
"displayMode": "hidden",
|
|
"showLegend": false
|
|
},
|
|
"orientation": "horizontal",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showUnfilled": true
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "topk(10, sum by (router) (rate(traefik_router_requests_total{router=~\"$router\"}[$__rate_interval])))",
|
|
"legendFormat": "{{router}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Top Routers by RPS",
|
|
"type": "bargauge"
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 8,
|
|
"x": 0,
|
|
"y": 22
|
|
},
|
|
"id": 9,
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "sum by (entrypoint) (traefik_open_connections{entrypoint=~\"$entrypoint\"})",
|
|
"legendFormat": "{{entrypoint}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Open Connections",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 1
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 5
|
|
}
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 4,
|
|
"x": 8,
|
|
"y": 22
|
|
},
|
|
"id": 10,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "none",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "count(traefik_tls_certs_not_after < (time() + 14 * 24 * 3600))",
|
|
"legendFormat": "",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Certs expiring in 14d",
|
|
"type": "stat"
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "reqps"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 22
|
|
},
|
|
"id": 11,
|
|
"options": {
|
|
"displayMode": "gradient",
|
|
"legend": {
|
|
"displayMode": "hidden",
|
|
"showLegend": false
|
|
},
|
|
"orientation": "horizontal",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showUnfilled": true
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "topk(10, sum by (router) (rate(traefik_router_requests_total{router=~\"$router\",code=~\"5..\"}[$__rate_interval])))",
|
|
"legendFormat": "{{router}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Top Routers by 5xx/s",
|
|
"type": "bargauge"
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 30
|
|
},
|
|
"id": 34,
|
|
"panels": [],
|
|
"title": "Prometheus Deep Dive",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 50
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 90
|
|
}
|
|
]
|
|
},
|
|
"unit": "percent"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 4,
|
|
"x": 0,
|
|
"y": 31
|
|
},
|
|
"id": 35,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "100 * sum(rate(traefik_entrypoint_requests_tls_total{entrypoint=~\"$entrypoint\"}[5m])) / clamp_min(sum(rate(traefik_entrypoint_requests_total{entrypoint=~\"$entrypoint\"}[5m])), 0.001)",
|
|
"legendFormat": "",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "TLS Share",
|
|
"type": "stat",
|
|
"description": "Share of Traefik requests arriving over TLS for the selected entrypoints."
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 1
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 10
|
|
}
|
|
]
|
|
},
|
|
"unit": "reqps"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 4,
|
|
"x": 4,
|
|
"y": 31
|
|
},
|
|
"id": 36,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "sum(rate(traefik_entrypoint_requests_tls_total{entrypoint=~\"$entrypoint\"}[5m]))",
|
|
"legendFormat": "",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "TLS Requests/s",
|
|
"type": "stat",
|
|
"description": "TLS request rate across the selected entrypoints."
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 1048576
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 10485760
|
|
}
|
|
]
|
|
},
|
|
"unit": "binBps"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 4,
|
|
"x": 8,
|
|
"y": 31
|
|
},
|
|
"id": 37,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "sum(rate(traefik_entrypoint_requests_bytes_total{entrypoint=~\"$entrypoint\"}[5m]))",
|
|
"legendFormat": "",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Ingress Traffic",
|
|
"type": "stat",
|
|
"description": "Request bandwidth entering Traefik."
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 1048576
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 10485760
|
|
}
|
|
]
|
|
},
|
|
"unit": "binBps"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 4,
|
|
"x": 12,
|
|
"y": 31
|
|
},
|
|
"id": 38,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "sum(rate(traefik_entrypoint_responses_bytes_total{entrypoint=~\"$entrypoint\"}[5m]))",
|
|
"legendFormat": "",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Egress Traffic",
|
|
"type": "stat",
|
|
"description": "Response bandwidth leaving Traefik."
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 1
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 10
|
|
}
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 4,
|
|
"x": 16,
|
|
"y": 31
|
|
},
|
|
"id": 39,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "sum(increase(traefik_config_reloads_total[24h]))",
|
|
"legendFormat": "",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Config Reloads 24h",
|
|
"type": "stat",
|
|
"description": "How often Traefik reloaded its dynamic configuration in the last 24 hours."
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 24
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 168
|
|
}
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 4,
|
|
"x": 20,
|
|
"y": 31
|
|
},
|
|
"id": 40,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "(time() - max(traefik_config_last_reload_success)) / 3600",
|
|
"legendFormat": "",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Last Successful Reload Age (h)",
|
|
"type": "stat",
|
|
"description": "Hours since the last successful configuration reload reported by Traefik."
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "reqps"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 8,
|
|
"x": 0,
|
|
"y": 35
|
|
},
|
|
"id": 41,
|
|
"options": {
|
|
"displayMode": "gradient",
|
|
"legend": {
|
|
"displayMode": "hidden",
|
|
"showLegend": false
|
|
},
|
|
"orientation": "horizontal",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showUnfilled": true
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "topk(12, sum by (exported_service) (rate(traefik_service_requests_total{exported_service=~\"$backend_regex\"}[$__rate_interval])))",
|
|
"legendFormat": "{{exported_service}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Top Backends by RPS",
|
|
"type": "bargauge",
|
|
"description": "Backend services with the highest request rate according to Traefik service metrics."
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "binBps"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 8,
|
|
"x": 8,
|
|
"y": 35
|
|
},
|
|
"id": 42,
|
|
"options": {
|
|
"displayMode": "gradient",
|
|
"legend": {
|
|
"displayMode": "hidden",
|
|
"showLegend": false
|
|
},
|
|
"orientation": "horizontal",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showUnfilled": true
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "topk(12, sum by (exported_service) (rate(traefik_service_responses_bytes_total{exported_service=~\"$backend_regex\"}[$__rate_interval])))",
|
|
"legendFormat": "{{exported_service}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Top Backends by Response Throughput",
|
|
"type": "bargauge",
|
|
"description": "Backend services returning the most response traffic."
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 8,
|
|
"x": 16,
|
|
"y": 35
|
|
},
|
|
"id": 43,
|
|
"options": {
|
|
"displayMode": "gradient",
|
|
"legend": {
|
|
"displayMode": "hidden",
|
|
"showLegend": false
|
|
},
|
|
"orientation": "horizontal",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showUnfilled": true
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "topk(12, 1000 * histogram_quantile(0.95, sum by (exported_service, le) (rate(traefik_service_request_duration_seconds_bucket{exported_service=~\"$backend_regex\"}[$__rate_interval]))))",
|
|
"legendFormat": "{{exported_service}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Slowest Backends by P95",
|
|
"type": "bargauge",
|
|
"description": "Backends with the highest p95 request latency from Traefik's point of view."
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 8,
|
|
"x": 0,
|
|
"y": 43
|
|
},
|
|
"id": 44,
|
|
"options": {
|
|
"displayMode": "gradient",
|
|
"legend": {
|
|
"displayMode": "hidden",
|
|
"showLegend": false
|
|
},
|
|
"orientation": "horizontal",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showUnfilled": true
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "topk(12, 1000 * histogram_quantile(0.95, sum by (router, le) (rate(traefik_router_request_duration_seconds_bucket{router=~\"$router\"}[$__rate_interval]))))",
|
|
"legendFormat": "{{router}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Slowest Routers by P95",
|
|
"type": "bargauge",
|
|
"description": "Routers with the highest p95 latency."
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "reqps"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 8,
|
|
"x": 8,
|
|
"y": 43
|
|
},
|
|
"id": 45,
|
|
"options": {
|
|
"displayMode": "gradient",
|
|
"legend": {
|
|
"displayMode": "hidden",
|
|
"showLegend": false
|
|
},
|
|
"orientation": "horizontal",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showUnfilled": true
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "sum by (tls_version) (rate(traefik_service_requests_tls_total{exported_service=~\"$backend_regex\"}[$__rate_interval]))",
|
|
"legendFormat": "TLS {{tls_version}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "TLS Requests by Version",
|
|
"type": "bargauge",
|
|
"description": "Current TLS request split by negotiated TLS version."
|
|
},
|
|
{
|
|
"datasource": "$prometheus_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 8,
|
|
"x": 16,
|
|
"y": 43
|
|
},
|
|
"id": 46,
|
|
"options": {
|
|
"displayMode": "gradient",
|
|
"legend": {
|
|
"displayMode": "hidden",
|
|
"showLegend": false
|
|
},
|
|
"orientation": "horizontal",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showUnfilled": true
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "bottomk(12, (max by (cn) (traefik_tls_certs_not_after) - time()) / 86400)",
|
|
"legendFormat": "{{cn}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Soonest Certificate Expiry (days)",
|
|
"type": "bargauge",
|
|
"description": "Certificates with the fewest days remaining before expiry, deduplicated by CN."
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 51
|
|
},
|
|
"id": 32,
|
|
"panels": [],
|
|
"title": "Fail2Ban & Ban History",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": "$loki_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 1
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 5
|
|
}
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 0,
|
|
"y": 52
|
|
},
|
|
"id": 14,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"targets": [
|
|
{
|
|
"editorMode": "code",
|
|
"expr": "sum(count_over_time({namespace=\"traefik\", pod=~\"$pod_regex\", container=\"traefik\"} | json | __error__=\"\" | prefix=\"Fail-2-Ban\" | msg =~ \"(Extend Ban for .*|Ban for .*)\" [$__range]))",
|
|
"instant": true,
|
|
"queryType": "instant",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Ban / Extend Events",
|
|
"type": "stat",
|
|
"description": "Log-based count of Fail2Ban ban or ban-extension events in the selected time range."
|
|
},
|
|
{
|
|
"datasource": "$loki_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 1
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 5
|
|
}
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 6,
|
|
"y": 52
|
|
},
|
|
"id": 15,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"targets": [
|
|
{
|
|
"editorMode": "code",
|
|
"expr": "count(sum by (ip) (count_over_time({namespace=\"traefik\", pod=~\"$pod_regex\", container=\"traefik\"} | json | __error__=\"\" | prefix=\"Fail-2-Ban\" | msg =~ \"(Extend Ban for .*|Ban for .*)\" | regexp \"(?:Extend Ban|Ban) for (?P<ip>[0-9A-Fa-f:.]+)\" | ip =~ \"$ip_regex\" [$__range])))",
|
|
"instant": true,
|
|
"queryType": "instant",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "IPs Seen in Ban Events",
|
|
"type": "stat",
|
|
"description": "Unique IPs with at least one Fail2Ban ban event in the selected time range. This is log-derived, not a kernel live-ban list."
|
|
},
|
|
{
|
|
"datasource": "$loki_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 52
|
|
},
|
|
"id": 16,
|
|
"options": {
|
|
"displayMode": "gradient",
|
|
"legend": {
|
|
"displayMode": "hidden",
|
|
"showLegend": false
|
|
},
|
|
"orientation": "horizontal",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showUnfilled": true
|
|
},
|
|
"targets": [
|
|
{
|
|
"editorMode": "code",
|
|
"expr": "topk(25, sum by (ip) (count_over_time({namespace=\"traefik\", pod=~\"$pod_regex\", container=\"traefik\"} | json | __error__=\"\" | prefix=\"Fail-2-Ban\" | msg =~ \"(Extend Ban for .*|Ban for .*)\" | regexp \"(?:Extend Ban|Ban) for (?P<ip>[0-9A-Fa-f:.]+)\" | ip =~ \"$ip_regex\" [$__range])))",
|
|
"instant": true,
|
|
"legendFormat": "{{ip}}",
|
|
"queryType": "instant",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Blocked IPs by Ban Events",
|
|
"type": "bargauge",
|
|
"description": "Top IPs ranked by Fail2Ban ban events seen in logs during the selected time range."
|
|
},
|
|
{
|
|
"datasource": "$loki_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 56
|
|
},
|
|
"id": 17,
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"editorMode": "code",
|
|
"expr": "sum(count_over_time({namespace=\"traefik\", pod=~\"$pod_regex\", container=\"traefik\"} | json | __error__=\"\" | prefix=\"Fail-2-Ban\" | msg =~ \"(Extend Ban for .*|Ban for .*)\" [$__interval]))",
|
|
"legendFormat": "block events",
|
|
"queryType": "range",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Ban Events Over Time",
|
|
"type": "timeseries",
|
|
"description": "Time series of Fail2Ban ban events. Useful for spotting brute-force or scan spikes."
|
|
},
|
|
{
|
|
"datasource": "$loki_ds",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 56
|
|
},
|
|
"id": 18,
|
|
"options": {
|
|
"dedupStrategy": "none",
|
|
"enableLogDetails": true,
|
|
"prettifyLogMessage": false,
|
|
"showCommonLabels": false,
|
|
"showLabels": true,
|
|
"showTime": true,
|
|
"sortOrder": "Descending",
|
|
"wrapLogMessage": true
|
|
},
|
|
"targets": [
|
|
{
|
|
"direction": "backward",
|
|
"editorMode": "code",
|
|
"expr": "{namespace=\"traefik\", pod=~\"$pod_regex\", container=\"traefik\"} | json | __error__=\"\" | prefix=\"Fail-2-Ban\" | msg =~ \"(Extend Ban for .*|Ban for .*|Un-Banned .*|Clearing out state for .*|Failed to get Client Identifier.*)\" | msg =~ \".*$ip_regex.*\"",
|
|
"queryType": "range",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Fail2Ban Event Logs",
|
|
"type": "logs",
|
|
"description": "Raw Fail2Ban event lines, filterable via the shared IP regex variable."
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 64
|
|
},
|
|
"id": 19,
|
|
"panels": [],
|
|
"title": "Client IP & Host Analysis",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": "$loki_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 100
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 250
|
|
}
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 8,
|
|
"x": 0,
|
|
"y": 65
|
|
},
|
|
"id": 20,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"targets": [
|
|
{
|
|
"editorMode": "code",
|
|
"expr": "count(sum by (ClientHost) (count_over_time({namespace=\"traefik\", pod=~\"$pod_regex\", container=\"traefik\"} | json | __error__=\"\" | RequestHost =~ \"$request_host\" | ClientHost =~ \"$ip_regex\" [$__range])))",
|
|
"instant": true,
|
|
"queryType": "instant",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Unique Client IPs",
|
|
"type": "stat",
|
|
"description": "Distinct client source IPs seen in Traefik access logs for the selected host/IP filters."
|
|
},
|
|
{
|
|
"datasource": "$loki_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 25
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 100
|
|
}
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 8,
|
|
"x": 8,
|
|
"y": 65
|
|
},
|
|
"id": 21,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"targets": [
|
|
{
|
|
"editorMode": "code",
|
|
"expr": "count(sum by (ClientHost) (count_over_time({namespace=\"traefik\", pod=~\"$pod_regex\", container=\"traefik\"} | json | __error__=\"\" | RequestHost =~ \"$request_host\" | ClientHost =~ \"$ip_regex\" | DownstreamStatus >= 400 | DownstreamStatus < 500 [$__range])))",
|
|
"instant": true,
|
|
"queryType": "instant",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Unique 4xx Client IPs",
|
|
"type": "stat",
|
|
"description": "Distinct source IPs that triggered 4xx responses in the selected time range."
|
|
},
|
|
{
|
|
"datasource": "$loki_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 5
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 20
|
|
}
|
|
]
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 8,
|
|
"x": 16,
|
|
"y": 65
|
|
},
|
|
"id": 22,
|
|
"options": {
|
|
"colorMode": "background",
|
|
"graphMode": "area",
|
|
"justifyMode": "auto",
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"textMode": "auto"
|
|
},
|
|
"targets": [
|
|
{
|
|
"editorMode": "code",
|
|
"expr": "count(sum by (ClientHost) (count_over_time({namespace=\"traefik\", pod=~\"$pod_regex\", container=\"traefik\"} | json | __error__=\"\" | RequestHost =~ \"$request_host\" | ClientHost =~ \"$ip_regex\" | DownstreamStatus >= 500 [$__range])))",
|
|
"instant": true,
|
|
"queryType": "instant",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Unique 5xx Client IPs",
|
|
"type": "stat",
|
|
"description": "Distinct source IPs that hit upstream/server-side failures in the selected time range."
|
|
},
|
|
{
|
|
"datasource": "$loki_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 8,
|
|
"x": 0,
|
|
"y": 69
|
|
},
|
|
"id": 23,
|
|
"options": {
|
|
"displayMode": "gradient",
|
|
"legend": {
|
|
"displayMode": "hidden",
|
|
"showLegend": false
|
|
},
|
|
"orientation": "horizontal",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showUnfilled": true
|
|
},
|
|
"targets": [
|
|
{
|
|
"editorMode": "code",
|
|
"expr": "topk(15, sum by (ClientHost) (count_over_time({namespace=\"traefik\", pod=~\"$pod_regex\", container=\"traefik\"} | json | __error__=\"\" | RequestHost =~ \"$request_host\" | ClientHost =~ \"$ip_regex\" [$__range])))",
|
|
"instant": true,
|
|
"legendFormat": "{{ClientHost}}",
|
|
"queryType": "instant",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Top Client IPs by Requests",
|
|
"type": "bargauge",
|
|
"description": "Request-heavy client IPs from Traefik access logs for the selected range."
|
|
},
|
|
{
|
|
"datasource": "$loki_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 8,
|
|
"x": 8,
|
|
"y": 69
|
|
},
|
|
"id": 24,
|
|
"options": {
|
|
"displayMode": "gradient",
|
|
"legend": {
|
|
"displayMode": "hidden",
|
|
"showLegend": false
|
|
},
|
|
"orientation": "horizontal",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showUnfilled": true
|
|
},
|
|
"targets": [
|
|
{
|
|
"editorMode": "code",
|
|
"expr": "topk(15, sum by (ClientHost) (count_over_time({namespace=\"traefik\", pod=~\"$pod_regex\", container=\"traefik\"} | json | __error__=\"\" | RequestHost =~ \"$request_host\" | ClientHost =~ \"$ip_regex\" | DownstreamStatus >= 400 | DownstreamStatus < 500 [$__range])))",
|
|
"instant": true,
|
|
"legendFormat": "{{ClientHost}}",
|
|
"queryType": "instant",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Top Client IPs by 4xx",
|
|
"type": "bargauge",
|
|
"description": "Client IPs producing the most 4xx responses in the selected range."
|
|
},
|
|
{
|
|
"datasource": "$loki_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 8,
|
|
"x": 16,
|
|
"y": 69
|
|
},
|
|
"id": 25,
|
|
"options": {
|
|
"displayMode": "gradient",
|
|
"legend": {
|
|
"displayMode": "hidden",
|
|
"showLegend": false
|
|
},
|
|
"orientation": "horizontal",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showUnfilled": true
|
|
},
|
|
"targets": [
|
|
{
|
|
"editorMode": "code",
|
|
"expr": "topk(15, sum by (ClientHost) (count_over_time({namespace=\"traefik\", pod=~\"$pod_regex\", container=\"traefik\"} | json | __error__=\"\" | RequestHost =~ \"$request_host\" | ClientHost =~ \"$ip_regex\" | DownstreamStatus >= 500 [$__range])))",
|
|
"instant": true,
|
|
"legendFormat": "{{ClientHost}}",
|
|
"queryType": "instant",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Top Client IPs by 5xx",
|
|
"type": "bargauge",
|
|
"description": "Client IPs associated with the most 5xx responses in the selected range."
|
|
},
|
|
{
|
|
"datasource": "$loki_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 77
|
|
},
|
|
"id": 26,
|
|
"options": {
|
|
"displayMode": "gradient",
|
|
"legend": {
|
|
"displayMode": "hidden",
|
|
"showLegend": false
|
|
},
|
|
"orientation": "horizontal",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showUnfilled": true
|
|
},
|
|
"targets": [
|
|
{
|
|
"editorMode": "code",
|
|
"expr": "topk(12, sum by (RequestHost) (count_over_time({namespace=\"traefik\", pod=~\"$pod_regex\", container=\"traefik\"} | json | __error__=\"\" | RequestHost =~ \"$request_host\" | ClientHost =~ \"$ip_regex\" | DownstreamStatus >= 400 | DownstreamStatus < 500 [$__range])))",
|
|
"instant": true,
|
|
"legendFormat": "{{RequestHost}}",
|
|
"queryType": "instant",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Top Request Hosts by 4xx",
|
|
"type": "bargauge",
|
|
"description": "Hosts currently attracting the most client-side errors or probes."
|
|
},
|
|
{
|
|
"datasource": "$loki_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 77
|
|
},
|
|
"id": 27,
|
|
"options": {
|
|
"displayMode": "gradient",
|
|
"legend": {
|
|
"displayMode": "hidden",
|
|
"showLegend": false
|
|
},
|
|
"orientation": "horizontal",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showUnfilled": true
|
|
},
|
|
"targets": [
|
|
{
|
|
"editorMode": "code",
|
|
"expr": "topk(12, sum by (RequestHost) (count_over_time({namespace=\"traefik\", pod=~\"$pod_regex\", container=\"traefik\"} | json | __error__=\"\" | RequestHost =~ \"$request_host\" | ClientHost =~ \"$ip_regex\" | DownstreamStatus >= 500 [$__range])))",
|
|
"instant": true,
|
|
"legendFormat": "{{RequestHost}}",
|
|
"queryType": "instant",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Top Request Hosts by 5xx",
|
|
"type": "bargauge",
|
|
"description": "Hosts whose backends currently generate the most 5xx responses."
|
|
},
|
|
{
|
|
"datasource": "$loki_ds",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 85
|
|
},
|
|
"id": 28,
|
|
"options": {
|
|
"cellHeight": "sm",
|
|
"showHeader": true,
|
|
"footer": {
|
|
"show": false,
|
|
"reducer": [
|
|
"sum"
|
|
],
|
|
"fields": ""
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"editorMode": "code",
|
|
"expr": "topk(50, sum by (ip) (count_over_time({namespace=\"traefik\", pod=~\"$pod_regex\", container=\"traefik\"} | json | __error__=\"\" | prefix=\"Fail-2-Ban\" | msg =~ \"(Extend Ban for .*|Ban for .*)\" | regexp \"(?:Extend Ban|Ban) for (?P<ip>[0-9A-Fa-f:.]+)\" | ip =~ \"$ip_regex\" [$__range])))",
|
|
"instant": true,
|
|
"legendFormat": "{{ip}}",
|
|
"queryType": "instant",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Blocked IPs in Selected Range",
|
|
"type": "table",
|
|
"description": "IP addresses that were blocked by Fail2Ban during the selected time range. This is log-derived history, not a live nftables/iptables inventory."
|
|
},
|
|
{
|
|
"datasource": "$loki_ds",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 85
|
|
},
|
|
"id": 29,
|
|
"options": {
|
|
"dedupStrategy": "none",
|
|
"enableLogDetails": true,
|
|
"prettifyLogMessage": false,
|
|
"showCommonLabels": false,
|
|
"showLabels": true,
|
|
"showTime": true,
|
|
"sortOrder": "Descending",
|
|
"wrapLogMessage": true
|
|
},
|
|
"targets": [
|
|
{
|
|
"direction": "backward",
|
|
"editorMode": "code",
|
|
"expr": "{namespace=\"traefik\", pod=~\"$pod_regex\", container=\"traefik\"} | json | __error__=\"\" | prefix=\"Fail-2-Ban\" | msg =~ \"(Extend Ban for .*|Ban for .*|Un-Banned .*|Clearing out state for .*|Failed to get Client Identifier.*)\" | msg =~ \".*$ip_regex.*\"",
|
|
"queryType": "range",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Recent Fail2Ban Ban / Unban Events",
|
|
"type": "logs",
|
|
"description": "Recent Fail2Ban state changes and related events, filtered by the shared IP regex when needed."
|
|
},
|
|
{
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 93
|
|
},
|
|
"id": 33,
|
|
"panels": [],
|
|
"title": "Raw Traefik Logs",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"datasource": "$loki_ds",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 94
|
|
},
|
|
"id": 12,
|
|
"options": {
|
|
"dedupStrategy": "none",
|
|
"enableLogDetails": true,
|
|
"prettifyLogMessage": false,
|
|
"showCommonLabels": false,
|
|
"showLabels": true,
|
|
"showTime": true,
|
|
"sortOrder": "Descending",
|
|
"wrapLogMessage": true
|
|
},
|
|
"targets": [
|
|
{
|
|
"direction": "backward",
|
|
"editorMode": "code",
|
|
"expr": "{namespace=\"traefik\", pod=~\"$pod_regex\", container=\"traefik\"} | json | __error__=\"\" | RequestHost =~ \"$request_host\" | ClientHost =~ \"$ip_regex\"",
|
|
"queryType": "range",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Access Logs (Filtered)",
|
|
"type": "logs"
|
|
},
|
|
{
|
|
"datasource": "$loki_ds",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 94
|
|
},
|
|
"id": 13,
|
|
"options": {
|
|
"dedupStrategy": "none",
|
|
"enableLogDetails": true,
|
|
"prettifyLogMessage": false,
|
|
"showCommonLabels": false,
|
|
"showLabels": true,
|
|
"showTime": true,
|
|
"sortOrder": "Descending",
|
|
"wrapLogMessage": true
|
|
},
|
|
"targets": [
|
|
{
|
|
"direction": "backward",
|
|
"editorMode": "code",
|
|
"expr": "{namespace=\"traefik\", pod=~\"$pod_regex\", container=\"traefik\"} | json | __error__=\"\" | RequestHost =~ \"$request_host\" | ClientHost =~ \"$ip_regex\" | DownstreamStatus >= 400",
|
|
"queryType": "range",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "Error Logs (4xx/5xx)",
|
|
"type": "logs"
|
|
}
|
|
],
|
|
"refresh": "30s",
|
|
"schemaVersion": 41,
|
|
"tags": [
|
|
"traefik",
|
|
"prometheus",
|
|
"loki",
|
|
"security",
|
|
"fail2ban"
|
|
],
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"current": {
|
|
"selected": true,
|
|
"text": "Prometheus",
|
|
"value": "Prometheus"
|
|
},
|
|
"hide": 0,
|
|
"includeAll": false,
|
|
"label": "Prometheus",
|
|
"multi": false,
|
|
"name": "prometheus_ds",
|
|
"options": [],
|
|
"query": "prometheus",
|
|
"refresh": 1,
|
|
"regex": "",
|
|
"skipUrlSync": false,
|
|
"type": "datasource"
|
|
},
|
|
{
|
|
"current": {
|
|
"selected": true,
|
|
"text": "Loki Traefik",
|
|
"value": "Loki Traefik"
|
|
},
|
|
"hide": 0,
|
|
"includeAll": false,
|
|
"label": "Loki",
|
|
"multi": false,
|
|
"name": "loki_ds",
|
|
"options": [],
|
|
"query": "loki",
|
|
"refresh": 1,
|
|
"regex": "",
|
|
"skipUrlSync": false,
|
|
"type": "datasource"
|
|
},
|
|
{
|
|
"allValue": ".*",
|
|
"current": {
|
|
"selected": true,
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"datasource": "$prometheus_ds",
|
|
"definition": "label_values(traefik_entrypoint_requests_total, entrypoint)",
|
|
"hide": 0,
|
|
"includeAll": true,
|
|
"label": "Entrypoint",
|
|
"multi": true,
|
|
"name": "entrypoint",
|
|
"options": [],
|
|
"query": {
|
|
"query": "label_values(traefik_entrypoint_requests_total, entrypoint)",
|
|
"refId": "EntrypointVar"
|
|
},
|
|
"refresh": 1,
|
|
"regex": "",
|
|
"skipUrlSync": false,
|
|
"sort": 1,
|
|
"type": "query"
|
|
},
|
|
{
|
|
"allValue": ".*",
|
|
"current": {
|
|
"selected": true,
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"datasource": "$prometheus_ds",
|
|
"definition": "label_values(traefik_router_requests_total, router)",
|
|
"hide": 0,
|
|
"includeAll": true,
|
|
"label": "Router",
|
|
"multi": true,
|
|
"name": "router",
|
|
"options": [],
|
|
"query": {
|
|
"query": "label_values(traefik_router_requests_total, router)",
|
|
"refId": "RouterVar"
|
|
},
|
|
"refresh": 1,
|
|
"regex": "",
|
|
"skipUrlSync": false,
|
|
"sort": 1,
|
|
"type": "query"
|
|
},
|
|
{
|
|
"current": {
|
|
"selected": true,
|
|
"text": "traefik-.*",
|
|
"value": "traefik-.*"
|
|
},
|
|
"hide": 0,
|
|
"label": "Pod Regex",
|
|
"name": "pod_regex",
|
|
"options": [
|
|
{
|
|
"selected": true,
|
|
"text": "traefik-.*",
|
|
"value": "traefik-.*"
|
|
}
|
|
],
|
|
"query": "traefik-.*",
|
|
"skipUrlSync": false,
|
|
"type": "textbox"
|
|
},
|
|
{
|
|
"current": {
|
|
"selected": true,
|
|
"text": ".*",
|
|
"value": ".*"
|
|
},
|
|
"hide": 0,
|
|
"label": "Host Regex",
|
|
"name": "request_host",
|
|
"options": [
|
|
{
|
|
"selected": true,
|
|
"text": ".*",
|
|
"value": ".*"
|
|
}
|
|
],
|
|
"query": ".*",
|
|
"skipUrlSync": false,
|
|
"type": "textbox"
|
|
},
|
|
{
|
|
"current": {
|
|
"selected": true,
|
|
"text": ".*",
|
|
"value": ".*"
|
|
},
|
|
"hide": 0,
|
|
"label": "IP Regex",
|
|
"name": "ip_regex",
|
|
"options": [
|
|
{
|
|
"selected": true,
|
|
"text": ".*",
|
|
"value": ".*"
|
|
}
|
|
],
|
|
"query": ".*",
|
|
"skipUrlSync": false,
|
|
"type": "textbox"
|
|
},
|
|
{
|
|
"current": {
|
|
"selected": true,
|
|
"text": ".*",
|
|
"value": ".*"
|
|
},
|
|
"hide": 0,
|
|
"label": "Backend Regex",
|
|
"name": "backend_regex",
|
|
"options": [
|
|
{
|
|
"selected": true,
|
|
"text": ".*",
|
|
"value": ".*"
|
|
}
|
|
],
|
|
"query": ".*",
|
|
"skipUrlSync": false,
|
|
"type": "textbox"
|
|
}
|
|
]
|
|
},
|
|
"time": {
|
|
"from": "now-6h",
|
|
"to": "now"
|
|
},
|
|
"timepicker": {
|
|
"refresh_intervals": [
|
|
"10s",
|
|
"30s",
|
|
"1m",
|
|
"5m",
|
|
"15m",
|
|
"30m",
|
|
"1h",
|
|
"2h",
|
|
"1d"
|
|
]
|
|
},
|
|
"timezone": "browser",
|
|
"title": "Traefik Overview",
|
|
"uid": "traefik-overview",
|
|
"version": 10,
|
|
"weekStart": ""
|
|
}
|