added alerting rules for grafana
This commit is contained in:
rezayaghobi-dev
502
dashboards/traefik-dashboards/traefik-homelab-dashboard.json
Normal file
502
dashboards/traefik-dashboards/traefik-homelab-dashboard.json
Normal file
@@ -0,0 +1,502 @@
|
||||
{
|
||||
"annotations": {
|
||||
"list": []
|
||||
},
|
||||
"editable": true,
|
||||
"fiscalYearStartMonth": 0,
|
||||
"graphTooltip": 1,
|
||||
"id": null,
|
||||
"links": [],
|
||||
"liveNow": false,
|
||||
"panels": [
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 0 },
|
||||
"id": 100,
|
||||
"panels": [],
|
||||
"title": "Overview",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "thresholds" },
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [{ "color": "green", "value": null }]
|
||||
},
|
||||
"unit": "reqps"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 4, "w": 6, "x": 0, "y": 1 },
|
||||
"id": 1,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"pluginVersion": "10.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"expr": "sum(rate(traefik_router_requests_total[5m]))",
|
||||
"legendFormat": "Total request rate",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Total Request Rate",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "thresholds" },
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "color": "green", "value": null },
|
||||
{ "color": "yellow", "value": 0.01 },
|
||||
{ "color": "red", "value": 0.05 }
|
||||
]
|
||||
},
|
||||
"unit": "percentunit"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 4, "w": 6, "x": 6, "y": 1 },
|
||||
"id": 2,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"pluginVersion": "10.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"expr": "sum(rate(traefik_router_requests_total{code=~\"5..\"}[5m])) / sum(rate(traefik_router_requests_total[5m]))",
|
||||
"legendFormat": "5xx error rate",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "5xx Error Rate",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "thresholds" },
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{ "color": "green", "value": null },
|
||||
{ "color": "yellow", "value": 0.02 },
|
||||
{ "color": "red", "value": 0.1 }
|
||||
]
|
||||
},
|
||||
"unit": "percentunit"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 4, "w": 6, "x": 12, "y": 1 },
|
||||
"id": 3,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"pluginVersion": "10.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"expr": "sum(rate(traefik_router_requests_total{code=~\"4..\"}[5m])) / sum(rate(traefik_router_requests_total[5m]))",
|
||||
"legendFormat": "4xx error rate",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "4xx Error Rate",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "thresholds" },
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [{ "color": "green", "value": null }]
|
||||
},
|
||||
"unit": "none"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 4, "w": 6, "x": 18, "y": 1 },
|
||||
"id": 4,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"reduceOptions": { "calcs": ["lastNotNull"], "fields": "", "values": false },
|
||||
"textMode": "auto"
|
||||
},
|
||||
"pluginVersion": "10.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"expr": "sum(traefik_open_connections)",
|
||||
"legendFormat": "Open connections",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Open Connections",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 5 },
|
||||
"id": 101,
|
||||
"panels": [],
|
||||
"title": "Which Sites Get Hit The Most",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"description": "Total requests per site (router) over the selected time range, highest first.",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": {
|
||||
"axisPlacement": "auto",
|
||||
"fillOpacity": 80,
|
||||
"gradientMode": "none",
|
||||
"lineWidth": 1
|
||||
},
|
||||
"mappings": [],
|
||||
"unit": "short"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 10, "w": 12, "x": 0, "y": 6 },
|
||||
"id": 5,
|
||||
"options": {
|
||||
"barRadius": 0,
|
||||
"barWidth": 0.7,
|
||||
"fullHighlight": false,
|
||||
"groupWidth": 0.7,
|
||||
"legend": { "displayMode": "list", "placement": "bottom", "showLegend": false },
|
||||
"orientation": "horizontal",
|
||||
"showValue": "auto",
|
||||
"stacking": "none",
|
||||
"tooltip": { "mode": "single", "sort": "none" },
|
||||
"xTickLabelRotation": 0,
|
||||
"xTickLabelSpacing": 0
|
||||
},
|
||||
"pluginVersion": "10.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"expr": "topk(10, sum by (router) (increase(traefik_router_requests_total[$__range])))",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"legendFormat": "{{router}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Top 10 Sites by Total Requests",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "renameByRegex",
|
||||
"options": {
|
||||
"regex": "(.*)@docker",
|
||||
"renamePattern": "$1"
|
||||
}
|
||||
}
|
||||
],
|
||||
"type": "barchart"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"description": "Live request rate per site — which sites are being hit right now.",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": {
|
||||
"axisPlacement": "auto",
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"lineWidth": 2,
|
||||
"pointSize": 5,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"mappings": [],
|
||||
"unit": "reqps"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 10, "w": 12, "x": 12, "y": 6 },
|
||||
"id": 6,
|
||||
"options": {
|
||||
"legend": { "calcs": ["mean", "max"], "displayMode": "table", "placement": "bottom", "showLegend": true },
|
||||
"tooltip": { "mode": "multi", "sort": "desc" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"expr": "sum by (router) (rate(traefik_router_requests_total[5m]))",
|
||||
"legendFormat": "{{router}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Request Rate by Site (live)",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "renameByRegex",
|
||||
"options": {
|
||||
"regex": "(.*)@docker",
|
||||
"renamePattern": "$1"
|
||||
}
|
||||
}
|
||||
],
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 16 },
|
||||
"id": 102,
|
||||
"panels": [],
|
||||
"title": "Health & Errors",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"description": "Requests per site broken down by status code family — spot which site is throwing errors.",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": {
|
||||
"axisPlacement": "auto",
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 25,
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true,
|
||||
"stacking": { "group": "A", "mode": "normal" }
|
||||
},
|
||||
"mappings": [],
|
||||
"unit": "reqps"
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": { "id": "byRegexp", "options": "/5\\d\\d/" },
|
||||
"properties": [{ "id": "color", "value": { "fixedColor": "red", "mode": "fixed" } }]
|
||||
},
|
||||
{
|
||||
"matcher": { "id": "byRegexp", "options": "/4\\d\\d/" },
|
||||
"properties": [{ "id": "color", "value": { "fixedColor": "orange", "mode": "fixed" } }]
|
||||
},
|
||||
{
|
||||
"matcher": { "id": "byRegexp", "options": "/2\\d\\d/" },
|
||||
"properties": [{ "id": "color", "value": { "fixedColor": "green", "mode": "fixed" } }]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": { "h": 9, "w": 12, "x": 0, "y": 17 },
|
||||
"id": 7,
|
||||
"options": {
|
||||
"legend": { "calcs": ["sum"], "displayMode": "table", "placement": "bottom", "showLegend": true },
|
||||
"tooltip": { "mode": "multi", "sort": "desc" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"expr": "sum by (code) (rate(traefik_router_requests_total[5m]))",
|
||||
"legendFormat": "{{code}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Response Codes Over Time",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"description": "Which specific site/router is generating 4xx or 5xx errors right now.",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": {
|
||||
"axisPlacement": "auto",
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"lineWidth": 2,
|
||||
"pointSize": 5,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"mappings": [],
|
||||
"unit": "reqps"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 9, "w": 12, "x": 12, "y": 17 },
|
||||
"id": 8,
|
||||
"options": {
|
||||
"legend": { "calcs": ["sum"], "displayMode": "table", "placement": "bottom", "showLegend": true },
|
||||
"tooltip": { "mode": "multi", "sort": "desc" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"expr": "sum by (router) (rate(traefik_router_requests_total{code=~\"4..|5..\"}[5m]))",
|
||||
"legendFormat": "{{router}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Errors by Site",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "renameByRegex",
|
||||
"options": {
|
||||
"regex": "(.*)@docker",
|
||||
"renamePattern": "$1"
|
||||
}
|
||||
}
|
||||
],
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": { "h": 1, "w": 24, "x": 0, "y": 26 },
|
||||
"id": 103,
|
||||
"panels": [],
|
||||
"title": "Performance",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"description": "How long each site takes to respond (average), per router.",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": {
|
||||
"axisPlacement": "auto",
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"lineWidth": 2,
|
||||
"pointSize": 5,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"mappings": [],
|
||||
"unit": "s"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 9, "w": 12, "x": 0, "y": 27 },
|
||||
"id": 9,
|
||||
"options": {
|
||||
"legend": { "calcs": ["mean", "max"], "displayMode": "table", "placement": "bottom", "showLegend": true },
|
||||
"tooltip": { "mode": "multi", "sort": "desc" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"expr": "sum by (router) (rate(traefik_router_request_duration_seconds_sum[5m])) / sum by (router) (rate(traefik_router_request_duration_seconds_count[5m]))",
|
||||
"legendFormat": "{{router}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Average Response Time by Site",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "renameByRegex",
|
||||
"options": {
|
||||
"regex": "(.*)@docker",
|
||||
"renamePattern": "$1"
|
||||
}
|
||||
}
|
||||
],
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"description": "Traffic split between HTTP (web) and HTTPS (websecure) entrypoints — confirms redirects are working.",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": { "mode": "palette-classic" },
|
||||
"custom": {
|
||||
"axisPlacement": "auto",
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 15,
|
||||
"lineWidth": 2,
|
||||
"pointSize": 5,
|
||||
"showPoints": "never",
|
||||
"spanNulls": true
|
||||
},
|
||||
"mappings": [],
|
||||
"unit": "reqps"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": { "h": 9, "w": 12, "x": 12, "y": 27 },
|
||||
"id": 10,
|
||||
"options": {
|
||||
"legend": { "calcs": ["mean"], "displayMode": "table", "placement": "bottom", "showLegend": true },
|
||||
"tooltip": { "mode": "multi", "sort": "desc" }
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": { "type": "prometheus", "uid": "${datasource}" },
|
||||
"expr": "sum by (entrypoint) (rate(traefik_entrypoint_requests_total[5m]))",
|
||||
"legendFormat": "{{entrypoint}}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Traffic by Entrypoint (web vs websecure)",
|
||||
"type": "timeseries"
|
||||
}
|
||||
],
|
||||
"refresh": "30s",
|
||||
"schemaVersion": 38,
|
||||
"tags": ["traefik", "homelab"],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"current": {},
|
||||
"hide": 0,
|
||||
"label": "Data source",
|
||||
"name": "datasource",
|
||||
"query": "prometheus",
|
||||
"refresh": 1,
|
||||
"regex": "",
|
||||
"type": "datasource"
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": { "from": "now-6h", "to": "now" },
|
||||
"timepicker": {},
|
||||
"timezone": "",
|
||||
"title": "Traefik - Homelab Overview",
|
||||
"uid": "traefik-homelab",
|
||||
"version": 1,
|
||||
"weekStart": ""
|
||||
}
|
||||
Reference in New Issue
Block a user