DevFW-CICD/ingress-nginx-helm
16
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
ingress-nginx-helm/deploy/grafana/dashboards/request-handling-performance.json

982 lines
23 KiB
JSON
Raw Normal View History

Add request handling performance dashboard This second dashboard helps end users drill down on a particular service and get more golden signals type metrics such as error rate by path and median upstream response time by path. Signed-off-by: Naseem <naseem@transit.app>
2020-02-19 21:56:25 +00:00
{
"__inputs": [
{
"name": "DS_PROMETHEUS",
"label": "Prometheus",
"description": "",
"type": "datasource",
"pluginId": "prometheus",
"pluginName": "Prometheus"
}
],
"__requires": [
{
"type": "grafana",
"id": "grafana",
"name": "Grafana",
"version": "6.6.0"
},
{
"type": "panel",
"id": "graph",
"name": "Graph",
"version": ""
},
{
"type": "datasource",
"id": "prometheus",
"name": "Prometheus",
"version": "1.0.0"
}
],
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": "-- Grafana --",
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"description": "",
"editable": true,
"gnetId": 9614,
"graphTooltip": 1,
"id": null,
"iteration": 1582146566338,
"links": [],
"panels": [
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"description": "Total time taken for nginx and upstream servers to process a request and send a response",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 0
},
"hiddenSeries": false,
"id": 91,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(\n 0.5,\n sum by (le)(\n rate(\n nginx_ingress_controller_request_duration_seconds_bucket{\n ingress =~ \"$ingress\"\n }[1m]\n )\n )\n)",
"interval": "",
"legendFormat": ".5",
"refId": "D"
},
{
"expr": "histogram_quantile(\n 0.95,\n sum by (le)(\n rate(\n nginx_ingress_controller_request_duration_seconds_bucket{\n ingress =~ \"$ingress\"\n }[1m]\n )\n )\n)",
"interval": "",
"legendFormat": ".95",
"refId": "B"
},
{
"expr": "histogram_quantile(\n 0.99,\n sum by (le)(\n rate(\n nginx_ingress_controller_request_duration_seconds_bucket{\n ingress =~ \"$ingress\"\n }[1m]\n )\n )\n)",
"interval": "",
"legendFormat": ".99",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Total request handling time",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"description": "The time spent on receiving the response from the upstream server",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 0
},
"hiddenSeries": false,
"id": 94,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(\n 0.5,\n sum by (le)(\n rate(\n nginx_ingress_controller_response_duration_seconds_bucket{\n ingress =~ \"$ingress\"\n }[1m]\n )\n )\n)",
"instant": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": ".5",
"refId": "D"
},
{
"expr": "histogram_quantile(\n 0.95,\n sum by (le)(\n rate(\n nginx_ingress_controller_response_duration_seconds_bucket{\n ingress =~ \"$ingress\"\n }[1m]\n )\n )\n)",
"interval": "",
"legendFormat": ".95",
"refId": "B"
},
{
"expr": "histogram_quantile(\n 0.99,\n sum by (le)(\n rate(\n nginx_ingress_controller_response_duration_seconds_bucket{\n ingress =~ \"$ingress\"\n }[1m]\n )\n )\n)",
"interval": "",
"legendFormat": ".99",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Upstream response time",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 8
},
"hiddenSeries": false,
"id": 93,
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": " sum by (path)(\n rate(\n nginx_ingress_controller_request_duration_seconds_count{\n ingress =~ \"$ingress\"\n }[1m]\n )\n )\n",
"interval": "",
"intervalFactor": 1,
"legendFormat": "{{ path }}",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Request volume by Path",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "reqps",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"description": "For each path observed, its median upstream response time",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 8
},
"hiddenSeries": false,
"id": 98,
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(\n .5,\n sum by (le, path)(\n rate(\n nginx_ingress_controller_response_duration_seconds_bucket{\n ingress =~ \"$ingress\"\n }[1m]\n )\n )\n)",
"interval": "",
"intervalFactor": 1,
"legendFormat": "{{ path }}",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Median upstream response time by Path",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"description": "Percentage of 4xx and 5xx responses among all responses.",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 16
},
"hiddenSeries": false,
"id": 100,
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null as zero",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
fix(dashboard): use regex for ingress
2021-03-29 18:05:08 +00:00
"expr": "sum by (path) (rate(nginx_ingress_controller_request_duration_seconds_count{\n ingress =~ \"$ingress\",\n status =~ \"[4-5].*\"\n}[1m])) / sum by (path) (rate(nginx_ingress_controller_request_duration_seconds_count{\n ingress =~ \"$ingress\",\n}[1m]))",
Add request handling performance dashboard This second dashboard helps end users drill down on a particular service and get more golden signals type metrics such as error rate by path and median upstream response time by path. Signed-off-by: Naseem <naseem@transit.app>
2020-02-19 21:56:25 +00:00
"interval": "",
"intervalFactor": 1,
"legendFormat": "{{ path }}",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Response error rate by Path",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "percentunit",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"description": "For each path observed, the sum of upstream request time",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 16
},
"hiddenSeries": false,
"id": 102,
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
fix(dashboard): use regex for ingress
2021-03-29 18:05:08 +00:00
"expr": "sum by (path) (rate(nginx_ingress_controller_response_duration_seconds_sum{ingress =~ \"$ingress\"}[1m]))",
Add request handling performance dashboard This second dashboard helps end users drill down on a particular service and get more golden signals type metrics such as error rate by path and median upstream response time by path. Signed-off-by: Naseem <naseem@transit.app>
2020-02-19 21:56:25 +00:00
"interval": "",
"intervalFactor": 1,
"legendFormat": "{{ path }}",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Upstream time consumed by Path",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 24
},
"hiddenSeries": false,
"id": 101,
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": " sum (\n rate(\n nginx_ingress_controller_request_duration_seconds_count{\n ingress =~ \"$ingress\",\n status =~\"[4-5].*\",\n }[1m]\n )\n ) by(path, status)\n",
"interval": "",
"intervalFactor": 1,
"legendFormat": "{{ path }} {{ status }}",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Response error volume by Path",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "reqps",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 24
},
"hiddenSeries": false,
"id": 99,
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum (\n rate (\n nginx_ingress_controller_response_size_sum {\n ingress =~ \"$ingress\",\n }[1m]\n )\n) by (path) / sum (\n rate(\n nginx_ingress_controller_response_size_count {\n ingress =~ \"$ingress\",\n }[1m]\n )\n) by (path)\n",
"hide": false,
"instant": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "{{ path }}",
"refId": "D"
},
{
fix(dashboard): remove unnecessary namespace variable in query
2021-03-29 18:20:05 +00:00
"expr": " sum (rate(nginx_ingress_controller_response_size_bucket{\n ingress =~ \"$ingress\",\n }[1m])) by (le)\n",
Add request handling performance dashboard This second dashboard helps end users drill down on a particular service and get more golden signals type metrics such as error rate by path and median upstream response time by path. Signed-off-by: Naseem <naseem@transit.app>
2020-02-19 21:56:25 +00:00
"hide": true,
"legendFormat": "{{le}}",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Average response size by Path",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "decbytes",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 32
},
"hiddenSeries": false,
"id": 96,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum (\n rate(\n nginx_ingress_controller_ingress_upstream_latency_seconds_sum {\n ingress =~ \"$ingress\",\n }[1m]\n)) / sum (\n rate(\n nginx_ingress_controller_ingress_upstream_latency_seconds_count {\n ingress =~ \"$ingress\",\n }[1m]\n )\n)\n",
"hide": false,
"instant": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "average",
"refId": "B"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Upstream service latency",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
}
],
"refresh": "30s",
"schemaVersion": 22,
"style": "dark",
"tags": [
"nginx"
],
"templating": {
"list": [
Add DS_PROMETHEUS datasource for templating When running this dashboard on Grafana, I received the error `Datasource named ${DS_PROMETHEUS} was not found`, this change fixes that issue.
2020-03-24 20:49:03 +00:00
{
"hide": 0,
"label": "datasource",
"name": "DS_PROMETHEUS",
"options": [],
"query": "prometheus",
"refresh": 1,
"regex": "",
"type": "datasource"
},
Add request handling performance dashboard This second dashboard helps end users drill down on a particular service and get more golden signals type metrics such as error rate by path and median upstream response time by path. Signed-off-by: Naseem <naseem@transit.app>
2020-02-19 21:56:25 +00:00
{
"allValue": ".*",
"current": {},
"datasource": "${DS_PROMETHEUS}",
"definition": "label_values(nginx_ingress_controller_requests, ingress) ",
"hide": 0,
"includeAll": true,
"label": "Service Ingress",
"multi": false,
"name": "ingress",
"options": [],
"query": "label_values(nginx_ingress_controller_requests, ingress) ",
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 2,
"tagValuesQuery": "",
"tags": [],
"tagsQuery": "",
"type": "query",
"useTags": false
}
]
},
"time": {
"from": "now-15m",
"to": "now"
},
"timepicker": {
"refresh_intervals": [
"5s",
"10s",
"30s",
"2m",
"5m",
"15m",
"30m",
"1h",
"2h",
"1d"
],
"time_options": [
"5m",
"15m",
"1h",
"6h",
"12h",
"24h",
"2d",
"7d",
"30d"
]
},
"timezone": "browser",
"title": "Request Handling Performance",
"uid": "4GFbkOsZk",
"version": 1
}
Reference in a new issue Copy permalink