diff --git a/deploy/grafana/dashboards/.markdownlint.json b/deploy/grafana/dashboards/.markdownlint.json new file mode 100644 index 000000000..8ab41456d --- /dev/null +++ b/deploy/grafana/dashboards/.markdownlint.json @@ -0,0 +1,3 @@ +{ + "MD024": { "siblings_only": true } +} diff --git a/deploy/grafana/dashboards/README.md b/deploy/grafana/dashboards/README.md index bfb428df0..26195583b 100644 --- a/deploy/grafana/dashboards/README.md +++ b/deploy/grafana/dashboards/README.md @@ -1,19 +1,39 @@ # Grafana Dashboards + Ingress-nginx supports a rich collection of prometheus metrics. If you have prometheus and grafana installed on your cluster then prometheus will already be scraping this data due to the `scrape` annotation on the deployment. -This folder contains a dashboard that you can import: +This folder contains two dashboards that you can import. + +## 1. NGINX Ingress Controller ![Dashboard](screenshot.png) -## Features +### Features - - Ability to filter by Namespace, Controller Class and Controller - - Visibility of Request Volume, connections, success rates, config reloads and configs out of sync. - - Network IO pressure, memory and CPU use - - Ingress P50, P95 and P99 percentile response times with IN/OUT throughput - - SSL certificate expiry - - Annotational overlays to show when config reloads happened +- Ability to filter by Namespace, Controller Class and Controller +- Visibility of Request Volume, connections, success rates, config reloads and configs out of sync. +- Network IO pressure, memory and CPU use +- Ingress P50, P95 and P99 percentile response times with IN/OUT throughput +- SSL certificate expiry +- Annotational overlays to show when config reloads happened -## Requirements +### Requirements - - **Grafana v5.2.0** (or newer) +- **Grafana v5.2.0** (or newer) + +## 2. Request Handling Performance + +![Dashboard](request-handling.png) + +### Features + +- Ability to filter by Ingress +- P50, P95 and P99 percentile of total request and upstream response times +- Request volume by path +- Error volume and error rate by path +- Average response time by path +- ...and more + +### Requirements + +- **Grafana v6.6.0** (or newer) diff --git a/deploy/grafana/dashboards/request-handling-performance.json b/deploy/grafana/dashboards/request-handling-performance.json new file mode 100644 index 000000000..1803ce965 --- /dev/null +++ b/deploy/grafana/dashboards/request-handling-performance.json @@ -0,0 +1,971 @@ +{ + "__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": "${DS_PROMETHEUS}", + "description": "Percentage of 4xx and 5xx responses among all responses.", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 16 + }, + "hiddenSeries": false, + "id": 100, + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "nullPointMode": "null as zero", + "options": { + "dataLinks": [] + }, + "percentage": false, + "pointradius": 2, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (path) (rate(nginx_ingress_controller_request_duration_seconds_count{\n ingress = \"$ingress\",\n status =~ \"[4-5].*\"\n}[1m])) / sum by (path) (rate(nginx_ingress_controller_request_duration_seconds_count{\n ingress = \"$ingress\",\n}[1m]))", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{ path }}", + "refId": "A" + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Response error rate by Path", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${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": [ + { + "expr": "sum by (path) (rate(nginx_ingress_controller_response_duration_seconds_sum{ingress = \"$ingress\"}[1m]))", + "interval": "", + "intervalFactor": 1, + "legendFormat": "{{ path }}", + "refId": "A" + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Upstream time consumed by Path", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${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" + }, + { + "expr": " sum (rate(nginx_ingress_controller_response_size_bucket{\n namespace =~ \"$namespace\",\n ingress =~ \"$ingress\",\n }[1m])) by (le)\n", + "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 =~ \"$ingress\",\n }[1m]\n )\n)\n", + "hide": false, + "instant": false, + "interval": "", + "intervalFactor": 1, + "legendFormat": "average", + "refId": "B" + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Upstream service latency", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "refresh": "30s", + "schemaVersion": 22, + "style": "dark", + "tags": [ + "nginx" + ], + "templating": { + "list": [ + { + "allValue": ".*", + "current": {}, + "datasource": "${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 +} diff --git a/deploy/grafana/dashboards/request-handling.png b/deploy/grafana/dashboards/request-handling.png new file mode 100644 index 000000000..2a051aaaf Binary files /dev/null and b/deploy/grafana/dashboards/request-handling.png differ