From 51225e17335e7e67d0533af8e74418ef6e41b657 Mon Sep 17 00:00:00 2001 From: Kaviraj Date: Fri, 16 Oct 2020 13:58:00 +0200 Subject: [PATCH 1/2] feat(mixin): Add grafana mixins support for postgres exporter Signed-off-by: Kaviraj --- postgres_mixin/.gitignore | 3 + postgres_mixin/Makefile | 23 + postgres_mixin/README.md | 26 + .../alerts/alerts.yaml | 0 .../dashboards/postgres-overview.json | 1321 +++++++++++++++++ postgres_mixin/go.mod | 3 + postgres_mixin/mixin.libsonnet | 13 + 7 files changed, 1389 insertions(+) create mode 100644 postgres_mixin/.gitignore create mode 100644 postgres_mixin/Makefile create mode 100644 postgres_mixin/README.md rename example.alerts.yml => postgres_mixin/alerts/alerts.yaml (100%) create mode 100644 postgres_mixin/dashboards/postgres-overview.json create mode 100644 postgres_mixin/go.mod create mode 100644 postgres_mixin/mixin.libsonnet diff --git a/postgres_mixin/.gitignore b/postgres_mixin/.gitignore new file mode 100644 index 00000000..97bf5f5c --- /dev/null +++ b/postgres_mixin/.gitignore @@ -0,0 +1,3 @@ +/alerts.yaml +/rules.yaml +dashboards_out diff --git a/postgres_mixin/Makefile b/postgres_mixin/Makefile new file mode 100644 index 00000000..f2643c2b --- /dev/null +++ b/postgres_mixin/Makefile @@ -0,0 +1,23 @@ +JSONNET_FMT := jsonnetfmt -n 2 --max-blank-lines 2 --string-style s --comment-style s + +default: build + +all: fmt lint build clean + +fmt: + find . -name 'vendor' -prune -o -name '*.libsonnet' -print -o -name '*.jsonnet' -print | \ + xargs -n 1 -- $(JSONNET_FMT) -i + +lint: + find . -name 'vendor' -prune -o -name '*.libsonnet' -print -o -name '*.jsonnet' -print | \ + while read f; do \ + $(JSONNET_FMT) "$$f" | diff -u "$$f" -; \ + done + + mixtool lint mixin.libsonnet + +build: + mixtool generate all mixin.libsonnet + +clean: + rm -rf dashboards_out alerts.yaml rules.yaml diff --git a/postgres_mixin/README.md b/postgres_mixin/README.md new file mode 100644 index 00000000..e5f12edf --- /dev/null +++ b/postgres_mixin/README.md @@ -0,0 +1,26 @@ +# Postgres Mixin + +_This is a work in progress. We aim for it to become a good role model for alerts +and dashboards eventually, but it is not quite there yet._ + +The Postgres Mixin is a set of configurable, reusable, and extensible alerts and +dashboards based on the metrics exported by the Postgres Exporter. The mixin creates +recording and alerting rules for Prometheus and suitable dashboard descriptions +for Grafana. + +To use them, you need to have `mixtool` and `jsonnetfmt` installed. If you +have a working Go development environment, it's easiest to run the following: +```bash +$ go get github.com/monitoring-mixins/mixtool/cmd/mixtool +$ go get github.com/google/go-jsonnet/cmd/jsonnetfmt +``` + +You can then build the Prometheus rules files `alerts.yaml` and +`rules.yaml` and a directory `dashboard_out` with the JSON dashboard files +for Grafana: +```bash +$ make build +``` + +For more advanced uses of mixins, see +https://github.com/monitoring-mixins/docs. diff --git a/example.alerts.yml b/postgres_mixin/alerts/alerts.yaml similarity index 100% rename from example.alerts.yml rename to postgres_mixin/alerts/alerts.yaml diff --git a/postgres_mixin/dashboards/postgres-overview.json b/postgres_mixin/dashboards/postgres-overview.json new file mode 100644 index 00000000..376f8dd2 --- /dev/null +++ b/postgres_mixin/dashboards/postgres-overview.json @@ -0,0 +1,1321 @@ +{ + "__inputs": [ + { + "name": "DS_PROMETHEUS", + "label": "Prometheus", + "description": "", + "type": "datasource", + "pluginId": "prometheus", + "pluginName": "Prometheus" + } + ], + "__requires": [ + { + "type": "grafana", + "id": "grafana", + "name": "Grafana", + "version": "5.2.0-pre1" + }, + { + "type": "panel", + "id": "graph", + "name": "Graph", + "version": "5.0.0" + }, + { + "type": "datasource", + "id": "prometheus", + "name": "Prometheus", + "version": "5.0.0" + }, + { + "type": "panel", + "id": "singlestat", + "name": "Singlestat", + "version": "5.0.0" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "description": "Performance metrics for Postgres", + "editable": true, + "gnetId": 455, + "graphTooltip": 0, + "id": null, + "iteration": 1534108418743, + "links": [], + "panels": [ + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "editable": true, + "error": false, + "fill": 1, + "grid": {}, + "gridPos": { + "h": 7, + "w": 20, + "x": 0, + "y": 0 + }, + "id": 1, + "isNew": true, + "legend": { + "alignAsTable": true, + "avg": true, + "current": false, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "alias": "fetched", + "dsType": "prometheus", + "expr": "sum(irate(pg_stat_database_tup_fetched{datname=~\"$db\",instance=~\"$host\"}[5m]))", + "format": "time_series", + "groupBy": [ + { + "params": [ + "$interval" + ], + "type": "time" + }, + { + "params": [ + "null" + ], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "fetched", + "measurement": "postgresql", + "policy": "default", + "refId": "A", + "resultFormat": "time_series", + "select": [ + [ + { + "params": [ + "tup_fetched" + ], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": [ + "10s" + ], + "type": "non_negative_derivative" + } + ] + ], + "step": 120, + "tags": [ + { + "key": "host", + "operator": "=~", + "value": "/^$host$/" + } + ] + }, + { + "alias": "fetched", + "dsType": "prometheus", + "expr": "sum(irate(pg_stat_database_tup_returned{datname=~\"$db\",instance=~\"$host\"}[5m]))", + "format": "time_series", + "groupBy": [ + { + "params": [ + "$interval" + ], + "type": "time" + }, + { + "params": [ + "null" + ], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "returned", + "measurement": "postgresql", + "policy": "default", + "refId": "B", + "resultFormat": "time_series", + "select": [ + [ + { + "params": [ + "tup_fetched" + ], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": [ + "10s" + ], + "type": "non_negative_derivative" + } + ] + ], + "step": 120, + "tags": [ + { + "key": "host", + "operator": "=~", + "value": "/^$host$/" + } + ] + }, + { + "alias": "fetched", + "dsType": "prometheus", + "expr": "sum(irate(pg_stat_database_tup_inserted{datname=~\"$db\",instance=~\"$host\"}[5m]))", + "format": "time_series", + "groupBy": [ + { + "params": [ + "$interval" + ], + "type": "time" + }, + { + "params": [ + "null" + ], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "inserted", + "measurement": "postgresql", + "policy": "default", + "refId": "C", + "resultFormat": "time_series", + "select": [ + [ + { + "params": [ + "tup_fetched" + ], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": [ + "10s" + ], + "type": "non_negative_derivative" + } + ] + ], + "step": 120, + "tags": [ + { + "key": "host", + "operator": "=~", + "value": "/^$host$/" + } + ] + }, + { + "alias": "fetched", + "dsType": "prometheus", + "expr": "sum(irate(pg_stat_database_tup_updated{datname=~\"$db\",instance=~\"$host\"}[5m]))", + "format": "time_series", + "groupBy": [ + { + "params": [ + "$interval" + ], + "type": "time" + }, + { + "params": [ + "null" + ], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "updated", + "measurement": "postgresql", + "policy": "default", + "refId": "D", + "resultFormat": "time_series", + "select": [ + [ + { + "params": [ + "tup_fetched" + ], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": [ + "10s" + ], + "type": "non_negative_derivative" + } + ] + ], + "step": 120, + "tags": [ + { + "key": "host", + "operator": "=~", + "value": "/^$host$/" + } + ] + }, + { + "alias": "fetched", + "dsType": "prometheus", + "expr": "sum(irate(pg_stat_database_tup_deleted{datname=~\"$db\",instance=~\"$host\"}[5m]))", + "format": "time_series", + "groupBy": [ + { + "params": [ + "$interval" + ], + "type": "time" + }, + { + "params": [ + "null" + ], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "deleted", + "measurement": "postgresql", + "policy": "default", + "refId": "E", + "resultFormat": "time_series", + "select": [ + [ + { + "params": [ + "tup_fetched" + ], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": [ + "10s" + ], + "type": "non_negative_derivative" + } + ] + ], + "step": 120, + "tags": [ + { + "key": "host", + "operator": "=~", + "value": "/^$host$/" + } + ] + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Rows", + "tooltip": { + "msResolution": true, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "datasource": "${DS_PROMETHEUS}", + "decimals": 0, + "editable": true, + "error": false, + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 3, + "w": 4, + "x": 20, + "y": 0 + }, + "height": "55px", + "id": 11, + "interval": null, + "isNew": true, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": true, + "lineColor": "rgb(31, 120, 193)", + "show": true + }, + "tableColumn": "", + "targets": [ + { + "dsType": "prometheus", + "expr": "sum(irate(pg_stat_database_xact_commit{datname=~\"$db\",instance=~\"$host\"}[5m])) + sum(irate(pg_stat_database_xact_rollback{datname=~\"$db\",instance=~\"$host\"}[5m]))", + "format": "time_series", + "groupBy": [ + { + "params": [ + "$interval" + ], + "type": "time" + }, + { + "params": [ + "null" + ], + "type": "fill" + } + ], + "intervalFactor": 2, + "measurement": "postgresql", + "policy": "default", + "refId": "A", + "resultFormat": "time_series", + "select": [ + [ + { + "params": [ + "xact_commit" + ], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": [ + "10s" + ], + "type": "non_negative_derivative" + } + ] + ], + "step": 1800, + "tags": [ + { + "key": "host", + "operator": "=~", + "value": "/^$host$/" + } + ] + } + ], + "thresholds": "", + "title": "QPS", + "transparent": true, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "avg" + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "decimals": 1, + "editable": true, + "error": false, + "fill": 1, + "grid": {}, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 7 + }, + "id": 2, + "isNew": true, + "legend": { + "alignAsTable": true, + "avg": true, + "current": false, + "hideZero": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "alias": "Buffers Allocated", + "dsType": "prometheus", + "expr": "irate(pg_stat_bgwriter_buffers_alloc{instance='$host'}[5m])", + "format": "time_series", + "groupBy": [ + { + "params": [ + "$interval" + ], + "type": "time" + }, + { + "params": [ + "null" + ], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "buffers_alloc", + "measurement": "postgresql", + "policy": "default", + "refId": "A", + "resultFormat": "time_series", + "select": [ + [ + { + "params": [ + "buffers_alloc" + ], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": [], + "type": "difference" + } + ] + ], + "step": 240, + "tags": [ + { + "key": "host", + "operator": "=~", + "value": "/^$host$/" + } + ] + }, + { + "alias": "Buffers Allocated", + "dsType": "prometheus", + "expr": "irate(pg_stat_bgwriter_buffers_backend_fsync{instance='$host'}[5m])", + "format": "time_series", + "groupBy": [ + { + "params": [ + "$interval" + ], + "type": "time" + }, + { + "params": [ + "null" + ], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "buffers_backend_fsync", + "measurement": "postgresql", + "policy": "default", + "refId": "B", + "resultFormat": "time_series", + "select": [ + [ + { + "params": [ + "buffers_alloc" + ], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": [], + "type": "difference" + } + ] + ], + "step": 240, + "tags": [ + { + "key": "host", + "operator": "=~", + "value": "/^$host$/" + } + ] + }, + { + "alias": "Buffers Allocated", + "dsType": "prometheus", + "expr": "irate(pg_stat_bgwriter_buffers_backend{instance='$host'}[5m])", + "format": "time_series", + "groupBy": [ + { + "params": [ + "$interval" + ], + "type": "time" + }, + { + "params": [ + "null" + ], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "buffers_backend", + "measurement": "postgresql", + "policy": "default", + "refId": "C", + "resultFormat": "time_series", + "select": [ + [ + { + "params": [ + "buffers_alloc" + ], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": [], + "type": "difference" + } + ] + ], + "step": 240, + "tags": [ + { + "key": "host", + "operator": "=~", + "value": "/^$host$/" + } + ] + }, + { + "alias": "Buffers Allocated", + "dsType": "prometheus", + "expr": "irate(pg_stat_bgwriter_buffers_clean{instance='$host'}[5m])", + "format": "time_series", + "groupBy": [ + { + "params": [ + "$interval" + ], + "type": "time" + }, + { + "params": [ + "null" + ], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "buffers_clean", + "measurement": "postgresql", + "policy": "default", + "refId": "D", + "resultFormat": "time_series", + "select": [ + [ + { + "params": [ + "buffers_alloc" + ], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": [], + "type": "difference" + } + ] + ], + "step": 240, + "tags": [ + { + "key": "host", + "operator": "=~", + "value": "/^$host$/" + } + ] + }, + { + "alias": "Buffers Allocated", + "dsType": "prometheus", + "expr": "irate(pg_stat_bgwriter_buffers_checkpoint{instance='$host'}[5m])", + "format": "time_series", + "groupBy": [ + { + "params": [ + "$interval" + ], + "type": "time" + }, + { + "params": [ + "null" + ], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "buffers_checkpoint", + "measurement": "postgresql", + "policy": "default", + "refId": "E", + "resultFormat": "time_series", + "select": [ + [ + { + "params": [ + "buffers_alloc" + ], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": [], + "type": "difference" + } + ] + ], + "step": 240, + "tags": [ + { + "key": "host", + "operator": "=~", + "value": "/^$host$/" + } + ] + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Buffers", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "editable": true, + "error": false, + "fill": 1, + "grid": {}, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 7 + }, + "id": 3, + "isNew": true, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "alias": "conflicts", + "dsType": "prometheus", + "expr": "sum(rate(pg_stat_database_deadlocks{datname=~\"$db\",instance=~\"$host\"}[5m]))", + "format": "time_series", + "groupBy": [ + { + "params": [ + "$interval" + ], + "type": "time" + }, + { + "params": [ + "null" + ], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "deadlocks", + "measurement": "postgresql", + "policy": "default", + "refId": "A", + "resultFormat": "time_series", + "select": [ + [ + { + "params": [ + "conflicts" + ], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": [], + "type": "difference" + } + ] + ], + "step": 240, + "tags": [ + { + "key": "host", + "operator": "=~", + "value": "/^$host$/" + } + ] + }, + { + "alias": "deadlocks", + "dsType": "prometheus", + "expr": "sum(rate(pg_stat_database_conflicts{datname=~\"$db\",instance=~\"$host\"}[5m]))", + "format": "time_series", + "groupBy": [ + { + "params": [ + "$interval" + ], + "type": "time" + }, + { + "params": [ + "null" + ], + "type": "fill" + } + ], + "intervalFactor": 2, + "legendFormat": "conflicts", + "measurement": "postgresql", + "policy": "default", + "refId": "B", + "resultFormat": "time_series", + "select": [ + [ + { + "params": [ + "deadlocks" + ], + "type": "field" + }, + { + "params": [], + "type": "mean" + }, + { + "params": [], + "type": "difference" + } + ] + ], + "step": 240, + "tags": [ + { + "key": "host", + "operator": "=~", + "value": "/^$host$/" + } + ] + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Conflicts/Deadlocks", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "editable": true, + "error": false, + "fill": 1, + "grid": {}, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 14 + }, + "id": 12, + "isNew": true, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": true, + "pointradius": 1, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(pg_stat_database_blks_hit{datname=~\"$db\",instance=~\"$host\"}) / (sum(pg_stat_database_blks_hit{datname=~\"$db\",instance=~\"$host\"}) + sum(pg_stat_database_blks_read{datname=~\"$db\",instance=~\"$host\"}))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "cache hit rate", + "refId": "A", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Cache hit ratio", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "${DS_PROMETHEUS}", + "editable": true, + "error": false, + "fill": 1, + "grid": {}, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 14 + }, + "id": 13, + "isNew": true, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [], + "nullPointMode": "connected", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "pg_stat_database_numbackends{datname=~\"$db\",instance=~\"$host\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{__name__}}", + "refId": "A", + "step": 240 + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Number of active connections", + "tooltip": { + "msResolution": false, + "shared": true, + "sort": 0, + "value_type": "cumulative" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "refresh": false, + "schemaVersion": 16, + "style": "dark", + "tags": [ + "postgres" + ], + "templating": { + "list": [ + { + "allValue": ".*", + "current": {}, + "datasource": "${DS_PROMETHEUS}", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "host", + "options": [], + "query": "label_values(up{job=~\"postgres.*\"},instance)", + "refresh": 1, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".*", + "current": {}, + "datasource": "${DS_PROMETHEUS}", + "hide": 0, + "includeAll": true, + "label": "db", + "multi": false, + "name": "db", + "options": [], + "query": "label_values(pg_stat_database_tup_fetched{instance=~\"$host\",datname!~\"template.*|postgres\"},datname)", + "refresh": 1, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "browser", + "title": "Postgres Overview", + "uid": "wGgaPlciz", + "version": 4 +} \ No newline at end of file diff --git a/postgres_mixin/go.mod b/postgres_mixin/go.mod new file mode 100644 index 00000000..fa5e2057 --- /dev/null +++ b/postgres_mixin/go.mod @@ -0,0 +1,3 @@ +module github.com/wrouesnel/postgres_exporter/postgres_mixin + +go 1.15 diff --git a/postgres_mixin/mixin.libsonnet b/postgres_mixin/mixin.libsonnet new file mode 100644 index 00000000..98c7ea7d --- /dev/null +++ b/postgres_mixin/mixin.libsonnet @@ -0,0 +1,13 @@ +{ + grafanaDashboards: { + 'postgres-overview.json': (import 'dashboards/postgres-overview.json'), + }, + + // Helper function to ensure that we don't override other rules, by forcing + // the patching of the groups list, and not the overall rules object. + local importRules(rules) = { + groups+: std.native('parseYaml')(rules)[0].groups, + }, + + prometheusAlerts+: importRules(importstr 'alerts/alerts.yaml'), +} From 2d6996bc3185dbd0c5d95ee0258decf60dd82223 Mon Sep 17 00:00:00 2001 From: Kaviraj Date: Tue, 20 Oct 2020 13:10:20 +0200 Subject: [PATCH 2/2] Add templating for job, instance and datasource Signed-off-by: Kaviraj --- .../dashboards/postgres-overview.json | 315 ++++++++++++------ 1 file changed, 216 insertions(+), 99 deletions(-) diff --git a/postgres_mixin/dashboards/postgres-overview.json b/postgres_mixin/dashboards/postgres-overview.json index 376f8dd2..24b7bc92 100644 --- a/postgres_mixin/dashboards/postgres-overview.json +++ b/postgres_mixin/dashboards/postgres-overview.json @@ -1,40 +1,4 @@ { - "__inputs": [ - { - "name": "DS_PROMETHEUS", - "label": "Prometheus", - "description": "", - "type": "datasource", - "pluginId": "prometheus", - "pluginName": "Prometheus" - } - ], - "__requires": [ - { - "type": "grafana", - "id": "grafana", - "name": "Grafana", - "version": "5.2.0-pre1" - }, - { - "type": "panel", - "id": "graph", - "name": "Graph", - "version": "5.0.0" - }, - { - "type": "datasource", - "id": "prometheus", - "name": "Prometheus", - "version": "5.0.0" - }, - { - "type": "panel", - "id": "singlestat", - "name": "Singlestat", - "version": "5.0.0" - } - ], "annotations": { "list": [ { @@ -52,8 +16,8 @@ "editable": true, "gnetId": 455, "graphTooltip": 0, - "id": null, - "iteration": 1534108418743, + "id": 1, + "iteration": 1603191461722, "links": [], "panels": [ { @@ -61,10 +25,17 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "${DS_PROMETHEUS}", + "datasource": "Postgres Overview", "editable": true, "error": false, + "fieldConfig": { + "defaults": { + "custom": {} + }, + "overrides": [] + }, "fill": 1, + "fillGradient": 0, "grid": {}, "gridPos": { "h": 7, @@ -72,6 +43,7 @@ "x": 0, "y": 0 }, + "hiddenSeries": false, "id": 1, "isNew": true, "legend": { @@ -89,7 +61,11 @@ "linewidth": 1, "links": [], "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, "percentage": false, + "pluginVersion": "7.2.1", "pointradius": 5, "points": false, "renderer": "flot", @@ -101,7 +77,7 @@ { "alias": "fetched", "dsType": "prometheus", - "expr": "sum(irate(pg_stat_database_tup_fetched{datname=~\"$db\",instance=~\"$host\"}[5m]))", + "expr": "sum(irate(pg_stat_database_tup_fetched{datname=~\"$db\",instance=~\"$instance\"}[5m]))", "format": "time_series", "groupBy": [ { @@ -146,16 +122,16 @@ "step": 120, "tags": [ { - "key": "host", + "key": "instance", "operator": "=~", - "value": "/^$host$/" + "value": "/^$instance$/" } ] }, { "alias": "fetched", "dsType": "prometheus", - "expr": "sum(irate(pg_stat_database_tup_returned{datname=~\"$db\",instance=~\"$host\"}[5m]))", + "expr": "sum(irate(pg_stat_database_tup_returned{datname=~\"$db\",instance=~\"$instance\"}[5m]))", "format": "time_series", "groupBy": [ { @@ -200,16 +176,16 @@ "step": 120, "tags": [ { - "key": "host", + "key": "instance", "operator": "=~", - "value": "/^$host$/" + "value": "/^$instance$/" } ] }, { "alias": "fetched", "dsType": "prometheus", - "expr": "sum(irate(pg_stat_database_tup_inserted{datname=~\"$db\",instance=~\"$host\"}[5m]))", + "expr": "sum(irate(pg_stat_database_tup_inserted{datname=~\"$db\",instance=~\"$instance\"}[5m]))", "format": "time_series", "groupBy": [ { @@ -254,16 +230,16 @@ "step": 120, "tags": [ { - "key": "host", + "key": "instance", "operator": "=~", - "value": "/^$host$/" + "value": "/^$instance$/" } ] }, { "alias": "fetched", "dsType": "prometheus", - "expr": "sum(irate(pg_stat_database_tup_updated{datname=~\"$db\",instance=~\"$host\"}[5m]))", + "expr": "sum(irate(pg_stat_database_tup_updated{datname=~\"$db\",instance=~\"$instance\"}[5m]))", "format": "time_series", "groupBy": [ { @@ -308,16 +284,16 @@ "step": 120, "tags": [ { - "key": "host", + "key": "instance", "operator": "=~", - "value": "/^$host$/" + "value": "/^$instance$/" } ] }, { "alias": "fetched", "dsType": "prometheus", - "expr": "sum(irate(pg_stat_database_tup_deleted{datname=~\"$db\",instance=~\"$host\"}[5m]))", + "expr": "sum(irate(pg_stat_database_tup_deleted{datname=~\"$db\",instance=~\"$instance\"}[5m]))", "format": "time_series", "groupBy": [ { @@ -362,15 +338,16 @@ "step": 120, "tags": [ { - "key": "host", + "key": "instance", "operator": "=~", - "value": "/^$host$/" + "value": "/^$instance$/" } ] } ], "thresholds": [], "timeFrom": null, + "timeRegions": [], "timeShift": null, "title": "Rows", "tooltip": { @@ -404,7 +381,11 @@ "min": null, "show": true } - ] + ], + "yaxis": { + "align": false, + "alignLevel": null + } }, { "cacheTimeout": null, @@ -415,10 +396,16 @@ "rgba(237, 129, 40, 0.89)", "rgba(50, 172, 45, 0.97)" ], - "datasource": "${DS_PROMETHEUS}", + "datasource": "Postgres Overview", "decimals": 0, "editable": true, "error": false, + "fieldConfig": { + "defaults": { + "custom": {} + }, + "overrides": [] + }, "format": "none", "gauge": { "maxValue": 100, @@ -473,7 +460,7 @@ "targets": [ { "dsType": "prometheus", - "expr": "sum(irate(pg_stat_database_xact_commit{datname=~\"$db\",instance=~\"$host\"}[5m])) + sum(irate(pg_stat_database_xact_rollback{datname=~\"$db\",instance=~\"$host\"}[5m]))", + "expr": "sum(irate(pg_stat_database_xact_commit{datname=~\"$db\",instance=~\"$instance\"}[5m])) + sum(irate(pg_stat_database_xact_rollback{datname=~\"$db\",instance=~\"$instance\"}[5m]))", "format": "time_series", "groupBy": [ { @@ -517,9 +504,9 @@ "step": 1800, "tags": [ { - "key": "host", + "key": "instance", "operator": "=~", - "value": "/^$host$/" + "value": "/^$instance$/" } ] } @@ -543,11 +530,18 @@ "bars": false, "dashLength": 10, "dashes": false, - "datasource": "${DS_PROMETHEUS}", + "datasource": "Postgres Overview", "decimals": 1, "editable": true, "error": false, + "fieldConfig": { + "defaults": { + "custom": {} + }, + "overrides": [] + }, "fill": 1, + "fillGradient": 0, "grid": {}, "gridPos": { "h": 7, @@ -555,6 +549,7 @@ "x": 0, "y": 7 }, + "hiddenSeries": false, "id": 2, "isNew": true, "legend": { @@ -573,7 +568,11 @@ "linewidth": 1, "links": [], "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, "percentage": false, + "pluginVersion": "7.2.1", "pointradius": 5, "points": false, "renderer": "flot", @@ -585,7 +584,7 @@ { "alias": "Buffers Allocated", "dsType": "prometheus", - "expr": "irate(pg_stat_bgwriter_buffers_alloc{instance='$host'}[5m])", + "expr": "irate(pg_stat_bgwriter_buffers_alloc{instance='$instance'}[5m])", "format": "time_series", "groupBy": [ { @@ -628,16 +627,16 @@ "step": 240, "tags": [ { - "key": "host", + "key": "instance", "operator": "=~", - "value": "/^$host$/" + "value": "/^$instance$/" } ] }, { "alias": "Buffers Allocated", "dsType": "prometheus", - "expr": "irate(pg_stat_bgwriter_buffers_backend_fsync{instance='$host'}[5m])", + "expr": "irate(pg_stat_bgwriter_buffers_backend_fsync{instance='$instance'}[5m])", "format": "time_series", "groupBy": [ { @@ -680,16 +679,16 @@ "step": 240, "tags": [ { - "key": "host", + "key": "instance", "operator": "=~", - "value": "/^$host$/" + "value": "/^$instance$/" } ] }, { "alias": "Buffers Allocated", "dsType": "prometheus", - "expr": "irate(pg_stat_bgwriter_buffers_backend{instance='$host'}[5m])", + "expr": "irate(pg_stat_bgwriter_buffers_backend{instance='$instance'}[5m])", "format": "time_series", "groupBy": [ { @@ -732,16 +731,16 @@ "step": 240, "tags": [ { - "key": "host", + "key": "instance", "operator": "=~", - "value": "/^$host$/" + "value": "/^$instance$/" } ] }, { "alias": "Buffers Allocated", "dsType": "prometheus", - "expr": "irate(pg_stat_bgwriter_buffers_clean{instance='$host'}[5m])", + "expr": "irate(pg_stat_bgwriter_buffers_clean{instance='$instance'}[5m])", "format": "time_series", "groupBy": [ { @@ -784,16 +783,16 @@ "step": 240, "tags": [ { - "key": "host", + "key": "instance", "operator": "=~", - "value": "/^$host$/" + "value": "/^$instance$/" } ] }, { "alias": "Buffers Allocated", "dsType": "prometheus", - "expr": "irate(pg_stat_bgwriter_buffers_checkpoint{instance='$host'}[5m])", + "expr": "irate(pg_stat_bgwriter_buffers_checkpoint{instance='$instance'}[5m])", "format": "time_series", "groupBy": [ { @@ -836,15 +835,16 @@ "step": 240, "tags": [ { - "key": "host", + "key": "instance", "operator": "=~", - "value": "/^$host$/" + "value": "/^$instance$/" } ] } ], "thresholds": [], "timeFrom": null, + "timeRegions": [], "timeShift": null, "title": "Buffers", "tooltip": { @@ -878,17 +878,28 @@ "min": null, "show": true } - ] + ], + "yaxis": { + "align": false, + "alignLevel": null + } }, { "aliasColors": {}, "bars": false, "dashLength": 10, "dashes": false, - "datasource": "${DS_PROMETHEUS}", + "datasource": "Postgres Overview", "editable": true, "error": false, + "fieldConfig": { + "defaults": { + "custom": {} + }, + "overrides": [] + }, "fill": 1, + "fillGradient": 0, "grid": {}, "gridPos": { "h": 7, @@ -896,6 +907,7 @@ "x": 12, "y": 7 }, + "hiddenSeries": false, "id": 3, "isNew": true, "legend": { @@ -911,7 +923,11 @@ "linewidth": 2, "links": [], "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, "percentage": false, + "pluginVersion": "7.2.1", "pointradius": 5, "points": false, "renderer": "flot", @@ -923,7 +939,7 @@ { "alias": "conflicts", "dsType": "prometheus", - "expr": "sum(rate(pg_stat_database_deadlocks{datname=~\"$db\",instance=~\"$host\"}[5m]))", + "expr": "sum(rate(pg_stat_database_deadlocks{datname=~\"$db\",instance=~\"$instance\"}[5m]))", "format": "time_series", "groupBy": [ { @@ -966,16 +982,16 @@ "step": 240, "tags": [ { - "key": "host", + "key": "instance", "operator": "=~", - "value": "/^$host$/" + "value": "/^$instance$/" } ] }, { "alias": "deadlocks", "dsType": "prometheus", - "expr": "sum(rate(pg_stat_database_conflicts{datname=~\"$db\",instance=~\"$host\"}[5m]))", + "expr": "sum(rate(pg_stat_database_conflicts{datname=~\"$db\",instance=~\"$instance\"}[5m]))", "format": "time_series", "groupBy": [ { @@ -1018,15 +1034,16 @@ "step": 240, "tags": [ { - "key": "host", + "key": "instance", "operator": "=~", - "value": "/^$host$/" + "value": "/^$instance$/" } ] } ], "thresholds": [], "timeFrom": null, + "timeRegions": [], "timeShift": null, "title": "Conflicts/Deadlocks", "tooltip": { @@ -1060,17 +1077,28 @@ "min": null, "show": true } - ] + ], + "yaxis": { + "align": false, + "alignLevel": null + } }, { "aliasColors": {}, "bars": false, "dashLength": 10, "dashes": false, - "datasource": "${DS_PROMETHEUS}", + "datasource": "Postgres Overview", "editable": true, "error": false, + "fieldConfig": { + "defaults": { + "custom": {} + }, + "overrides": [] + }, "fill": 1, + "fillGradient": 0, "grid": {}, "gridPos": { "h": 7, @@ -1078,6 +1106,7 @@ "x": 0, "y": 14 }, + "hiddenSeries": false, "id": 12, "isNew": true, "legend": { @@ -1093,7 +1122,11 @@ "linewidth": 2, "links": [], "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, "percentage": true, + "pluginVersion": "7.2.1", "pointradius": 1, "points": false, "renderer": "flot", @@ -1103,7 +1136,7 @@ "steppedLine": false, "targets": [ { - "expr": "sum(pg_stat_database_blks_hit{datname=~\"$db\",instance=~\"$host\"}) / (sum(pg_stat_database_blks_hit{datname=~\"$db\",instance=~\"$host\"}) + sum(pg_stat_database_blks_read{datname=~\"$db\",instance=~\"$host\"}))", + "expr": "sum(pg_stat_database_blks_hit{datname=~\"$db\",instance=~\"$instance\"}) / (sum(pg_stat_database_blks_hit{datname=~\"$db\",instance=~\"$instance\"}) + sum(pg_stat_database_blks_read{datname=~\"$db\",instance=~\"$instance\"}))", "format": "time_series", "intervalFactor": 2, "legendFormat": "cache hit rate", @@ -1113,6 +1146,7 @@ ], "thresholds": [], "timeFrom": null, + "timeRegions": [], "timeShift": null, "title": "Cache hit ratio", "tooltip": { @@ -1146,17 +1180,28 @@ "min": null, "show": true } - ] + ], + "yaxis": { + "align": false, + "alignLevel": null + } }, { "aliasColors": {}, "bars": false, "dashLength": 10, "dashes": false, - "datasource": "${DS_PROMETHEUS}", + "datasource": "Postgres Overview", "editable": true, "error": false, + "fieldConfig": { + "defaults": { + "custom": {} + }, + "overrides": [] + }, "fill": 1, + "fillGradient": 0, "grid": {}, "gridPos": { "h": 7, @@ -1164,6 +1209,7 @@ "x": 12, "y": 14 }, + "hiddenSeries": false, "id": 13, "isNew": true, "legend": { @@ -1179,7 +1225,11 @@ "linewidth": 2, "links": [], "nullPointMode": "connected", + "options": { + "alertThreshold": true + }, "percentage": false, + "pluginVersion": "7.2.1", "pointradius": 5, "points": false, "renderer": "flot", @@ -1189,7 +1239,7 @@ "steppedLine": false, "targets": [ { - "expr": "pg_stat_database_numbackends{datname=~\"$db\",instance=~\"$host\"}", + "expr": "pg_stat_database_numbackends{datname=~\"$db\",instance=~\"$instance\"}", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{__name__}}", @@ -1199,6 +1249,7 @@ ], "thresholds": [], "timeFrom": null, + "timeRegions": [], "timeShift": null, "title": "Number of active connections", "tooltip": { @@ -1232,11 +1283,15 @@ "min": null, "show": true } - ] + ], + "yaxis": { + "align": false, + "alignLevel": null + } } ], "refresh": false, - "schemaVersion": 16, + "schemaVersion": 26, "style": "dark", "tags": [ "postgres" @@ -1245,17 +1300,23 @@ "list": [ { "allValue": ".*", - "current": {}, - "datasource": "${DS_PROMETHEUS}", + "current": { + "selected": false, + "text": "All", + "value": "$__all" + }, + "datasource": "Postgres Overview", + "definition": "", "hide": 0, "includeAll": true, "label": null, "multi": false, - "name": "host", + "name": "instance", "options": [], "query": "label_values(up{job=~\"postgres.*\"},instance)", "refresh": 1, "regex": "", + "skipUrlSync": false, "sort": 0, "tagValuesQuery": "", "tags": [], @@ -1265,17 +1326,73 @@ }, { "allValue": ".*", - "current": {}, - "datasource": "${DS_PROMETHEUS}", + "current": { + "selected": false, + "text": "All", + "value": "$__all" + }, + "datasource": "Postgres Overview", + "definition": "label_values(pg_stat_database_tup_fetched{instance=~\"$instance\",datname!~\"template.*|postgres\"},datname)", "hide": 0, "includeAll": true, "label": "db", "multi": false, "name": "db", "options": [], - "query": "label_values(pg_stat_database_tup_fetched{instance=~\"$host\",datname!~\"template.*|postgres\"},datname)", + "query": "label_values(pg_stat_database_tup_fetched{instance=~\"$instance\",datname!~\"template.*|postgres\"},datname)", "refresh": 1, "regex": "", + "skipUrlSync": false, + "sort": 0, + "tagValuesQuery": "", + "tags": [], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "current": { + "selected": false, + "text": "Postgres Overview", + "value": "Postgres Overview" + }, + "hide": 0, + "includeAll": false, + "label": "datasource", + "multi": false, + "name": "datasource", + "options": [], + "query": "prometheus", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "type": "datasource" + }, + { + "allValue": null, + "current": { + "selected": true, + "text": "postgres", + "value": "postgres" + }, + "datasource": "$datasource", + "definition": "label_values(pg_up, job)", + "hide": 0, + "includeAll": false, + "label": "job", + "multi": false, + "name": "job", + "options": [ + { + "selected": true, + "text": "postgres", + "value": "postgres" + } + ], + "query": "label_values(pg_up, job)", + "refresh": 0, + "regex": "", + "skipUrlSync": false, "sort": 0, "tagValuesQuery": "", "tags": [], @@ -1317,5 +1434,5 @@ "timezone": "browser", "title": "Postgres Overview", "uid": "wGgaPlciz", - "version": 4 -} \ No newline at end of file + "version": 5 +}