From 8cd59e5d21711fb8e4f0ee9e75d12663fa175a68 Mon Sep 17 00:00:00 2001 From: mirsal Date: Tue, 20 Jul 2021 01:20:53 +0000 Subject: [PATCH] Provision a docker swarm node dashboard in grafana --- abra.sh | 2 + compose.yml | 10 + grafana-dashboards.yml | 13 + grafana-swarm-dashboard.json | 1729 ++++++++++++++++++++++++++++++++++ 4 files changed, 1754 insertions(+) create mode 100644 grafana-dashboards.yml create mode 100644 grafana-swarm-dashboard.json diff --git a/abra.sh b/abra.sh index c9e0728..09b25f2 100644 --- a/abra.sh +++ b/abra.sh @@ -3,3 +3,5 @@ export PROMTAIL_YML_VERSION=v1 export LOKI_YML_VERSION=v1 export NODE_EXPORTER_ENTRYPOINT_VERSION=v1 export GRAFANA_DATASOURCES_YML_VERSION=v1 +export GRAFANA_DASHBOARDS_YML_VERSION=v1 +export GRAFANA_SWARM_DASHBOARD_JSON_VERSION=v1 diff --git a/compose.yml b/compose.yml index 3be7d6d..32a2c52 100644 --- a/compose.yml +++ b/compose.yml @@ -111,6 +111,10 @@ services: configs: - source: grafana_datasources_yml target: /etc/grafana/provisioning/datasources/datasources.yml + - source: grafana_dashboards_yml + target: /etc/grafana/provisioning/dashboards/dashboards.yml + - source: grafana_swarm_dashboard_json + target: /var/lib/grafana/dashboards/docker-swarm-nodes.json networks: - api - proxy @@ -151,6 +155,12 @@ configs: grafana_datasources_yml: name: ${STACK_NAME}_grafana_datasources_yml_${GRAFANA_DATASOURCES_YML_VERSION} file: grafana-datasources.yml + grafana_dashboards_yml: + name: ${STACK_NAME}_grafana_dashboards_yml_${GRAFANA_DASHBOARDS_YML_VERSION} + file: grafana-dashboards.yml + grafana_swarm_dashboard_json: + name: ${STACK_NAME}_grafana_swarm_dashboard_json_${GRAFANA_SWARM_DASHBOARD_JSON_VERSION} + file: grafana-swarm-dashboard.json node_exporter_entrypoint_sh: name: ${STACK_NAME}_node_exporter_entrypoint_${NODE_EXPORTER_ENTRYPOINT_VERSION} file: node-exporter-entrypoint.sh diff --git a/grafana-dashboards.yml b/grafana-dashboards.yml new file mode 100644 index 0000000..8411cca --- /dev/null +++ b/grafana-dashboards.yml @@ -0,0 +1,13 @@ +apiVersion: 1 + +providers: + - name: 'default-dashboard-provider' + orgId: 1 + folder: 'default-dashboards' + type: file + disableDeletion: false + updateIntervalSeconds: 10 + allowUiUpdates: true + options: + path: /var/lib/grafana/dashboards + foldersFromFilesStructure: true diff --git a/grafana-swarm-dashboard.json b/grafana-swarm-dashboard.json new file mode 100644 index 0000000..6c9468a --- /dev/null +++ b/grafana-swarm-dashboard.json @@ -0,0 +1,1729 @@ +{ + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "description": "Docker Swarm nodes metrics", + "editable": true, + "gnetId": 7461, + "graphTooltip": 0, + "id": 1, + "iteration": 1626741910840, + "links": [], + "panels": [ + { + "cacheTimeout": null, + "datasource": "Prometheus", + "fieldConfig": { + "defaults": { + "decimals": 1, + "mappings": [ + { + "options": { + "match": "null", + "result": { + "text": "N/A" + } + }, + "type": "special" + } + ], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "red", + "value": null + }, + { + "color": "yellow", + "value": 3600 + }, + { + "color": "green", + "value": 86400 + } + ] + }, + "unit": "s" + }, + "overrides": [] + }, + "gridPos": { + "h": 4, + "w": 6, + "x": 0, + "y": 0 + }, + "hideTimeOverride": true, + "id": 2, + "interval": null, + "links": [], + "maxDataPoints": 100, + "options": { + "colorMode": "value", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "horizontal", + "reduceOptions": { + "calcs": [ + "mean" + ], + "fields": "", + "values": false + }, + "text": {}, + "textMode": "auto" + }, + "pluginVersion": "8.0.6", + "targets": [ + { + "expr": "topk(1, sum((node_time_seconds - node_boot_time_seconds) * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"}) by (node_name))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 2 + } + ], + "timeFrom": "1m", + "timeShift": null, + "title": "Uptime", + "type": "stat" + }, + { + "cacheTimeout": null, + "datasource": "Prometheus", + "fieldConfig": { + "defaults": { + "decimals": 0, + "mappings": [ + { + "options": { + "match": "null", + "result": { + "text": "N/A" + } + }, + "type": "special" + } + ], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "red", + "value": null + }, + { + "color": "green", + "value": 1 + } + ] + }, + "unit": "none" + }, + "overrides": [] + }, + "gridPos": { + "h": 4, + "w": 6, + "x": 6, + "y": 0 + }, + "id": 1, + "interval": null, + "links": [], + "maxDataPoints": 100, + "options": { + "colorMode": "value", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "horizontal", + "reduceOptions": { + "calcs": [ + "mean" + ], + "fields": "", + "values": false + }, + "text": {}, + "textMode": "auto" + }, + "pluginVersion": "8.0.6", + "targets": [ + { + "expr": "count(node_meta * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 20 + } + ], + "title": "Nodes", + "type": "stat" + }, + { + "cacheTimeout": null, + "datasource": "Prometheus", + "fieldConfig": { + "defaults": { + "decimals": 0, + "mappings": [ + { + "options": { + "match": "null", + "result": { + "text": "N/A" + } + }, + "type": "special" + } + ], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "red", + "value": null + }, + { + "color": "green", + "value": 8 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "gridPos": { + "h": 4, + "w": 6, + "x": 12, + "y": 0 + }, + "hideTimeOverride": true, + "id": 4, + "interval": null, + "links": [], + "maxDataPoints": 100, + "options": { + "colorMode": "value", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "horizontal", + "reduceOptions": { + "calcs": [ + "mean" + ], + "fields": "", + "values": false + }, + "text": {}, + "textMode": "auto" + }, + "pluginVersion": "8.0.6", + "targets": [ + { + "expr": "count(node_cpu_seconds_total{mode=\"idle\"} * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 2 + } + ], + "timeFrom": "1m", + "timeShift": null, + "title": "CPUs", + "type": "stat" + }, + { + "cacheTimeout": null, + "datasource": "Prometheus", + "fieldConfig": { + "defaults": { + "mappings": [ + { + "options": { + "match": "null", + "result": { + "text": "N/A" + } + }, + "type": "special" + } + ], + "max": 100, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "rgba(245, 54, 54, 0.9)", + "value": null + }, + { + "color": "rgba(237, 129, 40, 0.89)", + "value": 10 + }, + { + "color": "rgba(50, 172, 45, 0.97)", + "value": 25 + } + ] + }, + "unit": "percent" + }, + "overrides": [] + }, + "gridPos": { + "h": 4, + "w": 6, + "x": 18, + "y": 0 + }, + "hideTimeOverride": true, + "id": 11, + "interval": null, + "links": [], + "maxDataPoints": 100, + "options": { + "orientation": "horizontal", + "reduceOptions": { + "calcs": [ + "last" + ], + "fields": "", + "values": false + }, + "showThresholdLabels": false, + "showThresholdMarkers": true, + "text": {} + }, + "pluginVersion": "8.0.6", + "targets": [ + { + "expr": "sum(irate(node_cpu_seconds_total{mode=\"idle\"}[$interval]) * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"}) * 100 / count(node_cpu_seconds_total{mode=\"user\"} * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"}) ", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 2 + } + ], + "timeFrom": "1m", + "timeShift": null, + "title": "CPU Idle", + "type": "gauge" + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "Prometheus", + "decimals": 2, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 4 + }, + "hiddenSeries": false, + "id": 13, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": false, + "hideZero": false, + "max": true, + "min": true, + "rightSide": true, + "show": false, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "8.0.6", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_load5 * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"}", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "load5 {{node_name}}", + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "System Load by Node", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "Prometheus", + "decimals": 2, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 4 + }, + "hiddenSeries": false, + "id": 14, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": false, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null as zero", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "8.0.6", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "100 - (avg(irate(node_cpu_seconds_total{mode=\"idle\"}[$interval]) * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"} * 100) by (node_name))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{node_name}}", + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "CPU Usage by Node", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "percent", + "label": null, + "logBase": 1, + "max": "100", + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "cacheTimeout": null, + "datasource": "Prometheus", + "fieldConfig": { + "defaults": { + "color": { + "mode": "fixed" + }, + "decimals": 1, + "mappings": [ + { + "options": { + "match": "null", + "result": { + "text": "N/A" + } + }, + "type": "special" + } + ], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "decbytes" + }, + "overrides": [] + }, + "gridPos": { + "h": 4, + "w": 6, + "x": 0, + "y": 11 + }, + "hideTimeOverride": true, + "id": 3, + "interval": null, + "links": [], + "maxDataPoints": 100, + "options": { + "colorMode": "value", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "horizontal", + "reduceOptions": { + "calcs": [ + "last" + ], + "fields": "", + "values": false + }, + "text": {}, + "textMode": "auto" + }, + "pluginVersion": "8.0.6", + "targets": [ + { + "expr": "sum(node_memory_MemTotal_bytes * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 20 + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Total Memory", + "type": "stat" + }, + { + "cacheTimeout": null, + "datasource": "Prometheus", + "fieldConfig": { + "defaults": { + "mappings": [ + { + "options": { + "match": "null", + "result": { + "text": "N/A" + } + }, + "type": "special" + } + ], + "max": 100, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "rgba(245, 54, 54, 0.9)", + "value": null + }, + { + "color": "rgba(237, 129, 40, 0.89)", + "value": 10 + }, + { + "color": "rgba(50, 172, 45, 0.97)", + "value": 25 + } + ] + }, + "unit": "percent" + }, + "overrides": [] + }, + "gridPos": { + "h": 4, + "w": 6, + "x": 6, + "y": 11 + }, + "id": 8, + "interval": null, + "links": [], + "maxDataPoints": 100, + "options": { + "orientation": "horizontal", + "reduceOptions": { + "calcs": [ + "last" + ], + "fields": "", + "values": false + }, + "showThresholdLabels": false, + "showThresholdMarkers": true, + "text": {} + }, + "pluginVersion": "8.0.6", + "targets": [ + { + "expr": "sum((node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"} * 100) / count(node_meta * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 20 + } + ], + "title": "Available Memory", + "type": "gauge" + }, + { + "cacheTimeout": null, + "datasource": "Prometheus", + "fieldConfig": { + "defaults": { + "color": { + "mode": "fixed" + }, + "decimals": 1, + "mappings": [ + { + "options": { + "match": "null", + "result": { + "text": "N/A" + } + }, + "type": "special" + } + ], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "decbytes" + }, + "overrides": [] + }, + "gridPos": { + "h": 4, + "w": 6, + "x": 12, + "y": 11 + }, + "hideTimeOverride": true, + "id": 9, + "interval": null, + "links": [], + "maxDataPoints": 100, + "options": { + "colorMode": "value", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "horizontal", + "reduceOptions": { + "calcs": [ + "last" + ], + "fields": "", + "values": false + }, + "text": {}, + "textMode": "auto" + }, + "pluginVersion": "8.0.6", + "targets": [ + { + "exemplar": true, + "expr": "sum(node_filesystem_size_bytes{fstype=\"ext4\",mountpoint=~\"(/$)|(/media.*)\"} * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"})", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 20 + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Total Disk Space", + "type": "stat" + }, + { + "cacheTimeout": null, + "datasource": "Prometheus", + "fieldConfig": { + "defaults": { + "mappings": [ + { + "options": { + "match": "null", + "result": { + "text": "N/A" + } + }, + "type": "special" + } + ], + "max": 100, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "rgba(245, 54, 54, 0.9)", + "value": null + }, + { + "color": "rgba(237, 129, 40, 0.89)", + "value": 10 + }, + { + "color": "rgba(50, 172, 45, 0.97)", + "value": 25 + } + ] + }, + "unit": "percent" + }, + "overrides": [] + }, + "gridPos": { + "h": 4, + "w": 6, + "x": 18, + "y": 11 + }, + "id": 10, + "interval": null, + "links": [], + "maxDataPoints": 100, + "options": { + "orientation": "horizontal", + "reduceOptions": { + "calcs": [ + "last" + ], + "fields": "", + "values": false + }, + "showThresholdLabels": false, + "showThresholdMarkers": true, + "text": {} + }, + "pluginVersion": "8.0.6", + "targets": [ + { + "exemplar": true, + "expr": "sum((node_filesystem_free_bytes{fstype=\"ext4\",mountpoint=~\"(/$)|(/media.*)\"} / node_filesystem_size_bytes{fstype=\"ext4\",mountpoint=~\"(/$)|(/media.*)\"}) * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"} * 100) / count(node_meta * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"})", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 20 + } + ], + "title": "Available Disk Space", + "type": "gauge" + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "Prometheus", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 15 + }, + "hiddenSeries": false, + "id": 15, + "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": "null", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "8.0.6", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum((node_memory_MemTotal_bytes - node_memory_MemFree_bytes - node_memory_Cached_bytes - node_memory_Buffers_bytes - node_memory_Slab_bytes) * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"}) by (node_name)", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Used {{node_name}}", + "refId": "A", + "step": 2 + }, + { + "expr": "sum(node_memory_Cached * on(instance) group_left(node_name) node_meta{node_id=~\"$node_id\"}) by (node_name)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Cached {{node_name}}", + "refId": "B", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Memory usage by Node", + "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": "Prometheus", + "decimals": 2, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 22 + }, + "hiddenSeries": false, + "id": 16, + "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": "null as zero", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "8.0.6", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(node_disk_read_bytes_total[$interval]) * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"}) by (node_name)", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "Read {{node_name}}", + "refId": "A", + "step": 2 + }, + { + "expr": "sum(irate(node_disk_written_bytes_total[$interval]) * on(instance) group_left(node_name) node_meta{node_id=~\"$node_id\"}) by (node_name)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Written {{node_name}}", + "refId": "B", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Disk I/O by Node", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "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": "Prometheus", + "decimals": 2, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 29 + }, + "hiddenSeries": false, + "id": 18, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": true, + "show": false, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null as zero", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "8.0.6", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(node_disk_reads_completed_total[$interval]) * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"}) by (node_name)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Reads {{node_name}}", + "refId": "A", + "step": 2 + }, + { + "expr": "sum(irate(node_disk_writes_completed_total[$interval]) * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"}) by (node_name)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Writes {{node_name}}", + "refId": "B", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "IOPS by Node", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "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 + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "Prometheus", + "decimals": 2, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 29 + }, + "hiddenSeries": false, + "id": 19, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": false, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null as zero", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "8.0.6", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "(avg(irate(node_cpu_seconds_total{mode=\"iowait\"}[$interval]) * on(instance) group_left(node_name) node_meta{node_name=~\"$node_id\"} * 100) by (node_name))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{node_name}}", + "refId": "A", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "CPU IO Wait by Node", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "percent", + "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": "Prometheus", + "decimals": 0, + "fill": 3, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 18, + "x": 0, + "y": 36 + }, + "hiddenSeries": false, + "id": 12, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "8.0.6", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(container_last_seen[5m]) * on(container_label_com_docker_swarm_node_id) group_left(node_name) node_meta{node_name=~\"${node_id}\"}) by (container_label_com_docker_swarm_service_name)", + "format": "time_series", + "hide": false, + "intervalFactor": 10, + "legendFormat": "{{ container_label_com_docker_swarm_service_name }}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Running Containers by Service", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "cacheTimeout": null, + "datasource": "Prometheus", + "fieldConfig": { + "defaults": { + "color": { + "fixedColor": "rgb(31, 120, 193)", + "mode": "fixed" + }, + "decimals": 0, + "mappings": [ + { + "options": { + "match": "null", + "result": { + "text": "N/A" + } + }, + "type": "special" + } + ], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "none" + }, + "overrides": [] + }, + "gridPos": { + "h": 7, + "w": 6, + "x": 18, + "y": 36 + }, + "id": 7, + "interval": null, + "links": [], + "maxDataPoints": 100, + "options": { + "colorMode": "none", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "horizontal", + "reduceOptions": { + "calcs": [ + "mean" + ], + "fields": "", + "values": false + }, + "text": {}, + "textMode": "auto" + }, + "pluginVersion": "8.0.6", + "targets": [ + { + "expr": "count(rate(container_last_seen[5m]) * on(container_label_com_docker_swarm_node_id) group_left(node_name) node_meta{node_name=~\"$node_id\"})", + "format": "time_series", + "intervalFactor": 2, + "refId": "A", + "step": 20 + } + ], + "title": "Total Containers", + "type": "stat" + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "Prometheus", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 43 + }, + "hiddenSeries": false, + "id": 17, + "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": "null", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "8.0.6", + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(container_network_receive_bytes_total[$interval]) * on(container_label_com_docker_swarm_node_id) group_left(node_name) node_meta{node_name=~\"${node_id}\"}) by (node_name)", + "format": "time_series", + "interval": "", + "intervalFactor": 2, + "legendFormat": "IN {{node_name}}", + "refId": "A", + "step": 2 + }, + { + "expr": "- sum(rate(container_network_transmit_bytes_total[$interval]) * on(container_label_com_docker_swarm_node_id) group_left(node_name) node_meta{node_name=~\"${node_id}\"}) by (node_name)", + "format": "time_series", + "hide": false, + "intervalFactor": 2, + "legendFormat": "OUT {{node_name}}", + "metric": "", + "refId": "B", + "step": 2 + } + ], + "thresholds": [], + "timeFrom": null, + "timeRegions": [], + "timeShift": null, + "title": "Containers Network Traffic by Node", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "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 + } + }, + { + "columns": [], + "datasource": "Prometheus", + "fontSize": "100%", + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 50 + }, + "hideTimeOverride": true, + "id": 20, + "links": [], + "pageSize": null, + "scroll": true, + "showHeader": true, + "sort": { + "col": 0, + "desc": true + }, + "styles": [ + { + "alias": "Time", + "align": "auto", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "date" + }, + { + "alias": "", + "align": "auto", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "decimals": 2, + "pattern": "/.*/", + "thresholds": [], + "type": "number", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(node_meta) by (node_id, node_name, instance)", + "format": "table", + "intervalFactor": 2, + "refId": "A", + "step": 2 + } + ], + "timeFrom": "1s", + "title": "Cluster members", + "transform": "table", + "type": "table-old" + } + ], + "refresh": "5s", + "schemaVersion": 30, + "style": "dark", + "tags": [ + "swarmprom", + "prometheus", + "node-exporter", + "cadvisor" + ], + "templating": { + "list": [ + { + "allValue": ".+", + "current": { + "selected": false, + "text": "All", + "value": "$__all" + }, + "datasource": "Prometheus", + "definition": "", + "description": null, + "error": null, + "hide": 0, + "includeAll": true, + "label": "Swarm Node", + "multi": false, + "name": "node_id", + "options": [], + "query": { + "query": "node_meta", + "refId": "Prometheus-node_id-Variable-Query" + }, + "refresh": 1, + "regex": "/node_name=\"([^\"]+)\"/", + "skipUrlSync": false, + "sort": 0, + "type": "query" + }, + { + "auto": true, + "auto_count": 30, + "auto_min": "30s", + "current": { + "selected": false, + "text": "1m", + "value": "1m" + }, + "description": null, + "error": null, + "hide": 0, + "label": "Interval", + "name": "interval", + "options": [ + { + "selected": false, + "text": "auto", + "value": "$__auto_interval_interval" + }, + { + "selected": true, + "text": "1m", + "value": "1m" + }, + { + "selected": false, + "text": "10m", + "value": "10m" + }, + { + "selected": false, + "text": "30m", + "value": "30m" + }, + { + "selected": false, + "text": "1h", + "value": "1h" + }, + { + "selected": false, + "text": "6h", + "value": "6h" + }, + { + "selected": false, + "text": "12h", + "value": "12h" + }, + { + "selected": false, + "text": "1d", + "value": "1d" + }, + { + "selected": false, + "text": "7d", + "value": "7d" + }, + { + "selected": false, + "text": "14d", + "value": "14d" + }, + { + "selected": false, + "text": "30d", + "value": "30d" + } + ], + "query": "1m,10m,30m,1h,6h,12h,1d,7d,14d,30d", + "queryValue": "", + "refresh": 2, + "skipUrlSync": false, + "type": "interval" + } + ] + }, + "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": "", + "title": "Docker Swarm Nodes", + "uid": "BPlb-Sgik", + "version": 4 +}