From 75ec5a0d9400aaff18727e99cdc3153612e8d50f Mon Sep 17 00:00:00 2001
From: Brian Christner <brian.christner@gmail.com>
Date: Thu, 28 Jul 2016 13:37:16 +0200
Subject: [PATCH] added System_Monitoring Dashboard for Grafana with Alerting
metrics
---
dashboards/HighLoadDashboard.json | 259 -----------
dashboards/System_Monitoring.json | 749 ++++++++++++++++++++++++++++++
2 files changed, 749 insertions(+), 259 deletions(-)
delete mode 100644 dashboards/HighLoadDashboard.json
create mode 100644 dashboards/System_Monitoring.json
diff --git a/dashboards/HighLoadDashboard.json b/dashboards/HighLoadDashboard.json
deleted file mode 100644
index 66da47c..0000000
--- a/dashboards/HighLoadDashboard.json
+++ /dev/null
@@ -1,259 +0,0 @@
-{
- "__inputs": [
- {
- "name": "DS_PROMETHEUS",
- "label": "Prometheus",
- "description": "",
- "type": "datasource",
- "pluginId": "prometheus",
- "pluginName": "Prometheus"
- }
- ],
- "__requires": [
- {
- "type": "panel",
- "id": "graph",
- "name": "Graph",
- "version": ""
- },
- {
- "type": "grafana",
- "id": "grafana",
- "name": "Grafana",
- "version": "3.1.0"
- },
- {
- "type": "datasource",
- "id": "prometheus",
- "name": "Prometheus",
- "version": "1.0.0"
- }
- ],
- "id": null,
- "title": "High Load",
- "tags": [],
- "style": "dark",
- "timezone": "browser",
- "editable": true,
- "hideControls": false,
- "sharedCrosshair": false,
- "rows": [
- {
- "collapse": false,
- "editable": true,
- "height": 323.625,
- "panels": [
- {
- "aliasColors": {},
- "bars": false,
- "datasource": "${DS_PROMETHEUS}",
- "editable": true,
- "error": false,
- "fill": 1,
- "grid": {
- "threshold1": null,
- "threshold1Color": "rgba(216, 200, 27, 0.27)",
- "threshold2": null,
- "threshold2Color": "rgba(234, 112, 112, 0.22)"
- },
- "id": 1,
- "isNew": true,
- "legend": {
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "show": true,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 2,
- "links": [],
- "nullPointMode": "connected",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [],
- "span": 12,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "node_load1",
- "hide": false,
- "intervalFactor": 2,
- "legendFormat": "",
- "metric": "node_load1",
- "refId": "A",
- "step": 10
- }
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Panel Title",
- "tooltip": {
- "msResolution": false,
- "shared": true,
- "sort": 0,
- "value_type": "cumulative"
- },
- "type": "graph",
- "xaxis": {
- "show": true
- },
- "yaxes": [
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- },
- {
- "format": "short",
- "label": null,
- "logBase": 1,
- "max": null,
- "min": null,
- "show": true
- }
- ]
- }
- ],
- "title": "Row"
- },
- {
- "collapse": false,
- "editable": true,
- "height": 407.4375,
- "panels": [
- {
- "aliasColors": {
- "ALERTS{alertname=\"high_load\",alertstate=\"firing\",instance=\"node-exporter:9100\",job=\"prometheus\"}": "#BF1B00"
- },
- "bars": false,
- "datasource": "${DS_PROMETHEUS}",
- "editable": true,
- "error": false,
- "fill": 1,
- "grid": {
- "threshold1": null,
- "threshold1Color": "rgba(216, 200, 27, 0.27)",
- "threshold2": null,
- "threshold2Color": "rgba(234, 112, 112, 0.22)"
- },
- "id": 3,
- "isNew": true,
- "legend": {
- "alignAsTable": false,
- "avg": false,
- "current": false,
- "max": false,
- "min": false,
- "rightSide": true,
- "show": true,
- "sideWidth": null,
- "total": false,
- "values": false
- },
- "lines": true,
- "linewidth": 2,
- "links": [],
- "nullPointMode": "connected",
- "percentage": false,
- "pointradius": 5,
- "points": false,
- "renderer": "flot",
- "seriesOverrides": [],
- "span": 12,
- "stack": false,
- "steppedLine": false,
- "targets": [
- {
- "expr": "ALERTS",
- "intervalFactor": 1,
- "metric": "ALERTS",
- "refId": "A",
- "step": 5
- }
- ],
- "timeFrom": null,
- "timeShift": null,
- "title": "Panel Title",
- "tooltip": {
- "msResolution": false,
- "shared": true,
- "sort": 0,
- "value_type": "cumulative"
- },
- "type": "graph",
- "xaxis": {
- "show": true
- },
- "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
- }
- ]
- }
- ],
- "title": "New row"
- }
- ],
- "time": {
- "from": "now-3h",
- "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"
- ]
- },
- "templating": {
- "list": []
- },
- "annotations": {
- "list": []
- },
- "refresh": "10s",
- "schemaVersion": 12,
- "version": 4,
- "links": [],
- "gnetId": null
-}
\ No newline at end of file
diff --git a/dashboards/System_Monitoring.json b/dashboards/System_Monitoring.json
new file mode 100644
index 0000000..568a6a3
--- /dev/null
+++ b/dashboards/System_Monitoring.json
@@ -0,0 +1,749 @@
+{
+ "id": 3,
+ "title": "System Monitoring",
+ "tags": [
+ "alerts"
+ ],
+ "style": "dark",
+ "timezone": "browser",
+ "editable": true,
+ "hideControls": true,
+ "sharedCrosshair": false,
+ "rows": [
+ {
+ "collapse": false,
+ "editable": true,
+ "height": "250px",
+ "panels": [
+ {
+ "cacheTimeout": null,
+ "colorBackground": true,
+ "colorValue": false,
+ "colors": [
+ "rgba(50, 172, 45, 0.97)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(245, 54, 54, 0.9)"
+ ],
+ "datasource": null,
+ "decimals": null,
+ "editable": true,
+ "error": false,
+ "format": "none",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "id": 7,
+ "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"
+ }
+ ],
+ "span": 6,
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "targets": [
+ {
+ "expr": "ALERTS{alertname=\"high_load\",alertstate=\"firing\"}",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "metric": "ALERTS",
+ "refId": "A",
+ "step": 120
+ }
+ ],
+ "thresholds": "0.6,0.9",
+ "title": "Load Status",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "HIGH",
+ "value": "1"
+ },
+ {
+ "op": "=",
+ "text": "OK",
+ "value": "0"
+ }
+ ],
+ "valueName": "current"
+ },
+ {
+ "cacheTimeout": null,
+ "colorBackground": true,
+ "colorValue": false,
+ "colors": [
+ "rgba(50, 172, 45, 0.97)",
+ "rgba(237, 129, 40, 0.89)",
+ "rgba(245, 54, 54, 0.9)"
+ ],
+ "datasource": null,
+ "decimals": null,
+ "editable": true,
+ "error": false,
+ "format": "none",
+ "gauge": {
+ "maxValue": 100,
+ "minValue": 0,
+ "show": false,
+ "thresholdLabels": false,
+ "thresholdMarkers": true
+ },
+ "id": 9,
+ "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"
+ }
+ ],
+ "span": 6,
+ "sparkline": {
+ "fillColor": "rgba(31, 118, 189, 0.18)",
+ "full": false,
+ "lineColor": "rgb(31, 120, 193)",
+ "show": false
+ },
+ "targets": [
+ {
+ "expr": "ALERTS{alertname=\"service_down\",alertstate=\"firing\"}",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "",
+ "metric": "ALERTS",
+ "refId": "A",
+ "step": 120
+ }
+ ],
+ "thresholds": "0.6,0.9",
+ "title": "Service Down",
+ "type": "singlestat",
+ "valueFontSize": "80%",
+ "valueMaps": [
+ {
+ "op": "=",
+ "text": "Offline",
+ "value": "1"
+ },
+ {
+ "op": "=",
+ "text": "OK",
+ "value": "0"
+ }
+ ],
+ "valueName": "current"
+ }
+ ],
+ "title": "Row"
+ },
+ {
+ "collapse": false,
+ "editable": true,
+ "height": "250px",
+ "panels": [
+ {
+ "aliasColors": {},
+ "bars": false,
+ "datasource": null,
+ "editable": true,
+ "error": false,
+ "fill": 0,
+ "grid": {
+ "threshold1": null,
+ "threshold1Color": "rgba(216, 200, 27, 0.27)",
+ "threshold2": null,
+ "threshold2Color": "rgba(234, 112, 112, 0.22)"
+ },
+ "id": 2,
+ "isNew": true,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [],
+ "nullPointMode": "connected",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "span": 6,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_memory_MemFree",
+ "intervalFactor": 2,
+ "legendFormat": "{{job}}",
+ "metric": "node_memory_MemFree",
+ "refId": "A",
+ "step": 30
+ }
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Free RAM",
+ "tooltip": {
+ "msResolution": false,
+ "shared": true,
+ "sort": 0,
+ "value_type": "cumulative"
+ },
+ "type": "graph",
+ "xaxis": {
+ "show": true
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "datasource": null,
+ "editable": true,
+ "error": false,
+ "fill": 0,
+ "grid": {
+ "threshold1": 500000000,
+ "threshold1Color": "rgba(216, 200, 27, 0.27)",
+ "threshold2": 250000000,
+ "threshold2Color": "rgba(234, 112, 112, 0.22)"
+ },
+ "id": 3,
+ "isNew": true,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [],
+ "nullPointMode": "connected",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "span": 6,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_memory_SwapFree",
+ "intervalFactor": 2,
+ "legendFormat": "{{job}}",
+ "refId": "A",
+ "step": 30
+ }
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Free Swap",
+ "tooltip": {
+ "msResolution": true,
+ "shared": true,
+ "sort": 0,
+ "value_type": "cumulative"
+ },
+ "type": "graph",
+ "xaxis": {
+ "show": true
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ }
+ ],
+ "title": "New row"
+ },
+ {
+ "collapse": false,
+ "editable": true,
+ "height": "250px",
+ "panels": [
+ {
+ "aliasColors": {},
+ "bars": false,
+ "datasource": null,
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "grid": {
+ "threshold1": null,
+ "threshold1Color": "rgba(216, 200, 27, 0.27)",
+ "threshold2": null,
+ "threshold2Color": "rgba(234, 112, 112, 0.22)"
+ },
+ "id": 6,
+ "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": [],
+ "span": 12,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "process_virtual_memory_bytes",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "{{job}}",
+ "metric": "process_virtual_memory_bytes",
+ "refId": "A",
+ "step": 20
+ }
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Virtual Mem Size",
+ "tooltip": {
+ "msResolution": false,
+ "shared": true,
+ "sort": 0,
+ "value_type": "cumulative"
+ },
+ "type": "graph",
+ "xaxis": {
+ "show": true
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ }
+ ],
+ "title": "New row"
+ },
+ {
+ "collapse": false,
+ "editable": true,
+ "height": "250px",
+ "panels": [
+ {
+ "aliasColors": {},
+ "bars": false,
+ "datasource": null,
+ "decimals": null,
+ "editable": true,
+ "error": false,
+ "fill": 1,
+ "grid": {
+ "threshold1": 1,
+ "threshold1Color": "rgba(216, 200, 27, 0.27)",
+ "threshold2": 2,
+ "threshold2Color": "rgba(234, 112, 112, 0.22)"
+ },
+ "id": 5,
+ "isNew": true,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [],
+ "nullPointMode": "connected",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "span": 8,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_load1",
+ "interval": "",
+ "intervalFactor": 1,
+ "legendFormat": "{{job}}",
+ "metric": "node_load1",
+ "refId": "A",
+ "step": 15
+ }
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "CPU Load",
+ "tooltip": {
+ "msResolution": false,
+ "shared": true,
+ "sort": 0,
+ "value_type": "cumulative"
+ },
+ "type": "graph",
+ "xaxis": {
+ "show": true
+ },
+ "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
+ }
+ ]
+ },
+ {
+ "aliasColors": {},
+ "bars": false,
+ "datasource": "Prometheus",
+ "editable": true,
+ "error": false,
+ "fill": 0,
+ "grid": {
+ "threshold1": 20,
+ "threshold1Color": "rgba(216, 200, 27, 0.27)",
+ "threshold2": 10,
+ "threshold2Color": "rgba(234, 112, 112, 0.22)"
+ },
+ "id": 4,
+ "isNew": true,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [],
+ "nullPointMode": "connected",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "span": 4,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "(node_memory_MemFree + node_memory_SwapFree)/(node_memory_MemTotal + node_memory_SwapTotal)*100",
+ "intervalFactor": 2,
+ "legendFormat": "{{job}}",
+ "refId": "A",
+ "step": 60
+ }
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Free Memory (RAM + Swap)",
+ "tooltip": {
+ "msResolution": true,
+ "shared": true,
+ "sort": 0,
+ "value_type": "cumulative"
+ },
+ "type": "graph",
+ "xaxis": {
+ "show": true
+ },
+ "yaxes": [
+ {
+ "format": "percent",
+ "label": "",
+ "logBase": 1,
+ "max": 100,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": null,
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ }
+ ],
+ "title": "New row"
+ },
+ {
+ "collapse": false,
+ "editable": true,
+ "height": 229,
+ "panels": [
+ {
+ "aliasColors": {},
+ "bars": false,
+ "datasource": "Prometheus",
+ "decimals": null,
+ "editable": true,
+ "error": false,
+ "fill": 0,
+ "grid": {
+ "threshold1": 2500000000,
+ "threshold1Color": "rgba(216, 200, 27, 0.27)",
+ "threshold2": 1000000000,
+ "threshold2Color": "rgba(234, 112, 112, 0.22)"
+ },
+ "id": 1,
+ "isNew": true,
+ "legend": {
+ "alignAsTable": false,
+ "avg": false,
+ "current": false,
+ "max": false,
+ "min": false,
+ "rightSide": false,
+ "show": true,
+ "sideWidth": null,
+ "total": false,
+ "values": false
+ },
+ "lines": true,
+ "linewidth": 2,
+ "links": [],
+ "nullPointMode": "connected",
+ "percentage": false,
+ "pointradius": 5,
+ "points": false,
+ "renderer": "flot",
+ "seriesOverrides": [],
+ "span": 4,
+ "stack": false,
+ "steppedLine": false,
+ "targets": [
+ {
+ "expr": "node_filesystem_avail{mountpoint=\"/\"}",
+ "interval": "",
+ "intervalFactor": 2,
+ "legendFormat": "{{job}}",
+ "metric": "",
+ "refId": "A",
+ "step": 60
+ }
+ ],
+ "timeFrom": null,
+ "timeShift": null,
+ "title": "Free Storage",
+ "tooltip": {
+ "msResolution": false,
+ "shared": true,
+ "sort": 0,
+ "value_type": "cumulative"
+ },
+ "type": "graph",
+ "xaxis": {
+ "show": true
+ },
+ "yaxes": [
+ {
+ "format": "bytes",
+ "label": "",
+ "logBase": 1,
+ "max": null,
+ "min": 0,
+ "show": true
+ },
+ {
+ "format": "short",
+ "label": "",
+ "logBase": 1,
+ "max": null,
+ "min": null,
+ "show": true
+ }
+ ]
+ }
+ ],
+ "title": "New row"
+ }
+ ],
+ "time": {
+ "from": "now-3h",
+ "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"
+ ]
+ },
+ "templating": {
+ "list": []
+ },
+ "annotations": {
+ "list": []
+ },
+ "refresh": "10s",
+ "schemaVersion": 12,
+ "version": 5,
+ "links": [],
+ "gnetId": null
+}