Merge pull request #3194 from hashicorp/f-grafana-metrics

Grafana metrics

integrations/grafana_dashboards/README.md

+# Setting up a Grafana dashboard for Nomad
+
+This is a sample Grafana dashboard to use for a Nomad cluster.
+
+Requirements:
+
+1. Set up a Prometheus server configured to read data from Nomad. See
+  this [sample Prometheus configuration][https://github.com/hashicorp/nomad/integrations/prometheus]
+  for an example.
+
+2. Set up a Grafana server configured with a Prometheus data source. See
+[Prometheus's instructions for Grafana](https://prometheus.io/docs/visualization/grafana/#creating-a-prometheus-data-source)
+for more information
+
+3. [Import](http://docs.grafana.org/features/export_import/) this Grafana
+dashboard as a new Grafana dashboard. Make sure the data source name matches
+the Prometheus data source in #2.

integrations/grafana_dashboards/sample_grafana_dashboard.json

+{
+  "__inputs": [
+    {
+      "name": "DS_PROMETHEUS-DATA",
+      "label": "prometheus-data",
+      "description": "",
+      "type": "datasource",
+      "pluginId": "prometheus",
+      "pluginName": "Prometheus"
+    }
+  ],
+  "__requires": [
+    {
+      "type": "grafana",
+      "id": "grafana",
+      "name": "Grafana",
+      "version": "4.4.3"
+    },
+    {
+      "type": "panel",
+      "id": "graph",
+      "name": "Graph",
+      "version": ""
+    },
+    {
+      "type": "panel",
+      "id": "heatmap",
+      "name": "Heatmap",
+      "version": ""
+    },
+    {
+      "type": "datasource",
+      "id": "prometheus",
+      "name": "Prometheus",
+      "version": "1.0.0"
+    }
+  ],
+  "annotations": {
+    "list": []
+  },
+  "editable": true,
+  "gnetId": null,
+  "graphTooltip": 0,
+  "hideControls": false,
+  "id": null,
+  "links": [],
+  "rows": [
+    {
+      "collapse": false,
+      "height": "250px",
+      "panels": [
+        {
+          "aliasColors": {},
+          "bars": true,
+          "dashLength": 10,
+          "dashes": false,
+          "datasource": "${DS_PROMETHEUS-DATA}",
+          "fill": 1,
+          "id": 1,
+          "legend": {
+            "avg": false,
+            "current": false,
+            "max": false,
+            "min": false,
+            "show": true,
+            "total": false,
+            "values": false
+          },
+          "lines": true,
+          "linewidth": 1,
+          "links": [],
+          "nullPointMode": "null",
+          "percentage": false,
+          "pointradius": 5,
+          "points": false,
+          "renderer": "flot",
+          "seriesOverrides": [],
+          "spaceLength": 10,
+          "span": 12,
+          "stack": false,
+          "steppedLine": false,
+          "targets": [
+            {
+              "expr": "nomad_client_consul_check_regisrations",
+              "format": "time_series",
+              "intervalFactor": 2,
+              "metric": "nomad_client_consul_check_regisrations",
+              "refId": "B",
+              "step": 20
+            }
+          ],
+          "thresholds": [],
+          "timeFrom": null,
+          "timeShift": null,
+          "title": "Client Consul Check Regisrations",
+          "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
+            }
+          ]
+        }
+      ],
+      "repeat": null,
+      "repeatIteration": null,
+      "repeatRowId": null,
+      "showTitle": false,
+      "title": "Dashboard Row",
+      "titleSize": "h6"
+    },
+    {
+      "collapse": false,
+      "height": 250,
+      "panels": [
+        {
+          "aliasColors": {},
+          "bars": false,
+          "dashLength": 10,
+          "dashes": false,
+          "datasource": "${DS_PROMETHEUS-DATA}",
+          "fill": 1,
+          "id": 6,
+          "legend": {
+            "avg": false,
+            "current": false,
+            "max": false,
+            "min": false,
+            "show": true,
+            "total": false,
+            "values": false
+          },
+          "lines": true,
+          "linewidth": 1,
+          "links": [],
+          "nullPointMode": "null",
+          "percentage": false,
+          "pointradius": 5,
+          "points": false,
+          "renderer": "flot",
+          "seriesOverrides": [],
+          "spaceLength": 10,
+          "span": 6,
+          "stack": false,
+          "steppedLine": true,
+          "targets": [
+            {
+              "expr": "nomad_linux_client_allocations_running",
+              "format": "time_series",
+              "intervalFactor": 2,
+              "metric": "nomad_linux_client_allocations_running",
+              "refId": "A",
+              "step": 20
+            }
+          ],
+          "thresholds": [],
+          "timeFrom": null,
+          "timeShift": null,
+          "title": "Client Allocations Running",
+          "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
+            }
+          ]
+        },
+        {
+          "aliasColors": {},
+          "bars": true,
+          "dashLength": 10,
+          "dashes": false,
+          "datasource": "${DS_PROMETHEUS-DATA}",
+          "fill": 1,
+          "id": 5,
+          "legend": {
+            "avg": false,
+            "current": false,
+            "max": false,
+            "min": false,
+            "show": true,
+            "total": false,
+            "values": false
+          },
+          "lines": true,
+          "linewidth": 1,
+          "links": [],
+          "nullPointMode": "null",
+          "percentage": false,
+          "pointradius": 5,
+          "points": false,
+          "renderer": "flot",
+          "seriesOverrides": [],
+          "spaceLength": 10,
+          "span": 6,
+          "stack": false,
+          "steppedLine": false,
+          "targets": [
+            {
+              "expr": "nomad_linux_client_allocations_blocked",
+              "format": "time_series",
+              "intervalFactor": 2,
+              "metric": "nomad_linux_client_allocations_blocked",
+              "refId": "A",
+              "step": 40
+            }
+          ],
+          "thresholds": [],
+          "timeFrom": null,
+          "timeShift": null,
+          "title": "Client Allocations Blocked",
+          "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
+            }
+          ]
+        }
+      ],
+      "repeat": null,
+      "repeatIteration": null,
+      "repeatRowId": null,
+      "showTitle": false,
+      "title": "Dashboard Row",
+      "titleSize": "h6"
+    },
+    {
+      "collapse": false,
+      "height": 250,
+      "panels": [
+        {
+          "cards": {
+            "cardPadding": null,
+            "cardRound": null
+          },
+          "color": {
+            "cardColor": "rgb(255, 104, 0)",
+            "colorScale": "sqrt",
+            "colorScheme": "interpolateReds",
+            "exponent": 0.5,
+            "mode": "opacity"
+          },
+          "dataFormat": "timeseries",
+          "datasource": "${DS_PROMETHEUS-DATA}",
+          "heatmap": {},
+          "highlightCards": true,
+          "id": 3,
+          "links": [],
+          "span": 6,
+          "targets": [
+            {
+              "expr": "nomad_linux_runtime_total_gc_pause_ns",
+              "format": "time_series",
+              "intervalFactor": 2,
+              "metric": "nomad_linux_runtime_total_gc_pause_ns",
+              "refId": "A",
+              "step": 20
+            }
+          ],
+          "title": "Runtime Total GS Pauses",
+          "tooltip": {
+            "show": true,
+            "showHistogram": false
+          },
+          "type": "heatmap",
+          "xAxis": {
+            "show": true
+          },
+          "xBucketNumber": null,
+          "xBucketSize": null,
+          "yAxis": {
+            "decimals": null,
+            "format": "short",
+            "logBase": 1,
+            "max": null,
+            "min": null,
+            "show": true,
+            "splitFactor": null
+          },
+          "yBucketNumber": null,
+          "yBucketSize": null
+        },
+        {
+          "aliasColors": {},
+          "bars": true,
+          "dashLength": 10,
+          "dashes": false,
+          "datasource": "${DS_PROMETHEUS-DATA}",
+          "fill": 1,
+          "id": 2,
+          "legend": {
+            "avg": false,
+            "current": false,
+            "max": false,
+            "min": false,
+            "show": true,
+            "total": false,
+            "values": false
+          },
+          "lines": true,
+          "linewidth": 1,
+          "links": [],
+          "nullPointMode": "null",
+          "percentage": false,
+          "pointradius": 5,
+          "points": false,
+          "renderer": "flot",
+          "seriesOverrides": [],
+          "spaceLength": 10,
+          "span": 6,
+          "stack": false,
+          "steppedLine": false,
+          "targets": [
+            {
+              "expr": "nomad_linux_runtime_alloc_bytes",
+              "format": "time_series",
+              "intervalFactor": 2,
+              "metric": "nomad_linux_runtime_alloc_bytes",
+              "refId": "A",
+              "step": 40
+            }
+          ],
+          "thresholds": [],
+          "timeFrom": null,
+          "timeShift": null,
+          "title": "Runtime Alloc Bytes (Linux)",
+          "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
+            }
+          ]
+        }
+      ],
+      "repeat": null,
+      "repeatIteration": null,
+      "repeatRowId": null,
+      "showTitle": false,
+      "title": "Dashboard Row",
+      "titleSize": "h6"
+    },
+    {
+      "collapse": false,
+      "height": 250,
+      "panels": [],
+      "repeat": null,
+      "repeatIteration": null,
+      "repeatRowId": null,
+      "showTitle": false,
+      "title": "Dashboard Row",
+      "titleSize": "h6"
+    },
+    {
+      "collapse": false,
+      "height": 250,
+      "panels": [],
+      "repeat": null,
+      "repeatIteration": null,
+      "repeatRowId": null,
+      "showTitle": false,
+      "title": "Dashboard Row",
+      "titleSize": "h6"
+    },
+    {
+      "collapse": false,
+      "height": 250,
+      "panels": [],
+      "repeat": null,
+      "repeatIteration": null,
+      "repeatRowId": null,
+      "showTitle": false,
+      "title": "Dashboard Row",
+      "titleSize": "h6"
+    },
+    {
+      "collapse": false,
+      "height": 250,
+      "panels": [],
+      "repeat": null,
+      "repeatIteration": null,
+      "repeatRowId": null,
+      "showTitle": false,
+      "title": "Dashboard Row",
+      "titleSize": "h6"
+    },
+    {
+      "collapse": false,
+      "height": 250,
+      "panels": [],
+      "repeat": null,
+      "repeatIteration": null,
+      "repeatRowId": null,
+      "showTitle": false,
+      "title": "Dashboard Row",
+      "titleSize": "h6"
+    }
+  ],
+  "schemaVersion": 14,
+  "style": "dark",
+  "tags": [],
+  "templating": {
+    "list": []
+  },
+  "time": {
+    "from": "now-6h",
+    "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": "Prometheus Nomad",
+  "version": 7
+}
\ No newline at end of file