Add Node Problem Detector dashboard. (#401)

CHANGELOG.md

@@ -10,6 +10,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Added
 
 - Add Nginx admission controller dashboard.
+- Add Node Problem Detector dashboard.
 
 ## [3.2.4] - 2023-11-06
 

helm/dashboards/charts/public_dashboards/dashboards/shared/public/node-problem-detector.json

@@ -0,0 +1,303 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": {
+          "type": "grafana",
+          "uid": "-- Grafana --"
+        },
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "id": 116,
+  "links": [],
+  "liveNow": false,
+  "panels": [
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "PBFA97CFB590B2093"
+      },
+      "gridPos": {
+        "h": 4,
+        "w": 24,
+        "x": 0,
+        "y": 0
+      },
+      "id": 5,
+      "options": {
+        "code": {
+          "language": "plaintext",
+          "showLineNumbers": false,
+          "showMiniMap": false
+        },
+        "content": "# How to feed data into this dashboard\n\nThis dashboard displays data providede by the `node-problem-detector` managed app.\nPlease install it from the playground catalog to get it going.\n\nWARNING: installing the app on vintage clusters >= 19.3.0 will enable automatic node termination when `node-problem-detector` finds problems. While we tested this, it is still considered an experimental feature.",
+        "mode": "markdown"
+      },
+      "pluginVersion": "10.1.5",
+      "type": "text"
+    },
+    {
+      "gridPos": {
+        "h": 1,
+        "w": 24,
+        "x": 0,
+        "y": 4
+      },
+      "id": 3,
+      "panels": [],
+      "repeat": "cluster_id",
+      "repeatDirection": "h",
+      "title": "Cluster $cluster_id",
+      "type": "row"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "PBFA97CFB590B2093"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          }
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 12,
+        "w": 24,
+        "x": 0,
+        "y": 5
+      },
+      "id": 2,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "editorMode": "code",
+          "expr": "sum(problem_gauge{cluster_id=\"$cluster_id\"}) by (type)",
+          "instant": false,
+          "legendFormat": "{{reason}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Node problems detected on $cluster_id",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "PBFA97CFB590B2093"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "custom": {
+            "align": "auto",
+            "cellOptions": {
+              "type": "auto"
+            },
+            "inspect": false
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          }
+        },
+        "overrides": [
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "Value"
+            },
+            "properties": [
+              {
+                "id": "custom.hidden",
+                "value": true
+              }
+            ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "Time"
+            },
+            "properties": [
+              {
+                "id": "custom.hidden",
+                "value": true
+              }
+            ]
+          }
+        ]
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 24,
+        "x": 0,
+        "y": 17
+      },
+      "id": 4,
+      "options": {
+        "cellHeight": "sm",
+        "footer": {
+          "countRows": false,
+          "fields": "",
+          "reducer": [
+            "sum"
+          ],
+          "show": false
+        },
+        "showHeader": true
+      },
+      "pluginVersion": "10.1.5",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "editorMode": "code",
+          "exemplar": false,
+          "expr": "sum(problem_gauge{cluster_id=\"$cluster_id\"}) by (node,type) > 0",
+          "format": "table",
+          "instant": true,
+          "legendFormat": "__auto",
+          "range": false,
+          "refId": "A"
+        }
+      ],
+      "title": "Current Problems",
+      "type": "table"
+    }
+  ],
+  "refresh": "5s",
+  "schemaVersion": 38,
+  "style": "dark",
+  "tags": [
+    "owner:team-phoenix"
+  ],
+  "templating": {
+    "list": [
+      {
+        "current": {
+          "selected": false,
+          "text": "vr7i8",
+          "value": "vr7i8"
+        },
+        "datasource": {
+          "type": "prometheus",
+          "uid": "PBFA97CFB590B2093"
+        },
+        "definition": "label_values(problem_counter,cluster_id)",
+        "hide": 0,
+        "includeAll": false,
+        "label": "Cluster",
+        "multi": true,
+        "name": "cluster_id",
+        "options": [],
+        "query": {
+          "query": "label_values(problem_counter,cluster_id)",
+          "refId": "PrometheusVariableQueryEditor-VariableQuery"
+        },
+        "refresh": 1,
+        "regex": "",
+        "skipUrlSync": false,
+        "sort": 1,
+        "type": "query"
+      }
+    ]
+  },
+  "time": {
+    "from": "now-30m",
+    "to": "now"
+  },
+  "timepicker": {},
+  "timezone": "",
+  "title": "Node Problem Detector",
+  "uid": "f5fc3e61-0b36-40ba-bcc8-f0d9ecbe2900",
+  "version": 1,
+  "weekStart": ""
+}