feat(helm): ship portable Imp dashboards

.github/workflows/imp-dashboard-metrics-demo.yml

@@ -0,0 +1,35 @@
+name: Imp dashboard metrics demo
+
+on:
+  workflow_dispatch:
+    inputs:
+      hold_seconds:
+        description: Seconds to keep the runner handoff active for dashboard inspection
+        required: true
+        default: "120"
+        type: choice
+        options: ["60", "120", "300"]
+
+permissions:
+  contents: read
+
+jobs:
+  dashboard-demo:
+    name: Create observable runner activity
+    runs-on:
+      group: omni-runner
+      labels: [self-hosted, imp]
+    timeout-minutes: 10
+    steps:
+      - name: Report the dashboard correlation fields
+        run: |
+          printf '%s\n' \
+            "github_repository=$GITHUB_REPOSITORY" \
+            "github_run_id=$GITHUB_RUN_ID" \
+            "github_run_attempt=$GITHUB_RUN_ATTEMPT" \
+            "github_job=$GITHUB_JOB" \
+            "runner_name=$RUNNER_NAME"
+      - name: Hold the runner handoff open
+        run: |
+          echo "holding runner activity for ${{ inputs.hold_seconds }} seconds"
+          sleep "${{ inputs.hold_seconds }}"

charts/imp/dashboards/imp-admin.json

@@ -0,0 +1,351 @@
+{
+  "annotations": {
+    "list": []
+  },
+  "description": "Technical health. Missing data means unknown or missing telemetry, not healthy.",
+  "editable": true,
+  "refresh": "30s",
+  "schemaVersion": 38,
+  "tags": [
+    "imp",
+    "administrator",
+    "microvm"
+  ],
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "timezone": "browser",
+  "title": "Imp administrator",
+  "uid": "imp-admin-v1",
+  "version": 1,
+  "templating": {
+    "list": [
+      {
+        "name": "datasource",
+        "label": "Data source",
+        "type": "datasource",
+        "query": "prometheus",
+        "refresh": 1,
+        "current": {}
+      },
+      {
+        "name": "namespace",
+        "label": "Namespace",
+        "type": "query",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "${datasource}"
+        },
+        "definition": "label_values(imp_vm_state, namespace)",
+        "query": {
+          "query": "label_values(imp_vm_state, namespace)",
+          "refId": "NamespaceVariableQuery"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "multi": true,
+        "refresh": 2,
+        "current": {}
+      },
+      {
+        "name": "vm",
+        "label": "VM",
+        "type": "query",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "${datasource}"
+        },
+        "definition": "label_values(imp_vm_state{namespace=~\"${namespace:regex}\"}, impvm)",
+        "query": {
+          "query": "label_values(imp_vm_state{namespace=~\"${namespace:regex}\"}, impvm)",
+          "refId": "VMVariableQuery"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "multi": true,
+        "refresh": 2,
+        "current": {}
+      }
+    ]
+  },
+  "panels": [
+    {
+      "id": 1,
+      "type": "stat",
+      "title": "Runtime ready",
+      "description": "Missing series means unknown or missing telemetry.",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${datasource}"
+      },
+      "gridPos": {
+        "h": 6,
+        "w": 8,
+        "x": 0,
+        "y": 0
+      },
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "imp_runtime_ready"
+        }
+      ],
+      "options": {
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ]
+        },
+        "orientation": "auto",
+        "textMode": "auto",
+        "colorMode": "value",
+        "graphMode": "none"
+      },
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": []
+      }
+    },
+    {
+      "id": 2,
+      "type": "timeseries",
+      "title": "Observed VMs by state",
+      "description": "Missing series means no observed VMs or missing telemetry.",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${datasource}"
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 8,
+        "x": 8,
+        "y": 0
+      },
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "sum by (state) (imp_vm_state{namespace=~\"${namespace:regex}\",impvm=~\"${vm:regex}\"} == 1)",
+          "legendFormat": "{{state}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "custom": {
+            "lineWidth": 1,
+            "showPoints": "never"
+          }
+        },
+        "overrides": []
+      },
+      "options": {
+        "legend": {
+          "displayMode": "table",
+          "placement": "bottom"
+        },
+        "tooltip": {
+          "mode": "multi"
+        }
+      }
+    },
+    {
+      "id": 3,
+      "type": "timeseries",
+      "title": "Observed VMs by node",
+      "description": "Missing series means no observed VMs or missing telemetry.",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${datasource}"
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 8,
+        "x": 16,
+        "y": 0
+      },
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "sum by (node) (imp_vm_state{namespace=~\"${namespace:regex}\",impvm=~\"${vm:regex}\"} == 1)",
+          "legendFormat": "{{node}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "custom": {
+            "lineWidth": 1,
+            "showPoints": "never"
+          }
+        },
+        "overrides": []
+      },
+      "options": {
+        "legend": {
+          "displayMode": "table",
+          "placement": "bottom"
+        },
+        "tooltip": {
+          "mode": "multi"
+        }
+      }
+    },
+    {
+      "id": 4,
+      "type": "timeseries",
+      "title": "Provisioning latency p95",
+      "description": "Cluster-wide; namespace and VM filters do not apply.",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${datasource}"
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "histogram_quantile(0.95, sum by (le) (rate(imp_vm_scheduling_latency_seconds_bucket[$__rate_interval])))",
+          "legendFormat": "scheduling p95"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "custom": {
+            "lineWidth": 1,
+            "showPoints": "never"
+          },
+          "unit": "s"
+        },
+        "overrides": []
+      },
+      "options": {
+        "legend": {
+          "displayMode": "table",
+          "placement": "bottom"
+        },
+        "tooltip": {
+          "mode": "multi"
+        }
+      }
+    },
+    {
+      "id": 5,
+      "type": "timeseries",
+      "title": "Boot latency p95",
+      "description": "Cluster-wide; namespace and VM filters do not apply.",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${datasource}"
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "histogram_quantile(0.95, sum by (le) (rate(imp_vm_boot_latency_seconds_bucket[$__rate_interval])))",
+          "legendFormat": "boot p95"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "custom": {
+            "lineWidth": 1,
+            "showPoints": "never"
+          },
+          "unit": "s"
+        },
+        "overrides": []
+      },
+      "options": {
+        "legend": {
+          "displayMode": "table",
+          "placement": "bottom"
+        },
+        "tooltip": {
+          "mode": "multi"
+        }
+      }
+    },
+    {
+      "id": 6,
+      "type": "stat",
+      "title": "Recorded scheduling transitions",
+      "description": "Observed histogram events; not unique VM counts.",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${datasource}"
+      },
+      "gridPos": {
+        "h": 6,
+        "w": 12,
+        "x": 0,
+        "y": 16
+      },
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "sum(increase(imp_vm_scheduling_latency_seconds_count[$__range]))"
+        }
+      ],
+      "options": {
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ]
+        },
+        "orientation": "auto",
+        "textMode": "auto",
+        "colorMode": "value",
+        "graphMode": "none"
+      },
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": []
+      }
+    },
+    {
+      "id": 7,
+      "type": "stat",
+      "title": "Recorded boot transitions",
+      "description": "Observed histogram events; not unique VM counts.",
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${datasource}"
+      },
+      "gridPos": {
+        "h": 6,
+        "w": 12,
+        "x": 12,
+        "y": 16
+      },
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "sum(increase(imp_vm_boot_latency_seconds_count[$__range]))"
+        }
+      ],
+      "options": {
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ]
+        },
+        "orientation": "auto",
+        "textMode": "auto",
+        "colorMode": "value",
+        "graphMode": "none"
+      },
+      "fieldConfig": {
+        "defaults": {},
+        "overrides": []
+      }
+    }
+  ]
+}