apiVersion: v1
kind: ConfigMap
metadata:
  name: node-pool-health-dashboard
  labels:
    grafana_dashboard: "1"
data:
  node-pool-health.json: |
    {
      "annotations": {
        "list": []
      },
      "editable": true,
      "gnetId": null,
      "graphTooltip": 0,
      "hideControls": false,
      "id": null,
      "iteration": 1583185057230,
      "links": [],
      "panels": [
        {
          "datasource": "Prometheus",
          "fieldConfig": {
            "defaults": {
              "color": {
                "mode": "thresholds"
              },
              "mappings": [],
              "thresholds": {
                "mode": "absolute",
                "steps": [
                  { "color": "green", "value": null },
                  { "color": "yellow", "value": 70 },
                  { "color": "red", "value": 90 }
                ]
              },
              "unit": "percent"
            },
            "overrides": []
          },
          "gridPos": { "h": 4, "w": 12, "x": 0, "y": 0 },
          "id": 1,
          "options": {
            "orientation": "auto",
            "reduceOptions": {
              "calcs": ["mean"],
              "fields": "",
              "values": false
            }
          },
          "targets": [
            {
              "expr": "sum(rate(node_cpu_seconds_total{mode!=\"idle\"}[5m])) by (workload) / sum(machine_cpu_cores) by (workload) * 100",
              "legendFormat": "{{ "{{" }}workload{{ "}}" }} CPU %",
              "refId": "A"
            }
          ],
          "title": "CPU Utilization by Node Pool",
          "type": "stat"
        },
        {
          "datasource": "Prometheus",
          "fieldConfig": {
            "defaults": {
              "unit": "percent"
            }
          },
          "gridPos": { "h": 4, "w": 12, "x": 12, "y": 0 },
          "id": 2,
          "options": {
            "reduceOptions": { "calcs": ["mean"] }
          },
          "targets": [
            {
              "expr": "sum(node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) by (workload) / sum(node_memory_MemTotal_bytes) by (workload) * 100",
              "legendFormat": "{{ "{{" }}workload{{ "}}" }} Mem %",
              "refId": "A"
            }
          ],
          "title": "Memory Utilization by Node Pool",
          "type": "stat"
        },
        {
          "datasource": "Prometheus",
          "gridPos": { "h": 8, "w": 24, "x": 0, "y": 4 },
          "id": 3,
          "targets": [
            {
              "expr": "sum(rate(kube_pod_container_status_restarts_total[5m])) by (namespace, pod, node) > 0",
              "legendFormat": "{{ "{{" }}namespace{{ "}}" }}/{{ "{{" }}pod{{ "}}" }} ({{ "{{" }}node{{ "}}" }})",
              "refId": "A"
            }
          ],
          "title": "Pod Restarts (Last 5m)",
          "type": "timeseries"
        }
      ],
      "refresh": "10s",
      "schemaVersion": 30,
      "style": "dark",
      "tags": ["kubernetes", "infrastructure"],
      "time": {
        "from": "now-1h",
        "to": "now"
      },
      "title": "Node Pool Health",
      "uid": "node-pool-health"
    }