learning_ai_common_plat/services/monitoring/grafana/dashboards/fleet-overview.json

{
  "annotations": { "list": [] },
  "editable": true,
  "fiscalYearStartMonth": 0,
  "graphTooltip": 1,
  "id": null,
  "links": [],
  "title": "Fleet Overview",
  "tags": ["fleet", "gigafactory"],
  "uid": "fleet-overview",
  "schemaVersion": 38,
  "version": 2,
  "refresh": "30s",
  "time": { "from": "now-6h", "to": "now" },
  "timepicker": { "refresh_intervals": ["15s", "30s", "1m", "5m", "15m", "1h"] },
  "templating": {
    "list": [
      {
        "name": "product",
        "type": "query",
        "datasource": { "type": "prometheus", "uid": "prometheus" },
        "query": "label_values(fleet_queue_depth, product)",
        "refresh": 2,
        "includeAll": true,
        "multi": true,
        "current": { "text": "All", "value": "$__all" }
      }
    ]
  },
  "panels": [
    {
      "title": "Open circuit breakers",
      "type": "stat",
      "datasource": { "type": "prometheus", "uid": "prometheus" },
      "gridPos": { "h": 4, "w": 6, "x": 0, "y": 0 },
      "fieldConfig": {
        "defaults": {
          "thresholds": {
            "mode": "absolute",
            "steps": [
              { "color": "green", "value": null },
              { "color": "red", "value": 1 }
            ]
          }
        }
      },
      "options": {
        "colorMode": "value",
        "graphMode": "none",
        "reduceOptions": { "calcs": ["lastNotNull"] }
      },
      "targets": [{ "refId": "A", "expr": "fleet_engine_breaker_open_count" }]
    },
    {
      "title": "Dead-letter jobs",
      "type": "stat",
      "datasource": { "type": "prometheus", "uid": "prometheus" },
      "gridPos": { "h": 4, "w": 6, "x": 6, "y": 0 },
      "fieldConfig": {
        "defaults": {
          "thresholds": {
            "mode": "absolute",
            "steps": [
              { "color": "green", "value": null },
              { "color": "yellow", "value": 1 }
            ]
          }
        }
      },
      "options": {
        "colorMode": "value",
        "graphMode": "none",
        "reduceOptions": { "calcs": ["lastNotNull"] }
      },
      "targets": [
        {
          "refId": "A",
          "expr": "sum(fleet_jobs_by_stage{product=~\"$product\",stage=\"dead_letter\"})"
        }
      ]
    },
    {
      "title": "Stale factories",
      "type": "stat",
      "datasource": { "type": "prometheus", "uid": "prometheus" },
      "gridPos": { "h": 4, "w": 6, "x": 12, "y": 0 },
      "options": {
        "colorMode": "value",
        "graphMode": "none",
        "reduceOptions": { "calcs": ["lastNotNull"] }
      },
      "targets": [{ "refId": "A", "expr": "sum(fleet_factories_stale{product=~\"$product\"})" }]
    },
    {
      "title": "Active alerts",
      "type": "stat",
      "datasource": { "type": "prometheus", "uid": "prometheus" },
      "gridPos": { "h": 4, "w": 6, "x": 18, "y": 0 },
      "options": {
        "colorMode": "value",
        "graphMode": "none",
        "reduceOptions": { "calcs": ["lastNotNull"] }
      },
      "targets": [
        { "refId": "A", "expr": "count(fleet_alert_active{product=~\"$product\"}) or vector(0)" }
      ]
    },
    {
      "title": "Queue depth",
      "type": "timeseries",
      "datasource": { "type": "prometheus", "uid": "prometheus" },
      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 4 },
      "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 10 } } },
      "targets": [
        {
          "refId": "A",
          "expr": "fleet_queue_depth{product=~\"$product\"}",
          "legendFormat": "{{product}}"
        }
      ]
    },
    {
      "title": "Seat utilization %",
      "type": "timeseries",
      "datasource": { "type": "prometheus", "uid": "prometheus" },
      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 4 },
      "fieldConfig": {
        "defaults": { "unit": "percent", "custom": { "drawStyle": "line", "fillOpacity": 10 } }
      },
      "targets": [
        {
          "refId": "A",
          "expr": "fleet_utilization_pct{product=~\"$product\"}",
          "legendFormat": "{{product}}"
        }
      ]
    },
    {
      "title": "Budget: spent vs ceiling (USD)",
      "type": "timeseries",
      "datasource": { "type": "prometheus", "uid": "prometheus" },
      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 12 },
      "fieldConfig": {
        "defaults": { "unit": "currencyUSD", "custom": { "drawStyle": "line", "fillOpacity": 10 } }
      },
      "targets": [
        {
          "refId": "A",
          "expr": "fleet_budget_spent_usd{product=~\"$product\"}",
          "legendFormat": "{{product}} spent"
        },
        {
          "refId": "B",
          "expr": "fleet_budget_ceiling_usd{product=~\"$product\"}",
          "legendFormat": "{{product}} ceiling"
        },
        {
          "refId": "C",
          "expr": "fleet_budget_projected_usd{product=~\"$product\"}",
          "legendFormat": "{{product}} projected"
        }
      ]
    },
    {
      "title": "Reaper reclaims (rate/5m)",
      "type": "timeseries",
      "datasource": { "type": "prometheus", "uid": "prometheus" },
      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 12 },
      "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 10 } } },
      "targets": [
        {
          "refId": "A",
          "expr": "rate(fleet_reaper_expired_reclaimed_total[5m])",
          "legendFormat": "expired"
        },
        {
          "refId": "B",
          "expr": "rate(fleet_reaper_stale_reclaimed_total[5m])",
          "legendFormat": "stale"
        }
      ]
    },
    {
      "title": "Autoscale: products recommending scale-out",
      "type": "stat",
      "datasource": { "type": "prometheus", "uid": "prometheus" },
      "gridPos": { "h": 4, "w": 6, "x": 0, "y": 20 },
      "fieldConfig": {
        "defaults": {
          "thresholds": {
            "mode": "absolute",
            "steps": [
              { "color": "green", "value": null },
              { "color": "yellow", "value": 1 }
            ]
          }
        }
      },
      "options": {
        "colorMode": "value",
        "graphMode": "none",
        "reduceOptions": { "calcs": ["lastNotNull"] }
      },
      "targets": [
        {
          "refId": "A",
          "expr": "sum(fleet_autoscale_action{product=~\"$product\",action=\"scale_out\"}) or vector(0)"
        }
      ]
    },
    {
      "title": "Autoscale: recommended seat delta",
      "type": "timeseries",
      "description": "Recommended change in factory seats per product (positive = scale out, negative = scale in). Raw signal, pre-hysteresis.",
      "datasource": { "type": "prometheus", "uid": "prometheus" },
      "gridPos": { "h": 8, "w": 18, "x": 6, "y": 20 },
      "fieldConfig": {
        "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 10 } }
      },
      "targets": [
        {
          "refId": "A",
          "expr": "fleet_autoscale_delta{product=~\"$product\"}",
          "legendFormat": "{{product}} delta"
        },
        {
          "refId": "B",
          "expr": "fleet_autoscale_pressure{product=~\"$product\"}",
          "legendFormat": "{{product}} backlog"
        }
      ]
    }
  ]
}