26Y28c12

{
  "annotations": {
    "list": [
      {
        "builtIn": 1,
        "datasource": {
          "type": "datasource",
          "uid": "grafana"
        },
        "enable": true,
        "hide": true,
        "name": "Annotations & Alerts",
        "type": "dashboard"
      }
    ]
  },
  "editable": true,
  "fiscalYearStartMonth": 0,
  "graphTooltip": 1,
  "id": null,
  "links": [],
  "liveNow": false,
  "panels": [
    {
      "collapsed": false,
      "gridPos": {
        "h": 1,
        "w": 24,
        "x": 0,
        "y": 0
      },
      "id": 1200,
      "title": "🧠 1. GO RUNTIME CONCURRENCY & GOROUTINE CORE VITALS",
      "type": "row"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${datasource}"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "thresholds"
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              },
              {
                "color": "orange",
                "value": 50000
              },
              {
                "color": "red",
                "value": 120000
              }
            ]
          },
          "unit": "short"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 4,
        "w": 24,
        "x": 0,
        "y": 1
      },
      "id": 1201,
      "options": {
        "colorMode": "value",
        "graphMode": "none",
        "justifyMode": "center",
        "orientation": "auto",
        "reduceOptions": {
          "calcs": [
            "max"
          ],
          "fields": "",
          "values": false
        },
        "textMode": "value"
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${datasource}"
          },
          "editorMode": "code",
          "expr": "max(minio_system_process_go_routine_total{cluster=~\"${cluster:regex}\", namespace=~\"${namespace:regex}\"} or minio_node_sys_goroutines{cluster=~\"${cluster:regex}\", namespace=~\"${namespace:regex}\"})",
          "legendFormat": "Max Goroutines",
          "refId": "A"
        }
      ],
      "title": "Worst Peak Go Goroutines Count Across All Nodes",
      "type": "stat"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${datasource}"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "custom": {
            "axisBorderShow": false,
            "axisPlacement": "auto",
            "drawStyle": "line",
            "fillOpacity": 5,
            "lineInterpolation": "smooth",
            "lineWidth": 2,
            "showPoints": "none"
          },
          "mappings": [],
          "unit": "short"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 7,
        "w": 24,
        "x": 0,
        "y": 5
      },
      "id": 1202,
      "options": {
        "legend": {
          "calcs": [
            "max",
            "mean"
          ],
          "displayMode": "table",
          "placement": "right",
          "showLegend": true
        },
        "tooltip": {
          "mode": "multi",
          "sort": "desc"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${datasource}"
          },
          "editorMode": "code",
          "expr": "topk($topn, minio_system_process_go_routine_total{cluster=~\"${cluster:regex}\", namespace=~\"${namespace:regex}\"} or minio_node_sys_goroutines{cluster=~\"${cluster:regex}\", namespace=~\"${namespace:regex}\"})",
          "legendFormat": "Goroutines: {{server}}",
          "refId": "A"
        }
      ],
      "title": "Go Goroutines Active Count Distribution Timeline (Top N Nodes)",
      "type": "timeseries"
    },
    {
      "collapsed": false,
      "gridPos": {
        "h": 1,
        "w": 24,
        "x": 0,
        "y": 12
      },
      "id": 1300,
      "title": "🔍 2. WORKLOAD CORRELATION: METADATA (LIST) VS DATA (PUT/GET)",
      "type": "row"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${datasource}"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "custom": {
            "axisBorderShow": false,
            "axisPlacement": "auto",
            "drawStyle": "line",
            "fillOpacity": 10,
            "lineInterpolation": "smooth",
            "lineWidth": 2,
            "showPoints": "none"
          },
          "mappings": [],
          "unit": "reqps"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 0,
        "y": 13
      },
      "id": 1301,
      "options": {
        "legend": {
          "calcs": [
            "max",
            "mean"
          ],
          "displayMode": "table",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "multi",
          "sort": "desc"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${datasource}"
          },
          "editorMode": "code",
          "expr": "sum by (name) (rate(minio_api_requests_total{cluster=~\"${cluster:regex}\", namespace=~\"${namespace:regex}\"}[$interval]))",
          "legendFormat": "{{name}}",
          "refId": "A"
        }
      ],
      "title": "S3 API Operation Request Rate (TPS Breakdown by API Action Verb)",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${datasource}"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "custom": {
            "axisBorderShow": false,
            "axisPlacement": "auto",
            "drawStyle": "line",
            "fillOpacity": 5,
            "lineInterpolation": "smooth",
            "lineWidth": 2,
            "showPoints": "none"
          },
          "mappings": [],
          "unit": "s"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 12,
        "y": 13
      },
      "id": 1302,
      "options": {
        "legend": {
          "calcs": [
            "max",
            "mean"
          ],
          "displayMode": "table",
          "placement": "bottom",
          "showLegend": true
        },
        "tooltip": {
          "mode": "multi",
          "sort": "desc"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${datasource}"
          },
          "editorMode": "code",
          "expr": "histogram_quantile(0.99, sum by (le, name) (rate(minio_api_requests_ttfb_seconds_distribution{cluster=~\"${cluster:regex}\", namespace=~\"${namespace:regex}\"}[$interval])))",
          "legendFormat": "p99 TTFB: {{name}}",
          "refId": "A"
        }
      ],
      "title": "Time to First Byte (TTFB) Quantile Latency (p99 by Action Verb)",
      "type": "timeseries"
    },
    {
      "collapsed": false,
      "gridPos": {
        "h": 1,
        "w": 24,
        "x": 0,
        "y": 21
      },
      "id": 1400,
      "title": "🚦 3. BACKGROUND CRUISE LOAD: INTERNALS VS GOROUTINE SPIKES (TOP N NODES)",
      "type": "row"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${datasource}"
      },
      "fieldConfig": {
        "defaults": {
          "color": {
            "mode": "palette-classic"
          },
          "custom": {
            "axisBorderShow": false,
            "axisPlacement": "auto",
            "drawStyle": "line",
            "fillOpacity": 5,
            "lineInterpolation": "smooth",
            "lineWidth": 2,
            "showPoints": "none"
          },
          "mappings": [],
          "unit": "short"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 7,
        "w": 24,
        "x": 0,
        "y": 22
      },
      "id": 1401,
      "options": {
        "legend": {
          "calcs": [
            "max"
          ],
          "displayMode": "table",
          "placement": "right",
          "showLegend": true
        },
        "tooltip": {
          "mode": "multi",
          "sort": "desc"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${datasource}"
          },
          "editorMode": "code",
          "expr": "topk($topn, minio_cluster_scanner_active_workers{cluster=~\"${cluster:regex}\", namespace=~\"${namespace:regex}\"} or minio_scanner_active_workers{cluster=~\"${cluster:regex}\", namespace=~\"${namespace:regex}\"})",
          "legendFormat": "Scanner Workers: {{server}}",
          "refId": "A"
        }
      ],
      "title": "Background Scanner Active Workers Timeline per Node Server (Top N)",
      "type": "timeseries"
    }
  ],
  "refresh": "10s",
  "schemaVersion": 38,
  "style": "dark",
  "tags": [
    "AIStor",
    "Metrics-V3",
    "Diagnosis-Go",
    "Goroutine-Stall",
    "Multi-Cluster-Core"
  ],
  "templating": {
    "list": [
      {
        "current": {},
        "hide": 0,
        "includeAll": false,
        "label": "Data Source",
        "name": "datasource",
        "options": [],
        "query": "prometheus",
        "refresh": 1,
        "regex": "",
        "skipUrlSync": false,
        "type": "datasource"
      },
      {
        "current": {},
        "datasource": {
          "type": "prometheus",
          "uid": "${datasource}"
        },
        "definition": "label_values(cluster)",
        "hide": 0,
        "includeAll": true,
        "multi": true,
        "allValue": ".*",
        "label": "AIStor Cluster",
        "name": "cluster",
        "options": [],
        "query": "label_values(cluster)",
        "refresh": 1,
        "regex": "",
        "skipUrlSync": false,
        "sort": 1,
        "type": "query"
      },
      {
        "current": {},
        "datasource": {
          "type": "prometheus",
          "uid": "${datasource}"
        },
        "definition": "label_values({cluster=~\"${cluster:regex}\"}, namespace)",
        "hide": 0,
        "includeAll": true,
        "multi": true,
        "allValue": ".*",
        "label": "Namespace",
        "name": "namespace",
        "options": [],
        "query": "label_values({cluster=~\"${cluster:regex}\"}, namespace)",
        "refresh": 1,
        "regex": "",
        "skipUrlSync": false,
        "sort": 1,
        "type": "query"
      },
      {
        "name": "topn",
        "type": "custom",
        "query": "10,15,20,30",
        "label": "Top N Nodes",
        "hide": 0,
        "current": {
          "text": "15",
          "value": "15"
        },
        "options": [
          {
            "text": "10",
            "value": "10",
            "selected": false
          },
          {
            "text": "15",
            "value": "15",
            "selected": true
          },
          {
            "text": "20",
            "value": "20",
            "selected": false
          },
          {
            "text": "30",
            "value": "30",
            "selected": false
          }
        ]
      },
      {
        "current": {
          "selected": true,
          "text": "2m",
          "value": "2m"
        },
        "hide": 0,
        "label": "Interval",
        "name": "interval",
        "options": [
          {
            "selected": false,
            "text": "30s",
            "value": "30s"
          },
          {
            "selected": false,
            "text": "1m",
            "value": "1m"
          },
          {
            "selected": true,
            "text": "2m",
            "value": "2m"
          },
          {
            "selected": false,
            "text": "5m",
            "value": "5m"
          },
          {
            "selected": false,
            "text": "10m",
            "value": "10m"
          }
        ],
        "query": "30s,1m,2m,5m,10m",
        "type": "interval"
      }
    ]
  },
  "time": {
    "from": "now-1h",
    "to": "now"
  },
  "timepicker": {
    "refresh_intervals": [
      "5s",
      "10s",
      "30s"
    ]
  },
  "timezone": "browser",
  "title": "AIStor Operations - 12. Diagnosis & Goroutine Stalls (Multi-Cluster v3 - Fixed)",
  "uid": "aistor-operations-12-fixed",
  "version": 1
}