26S02g

{
  "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": 100,
      "title": "1. Bucket ListObjectsV2 Bottleneck & Lock Contention Identification",
      "type": "row"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${DS_PROMETHEUS}"
      },
      "fieldConfig": {
        "defaults": {
          "custom": {
            "drawStyle": "line",
            "lineInterpolation": "smooth",
            "lineWidth": 2
          },
          "unit": "s"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 8,
        "x": 0,
        "y": 1
      },
      "id": 1,
      "options": {
        "legend": {
          "calcs": [
            "mean",
            "max",
            "lastNotNull"
          ],
          "displayMode": "table",
          "placement": "bottom"
        },
        "tooltip": {
          "mode": "multi"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${DS_PROMETHEUS}"
          },
          "expr": "topk(10, sum by (bucket) (rate(minio_api_requests_duration_total{namespace=~\"$namespace\", bucket=~\"$bucket\", name=~\"(?i).*(list).*\"}[5m])) / clamp_min(sum by (bucket) (rate(minio_api_requests_total{namespace=~\"$namespace\", bucket=~\"$bucket\", name=~\"(?i).*(list).*\"}[5m])), 0.001))",
          "legendFormat": "{{bucket}}",
          "refId": "A"
        }
      ],
      "title": "Top 10 Slowest Buckets: List Duration (s)",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${DS_PROMETHEUS}"
      },
      "fieldConfig": {
        "defaults": {
          "custom": {
            "align": "auto",
            "displayMode": "auto"
          },
          "mappings": [],
          "thresholds": {
            "mode": "absolute",
            "steps": [
              {
                "color": "green",
                "value": null
              },
              {
                "color": "orange",
                "value": 5
              },
              {
                "color": "red",
                "value": 30
              }
            ]
          }
        },
        "overrides": [
          {
            "matcher": {
              "id": "byName",
              "options": "Avg List Latency (s)"
            },
            "properties": [
              {
                "id": "unit",
                "value": "s"
              },
              {
                "id": "custom.displayMode",
                "value": "color-background"
              }
            ]
          },
          {
            "matcher": {
              "id": "byName",
              "options": "List Req/s"
            },
            "properties": [
              {
                "id": "unit",
                "value": "reqps"
              }
            ]
          },
          {
            "matcher": {
              "id": "byName",
              "options": "Total Time Spent (s/s)"
            },
            "properties": [
              {
                "id": "unit",
                "value": "s"
              }
            ]
          }
        ]
      },
      "gridPos": {
        "h": 8,
        "w": 8,
        "x": 8,
        "y": 1
      },
      "id": 10,
      "options": {
        "cellHeight": "sm",
        "footer": {
          "countRows": false,
          "fields": "",
          "reducer": [
            "sum"
          ],
          "show": false
        },
        "sortBy": [
          {
            "desc": true,
            "displayName": "Avg List Latency (s)"
          }
        ]
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${DS_PROMETHEUS}"
          },
          "expr": "topk(10, sum by (bucket) (rate(minio_api_requests_duration_total{namespace=~\"$namespace\", bucket=~\"$bucket\", name=~\"(?i).*(list).*\"}[5m])) / clamp_min(sum by (bucket) (rate(minio_api_requests_total{namespace=~\"$namespace\", bucket=~\"$bucket\", name=~\"(?i).*(list).*\"}[5m])), 0.001))",
          "format": "table",
          "instant": true,
          "legendFormat": "Avg List Latency (s)",
          "refId": "A"
        },
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${DS_PROMETHEUS}"
          },
          "expr": "sum by (bucket) (rate(minio_api_requests_total{namespace=~\"$namespace\", bucket=~\"$bucket\", name=~\"(?i).*(list).*\"}[5m]))",
          "format": "table",
          "instant": true,
          "legendFormat": "List Req/s",
          "refId": "B"
        },
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${DS_PROMETHEUS}"
          },
          "expr": "sum by (bucket) (rate(minio_api_requests_duration_total{namespace=~\"$namespace\", bucket=~\"$bucket\", name=~\"(?i).*(list).*\"}[5m]))",
          "format": "table",
          "instant": true,
          "legendFormat": "Total Time Spent (s/s)",
          "refId": "C"
        }
      ],
      "transformations": [
        {
          "id": "joinByField",
          "options": {
            "byField": "bucket",
            "mode": "outer"
          }
        },
        {
          "id": "organize",
          "options": {
            "excludeByName": {
              "Time": true,
              "Time 1": true,
              "Time 2": true,
              "Time 3": true
            },
            "indexByName": {
              "bucket": 0,
              "Value #A": 1,
              "Value #B": 2,
              "Value #C": 3
            },
            "renameByName": {
              "Value #A": "Avg List Latency (s)",
              "Value #B": "List Req/s",
              "Value #C": "Total Time Spent (s/s)"
            }
          }
        }
      ],
      "title": "Slowest Buckets Ranking Table (ListObjectsV2)",
      "type": "table"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${DS_PROMETHEUS}"
      },
      "fieldConfig": {
        "defaults": {
          "custom": {
            "drawStyle": "line",
            "lineInterpolation": "smooth",
            "lineWidth": 2
          },
          "unit": "s"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 8,
        "x": 16,
        "y": 1
      },
      "id": 2,
      "options": {
        "legend": {
          "calcs": [
            "mean",
            "max"
          ],
          "displayMode": "table",
          "placement": "bottom"
        },
        "tooltip": {
          "mode": "multi"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${DS_PROMETHEUS}"
          },
          "expr": "topk(10, sum by (bucket, name) (rate(minio_api_requests_duration_total{namespace=~\"$namespace\", bucket=~\"$bucket\", name=~\"(?i).*(put|multipart|delete|complete).*\"}[5m])) / clamp_min(sum by (bucket, name) (rate(minio_api_requests_total{namespace=~\"$namespace\", bucket=~\"$bucket\", name=~\"(?i).*(put|multipart|delete|complete).*\"}[5m])), 0.001))",
          "legendFormat": "{{bucket}} - {{name}}",
          "refId": "A"
        }
      ],
      "title": "Lock-Holding APIs Duration (Put/CompleteMPU/Delete)",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${DS_PROMETHEUS}"
      },
      "fieldConfig": {
        "defaults": {
          "custom": {
            "drawStyle": "line",
            "lineInterpolation": "smooth",
            "lineWidth": 2
          },
          "unit": "s"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 0,
        "y": 9
      },
      "id": 3,
      "options": {
        "legend": {
          "calcs": [
            "mean",
            "max"
          ],
          "displayMode": "table",
          "placement": "bottom"
        },
        "tooltip": {
          "mode": "multi"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${DS_PROMETHEUS}"
          },
          "expr": "minio_locks_dist_avg_latency",
          "legendFormat": "Cluster Avg Lock Latency",
          "refId": "A"
        },
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${DS_PROMETHEUS}"
          },
          "expr": "sum(minio_locks_waiting_total{namespace=~\"$namespace\"}) / clamp_min(count(count by (instance) (minio_api_requests_total{namespace=~\"$namespace\"})), 1)",
          "legendFormat": "Avg Waiting Locks / Pod",
          "refId": "B"
        }
      ],
      "title": "Cluster Lock Latency & Waiting Queue",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${DS_PROMETHEUS}"
      },
      "fieldConfig": {
        "defaults": {
          "custom": {
            "drawStyle": "line",
            "lineInterpolation": "linear",
            "lineWidth": 2
          },
          "unit": "reqps"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 12,
        "x": 12,
        "y": 9
      },
      "id": 4,
      "options": {
        "legend": {
          "calcs": [
            "mean",
            "max"
          ],
          "displayMode": "table",
          "placement": "bottom"
        },
        "tooltip": {
          "mode": "multi"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${DS_PROMETHEUS}"
          },
          "expr": "topk(10, sum by (bucket) (rate(minio_api_requests_total{namespace=~\"$namespace\", bucket=~\"$bucket\", name=~\"(?i).*(list).*\"}[5m])))",
          "legendFormat": "Cluster Total req/s: {{bucket}}",
          "refId": "A"
        },
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${DS_PROMETHEUS}"
          },
          "expr": "topk(10, sum by (bucket) (rate(minio_api_requests_total{namespace=~\"$namespace\", bucket=~\"$bucket\", name=~\"(?i).*(list).*\"}[5m])) / clamp_min(count(count by (instance) (minio_api_requests_total{namespace=~\"$namespace\"})), 1))",
          "legendFormat": "Per-Pod Avg req/s: {{bucket}}",
          "refId": "B"
        }
      ],
      "title": "List Request Rate (Total Cluster vs Per-Pod Avg)",
      "type": "timeseries"
    },
    {
      "collapsed": false,
      "gridPos": {
        "h": 1,
        "w": 24,
        "x": 0,
        "y": 17
      },
      "id": 200,
      "title": "2. Internal Goroutine Amplification & Disk Metadata Contention",
      "type": "row"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${DS_PROMETHEUS}"
      },
      "fieldConfig": {
        "defaults": {
          "custom": {
            "drawStyle": "line",
            "lineInterpolation": "linear",
            "lineWidth": 2
          },
          "unit": "short"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 8,
        "x": 0,
        "y": 18
      },
      "id": 5,
      "options": {
        "legend": {
          "calcs": [
            "max",
            "lastNotNull"
          ],
          "displayMode": "table",
          "placement": "bottom"
        },
        "tooltip": {
          "mode": "multi"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${DS_PROMETHEUS}"
          },
          "expr": "topk(5, go_goroutines{namespace=~\"$namespace\"} or minio_process_goroutines{namespace=~\"$namespace\"})",
          "legendFormat": "Pod Goroutines: {{instance}}",
          "refId": "A"
        },
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${DS_PROMETHEUS}"
          },
          "expr": "avg(go_goroutines{namespace=~\"$namespace\"} or minio_process_goroutines{namespace=~\"$namespace\"})",
          "legendFormat": "Cluster Avg Goroutines / Pod",
          "refId": "B"
        }
      ],
      "title": "Pod Goroutine Spike (Internal Parallel Scan Amplification)",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${DS_PROMETHEUS}"
      },
      "fieldConfig": {
        "defaults": {
          "custom": {
            "drawStyle": "line",
            "lineInterpolation": "linear",
            "lineWidth": 2
          },
          "unit": "iops"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 8,
        "x": 8,
        "y": 18
      },
      "id": 6,
      "options": {
        "legend": {
          "calcs": [
            "mean",
            "max"
          ],
          "displayMode": "table",
          "placement": "bottom"
        },
        "tooltip": {
          "mode": "multi"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${DS_PROMETHEUS}"
          },
          "expr": "topk(10, rate(node_disk_reads_completed_total{namespace=~\"$namespace\"}[5m]) or rate(minio_node_drive_reads_total{namespace=~\"$namespace\"}[5m]))",
          "legendFormat": "Read IOPS: {{instance}} - {{device}}",
          "refId": "A"
        },
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${DS_PROMETHEUS}"
          },
          "expr": "topk(10, rate(node_disk_writes_completed_total{namespace=~\"$namespace\"}[5m]) or rate(minio_node_drive_writes_total{namespace=~\"$namespace\"}[5m]))",
          "legendFormat": "Write IOPS: {{instance}} - {{device}}",
          "refId": "B"
        }
      ],
      "title": "Drive IOPS (Random Small Read Spike by List Scan)",
      "type": "timeseries"
    },
    {
      "datasource": {
        "type": "prometheus",
        "uid": "${DS_PROMETHEUS}"
      },
      "fieldConfig": {
        "defaults": {
          "custom": {
            "drawStyle": "line",
            "lineInterpolation": "linear",
            "lineWidth": 2
          },
          "unit": "s"
        },
        "overrides": []
      },
      "gridPos": {
        "h": 8,
        "w": 8,
        "x": 16,
        "y": 18
      },
      "id": 7,
      "options": {
        "legend": {
          "calcs": [
            "mean",
            "max"
          ],
          "displayMode": "table",
          "placement": "bottom"
        },
        "tooltip": {
          "mode": "multi"
        }
      },
      "targets": [
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${DS_PROMETHEUS}"
          },
          "expr": "topk(10, rate(minio_node_drive_total_waiting_time_seconds{namespace=~\"$namespace\"}[5m]) / clamp_min(rate(minio_node_drive_total_waiting{namespace=~\"$namespace\"}[5m]), 0.001))",
          "legendFormat": "Drive Wait Time: {{instance}} - {{drive}}",
          "refId": "A"
        },
        {
          "datasource": {
            "type": "prometheus",
            "uid": "${DS_PROMETHEUS}"
          },
          "expr": "topk(10, rate(node_disk_io_time_seconds_total{namespace=~\"$namespace\"}[5m]))",
          "legendFormat": "Disk Saturation: {{instance}} - {{device}}",
          "refId": "B"
        }
      ],
      "title": "Drive Waiting Time & Saturation (Delaying Commit fsync)",
      "type": "timeseries"
    }
  ],
  "refresh": "30s",
  "schemaVersion": 38,
  "style": "dark",
  "tags": [
    "minio",
    "aistor",
    "v3",
    "duration_total",
    "locks"
  ],
  "templating": {
    "list": [
      {
        "current": {},
        "hide": 0,
        "label": "Data Source",
        "name": "DS_PROMETHEUS",
        "options": [],
        "query": "prometheus",
        "refresh": 1,
        "regex": "",
        "type": "datasource"
      },
      {
        "allValue": ".*",
        "current": {
          "selected": true,
          "text": "All",
          "value": "$__all"
        },
        "datasource": {
          "type": "prometheus",
          "uid": "${DS_PROMETHEUS}"
        },
        "definition": "label_values(minio_api_requests_total, namespace)",
        "hide": 0,
        "includeAll": true,
        "label": "Namespace",
        "multi": false,
        "name": "namespace",
        "options": [],
        "query": {
          "query": "label_values(minio_api_requests_total, namespace)",
          "refId": "Prometheus-Namespace-Variable"
        },
        "refresh": 2,
        "regex": "",
        "type": "query"
      },
      {
        "allValue": ".*",
        "current": {
          "selected": true,
          "text": "All",
          "value": "$__all"
        },
        "datasource": {
          "type": "prometheus",
          "uid": "${DS_PROMETHEUS}"
        },
        "definition": "label_values(minio_api_requests_total, bucket)",
        "hide": 0,
        "includeAll": true,
        "label": "Bucket",
        "multi": true,
        "name": "bucket",
        "options": [],
        "query": {
          "query": "label_values(minio_api_requests_total, bucket)",
          "refId": "Prometheus-Bucket-Variable"
        },
        "refresh": 2,
        "regex": "",
        "type": "query"
      }
    ]
  },
  "time": {
    "from": "now-24h",
    "to": "now"
  },
  "timepicker": {
    "refresh_intervals": [
      "5s",
      "10s",
      "30s",
      "1m",
      "5m"
    ]
  },
  "timezone": "browser",
  "title": "MinIO AIStor v3 - Slowest Buckets & Lock Diagnostic (Label: name)",
  "version": 7
}