26Y28c8
{
"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": 800,
"title": "📊 1. SELECTED CLUSTER PHYSICAL DRIVE VITAL HEALTH INDICATORS (2,560 DRIVES)",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "orange",
"value": 20
},
{
"color": "red",
"value": 50
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 12,
"x": 0,
"y": 1
},
"id": 801,
"options": {
"colorMode": "value",
"graphMode": "none",
"justifyMode": "center",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"max"
],
"fields": "",
"values": false
},
"textMode": "value"
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "max(minio_node_drive_queued_operations{cluster=~\"${cluster:regex}\", namespace=~\"${namespace:regex}\"} or minio_system_drive_queued_operations{cluster=~\"${cluster:regex}\", namespace=~\"${namespace:regex}\"})",
"legendFormat": "Max Queue Depth",
"refId": "A"
}
],
"title": "Worst Real-time Disk Queue Depth Across All 2,560 Drives",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 1
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 12,
"x": 12,
"y": 1
},
"id": 802,
"options": {
"colorMode": "value",
"graphMode": "none",
"justifyMode": "center",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"sum"
],
"fields": "",
"values": false
},
"textMode": "value"
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum(increase(minio_node_drive_errors_total{cluster=~\"${cluster:regex}\", namespace=~\"${namespace:regex}\"}[$interval]) or increase(minio_system_drive_io_errors_total{cluster=~\"${cluster:regex}\", namespace=~\"${namespace:regex}\"}[$interval]))",
"legendFormat": "Total Drive Errors",
"refId": "A"
}
],
"title": "Aggregated Drive I/O Errors Count",
"type": "stat"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 5
},
"id": 900,
"title": "📈 2. DRIVE LATENCY & IOPS PERFORMANCE PROFILE (TOP N BOTTLENECK DRIVES)",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisPlacement": "auto",
"drawStyle": "line",
"fillOpacity": 5,
"lineInterpolation": "smooth",
"lineWidth": 2,
"showPoints": "none"
},
"mappings": [],
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 6
},
"id": 901,
"options": {
"legend": {
"calcs": [
"mean",
"max"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "topk($topn, sum by (server, drive) (rate(minio_node_drive_latency_seconds_sum{cluster=~\"${cluster:regex}\", namespace=~\"${namespace:regex}\"}[$interval])) / sum by (server, drive) (rate(minio_node_drive_latency_seconds_count{cluster=~\"${cluster:regex}\", namespace=~\"${namespace:regex}\"}[$interval])))",
"legendFormat": "{{server}} - {{drive}} Latency",
"refId": "A"
}
],
"title": "Average Physical Drive Response Latency (Slowest Drives - Top N)",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisPlacement": "auto",
"drawStyle": "line",
"fillOpacity": 10,
"lineInterpolation": "smooth",
"lineWidth": 2,
"showPoints": "none"
},
"mappings": [],
"unit": "iops"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 6
},
"id": 902,
"options": {
"legend": {
"calcs": [
"max",
"mean"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "topk($topn, sum by (server, type) (rate(minio_node_drive_io_operations_total{cluster=~\"${cluster:regex}\", namespace=~\"${namespace:regex}\"}[$interval])))",
"legendFormat": "{{server}} - IOPS: {{type}}",
"refId": "A"
}
],
"title": "Drive IOPS Performance Profile by Operation Type (Top N Hotspot Nodes)",
"type": "timeseries"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 14
},
"id": 1000,
"title": "🚨 3. REAL-TIME DISK QUEUE DEPTH & SATURATION BREAKDOWN (TOP N HIGH QUEUE DRIVES)",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisPlacement": "auto",
"drawStyle": "line",
"fillOpacity": 5,
"lineInterpolation": "linear",
"lineWidth": 2,
"showPoints": "none"
},
"mappings": []
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 24,
"x": 0,
"y": 15
},
"id": 1001,
"options": {
"legend": {
"calcs": [
"max",
"lastNotNull"
],
"displayMode": "table",
"placement": "right",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "topk($topn, minio_node_drive_queued_operations{cluster=~\"${cluster:regex}\", namespace=~\"${namespace:regex}\"} or minio_system_drive_queued_operations{cluster=~\"${cluster:regex}\", namespace=~\"${namespace:regex}\"})",
"legendFormat": "{{server}} - {{drive}} Queue Depth",
"refId": "A"
}
],
"title": "Granular Disk Queue Depth Saturation Profile per Device Drive (Top N Saturated Drives)",
"type": "timeseries"
}
],
"refresh": "10s",
"schemaVersion": 38,
"style": "dark",
"tags": [
"AIStor",
"Metrics-V3",
"Storage-Hardware",
"Multi-Cluster-IO"
],
"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 Drives/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 - 8. Storage Hardware (Multi-Cluster v3 - Fixed)",
"uid": "aistor-operations-8-fixed",
"version": 1
}
engineer