26Y27g4
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": "-- 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": "Executive Summary - Goroutines & TTFB KPI",
"type": "row"
},
{
"id": 1,
"title": "Total Cluster Goroutines",
"type": "stat",
"gridPos": {
"h": 4,
"w": 4,
"x": 0,
"y": 1
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 50000
},
{
"color": "red",
"value": 100000
}
]
},
"unit": "short"
}
},
"options": {
"colorMode": "value",
"graphMode": "area",
"reduceOptions": {
"calcs": [
"lastNotNull"
]
}
},
"targets": [
{
"datasource": "$datasource",
"editorMode": "code",
"expr": "sum(minio_system_process_goroutines{cluster=~\"$cluster\"} or minio_node_process_goroutines{cluster=~\"$cluster\"})",
"legendFormat": "Total Goroutines",
"refId": "A"
}
]
},
{
"id": 2,
"title": "Max Node Goroutines",
"type": "stat",
"gridPos": {
"h": 4,
"w": 5,
"x": 4,
"y": 1
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 2000
},
{
"color": "red",
"value": 5000
}
]
},
"unit": "short"
}
},
"options": {
"colorMode": "value",
"graphMode": "area",
"reduceOptions": {
"calcs": [
"lastNotNull"
]
}
},
"targets": [
{
"datasource": "$datasource",
"expr": "max(minio_system_process_goroutines{cluster=~\"$cluster\"} or minio_node_process_goroutines{cluster=~\"$cluster\"})",
"legendFormat": "Max Node Goroutines",
"refId": "A"
}
]
},
{
"id": 3,
"title": "Cluster TTFB (p90)",
"type": "stat",
"gridPos": {
"h": 4,
"w": 5,
"x": 9,
"y": 1
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 0.1
},
{
"color": "red",
"value": 0.3
}
]
},
"unit": "s"
}
},
"options": {
"colorMode": "value",
"graphMode": "area",
"reduceOptions": {
"calcs": [
"lastNotNull"
]
}
},
"targets": [
{
"datasource": "$datasource",
"expr": "histogram_quantile(0.90, sum(rate(minio_s3_requests_ttfb_seconds_bucket{cluster=~\"$cluster\"}[$interval])) by (le))",
"legendFormat": "p90 TTFB",
"refId": "A"
}
]
},
{
"id": 4,
"title": "Cluster TTFB (p99)",
"type": "stat",
"gridPos": {
"h": 4,
"w": 5,
"x": 14,
"y": 1
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 0.2
},
{
"color": "red",
"value": 0.5
}
]
},
"unit": "s"
}
},
"options": {
"colorMode": "value",
"graphMode": "area",
"reduceOptions": {
"calcs": [
"lastNotNull"
]
}
},
"targets": [
{
"datasource": "$datasource",
"expr": "histogram_quantile(0.99, sum(rate(minio_s3_requests_ttfb_seconds_bucket{cluster=~\"$cluster\"}[$interval])) by (le))",
"legendFormat": "p99 TTFB",
"refId": "A"
}
]
},
{
"id": 5,
"title": "Active S3 Requests",
"type": "stat",
"gridPos": {
"h": 4,
"w": 5,
"x": 19,
"y": 1
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "blue",
"value": null
}
]
},
"unit": "short"
}
},
"options": {
"colorMode": "value",
"graphMode": "area",
"reduceOptions": {
"calcs": [
"lastNotNull"
]
}
},
"targets": [
{
"datasource": "$datasource",
"expr": "sum(minio_s3_requests_active_total{cluster=~\"$cluster\"})",
"legendFormat": "Active Requests",
"refId": "A"
}
]
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 5
},
"id": 200,
"title": "Goroutine Analytics & Node Imbalance Distribution",
"type": "row"
},
{
"id": 6,
"title": "Goroutine Distribution Heatmap across Nodes",
"type": "heatmap",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 6
},
"options": {
"calculate": false,
"color": {
"mode": "scheme",
"scheme": "Spectral",
"exponent": 0.5,
"fill": "dark-orange"
},
"yAxis": {
"axisPlacement": "left"
}
},
"targets": [
{
"datasource": "$datasource",
"expr": "(minio_system_process_goroutines{cluster=~\"$cluster\", instance=~\"$node\"} or minio_node_process_goroutines{cluster=~\"$cluster\", instance=~\"$node\"})",
"format": "heatmap",
"legendFormat": "{{instance}}",
"refId": "A"
}
]
},
{
"id": 7,
"title": "Top 10 Goroutine Outlier Nodes",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 6
},
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"lineInterpolation": "smooth",
"lineWidth": 2
},
"unit": "short"
}
},
"options": {
"legend": {
"displayMode": "table",
"placement": "bottom",
"calcs": [
"mean",
"max"
]
}
},
"targets": [
{
"datasource": "$datasource",
"expr": "topk(10, (minio_system_process_goroutines{cluster=~\"$cluster\", instance=~\"$node\"} or minio_node_process_goroutines{cluster=~\"$cluster\", instance=~\"$node\"}))",
"legendFormat": "{{instance}}",
"refId": "A"
}
]
},
{
"id": 8,
"title": "Total Goroutines vs Active Requests by Verb",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 24,
"x": 0,
"y": 14
},
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"lineWidth": 2
},
"unit": "short"
}
},
"options": {
"legend": {
"displayMode": "table",
"placement": "right",
"calcs": [
"lastNotNull",
"max"
]
}
},
"targets": [
{
"datasource": "$datasource",
"expr": "sum(minio_system_process_goroutines{cluster=~\"$cluster\"} or minio_node_process_goroutines{cluster=~\"$cluster\"})",
"legendFormat": "Total Goroutines (Left Y)",
"refId": "A"
},
{
"datasource": "$datasource",
"expr": "sum(minio_s3_requests_active_total{cluster=~\"$cluster\"}) by (api)",
"legendFormat": "Active Requests - {{api}}",
"refId": "B"
}
]
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 22
},
"id": 300,
"title": "TTFB (Time To First Byte) Multi-Dimensional Performance Analysis",
"type": "row"
},
{
"id": 9,
"title": "Cluster-wide TTFB Quantiles (p50, p90, p99, p99.9)",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 23
},
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"lineWidth": 2
},
"unit": "s"
}
},
"options": {
"legend": {
"displayMode": "table",
"placement": "bottom",
"calcs": [
"mean",
"max"
]
}
},
"targets": [
{
"datasource": "$datasource",
"expr": "histogram_quantile(0.50, sum(rate(minio_s3_requests_ttfb_seconds_bucket{cluster=~\"$cluster\", instance=~\"$node\", bucket=~\"$bucket\"}[$interval])) by (le))",
"legendFormat": "p50 TTFB",
"refId": "A"
},
{
"datasource": "$datasource",
"expr": "histogram_quantile(0.90, sum(rate(minio_s3_requests_ttfb_seconds_bucket{cluster=~\"$cluster\", instance=~\"$node\", bucket=~\"$bucket\"}[$interval])) by (le))",
"legendFormat": "p90 TTFB",
"refId": "B"
},
{
"datasource": "$datasource",
"expr": "histogram_quantile(0.99, sum(rate(minio_s3_requests_ttfb_seconds_bucket{cluster=~\"$cluster\", instance=~\"$node\", bucket=~\"$bucket\"}[$interval])) by (le))",
"legendFormat": "p99 TTFB",
"refId": "C"
},
{
"datasource": "$datasource",
"expr": "histogram_quantile(0.999, sum(rate(minio_s3_requests_ttfb_seconds_bucket{cluster=~\"$cluster\", instance=~\"$node\", bucket=~\"$bucket\"}[$interval])) by (le))",
"legendFormat": "p99.9 TTFB",
"refId": "D"
}
]
},
{
"id": 10,
"title": "Top 10 Slowest Buckets by p99 TTFB",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 23
},
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"lineWidth": 2
},
"unit": "s"
}
},
"options": {
"legend": {
"displayMode": "table",
"placement": "bottom",
"calcs": [
"mean",
"max"
]
}
},
"targets": [
{
"datasource": "$datasource",
"expr": "topk(10, histogram_quantile(0.99, sum(rate(minio_s3_requests_ttfb_seconds_bucket{cluster=~\"$cluster\"}[$interval])) by (le, bucket)))",
"legendFormat": "Bucket: {{bucket}}",
"refId": "A"
}
]
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 31
},
"id": 400,
"title": "Goroutine Spike Root Cause & Impact Analysis",
"type": "row"
},
{
"id": 11,
"title": "S3 API Verb Throughput (RPS) by API",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 32
},
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"stacking": {
"group": "A",
"mode": "normal"
}
},
"unit": "reqps"
}
},
"options": {
"legend": {
"displayMode": "table",
"placement": "bottom",
"calcs": [
"mean",
"max"
]
}
},
"targets": [
{
"datasource": "$datasource",
"expr": "sum(rate(minio_s3_requests_total{cluster=~\"$cluster\", instance=~\"$node\", bucket=~\"$bucket\"}[$interval])) by (api)",
"legendFormat": "{{api}}",
"refId": "A"
}
]
},
{
"id": 12,
"title": "API 503 SlowDown Errors & Distributed Lock Waiters",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 32
},
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"lineWidth": 2
},
"unit": "short"
}
},
"options": {
"legend": {
"displayMode": "table",
"placement": "bottom",
"calcs": [
"max"
]
}
},
"targets": [
{
"datasource": "$datasource",
"expr": "sum(rate(minio_s3_requests_errors_total{code=\"503\", cluster=~\"$cluster\", instance=~\"$node\"}[$interval])) by (instance)",
"legendFormat": "503 SlowDown - {{instance}}",
"refId": "A"
},
{
"datasource": "$datasource",
"expr": "sum(minio_locks_waiting_total{cluster=~\"$cluster\", instance=~\"$node\"}) by (instance)",
"legendFormat": "Lock Waiters - {{instance}}",
"refId": "B"
}
]
}
],
"refresh": "30s",
"schemaVersion": 38,
"style": "dark",
"tags": [
"minio",
"aistor",
"goroutine",
"ttfb",
"performance"
],
"templating": {
"list": [
{
"current": {
"selected": true,
"text": "Prometheus",
"value": "Prometheus"
},
"hide": 0,
"includeAll": false,
"label": "Data Source",
"name": "datasource",
"options": [],
"query": "prometheus",
"refresh": 1,
"type": "datasource"
},
{
"allValue": ".*",
"current": {
"selected": true,
"text": "All",
"value": "$__all"
},
"datasource": "$datasource",
"definition": "label_values(cluster) or label_values(minio_cluster) or label_values(job)",
"hide": 0,
"includeAll": true,
"label": "Cluster",
"multi": false,
"name": "cluster",
"options": [],
"query": "label_values(cluster) or label_values(minio_cluster) or label_values(job)",
"refresh": 2,
"regex": "",
"sort": 1,
"type": "query"
},
{
"allValue": ".*",
"current": {
"selected": true,
"text": "All",
"value": "$__all"
},
"datasource": "$datasource",
"definition": "label_values(bucket)",
"hide": 0,
"includeAll": true,
"label": "Bucket",
"multi": false,
"name": "bucket",
"options": [],
"query": "label_values(bucket)",
"refresh": 2,
"regex": "",
"sort": 1,
"type": "query"
},
{
"allValue": ".*",
"current": {
"selected": true,
"text": "All",
"value": "$__all"
},
"datasource": "$datasource",
"definition": "label_values(instance)",
"hide": 0,
"includeAll": true,
"label": "Node Instance",
"multi": true,
"name": "node",
"options": [],
"query": "label_values(instance)",
"refresh": 2,
"regex": "",
"sort": 1,
"type": "query"
},
{
"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-3h",
"to": "now"
},
"timepicker": {
"refresh_intervals": [
"5s",
"10s",
"30s",
"1m",
"5m"
]
},
"timezone": "browser",
"title": "MinIO AIStor - Goroutine & TTFB Deep Analytics (v2)",
"uid": "minio-aistor-goroutine-ttfb-v2",
"version": 1
}
engineer