26Y28d1
{
"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": "SECTION 1: Weekly Executive Summary & SLA KPIs",
"type": "row"
},
{
"id": 1,
"title": "Peak S3 API RPS",
"type": "stat",
"gridPos": {
"h": 4,
"w": 4,
"x": 0,
"y": 1
},
"fieldConfig": {
"defaults": {
"unit": "reqps"
}
},
"options": {
"colorMode": "value",
"graphMode": "area",
"reduceOptions": {
"calcs": [
"max"
]
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "max_over_time(sum(rate(minio_api_requests_total{cluster=~\"$cluster\"}[$interval]))[7d:1m]) or sum(rate(minio_api_requests_total{cluster=~\"$cluster\"}[$interval]))",
"legendFormat": "Peak RPS",
"refId": "A"
}
]
},
{
"id": 2,
"title": "Read TTFB p99 (GetObject)",
"type": "stat",
"gridPos": {
"h": 4,
"w": 4,
"x": 4,
"y": 1
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 0.1
},
{
"color": "red",
"value": 0.3
}
]
},
"unit": "s"
}
},
"options": {
"colorMode": "value",
"graphMode": "area",
"reduceOptions": {
"calcs": [
"lastNotNull"
]
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "histogram_quantile(0.99, sum(rate(minio_api_requests_ttfb_seconds_distribution{cluster=~\"$cluster\", name=~\"s3.GetObject.*\"}[$interval])) by (le))",
"legendFormat": "Read p99 TTFB",
"refId": "A"
}
]
},
{
"id": 3,
"title": "Write TTFB p99 (PutObject)",
"type": "stat",
"gridPos": {
"h": 4,
"w": 4,
"x": 8,
"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": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "histogram_quantile(0.99, sum(rate(minio_api_requests_ttfb_seconds_distribution{cluster=~\"$cluster\", name=~\"s3.PutObject.*\"}[$interval])) by (le))",
"legendFormat": "Write p99 TTFB",
"refId": "A"
}
]
},
{
"id": 4,
"title": "Weekly Max Goroutines",
"type": "stat",
"gridPos": {
"h": 4,
"w": 4,
"x": 12,
"y": 1
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 80000
},
{
"color": "red",
"value": 150000
}
]
},
"unit": "short"
}
},
"options": {
"colorMode": "value",
"graphMode": "area",
"reduceOptions": {
"calcs": [
"max"
]
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "max(minio_system_process_go_routine_total{cluster=~\"$cluster\"})",
"legendFormat": "Max Goroutines",
"refId": "A"
}
]
},
{
"id": 5,
"title": "Total QoS Throttled Counts",
"type": "stat",
"gridPos": {
"h": 4,
"w": 4,
"x": 16,
"y": 1
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 100
},
{
"color": "red",
"value": 1000
}
]
},
"unit": "short"
}
},
"options": {
"colorMode": "value",
"graphMode": "area",
"reduceOptions": {
"calcs": [
"sum"
]
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "sum(increase(minio_bucket_api_last_minute_qos_throttled_total{cluster=~\"$cluster\"}[$interval]))",
"legendFormat": "QoS Throttles",
"refId": "A"
}
]
},
{
"id": 6,
"title": "5xx Error Rate SLA",
"type": "stat",
"gridPos": {
"h": 4,
"w": 4,
"x": 20,
"y": 1
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 0.01
}
]
},
"unit": "percentunit"
}
},
"options": {
"colorMode": "value",
"graphMode": "area",
"reduceOptions": {
"calcs": [
"lastNotNull"
]
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "sum(rate(minio_api_requests_5xx_errors_total{cluster=~\"$cluster\"}[$interval])) / sum(rate(minio_api_requests_total{cluster=~\"$cluster\"}[$interval]))",
"legendFormat": "5xx Ratio",
"refId": "A"
}
]
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 5
},
"id": 200,
"title": "SECTION 2: Response Latency (TTFB) & SLA Trend Analysis",
"type": "row"
},
{
"id": 7,
"title": "Read (GetObject) vs Write (PutObject) TTFB Trend (p50, p95, p99)",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 6
},
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"lineWidth": 2
},
"unit": "s"
}
},
"options": {
"legend": {
"displayMode": "table",
"placement": "bottom",
"calcs": [
"mean",
"max"
]
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "histogram_quantile(0.95, sum(rate(minio_api_requests_ttfb_seconds_distribution{cluster=~\"$cluster\", name=~\"s3.GetObject.*\"}[$interval])) by (le))",
"legendFormat": "Read p95 TTFB",
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "histogram_quantile(0.99, sum(rate(minio_api_requests_ttfb_seconds_distribution{cluster=~\"$cluster\", name=~\"s3.GetObject.*\"}[$interval])) by (le))",
"legendFormat": "Read p99 TTFB",
"refId": "B"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "histogram_quantile(0.95, sum(rate(minio_api_requests_ttfb_seconds_distribution{cluster=~\"$cluster\", name=~\"s3.PutObject.*\"}[$interval])) by (le))",
"legendFormat": "Write p95 TTFB",
"refId": "C"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "histogram_quantile(0.99, sum(rate(minio_api_requests_ttfb_seconds_distribution{cluster=~\"$cluster\", name=~\"s3.PutObject.*\"}[$interval])) by (le))",
"legendFormat": "Write p99 TTFB",
"refId": "D"
}
]
},
{
"id": 8,
"title": "Top N Outlier Buckets by Weekly p99 TTFB",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 6
},
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"lineWidth": 2
},
"unit": "s"
}
},
"options": {
"legend": {
"displayMode": "table",
"placement": "bottom",
"calcs": [
"mean",
"max"
]
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "topk($topn, histogram_quantile(0.99, sum(rate(minio_bucket_api_ttfb_seconds_distribution{cluster=~\"$cluster\"}[$interval])) by (le, bucket)))",
"legendFormat": "Bucket: {{bucket}}",
"refId": "A"
}
]
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 14
},
"id": 300,
"title": "SECTION 3: Workload Pattern & S3 Verb Distribution",
"type": "row"
},
{
"id": 9,
"title": "S3 API Verb Throughput Distribution (GET / PUT / LIST / DELETE)",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 15
},
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"stacking": {
"group": "A",
"mode": "normal"
}
},
"unit": "reqps"
}
},
"options": {
"legend": {
"displayMode": "table",
"placement": "bottom",
"calcs": [
"mean",
"max"
]
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "sum by (name) (rate(minio_api_requests_total{cluster=~\"$cluster\"}[$interval]))",
"legendFormat": "{{name}}",
"refId": "A"
}
]
},
{
"id": 10,
"title": "Inflight vs Queued Waiting API Requests",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 15
},
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"lineWidth": 2
},
"unit": "short"
}
},
"options": {
"legend": {
"displayMode": "table",
"placement": "bottom",
"calcs": [
"mean",
"max"
]
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "sum(minio_api_requests_inflight_total{cluster=~\"$cluster\"})",
"legendFormat": "Inflight Requests",
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "sum(minio_api_requests_waiting_total{cluster=~\"$cluster\"})",
"legendFormat": "Queued Waiting Requests",
"refId": "B"
}
]
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 23
},
"id": 400,
"title": "SECTION 4: Cluster Imbalance & Hardware Health (128 Nodes / 2,560 Drives)",
"type": "row"
},
{
"id": 11,
"title": "Top N Hotspot Servers (High Goroutines & CPU)",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 24
},
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"lineWidth": 2
},
"unit": "short"
}
},
"options": {
"legend": {
"displayMode": "table",
"placement": "bottom",
"calcs": [
"mean",
"max"
]
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "topk($topn, minio_system_process_go_routine_total{cluster=~\"$cluster\", server=~\"$server\"})",
"legendFormat": "Goroutines - {{server}}",
"refId": "A"
}
]
},
{
"id": 12,
"title": "Drive Timeout & IO Errors Across 2,560 Drives",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 24
},
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"lineWidth": 2
},
"unit": "errorsps"
}
},
"options": {
"legend": {
"displayMode": "table",
"placement": "bottom",
"calcs": [
"max"
]
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "topk($topn, sum by (server, drive_id) (rate(minio_system_drive_timeout_errors_total{cluster=~\"$cluster\"}[$interval])))",
"legendFormat": "Drive Timeout - {{server}} {{drive_id}}",
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "topk($topn, sum by (server, drive_id) (rate(minio_system_drive_io_errors_total{cluster=~\"$cluster\"}[$interval])))",
"legendFormat": "Drive IO Err - {{server}} {{drive_id}}",
"refId": "B"
}
]
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 32
},
"id": 500,
"title": "SECTION 5: Goroutine Spikes vs Background Task Correlation",
"type": "row"
},
{
"id": 13,
"title": "Goroutines vs Active Background Workers (Replication / ILM / Batch Jobs)",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 33
},
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"lineWidth": 2
},
"unit": "short"
}
},
"options": {
"legend": {
"displayMode": "table",
"placement": "bottom",
"calcs": [
"mean",
"max"
]
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "sum(minio_system_process_go_routine_total{cluster=~\"$cluster\"})",
"legendFormat": "Total Goroutines (Left Y)",
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "sum(minio_cluster_replication_active_workers{cluster=~\"$cluster\"})",
"legendFormat": "Replication Workers",
"refId": "B"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "sum(minio_ilm_transition_active_tasks{cluster=~\"$cluster\"})",
"legendFormat": "ILM Transition Tasks",
"refId": "C"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "sum(minio_batch_jobs_in_progress{cluster=~\"$cluster\"})",
"legendFormat": "Batch Jobs",
"refId": "D"
}
]
},
{
"id": 14,
"title": "Internode RPC Failures vs QoS Throttled Counts",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 33
},
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line",
"lineWidth": 2
},
"unit": "short"
}
},
"options": {
"legend": {
"displayMode": "table",
"placement": "bottom",
"calcs": [
"max"
]
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "sum(rate(minio_internode_failed_calls_total{cluster=~\"$cluster\"}[$interval]))",
"legendFormat": "Internode RPC Failures",
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "sum(rate(minio_bucket_api_last_minute_qos_throttled_total{cluster=~\"$cluster\"}[$interval]))",
"legendFormat": "QoS Throttled Rate",
"refId": "B"
}
]
}
],
"refresh": "1m",
"schemaVersion": 38,
"style": "dark",
"tags": [
"minio",
"aistor",
"weekly",
"executive",
"report"
],
"templating": {
"list": [
{
"name": "datasource",
"type": "datasource",
"query": "prometheus",
"hide": 0,
"label": "Prometheus",
"current": {}
},
{
"name": "cluster",
"type": "query",
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"query": "label_values(minio_cluster_health_nodes_online_count, cluster)",
"label": "Cluster",
"hide": 0,
"includeAll": true,
"multi": true,
"allValue": ".*",
"current": {
"text": "All",
"value": "$__all"
},
"refresh": 2,
"sort": 1
},
{
"name": "server",
"type": "query",
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"query": "label_values(minio_system_process_go_routine_total{cluster=~\"$cluster\"}, server)",
"label": "Node (server)",
"hide": 0,
"includeAll": true,
"multi": true,
"allValue": ".*",
"current": {
"text": "All",
"value": "$__all"
},
"refresh": 2,
"sort": 1
},
{
"name": "topn",
"type": "custom",
"query": "10,15,20,30",
"label": "Top N",
"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": "15m",
"value": "15m"
},
"hide": 0,
"label": "Interval",
"name": "interval",
"options": [
{
"selected": false,
"text": "5m",
"value": "5m"
},
{
"selected": true,
"text": "15m",
"value": "15m"
},
{
"selected": false,
"text": "30m",
"value": "30m"
},
{
"selected": false,
"text": "1h",
"value": "1h"
}
],
"query": "5m,15m,30m,1h",
"type": "interval"
}
]
},
"time": {
"from": "now-7d",
"to": "now"
},
"timepicker": {
"refresh_intervals": [
"1m",
"5m",
"15m",
"1h"
]
},
"timezone": "browser",
"title": "7. MinIO AIStor - Weekly Executive Performance & SLA Report",
"uid": "minio-aistor-weekly-executive-report",
"version": 1
}
engineer