{
"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": "Drive Health & IO Errors (Across 2,560 Drives)",
"type": "row"
},
{
"id": 1,
"title": "Drive Timeout Errors Rate",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 1
},
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line"
},
"unit": "errorsps"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "topk($topn, sum by (server, drive_id) (rate(minio_system_drive_timeout_errors_total{cluster=~\"$cluster\", server=~\"$server\"}[$interval])))",
"legendFormat": "{{server}} - Drive {{drive_id}}",
"refId": "A"
}
]
},
{
"id": 2,
"title": "Drive IO Errors Rate",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 1
},
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line"
},
"unit": "errorsps"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "topk($topn, sum by (server, drive_id) (rate(minio_system_drive_io_errors_total{cluster=~\"$cluster\", server=~\"$server\"}[$interval])))",
"legendFormat": "{{server}} - Drive {{drive_id}}",
"refId": "A"
}
]
},
{
"id": 3,
"title": "Waiting IO Heatmap / Outliers",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 24,
"x": 0,
"y": 9
},
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line"
},
"unit": "short"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "topk($topn, minio_system_drive_waiting_io{cluster=~\"$cluster\", server=~\"$server\"})",
"legendFormat": "{{server}} - Drive {{drive_id}}",
"refId": "A"
}
]
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 17
},
"id": 200,
"title": "Internode Network & Lock Performance",
"type": "row"
},
{
"id": 4,
"title": "Internode Failed Calls Rate",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 18
},
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line"
},
"unit": "short"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "topk($topn, sum by (server) (rate(minio_internode_failed_calls_total{cluster=~\"$cluster\", server=~\"$server\"}[$interval])))",
"legendFormat": "Failed RPC - {{server}}",
"refId": "A"
}
]
},
{
"id": 5,
"title": "Internode Traffic Throughput (Rx / Tx)",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 18
},
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line"
},
"unit": "Bps"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "sum by (server) (rate(minio_internode_rx_bytes_total{cluster=~\"$cluster\", server=~\"$server\"}[$interval]))",
"legendFormat": "Rx - {{server}}",
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "sum by (server) (rate(minio_internode_tx_bytes_total{cluster=~\"$cluster\", server=~\"$server\"}[$interval]))",
"legendFormat": "Tx - {{server}}",
"refId": "B"
}
]
},
{
"id": 6,
"title": "Internode Distributed READ / WRITE Active Locks",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 24,
"x": 0,
"y": 26
},
"fieldConfig": {
"defaults": {
"custom": {
"drawStyle": "line"
},
"unit": "short"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "sum by (server) (minio_internode_locks_read_total{cluster=~\"$cluster\", server=~\"$server\"})",
"legendFormat": "Read Locks - {{server}}",
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"expr": "sum by (server) (minio_internode_locks_write_total{cluster=~\"$cluster\", server=~\"$server\"})",
"legendFormat": "Write Locks - {{server}}",
"refId": "B"
}
]
}
],
"refresh": "30s",
"schemaVersion": 38,
"style": "dark",
"tags": [
"minio",
"aistor",
"drive",
"network"
],
"templating": {
"list": [
{
"name": "datasource",
"type": "datasource",
"query": "prometheus",
"hide": 0,
"label": "Prometheus",
"current": {}
},
{
"name": "cluster",
"type": "query",
"datasource": {
"type": "prometheus",
"uid": "${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": "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": "2. MinIO AIStor - Drive & Internode Performance",
"uid": "minio-aistor-2-drive-internode",
"version": 1
}