26Z27e
{
"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": "1. Leading Indicators & Goroutine Anomaly",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "Requests",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 20,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "line"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 1
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 1
},
"id": 1,
"options": {
"legend": {
"calcs": ["lastNotNull", "max"],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"title": "API Wait Queue (Leading Indicator - maxClients Backlog)",
"description": "maxClients 제한 뒤에 대기 중인 요청 수. 고루틴 폭증 전에 가장 먼저 튀는 선행 지표입니다.",
"type": "timeseries",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum(minio_api_requests_waiting_total{cluster=~\"$cluster\"})",
"legendFormat": "Waiting Queue (Cluster Total)",
"range": true,
"refId": "A"
}
]
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "In-Flight Count",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 10,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "short"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "Goroutines Total"
},
"properties": [
{
"id": "custom.axisPlacement",
"value": "right"
},
{
"id": "custom.axisLabel",
"value": "Goroutine Count"
}
]
}
]
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 1
},
"id": 2,
"options": {
"legend": {
"calcs": ["lastNotNull", "max"],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"title": "Goroutines vs API In-Flight Requests",
"description": "In-flight 요청 수는 적은데 Goroutine만 폭증한다면 내부 재귀 스캔(ListObjects) 등의 비대칭 부하를 의심할 수 있습니다.",
"type": "timeseries",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum(minio_system_process_go_routine_total{cluster=~\"$cluster\"})",
"legendFormat": "Goroutines Total",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum(minio_api_requests_inflight_total{cluster=~\"$cluster\"})",
"legendFormat": "API In-Flight Total",
"range": true,
"refId": "B"
}
]
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 9
},
"id": 200,
"title": "2. Root Cause: Latency & Traffic Spikes by Bucket & API",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "Duration",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 15,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 10
},
"id": 11,
"options": {
"legend": {
"calcs": ["lastNotNull", "max"],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"title": "P99 TTFB by Bucket & API Operation (5m)",
"description": "어떤 버킷의 어떤 API 호출이 가장 긴 지연 시간(TTFB)을 유발하는지 특정합니다.",
"type": "timeseries",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "topk(10, histogram_quantile(0.99, sum by (bucket, name, le) (rate(minio_api_requests_ttfb_seconds_distribution{cluster=~\"$cluster\"}[5m]))))",
"legendFormat": "{{bucket}} - {{name}}",
"range": true,
"refId": "A"
}
]
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "Ops/sec",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 15,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "reqps"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 10
},
"id": 12,
"options": {
"legend": {
"calcs": ["lastNotNull", "mean", "max"],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"title": "Top Request Rate (1m) by Bucket & Operation",
"description": "버킷별 API 요청 인입량(RPS)을 추적하여 트래픽이 몰리는 지점을 확인합니다.",
"type": "timeseries",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "topk(10, sum by (bucket, name) (rate(minio_api_requests_total{cluster=~\"$cluster\"}[1m])))",
"legendFormat": "{{bucket}} - {{name}}",
"range": true,
"refId": "A"
}
]
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 18
},
"id": 300,
"title": "3. In-Flight Requests by Bucket & Operation",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "Active Requests",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 15,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 19
},
"id": 3,
"options": {
"legend": {
"calcs": ["lastNotNull", "max"],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"title": "Top In-Flight Requests by Bucket & API",
"description": "어떤 버킷의 어떤 API가 핸들러를 점유한 채 완료되지 못하고 체류 중인지 파악합니다.",
"type": "timeseries",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "topk(10, sum by (bucket, name) (minio_api_requests_inflight_total{cluster=~\"$cluster\"}))",
"legendFormat": "{{bucket}} - {{name}}",
"range": true,
"refId": "A"
}
]
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "Ops/sec",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 15,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "reqps"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 19
},
"id": 4,
"options": {
"legend": {
"calcs": ["lastNotNull", "max"],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"title": "ListObjects Rate Spikes by Bucket",
"description": "s3.ListObjects* 호출이 발생한 특정 버킷을 모니터링합니다.",
"type": "timeseries",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum by (bucket, name) (rate(minio_api_requests_total{cluster=~\"$cluster\", name=~\"s3.ListObjects.*\"}[1m])) > 0",
"legendFormat": "{{bucket}} - {{name}}",
"range": true,
"refId": "A"
}
]
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 27
},
"id": 400,
"title": "4. Node CPU & Drive Subsystem Pressure",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "Cores / Usage",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 15,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 28
},
"id": 13,
"options": {
"legend": {
"calcs": ["lastNotNull", "max"],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"title": "MinIO Process CPU Usage by Instance",
"description": "대량 메타데이터 탐색 시 노드별 CPU 사용률 급증 여부를 확인합니다.",
"type": "timeseries",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "topk(10, rate(minio_system_process_cpu_total{cluster=~\"$cluster\"}[1m]))",
"legendFormat": "{{instance}} (CPU Cores)",
"range": true,
"refId": "A"
}
]
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "Latency (µs)",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 15,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "µs"
},
"overrides": [
{
"matcher": {
"id": "byRegexp",
"options": ".*Util.*"
},
"properties": [
{
"id": "custom.axisPlacement",
"value": "right"
},
{
"id": "custom.axisLabel",
"value": "Disk Utilization"
},
{
"id": "unit",
"value": "percent"
}
]
}
]
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 28
},
"id": 14,
"options": {
"legend": {
"calcs": ["lastNotNull", "max"],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"title": "Top Drive Latency & Disk Utilization",
"description": "드라이브 응답 지연(µs) 및 I/O 점유율(%)을 통해 디스크 포화 상태를 파악합니다.",
"type": "timeseries",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "topk(5, max by (instance, drive) (minio_node_drive_latency_microseconds{cluster=~\"$cluster\"}))",
"legendFormat": "{{instance}} - {{drive}} (µs)",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "topk(5, rate(minio_node_drive_io_time_seconds_total{cluster=~\"$cluster\"}[1m]) * 100)",
"legendFormat": "{{instance}} - {{drive}} (Util %)",
"range": true,
"refId": "B"
}
]
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 36
},
"id": 500,
"title": "5. Error Distribution & Client Cancellations",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "Errors/sec",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 15,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 2,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "reqps"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 24,
"x": 0,
"y": 37
},
"id": 6,
"options": {
"legend": {
"calcs": ["lastNotNull", "max"],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"title": "API Errors & Client Cancellations Rate (1m)",
"description": "클라이언트 취소(타임아웃) 및 4xx/5xx 에러 발생 추이를 추적합니다.",
"type": "timeseries",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum by (name) (rate(minio_api_requests_5xx_errors_total{cluster=~\"$cluster\"}[1m])) > 0",
"legendFormat": "5xx Error - {{name}}",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum by (name) (rate(minio_api_requests_4xx_errors_total{cluster=~\"$cluster\"}[1m])) > 0",
"legendFormat": "4xx Error - {{name}}",
"range": true,
"refId": "B"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum by (name) (rate(minio_api_requests_canceled_total{cluster=~\"$cluster\"}[1m])) > 0",
"legendFormat": "Canceled - {{name}}",
"range": true,
"refId": "C"
}
]
}
],
"refresh": "10s",
"schemaVersion": 38,
"style": "dark",
"tags": ["minio", "aistor", "sre", "troubleshooting", "v3-metrics"],
"templating": {
"list": [
{
"current": {},
"hide": 0,
"includeAll": false,
"label": "Datasource",
"name": "datasource",
"options": [],
"query": "prometheus",
"refresh": 1,
"type": "datasource"
},
{
"allValue": ".*",
"current": {
"selected": true,
"text": "All",
"value": "$__all"
},
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"definition": "label_values(minio_api_requests_total, cluster)",
"hide": 0,
"includeAll": true,
"label": "Cluster",
"multi": false,
"name": "cluster",
"options": [],
"query": {
"query": "label_values(minio_api_requests_total, cluster)",
"refId": "StandardVariableQuery"
},
"refresh": 2,
"sort": 1,
"type": "query"
}
]
},
"time": {
"from": "now-1h",
"to": "now"
},
"timepicker": {
"refresh_intervals": [
"5s",
"10s",
"30s",
"1m",
"5m"
]
},
"timezone": "browser",
"title": "MinIO / AIStor - Root Cause & Asymmetric Load Triage (v3 Compatible)",
"uid": "minio-aistor-triage-v3",
"version": 5
}
engineer