chore(grafana): Added Grafana dashboard

This commit is contained in:
l-nmch
2025-11-11 02:58:50 +01:00
parent e1b9067c05
commit 83187ca800

770
grafana.json Normal file
View File

@@ -0,0 +1,770 @@
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "grafana",
"uid": "-- Grafana --"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 0,
"id": 0,
"links": [],
"panels": [
{
"collapsed": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 0
},
"id": 9,
"panels": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "#EAB839",
"value": 40
},
{
"color": "red",
"value": 80
}
]
},
"unit": "watt"
},
"overrides": []
},
"gridPos": {
"h": 6,
"w": 12,
"x": 0,
"y": 34
},
"id": 6,
"options": {
"minVizHeight": 75,
"minVizWidth": 75,
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showThresholdLabels": false,
"showThresholdMarkers": true,
"sizing": "auto"
},
"pluginVersion": "12.2.1",
"targets": [
{
"editorMode": "builder",
"expr": "gpu_power_watts{instance=\"$Instance\"}",
"legendFormat": "{{name}}",
"range": true,
"refId": "A"
}
],
"title": "Power Consumption(W)",
"type": "gauge"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
},
"unit": "watt"
},
"overrides": []
},
"gridPos": {
"h": 6,
"w": 12,
"x": 12,
"y": 34
},
"id": 1,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "12.2.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"editorMode": "builder",
"expr": "gpu_power_watts{instance=\"$Instance\"}",
"legendFormat": "{{name}}",
"range": true,
"refId": "A"
}
],
"title": "Power Consumption (W)",
"type": "timeseries"
}
],
"repeat": "Instance",
"title": "Power Consumption",
"type": "row"
},
{
"collapsed": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 1
},
"id": 11,
"panels": [
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "#EAB839",
"value": 50
},
{
"color": "red",
"value": 60
}
]
},
"unit": "celsius"
},
"overrides": []
},
"gridPos": {
"h": 6,
"w": 12,
"x": 0,
"y": 20
},
"id": 8,
"options": {
"minVizHeight": 75,
"minVizWidth": 75,
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showThresholdLabels": false,
"showThresholdMarkers": true,
"sizing": "auto"
},
"pluginVersion": "12.2.1",
"targets": [
{
"editorMode": "builder",
"expr": "gpu_temperature_celsius{instance=\"$Instance\"}",
"legendFormat": "{{name}}",
"range": true,
"refId": "A"
}
],
"title": "GPU Temperature(°C)",
"type": "gauge"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
},
"unit": "celsius"
},
"overrides": []
},
"gridPos": {
"h": 6,
"w": 12,
"x": 12,
"y": 20
},
"id": 7,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "12.2.1",
"targets": [
{
"editorMode": "builder",
"expr": "gpu_temperature_celsius{instance=\"$Instance\"}",
"legendFormat": "{{name}}",
"range": true,
"refId": "A"
}
],
"title": "GPU Temperature(°C)",
"type": "timeseries"
}
],
"repeat": "Instance",
"title": "CPU Temperature",
"type": "row"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 2
},
"id": 10,
"panels": [],
"repeat": "Instance",
"title": "vRAM Usage",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "#EAB839",
"value": 60
},
{
"color": "red",
"value": 80
}
]
},
"unit": "percent"
},
"overrides": []
},
"gridPos": {
"h": 6,
"w": 12,
"x": 0,
"y": 3
},
"id": 2,
"options": {
"minVizHeight": 75,
"minVizWidth": 75,
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showThresholdLabels": false,
"showThresholdMarkers": true,
"sizing": "auto"
},
"pluginVersion": "12.2.1",
"targets": [
{
"editorMode": "builder",
"expr": "gpu_memory_utilization_percent{instance=\"$Instance\"}",
"legendFormat": "{{name}}",
"range": true,
"refId": "A"
}
],
"title": "vRAM Usage(%)",
"type": "gauge"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
},
"unit": "mbytes"
},
"overrides": []
},
"gridPos": {
"h": 6,
"w": 12,
"x": 12,
"y": 3
},
"id": 4,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "12.2.1",
"targets": [
{
"editorMode": "builder",
"expr": "gpu_memory_used_mib{instance=\"$Instance\"}",
"legendFormat": "{{name}}",
"range": true,
"refId": "A"
}
],
"title": "vRAM Usage(MiB)",
"type": "timeseries"
},
{
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 9
},
"id": 12,
"panels": [],
"repeat": "Instance",
"title": "GPU Usage",
"type": "row"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "#EAB839",
"value": 50
},
{
"color": "red",
"value": 80
}
]
},
"unit": "percent"
},
"overrides": []
},
"gridPos": {
"h": 6,
"w": 12,
"x": 0,
"y": 10
},
"id": 3,
"options": {
"minVizHeight": 75,
"minVizWidth": 75,
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showThresholdLabels": false,
"showThresholdMarkers": true,
"sizing": "auto"
},
"pluginVersion": "12.2.1",
"targets": [
{
"editorMode": "builder",
"expr": "gpu_utilization_percent{instance=\"$Instance\"}",
"legendFormat": "{{name}}",
"range": true,
"refId": "A"
}
],
"title": "GPU Utilisation(%)",
"type": "gauge"
},
{
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"showValues": false,
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
},
"unit": "rotmhz"
},
"overrides": []
},
"gridPos": {
"h": 6,
"w": 12,
"x": 12,
"y": 10
},
"id": 5,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "12.2.1",
"targets": [
{
"editorMode": "builder",
"expr": "gpu_clock_mhz{instance=\"$Instance\"}",
"legendFormat": "{{name}}",
"range": true,
"refId": "A"
}
],
"title": "GPU Clock(MHz)",
"type": "timeseries"
}
],
"preload": false,
"refresh": "auto",
"schemaVersion": 42,
"tags": [],
"templating": {
"list": [
{
"current": {
"text": "10.5.0.1:8000",
"value": "10.5.0.1:8000"
},
"definition": "label_values({__name__=~\"gpu_clock_mhz\"},instance)",
"label": "instance",
"name": "Instance",
"options": [],
"query": {
"qryType": 1,
"query": "label_values({__name__=~\"gpu_clock_mhz\"},instance)",
"refId": "PrometheusVariableQueryEditor-VariableQuery"
},
"refresh": 1,
"regex": "",
"type": "query"
}
]
},
"time": {
"from": "now-5m",
"to": "now"
},
"timepicker": {},
"timezone": "browser",
"title": "GPU Utilization",
"uid": "ad2h9f6",
"version": 15
}