diff --git a/NVIDIA DCGM Exporter-1684242180498.json b/NVIDIA DCGM Exporter-1684242180498.json index e08368f..20009f4 100644 --- a/NVIDIA DCGM Exporter-1684242180498.json +++ b/NVIDIA DCGM Exporter-1684242180498.json @@ -1,83 +1,3 @@ -Skip to main content - -Home -Dashboards -NVIDIA DCGM Exporter - - - -Add - - - -Last 1 hour - - - - - -gpu - -Machine - -GPU Utilization -Name Mean Max -GPU 0 -0% 0% -GPU Hot Spot Temperature -Name Mean Max -GPU 0 -41.2 °C 42 °C -GPU Temperature -Name Mean Max -GPU 0 -33.4 °C 34 °C -GPU VRAM Temperature -Name Mean Max -GPU 0 -38.2 °C 40 °C -GPU Fan Speed -Name Mean Max -GPU 0 -40% 40% -GPU THROTTLE_REASON -Name Mean -SwThermalSlowdown GPU 0 -False -HwThermalSlowdown GPU 0 -False -HwPowerBrakeSlowdownGPU 0 -False -GPU Memory Clock -Name Mean Max -GPU 0 -405 MHz 405 MHz -GPU Power Usage -Name Mean Max -GPU 0 -22.3 W 23.5 W -GPU Framebuffer Memory Used -Name Mean Max -GPU 0 -466 MiB 466 MiB -GPU Memory Bandwidth Utilization -Name Mean Max -GPU 0 -0% 0% -GPU SM Clock -Name Mean Max -GPU 0 -210 MHz 210 MHz -GPU NVLink Bandwidth -Name Mean Max -GPU 0 -0 c/s 0 c/s -GPU Graphics Engine Utilization -No data -GPU PCIe Receive -No data -JSON - { "__inputs": [ { @@ -88,7 +8,1925 @@ JSON "pluginId": "prometheus", "pluginName": "Prometheus" } -… "weekStart": "" + ], + "__elements": {}, + "__requires": [ + { + "type": "grafana", + "id": "grafana", + "name": "Grafana", + "version": "10.3.1" + }, + { + "type": "datasource", + "id": "prometheus", + "name": "Prometheus", + "version": "1.0.0" + }, + { + "type": "panel", + "id": "timeseries", + "name": "Time series", + "version": "" + } + ], + "annotations": { + "list": [ + { + "$$hashKey": "object:192", + "builtIn": 1, + "datasource": { + "type": "datasource", + "uid": "grafana" + }, + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "target": { + "limit": 100, + "matchAny": false, + "tags": [], + "type": "dashboard" + }, + "type": "dashboard" + } + ] + }, + "description": "This dashboard is to display the metrics from DCGM Exporter", + "editable": true, + "fiscalYearStartMonth": 0, + "gnetId": 15117, + "graphTooltip": 0, + "id": null, + "links": [], + "liveNow": false, + "panels": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "description": "", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": 60000, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "max": 100, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "percent", + "unitScale": true + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 0 + }, + "id": 6, + "options": { + "legend": { + "calcs": [ + "mean", + "max" + ], + "displayMode": "table", + "placement": "right", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "8.2.1", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "exemplar": true, + "expr": "DCGM_FI_DEV_GPU_UTIL{job=\"$job\", gpu=~\"${gpu}\"}", + "interval": "", + "legendFormat": "GPU {{gpu}}", + "range": true, + "refId": "A" + } + ], + "title": "GPU Utilization", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineStyle": { + "fill": "solid" + }, + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": 60000, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "celsius", + "unitScale": true + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 0 + }, + "id": 27, + "options": { + "legend": { + "calcs": [ + "mean", + "max" + ], + "displayMode": "table", + "placement": "right", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "8.2.1", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "DCGM_FI_DEV_HOT_SPOT_TEMP{job=\"$job\", gpu=~\"${gpu}\"}", + "instant": false, + "interval": "", + "legendFormat": "GPU {{gpu}}", + "refId": "A" + } + ], + "title": "GPU Hot Spot Temperature", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineStyle": { + "fill": "solid" + }, + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": 60000, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "celsius", + "unitScale": true + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 8 + }, + "id": 28, + "options": { + "legend": { + "calcs": [ + "mean", + "max" + ], + "displayMode": "table", + "placement": "right", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "8.2.1", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "exemplar": true, + "expr": "DCGM_FI_DEV_GPU_TEMP{job=\"${job}\",gpu=~\"${gpu}\"}", + "instant": false, + "interval": "", + "legendFormat": "GPU {{gpu}}", + "refId": "A" + } + ], + "title": "GPU Temperature", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineStyle": { + "fill": "solid" + }, + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": 60000, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "celsius", + "unitScale": true + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 8 + }, + "id": 29, + "options": { + "legend": { + "calcs": [ + "mean", + "max" + ], + "displayMode": "table", + "placement": "right", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "8.2.1", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "DCGM_FI_DEV_VRAM_TEMP{job=\"$job\", gpu=~\"${gpu}\"}", + "instant": false, + "interval": "", + "legendFormat": "GPU {{gpu}}", + "refId": "A" + } + ], + "title": "GPU VRAM Temperature", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "axisSoftMax": 100, + "axisSoftMin": 0, + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineStyle": { + "fill": "solid" + }, + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": 60000, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "percent", + "unitScale": true + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 16 + }, + "id": 19, + "options": { + "legend": { + "calcs": [ + "mean", + "max" + ], + "displayMode": "table", + "placement": "right", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "8.2.1", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "exemplar": true, + "expr": "DCGM_FI_DEV_FAN_SPEED{job=\"$job\",gpu=~\"${gpu}\"}", + "instant": false, + "interval": "", + "legendFormat": "GPU {{gpu}}", + "refId": "A" + } + ], + "title": "GPU Fan Speed", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineStyle": { + "fill": "solid" + }, + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": 60000, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "bool", + "unitScale": true + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 16 + }, + "id": 30, + "options": { + "legend": { + "calcs": [ + "mean" + ], + "displayMode": "table", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "8.2.1", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "DCGM_FI_DEV_CLOCKS_THROTTLE_REASON{reason=\"SwThermalSlowdown\", job=\"$job\", gpu=~\"${gpu}\"}", + "format": "time_series", + "instant": false, + "interval": "", + "legendFormat": "SwThermalSlowdown GPU {{gpu}}", + "range": true, + "refId": "A" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "DCGM_FI_DEV_CLOCKS_THROTTLE_REASON{reason=\"HwThermalSlowdown\", job=\"$job\", gpu=~\"${gpu}\"}", + "format": "time_series", + "hide": false, + "instant": false, + "interval": "", + "legendFormat": "HwThermalSlowdown GPU {{gpu}}", + "range": true, + "refId": "B" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "expr": "DCGM_FI_DEV_CLOCKS_THROTTLE_REASON{reason=\"HwPowerBrakeSlowdown\", job=\"$job\", gpu=~\"${gpu}\"}", + "format": "time_series", + "hide": false, + "instant": false, + "interval": "", + "legendFormat": "HwPowerBrakeSlowdownGPU {{gpu}}", + "range": true, + "refId": "C" + } + ], + "title": "GPU THROTTLE_REASON", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "description": "", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineStyle": { + "fill": "solid" + }, + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": 60000, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "rothz", + "unitScale": true + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 24 + }, + "id": 20, + "interval": "", + "options": { + "legend": { + "calcs": [ + "mean", + "max" + ], + "displayMode": "table", + "placement": "right", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "8.2.1", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "exemplar": true, + "expr": "DCGM_FI_DEV_MEM_CLOCK{job=\"$job\", gpu=~\"${gpu}\"} * 1000000", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "GPU {{gpu}}", + "range": true, + "refId": "A" + } + ], + "title": "GPU Memory Clock", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": 60000, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "watt", + "unitScale": true + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 24 + }, + "id": 10, + "options": { + "legend": { + "calcs": [ + "mean", + "max" + ], + "displayMode": "table", + "placement": "right", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "8.2.1", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "exemplar": true, + "expr": "DCGM_FI_DEV_POWER_USAGE{job=\"$job\", gpu=~\"${gpu}\"}", + "interval": "", + "legendFormat": "GPU {{gpu}}", + "range": true, + "refId": "A" + } + ], + "title": "GPU Power Usage", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "description": "", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": 60000, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "mbytes", + "unitScale": true + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 32 + }, + "id": 18, + "options": { + "legend": { + "calcs": [ + "mean", + "max" + ], + "displayMode": "table", + "placement": "right", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "8.2.1", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "exemplar": true, + "expr": "DCGM_FI_DEV_FB_USED{job=\"$job\", gpu=~\"${gpu}\"}", + "interval": "", + "legendFormat": "GPU {{gpu}}", + "range": true, + "refId": "A" + } + ], + "title": "GPU Framebuffer Memory Used", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "description": "", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": 60000, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "max": 100, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "percent", + "unitScale": true + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 32 + }, + "id": 21, + "options": { + "legend": { + "calcs": [ + "mean", + "max" + ], + "displayMode": "table", + "placement": "right", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "8.2.1", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "exemplar": true, + "expr": "DCGM_FI_DEV_MEM_COPY_UTIL{job=\"$job\", gpu=~\"${gpu}\"}", + "interval": "", + "legendFormat": "GPU {{gpu}}", + "range": true, + "refId": "A" + } + ], + "title": "GPU Memory Bandwidth Utilization", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "description": "", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineStyle": { + "fill": "solid" + }, + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "spanNulls": 60000, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "rothz", + "unitScale": true + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 40 + }, + "id": 2, + "interval": "", + "options": { + "legend": { + "calcs": [ + "mean", + "max" + ], + "displayMode": "table", + "placement": "right", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "8.2.1", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "exemplar": true, + "expr": "DCGM_FI_DEV_SM_CLOCK{job=\"$job\", gpu=~\"${gpu}\"} * 1000000", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "GPU {{gpu}}", + "range": true, + "refId": "A" + } + ], + "title": "GPU SM Clock", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "description": "", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineStyle": { + "fill": "solid" + }, + "lineWidth": 2, + "pointSize": 4, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "spanNulls": 60000, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "cps", + "unitScale": true + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 40 + }, + "id": 22, + "options": { + "legend": { + "calcs": [ + "mean", + "max" + ], + "displayMode": "table", + "placement": "right", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "8.2.1", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "exemplar": true, + "expr": "DCGM_FI_DEV_NVLINK_BANDWIDTH_TOTAL{job=\"$job\", gpu=~\"${gpu}\"}", + "interval": "", + "legendFormat": "GPU {{gpu}}", + "range": true, + "refId": "A" + } + ], + "title": "GPU NVLink Bandwidth", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "description": "", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "spanNulls": 60000, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "max": 1, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "percentunit", + "unitScale": true + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 48 + }, + "id": 4, + "options": { + "legend": { + "calcs": [ + "mean", + "max" + ], + "displayMode": "table", + "placement": "right", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "8.2.1", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "exemplar": true, + "expr": "DCGM_FI_PROF_GR_ENGINE_ACTIVE{job=\"$job\", gpu=~\"${gpu}\"}", + "interval": "", + "legendFormat": "GPU {{gpu}}", + "range": true, + "refId": "A" + } + ], + "title": "GPU Graphics Engine Utilization", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "description": "", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineStyle": { + "fill": "solid" + }, + "lineWidth": 2, + "pointSize": 4, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "spanNulls": 60000, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + } + ] + }, + "unit": "binBps", + "unitScale": true + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 48 + }, + "id": 26, + "options": { + "legend": { + "calcs": [ + "mean", + "max" + ], + "displayMode": "table", + "placement": "right", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "8.2.1", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "exemplar": true, + "expr": "DCGM_FI_PROF_PCIE_RX_BYTES{job=\"$job\", gpu=~\"${gpu}\"}", + "interval": "", + "legendFormat": "GPU {{gpu}}", + "range": true, + "refId": "A" + } + ], + "title": "GPU PCIe Receive", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "description": "", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "spanNulls": 60000, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "max": 1, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + } + ] + }, + "unit": "percentunit", + "unitScale": true + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 56 + }, + "id": 24, + "options": { + "legend": { + "calcs": [ + "mean", + "max" + ], + "displayMode": "table", + "placement": "right", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "8.2.1", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "exemplar": true, + "expr": "DCGM_FI_PROF_DRAM_ACTIVE{job=\"$job\", gpu=~\"${gpu}\"}", + "interval": "", + "legendFormat": "GPU {{gpu}}", + "range": true, + "refId": "A" + } + ], + "title": "GPU Memory Interface Utilization", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "spanNulls": 60000, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "max": 1, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + } + ] + }, + "unit": "percentunit", + "unitScale": true + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 56 + }, + "id": 23, + "options": { + "legend": { + "calcs": [ + "mean", + "max" + ], + "displayMode": "table", + "placement": "right", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "8.2.1", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "exemplar": true, + "expr": "DCGM_FI_PROF_PIPE_TENSOR_ACTIVE{job=\"$job\", gpu=~\"${gpu}\"}", + "interval": "", + "legendFormat": "GPU {{gpu}}", + "range": true, + "refId": "A" + } + ], + "title": "GPU Tensor Core Utilization", + "type": "timeseries" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "description": "", + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "drawStyle": "line", + "fillOpacity": 10, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineStyle": { + "fill": "solid" + }, + "lineWidth": 2, + "pointSize": 4, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "spanNulls": 60000, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "links": [], + "mappings": [], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + } + ] + }, + "unit": "binBps", + "unitScale": true + }, + "overrides": [] + }, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 64 + }, + "id": 25, + "options": { + "legend": { + "calcs": [ + "mean", + "max" + ], + "displayMode": "table", + "placement": "right", + "showLegend": true + }, + "tooltip": { + "mode": "multi", + "sort": "none" + } + }, + "pluginVersion": "8.2.1", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "editorMode": "code", + "exemplar": true, + "expr": "DCGM_FI_PROF_PCIE_TX_BYTES{job=\"$job\", gpu=~\"${gpu}\"}", + "interval": "", + "legendFormat": "GPU {{gpu}}", + "range": true, + "refId": "A" + } + ], + "title": "GPU PCIe Transmit", + "type": "timeseries" + } + ], + "refresh": "", + "schemaVersion": 39, + "tags": [ + "nvidia" + ], + "templating": { + "list": [ + { + "current": {}, + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "definition": "label_values(gpu)", + "hide": 0, + "includeAll": true, + "multi": true, + "name": "gpu", + "options": [], + "query": { + "query": "label_values(gpu)", + "refId": "Prometheus-hpc-gpu-Variable-Query" + }, + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "current": {}, + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "definition": "label_values(node_uname_info,job)", + "hide": 0, + "includeAll": false, + "label": "Machine", + "multi": false, + "name": "job", + "options": [], + "query": { + "query": "label_values(node_uname_info,job)", + "refId": "PrometheusVariableQueryEditor-VariableQuery" + }, + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "type": "query" + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ] + }, + "timezone": "", + "title": "NVIDIA DCGM Exporter", + "uid": "Oxed_c6Wz2", + "version": 18, + "weekStart": "" } - -Copy to Clipboard