e6420c7b36
Move all 88 service modules (66 individual + 22 platform) from modules/kubernetes/<service>/ into their corresponding stack directories: - Service stacks: stacks/<service>/module/ - Platform stack: stacks/platform/modules/<service>/ This collocates module source code with its Terragrunt definition. Only shared utility modules remain in modules/kubernetes/: ingress_factory, setup_tls_secret, dockerhub_secret, oauth-proxy. All cross-references to shared modules updated to use correct relative paths. Verified with terragrunt run --all -- plan: 0 adds, 0 destroys across all 68 stacks.
816 lines
27 KiB
JSON
816 lines
27 KiB
JSON
{
|
|
"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",
|
|
"type": "dashboard"
|
|
}
|
|
]
|
|
},
|
|
"description": "This dashboard is to display the metrics from DCGM Exporter on a Kubernetes (1.13+) cluster",
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 0,
|
|
"id": 0,
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "PBFA97CFB590B2093"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"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",
|
|
"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": 8,
|
|
"w": 18,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"id": 12,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [
|
|
"mean",
|
|
"lastNotNull",
|
|
"max"
|
|
],
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.3.1",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "PBFA97CFB590B2093"
|
|
},
|
|
"editorMode": "code",
|
|
"expr": "nvidia_tesla_t4_DCGM_FI_DEV_GPU_TEMP",
|
|
"instant": false,
|
|
"interval": "",
|
|
"legendFormat": "GPU 0",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "GPU Temperature",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "PBFA97CFB590B2093"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"mappings": [],
|
|
"max": 100,
|
|
"min": 0,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "#EAB839",
|
|
"value": 70
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
},
|
|
"unit": "celsius"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 6,
|
|
"x": 18,
|
|
"y": 0
|
|
},
|
|
"id": 14,
|
|
"options": {
|
|
"minVizHeight": 75,
|
|
"minVizWidth": 75,
|
|
"orientation": "auto",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showThresholdLabels": false,
|
|
"showThresholdMarkers": true,
|
|
"sizing": "auto"
|
|
},
|
|
"pluginVersion": "12.3.1",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "PBFA97CFB590B2093"
|
|
},
|
|
"editorMode": "code",
|
|
"expr": "nvidia_tesla_t4_DCGM_FI_DEV_GPU_TEMP",
|
|
"interval": "",
|
|
"legendFormat": "",
|
|
"range": true,
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "GPU Current Temp",
|
|
"type": "gauge"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "PBFA97CFB590B2093"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"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",
|
|
"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": 8,
|
|
"w": 18,
|
|
"x": 0,
|
|
"y": 8
|
|
},
|
|
"id": 10,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [
|
|
"mean",
|
|
"lastNotNull",
|
|
"max"
|
|
],
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.3.1",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "PBFA97CFB590B2093"
|
|
},
|
|
"editorMode": "code",
|
|
"expr": "nvidia_tesla_t4_DCGM_FI_DEV_POWER_USAGE",
|
|
"interval": "",
|
|
"legendFormat": "GPU {{gpu}}",
|
|
"range": true,
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "GPU Power Usage",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "PBFA97CFB590B2093"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"mappings": [],
|
|
"max": 2400,
|
|
"min": 0,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "#EAB839",
|
|
"value": 1800
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 2200
|
|
}
|
|
]
|
|
},
|
|
"unit": "watt"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 6,
|
|
"x": 18,
|
|
"y": 8
|
|
},
|
|
"id": 16,
|
|
"options": {
|
|
"minVizHeight": 75,
|
|
"minVizWidth": 75,
|
|
"orientation": "horizontal",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"sum"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"showThresholdLabels": false,
|
|
"showThresholdMarkers": true,
|
|
"sizing": "auto"
|
|
},
|
|
"pluginVersion": "12.3.1",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "PBFA97CFB590B2093"
|
|
},
|
|
"editorMode": "code",
|
|
"exemplar": false,
|
|
"expr": "sum(nvidia_tesla_t4_DCGM_FI_DEV_POWER_USAGE)",
|
|
"instant": true,
|
|
"interval": "",
|
|
"legendFormat": "",
|
|
"range": false,
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "GPU Power Total",
|
|
"type": "gauge"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "PBFA97CFB590B2093"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"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",
|
|
"showValues": false,
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
},
|
|
"thresholdsStyle": {
|
|
"mode": "off"
|
|
}
|
|
},
|
|
"mappings": [],
|
|
"max": 100,
|
|
"min": 0,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": 0
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 80
|
|
}
|
|
]
|
|
},
|
|
"unit": "percent"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 16
|
|
},
|
|
"id": 6,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [
|
|
"mean",
|
|
"lastNotNull",
|
|
"max"
|
|
],
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.3.1",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "PBFA97CFB590B2093"
|
|
},
|
|
"editorMode": "code",
|
|
"expr": "nvidia_tesla_t4_DCGM_FI_DEV_GPU_UTIL",
|
|
"interval": "",
|
|
"legendFormat": "GPU {{gpu}}",
|
|
"range": true,
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "GPU Utilization",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "PBFA97CFB590B2093"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"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",
|
|
"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": "decmbytes"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 16
|
|
},
|
|
"id": 18,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [
|
|
"mean",
|
|
"max"
|
|
],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.3.1",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "PBFA97CFB590B2093"
|
|
},
|
|
"editorMode": "code",
|
|
"expr": "nvidia_tesla_t4_DCGM_FI_DEV_FB_USED",
|
|
"interval": "",
|
|
"legendFormat": "GPU {{gpu}}",
|
|
"range": true,
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "GPU Framebuffer Mem Used",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "PBFA97CFB590B2093"
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"axisBorderShow": false,
|
|
"axisCenteredZero": false,
|
|
"axisColorMode": "text",
|
|
"axisLabel": "",
|
|
"axisPlacement": "auto",
|
|
"barAlignment": 0,
|
|
"barWidthFactor": 0.6,
|
|
"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",
|
|
"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": "hertz"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 24
|
|
},
|
|
"id": 2,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [
|
|
"mean",
|
|
"lastNotNull",
|
|
"max"
|
|
],
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "multi",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.3.1",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "PBFA97CFB590B2093"
|
|
},
|
|
"editorMode": "code",
|
|
"expr": "nvidia_tesla_t4_DCGM_FI_DEV_SM_CLOCK* 1000000",
|
|
"format": "time_series",
|
|
"interval": "",
|
|
"intervalFactor": 1,
|
|
"legendFormat": "GPU {{gpu}}",
|
|
"range": true,
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "GPU SM Clocks",
|
|
"type": "timeseries"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "PBFA97CFB590B2093"
|
|
},
|
|
"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": "bytes"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 24
|
|
},
|
|
"id": 19,
|
|
"options": {
|
|
"legend": {
|
|
"calcs": [],
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"hideZeros": false,
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"pluginVersion": "12.3.1",
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "PBFA97CFB590B2093"
|
|
},
|
|
"editorMode": "code",
|
|
"expr": "sum by (namespace) (gpu_pod_memory_used_bytes)",
|
|
"instant": false,
|
|
"legendFormat": "{{namespace}}",
|
|
"range": true,
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"title": "GPU Memory per Application",
|
|
"type": "timeseries"
|
|
}
|
|
],
|
|
"preload": false,
|
|
"refresh": "auto",
|
|
"schemaVersion": 42,
|
|
"tags": [],
|
|
"templating": {
|
|
"list": []
|
|
},
|
|
"time": {
|
|
"from": "now-12h",
|
|
"to": "now"
|
|
},
|
|
"timepicker": {},
|
|
"timezone": "",
|
|
"title": "NVIDIA DCGM Exporter Dashboard",
|
|
"uid": "Oxed_c6Wz",
|
|
"version": 9
|
|
}
|