Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

use package power metrics #24

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 22 additions & 4 deletions grafana/dashboard_gpu.json
Original file line number Diff line number Diff line change
Expand Up @@ -154,7 +154,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"description": "GPU current power usage",
"description": "GPU package power usage",
"fieldConfig": {
"defaults": {
"color": {
Expand Down Expand Up @@ -210,14 +210,32 @@
"disableTextWrap": false,
"editorMode": "builder",
"exemplar": false,
"expr": "gpu_power_usage{gpu_uuid=\"$g_gpu_uuid\", hostname=\"$g_hostname\"}",
"expr": "gpu_average_package_power{gpu_uuid=\"$g_gpu_uuid\", hostname=\"$g_hostname\"}",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "{{hostname}}[{{gpu_id}}]",
"range": true,
"refId": "A",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "gpu_package_power{gpu_uuid=\"$g_gpu_uuid\", hostname=\"$g_hostname\"}",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "{{hostname}}[{{gpu_id}}]",
"range": true,
"refId": "B",
"useBackend": false
}
],
"title": "GPU Power Usage",
Expand Down Expand Up @@ -1788,7 +1806,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"definition": "label_values(gpu_id)",
"definition": "label_values({hostname=\"$g_hostname\"},gpu_id)",
"hide": 0,
"includeAll": false,
"label": "GPU ID",
Expand All @@ -1797,7 +1815,7 @@
"options": [],
"query": {
"qryType": 1,
"query": "label_values(gpu_id)",
"query": "label_values({hostname=\"$g_hostname\"},gpu_id)",
"refId": "PrometheusVariableQueryEditor-VariableQuery"
},
"refresh": 2,
Expand Down
69 changes: 63 additions & 6 deletions grafana/dashboard_job.json
Original file line number Diff line number Diff line change
Expand Up @@ -946,7 +946,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"description": "Latest total power usage, in Watts",
"description": "Total package power usage, in Watts",
"fieldConfig": {
"defaults": {
"color": {
Expand Down Expand Up @@ -1000,11 +1000,12 @@
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "sum(gpu_power_usage{job_id!=\"\", job_id=\"$g_job_id\"})",
"expr": "sum(gpu_average_package_power{job_id!=\"\", job_id=\"$g_job_id\"})",
"fullMetaSearch": false,
"hide": true,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "Power Usage",
"legendFormat": "Average Job Package Power Usage",
"range": true,
"refId": "A",
"useBackend": false
Expand All @@ -1016,15 +1017,69 @@
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "sum(gpu_power_usage{pod!=\"\", pod=\"$g_pod\"})",
"expr": "sum(gpu_package_power{job_id!=\"\", job_id=\"$g_job_id\"})",
"fullMetaSearch": false,
"hide": false,
"hide": true,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "Power Usage",
"legendFormat": "Job Package Power Usage",
"range": true,
"refId": "B",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "sum(gpu_average_package_power{pod!=\"\", pod=\"$g_pod\"})",
"fullMetaSearch": false,
"hide": true,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "Average Pod Package Power Usage",
"range": true,
"refId": "C",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "sum(gpu_package_power{pod!=\"\", pod=\"$g_pod\"})",
"fullMetaSearch": false,
"hide": true,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "Pod Package Power Usage",
"range": true,
"refId": "D",
"useBackend": false
},
{
"datasource": {
"type": "__expr__",
"uid": "${DS_EXPRESSION}"
},
"expression": "$A+$B",
"hide": false,
"refId": "Total Job Package Power Usage",
"type": "math"
},
{
"datasource": {
"type": "__expr__",
"uid": "${DS_EXPRESSION}"
},
"expression": "$C+$D",
"hide": false,
"refId": "Total Pod Package Power Usage",
"type": "math"
}
],
"title": "Total Power Usage",
Expand Down Expand Up @@ -2503,6 +2558,7 @@
"templating": {
"list": [
{
"allValue": "+",
"current": {},
"datasource": {
"type": "prometheus",
Expand All @@ -2527,6 +2583,7 @@
"type": "query"
},
{
"allValue": "+",
"current": {},
"datasource": {
"type": "prometheus",
Expand Down
34 changes: 31 additions & 3 deletions grafana/dashboard_node.json
Original file line number Diff line number Diff line change
Expand Up @@ -774,7 +774,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"description": "Total power usage, in Watts",
"description": "Total package power usage, in Watts",
"fieldConfig": {
"defaults": {
"color": {
Expand Down Expand Up @@ -828,13 +828,41 @@
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "sum(gpu_power_usage{hostname=\"$g_hostname\"})",
"expr": "sum(gpu_average_package_power{hostname=\"$g_hostname\"})",
"fullMetaSearch": false,
"hide": true,
"includeNullMetadata": true,
"legendFormat": "Power Usage (W)",
"legendFormat": "Average Package Power Usage",
"range": true,
"refId": "A",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "sum(gpu_package_power{hostname=\"$g_hostname\"})",
"fullMetaSearch": false,
"hide": true,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "Package Power Usage",
"range": true,
"refId": "B",
"useBackend": false
},
{
"datasource": {
"type": "__expr__",
"uid": "${DS_EXPRESSION}"
},
"expression": "$A+$B",
"hide": false,
"refId": "Total Package Power Usage",
"type": "math"
}
],
"title": "Total Power Usage",
Expand Down
32 changes: 30 additions & 2 deletions grafana/dashboard_overview.json
Original file line number Diff line number Diff line change
Expand Up @@ -307,14 +307,42 @@
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "sum(gpu_power_usage)",
"expr": "sum(gpu_average_package_power)",
"fullMetaSearch": false,
"hide": true,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "Power Usage (W)",
"legendFormat": "Average Package Power (W)",
"range": true,
"refId": "A",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "sum(gpu_package_power)",
"fullMetaSearch": false,
"hide": true,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "Current Package Power (W)",
"range": true,
"refId": "B",
"useBackend": false
},
{
"datasource": {
"type": "__expr__",
"uid": "${DS_EXPRESSION}"
},
"expression": "$A+$B",
"hide": false,
"refId": "Total Package Power Usage",
"type": "math"
}
],
"title": "Total Power Usage",
Expand Down