vrr/cozystack
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix(efficiency): drop namespace filter on cluster-level throttle metrics

Browse source 
Signed-off-by: Arsolitt <arsolitt@gmail.com>
This commit is contained in:
Arsolitt 2026-04-19 10:59:42 +03:00
parent 165e175d70
commit 549b341675
No known key found for this signature in database
GPG key ID: 4D8302CE6A9247C4
1 changed files with 4 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

8
dashboards/gpu/gpu-efficiency.json
View file

@ -166,12 +166,12 @@
"id": 4,
"targets": [
{
"expr": "avg(gpu:power_throttle_fraction:rate5m{namespace=~\"$namespace\"})",
"expr": "avg(gpu:power_throttle_fraction:rate5m)",
"refId": "A"
}
],
"title": "Avg Power Throttling",
"description": "Fraction of time GPUs hit the TDP cap and lose performance. \u003e5% means tenants underutilize billed FLOPS.",
"description": "Fraction of time GPUs hit the TDP cap and lose performance. \u003e5% means tenants underutilize billed FLOPS. Cluster-wide — rule aggregates by (Hostname, gpu, UUID) and drops namespace label.",
"transparent": false,
"datasource": {
"type": "prometheus",
@ -658,7 +658,7 @@
}
],
"title": "Power throttle fraction per GPU",
"description": "Fraction of time the GPU was power-throttled. 1.0 = always throttled.",
"description": "Fraction of time the GPU was power-throttled. 1.0 = always throttled. Cluster-wide — rule aggregates by (Hostname, gpu, UUID) and drops namespace label.",
"transparent": false,
"datasource": {
"type": "prometheus",
@ -729,7 +729,7 @@
}
],
"title": "Thermal throttle fraction per GPU",
"description": "Fraction of time the GPU was thermal-throttled.",
"description": "Fraction of time the GPU was thermal-throttled. Cluster-wide — rule aggregates by (Hostname, gpu, UUID) and drops namespace label.",
"transparent": false,
"datasource": {
"type": "prometheus",