fix(monitoring): prevent many-to-many match in util-per-watt recording rule
Address review feedback from coderabbitai on packages/system/monitoring-agents/alerts/gpu-recording.rules.yaml:119 Signed-off-by: Arsolitt <arsolitt@gmail.com>
This commit is contained in:
parent
5718740ae3
commit
aba5ae3fcd
1 changed files with 8 additions and 6 deletions
|
|
@ -109,13 +109,15 @@ spec:
|
|||
# to GPU-identifying labels.
|
||||
- record: gpu:util_per_watt:avg5m
|
||||
expr: |
|
||||
avg by (Hostname, gpu, UUID) (
|
||||
max by (Hostname, gpu, UUID) (
|
||||
avg_over_time(DCGM_FI_DEV_GPU_UTIL[5m])
|
||||
/ on (Hostname, gpu, UUID)
|
||||
clamp_min(
|
||||
avg_over_time(DCGM_FI_DEV_POWER_USAGE[5m]),
|
||||
1
|
||||
)
|
||||
)
|
||||
/ on (Hostname, gpu, UUID)
|
||||
clamp_min(
|
||||
max by (Hostname, gpu, UUID) (
|
||||
avg_over_time(DCGM_FI_DEV_POWER_USAGE[5m])
|
||||
),
|
||||
1
|
||||
)
|
||||
|
||||
# Fraction of time power-throttled (TDP cap) — 1.0 = fully throttled.
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue