Oliver/video-accessibility
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

cost: enable CPU throttling for Whisper and FFmpeg Cloud Run services

Browse source 
Changed cpu-throttling from "false" to "true" for both services.
This reduces costs when instances are idle between requests:
- Idle CPU billed at ~10% of active rate instead of 100%
- Instances still scale to zero after ~15 min of no traffic

Trade-off: Slightly slower response when resuming from throttled state,
but startup-cpu-boost is still enabled to mitigate cold starts.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
michael 2026-01-02 17:22:14 -06:00
parent e2302d497d
commit 593d3bf346
2 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
infra/cloud-run/ffmpeg-http-service.yaml
View file

@ -29,7 +29,7 @@ spec:
# Cloud Run Gen2 features
run.googleapis.com/execution-environment: gen2 # Required for 8 vCPU
run.googleapis.com/cpu-throttling: "false" # Always-on CPU during requests
run.googleapis.com/cpu-throttling: "true" # Throttle CPU when idle to reduce costs
run.googleapis.com/startup-cpu-boost: "true" # Faster cold start
spec:

2
infra/cloud-run/whisper-http-service.yaml
View file

@ -28,7 +28,7 @@ spec:
# Cloud Run Gen2 features
run.googleapis.com/execution-environment: gen2 # Required for 8 vCPU
run.googleapis.com/cpu-throttling: "false" # Always-on CPU during requests
run.googleapis.com/cpu-throttling: "true" # Throttle CPU when idle to reduce costs
run.googleapis.com/startup-cpu-boost: "true" # Faster cold start
spec: