Skip to content

docs: Document jobs-funneled-to-one-worker fix (SDK 1.10.1) #698

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.

Sign up for GitHub

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

Open
promptless wants to merge 1 commit into
base: main
Choose a base branch
from
+14 −0
Open

docs: Document jobs-funneled-to-one-worker fix (SDK 1.10.1) #698

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
14 changes: 14 additions & 0 deletions serverless/troubleshooting.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,20 @@ If jobs remain `IN_QUEUE` for extended periods:
- **Workers throttled**: Your endpoint may be hitting rate limits. Check the Workers tab for throttled workers.
- **Cold start delays**: First requests after idle periods require worker initialization. Consider increasing `min_workers` or enabling [FlashBoot](/serverless/endpoints/endpoint-configurations#flashboot).

### Jobs funneled to a single worker

If your endpoint has multiple workers but nearly all jobs run on one worker while the others sit idle, and jobs stay `IN_QUEUE` even though workers are available, you may be running an affected version of the Runpod Python SDK.

Versions 1.9.1 through 1.10.0 could corrupt per-worker job tracking on endpoints that use a network volume, causing most workers to stop pulling new jobs. This most often appeared on network volume endpoints such as ComfyUI workers.

@promptless promptless Bot Jul 8, 2026

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sourced the affected version range (1.9.1–1.10.0), the network-volume root cause, and the 1.10.1 fix from PR #517, which reverted JobsProgress in worker_state.py from a shared pickle file at os.getcwd()/.runpod_jobs.pkl back to an in-memory set. Network volumes made os.getcwd() a shared mount across workers, corrupting per-worker occupancy so workers stopped pulling jobs — the ComfyUI-on-network-volume symptom in the linked issue #432.

Source: runpod/runpod-python#517


To fix this, upgrade the Runpod Python SDK to version 1.10.1 or later:

```bash
pip install --upgrade "runpod>=1.10.1"
```

Then rebuild and redeploy your worker image so the fix takes effect. No configuration or code changes are required.

### Jobs timing out

| Cause | Solution |
Expand Down
Loading