vllm-project / vllm-project/production-stack

Dynamic config reload gets stuck after invalid JSON; does not recover after fixing

Open
#659 4 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

bug
Dominant language
Python
Stars
2.6k
Forks
503
Avg merge
4d 17h
Merged PRs (30d)
8

Description

Describe the bug

When the configuration is updated dynamically with non-parsable JSON, the service enters a stuck/error state and does not recover even after the config is corrected to valid JSON. A manual restart is required.

To Reproduce

forget a , in your dynamic json (not in start)

Expected behavior

No response

Additional context

No response

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the dynamic configuration reload with malformed JSON, then correct the configuration and observe why recovery does not occur. Trace the reload and error-handling entry points to identify where the service remains stuck. Done means a corrected configuration is applied without requiring a manual restart, with a regression test covering the invalid-then-valid sequence.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
backend
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.