fix false negative healthy status check for turbomind #4745
Open
irexyc wants to merge 2 commits into
Open
Conversation
irexyc
changed the title
Contributor
There was a problem hiding this comment.
Pull request overview
This PR adjusts TurboMind’s async health probe implementation to reduce false-negative “unhealthy” reports caused by event-loop/default threadpool contention (notably when multimodal workloads enqueue many background tasks).
Changes:
- Introduces a (dedicated)
ThreadPoolExecutorintended for health checks. - Switches
get_health_status()fromasyncio.to_thread(...)toloop.run_in_executor(...)to avoid blocking/queueing behind the default executor.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| self._create_engine() | ||
|
|
||
| self.session_len = _engine_config.session_len | ||
| self.health_executor = ThreadPoolExecutor(max_workers=1) if engine_config.enable_metrics else None |
| self._create_engine() | ||
|
|
||
| self.session_len = _engine_config.session_len | ||
| self.health_executor = ThreadPoolExecutor(max_workers=1) if engine_config.enable_metrics else None |
Comment on lines
+423
to
+426
| # MultimodalProcessor may submit a large number of tasks to the default thread pool, causing | ||
| # the _get_health_status task to be selected after the DEFAULT_PROBE_TIMEOUT has already elapsed. | ||
| loop = asyncio.get_running_loop() | ||
| return await loop.run_in_executor(self.health_executor, self._get_health_status) |
Comment on lines
175
to
+176
| self.session_len = _engine_config.session_len | ||
| self.health_executor = ThreadPoolExecutor(max_workers=1) |
Comment on lines
+425
to
+426
| loop = asyncio.get_running_loop() | ||
| return await loop.run_in_executor(self.health_executor, self._get_health_status) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily receiving feedbacks. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.
Motivation
Please describe the motivation of this PR and the goal you want to achieve through this PR.
Modification
Please briefly describe what modification is made in this PR.
BC-breaking (Optional)
Does the modification introduce changes that break the backward-compatibility of the downstream repositories?
If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.
Use cases (Optional)
If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.
Checklist