Skip to content

Tiny add stuck simulation#15613

Merged
fzyzcjy merged 67 commits intosgl-project:mainfrom
fzyzcjy:feat/test_stuck
Dec 22, 2025
Merged

Tiny add stuck simulation#15613
fzyzcjy merged 67 commits intosgl-project:mainfrom
fzyzcjy:feat/test_stuck

Conversation

@fzyzcjy
Copy link
Copy Markdown
Collaborator

@fzyzcjy fzyzcjy commented Dec 22, 2025

Motivation

Modifications

Accuracy Tests

Benchmarking and Profiling

Checklist

@gemini-code-assist
Copy link
Copy Markdown
Contributor

gemini-code-assist Bot commented Dec 22, 2025

Summary of Changes

Hello @fzyzcjy, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly improves the robustness and debuggability of the SGLang system by introducing a comprehensive watchdog mechanism. It allows for the detection of unresponsive managers, provides tools to simulate these stuck states for testing, and refactors existing watchdog logic into a more unified and flexible utility. This change aims to prevent silent failures and aid in diagnosing performance bottlenecks or deadlocks.

Highlights

  • New Watchdog Utility: Introduced a new Watchdog utility to monitor the activity of various managers (DataParallelController, DetokenizerManager, TokenizerManager) and detect if they become stuck. This enhances system reliability by identifying unresponsive components.
  • Refactored Scheduler Watchdog: The existing SchedulerWatchdog has been refactored into a more generic WatchdogRaw class and a create_scheduler_watchdog function, allowing for consistent watchdog implementation across different parts of the system.
  • Stuck Simulation for Testing: Added new environment variables (SGLANG_TEST_STUCK_DETOKENIZER, SGLANG_TEST_STUCK_DP_CONTROLLER, SGLANG_TEST_STUCK_TOKENIZER) and corresponding logic to deliberately simulate stuck conditions in managers, which is crucial for testing the watchdog's effectiveness.
  • Watchdog Disablement Context: Implemented a context manager (watchdog.disable()) to temporarily pause watchdog monitoring during blocking operations (e.g., receiving objects from a queue), preventing false positives.
  • New Test Cases: Added test_soft_watchdog.py with specific test cases to validate the soft watchdog functionality for the detokenizer and tokenizer managers, ensuring the new mechanism works as expected.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

gemini-code-assist[bot]
gemini-code-assist Bot reviewed Dec 22, 2025
View reviewed changes
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

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

Code Review

This pull request introduces a feature to simulate stuck components for testing watchdog functionality. This is achieved by refactoring the watchdog logic into a more generic and reusable Watchdog class in a new watchdog.py file. The new watchdog is then integrated into TokenizerManager, DetokenizerManager, and DataParallelController. I've identified a potential race condition in the new Watchdog implementation and provided a suggestion to address it. Overall, this is a valuable addition for improving the robustness of the system.

Comment thread python/sglang/srt/utils/watchdog.py
@fzyzcjy
Copy link
Copy Markdown
Collaborator Author

fzyzcjy commented Dec 22, 2025

/tag-and-rerun-ci

@fzyzcjy fzyzcjy removed the run-ci label Dec 22, 2025
@fzyzcjy fzyzcjy merged commit d5431ff into sgl-project:main Dec 22, 2025
18 of 23 checks passed
Liwansi added a commit to iforgetmyname/sglang that referenced this pull request Dec 23, 2025
@Liwansi
Merge branch 'main' of https://github.com/sgl-project/sglang into qwe…
d2ed9e6 
…n_eagle3_dp

* 'main' of https://github.com/sgl-project/sglang: (208 commits)
  MoE: Skip SiLU/GELU activation for masked experts (sgl-project#15539)
  [GLM-ASR] GLM-ASR Support  (sgl-project#15570)
  Improve engine customization interface (sgl-project#15635)
  chore: bump sgl-kernel version to 0.3.20 (sgl-project#15590)
  bugfix[schedule]: Refactor sort method and add related UT (sgl-project#13576)
  Adjust wrong `mtp` meaning introduce by mimo (sgl-project#15632)
  Tiny add back missing router per attempt response metric (sgl-project#15621)
  Fix router gRPC mode launch error caused by async loading (sgl-project#15368)
  [model-gateway] return 503 when all workers are circuit-broken (sgl-project#15611)
  [Diffusion] Support peak memory record in offline generate and serving (sgl-project#15610)
  [VLM] Tiny: Unify VLM environment variables (sgl-project#15572)
  [diffusion] chore: remove default post-denoising dit offload in local mode (sgl-project#15573)
  Tiny enable soft watchdog in CI for stuck without logs (sgl-project#15616)
  Tiny add stuck simulation (sgl-project#15613)
  Support soft watchdog for tokenizer/detokenizer/dp-controller processes (sgl-project#15607)
  Tiny avoid EnvField misuse (sgl-project#15612)
  add decode round robin policy (sgl-project#15164)
  Add glm-4.6-fp8 with/without mtp in nightly ci (sgl-project#15566)
  Adapt fixture-kit to gsm8k mixin (sgl-project#15599)
  [model-gateway] add retry support to OpenAI router chat endpoint (sgl-project#15589)
  ...
jiaming1130 pushed a commit to zhuyijie88/sglang that referenced this pull request Dec 25, 2025
@fzyzcjy @jiaming1130
Tiny add stuck simulation (sgl-project#15613)
c326383
YChange01 pushed a commit to YChange01/sglang that referenced this pull request Jan 13, 2026
@fzyzcjy @YChange01
Tiny add stuck simulation (sgl-project#15613)
71dfe06
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@merrymercy merrymercy Awaiting requested review from merrymercy merrymercy is a code owner

@Ying1123 Ying1123 Awaiting requested review from Ying1123 Ying1123 is a code owner

@hnyls2002 hnyls2002 Awaiting requested review from hnyls2002 hnyls2002 is a code owner

@xiezhq-hermann xiezhq-hermann Awaiting requested review from xiezhq-hermann xiezhq-hermann is a code owner

1 more reviewer

@gemini-code-assist gemini-code-assist[bot] gemini-code-assist[bot] left review comments

Reviewers whose approvals may not affect merge requirements

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@fzyzcjy