[Bugfix] Increase liveness failure threshold for crd

[zerofishnoodles]

Increase liveness failure threshold for crd to solve that when the model is too big, the liveness probe fail.

FIX #xxxx (link existing issues this PR will resolve)

BEFORE SUBMITTING, PLEASE READ THE CHECKLIST BELOW AND FILL IN THE DESCRIPTION ABOVE

---

• Make sure the code changes pass the pre-commit checks.
• Sign-off your commit by using -s when doing git commit
• Try to classify PRs for easy understanding of the type of changes, such as [Bugfix], [Feat], and [CI].

Detailed Checklist (Click to Expand)

Thank you for your contribution to production-stack! Before submitting the pull request, please ensure the PR meets the following criteria. This helps us maintain the code quality and improve the efficiency of the review process.

PR Title and Classification

Please try to classify PRs for easy understanding of the type of changes. The PR title is prefixed appropriately to indicate the type of change. Please use one of the following:

• [Bugfix] for bug fixes.
• [CI/Build] for build or continuous integration improvements.
• [Doc] for documentation fixes and improvements.
• [Feat] for new features in the cluster (e.g., autoscaling, disaggregated prefill, etc.).
• [Router] for changes to the vllm_router (e.g., routing algorithm, router observability, etc.).
• [Misc] for PRs that do not fit the above categories. Please use this sparingly.

Note: If the PR spans more than one category, please include all relevant prefixes.

Code Quality

The PR need to meet the following code quality standards:

• Pass all linter checks. Please use pre-commit to format your code. See README.md for installation.
• The code need to be well-documented to ensure future contributors can easily understand the code.
• Please include sufficient tests to ensure the change is stay correct and robust. This includes both unit tests and integration tests.

DCO and Signed-off-by

When contributing changes to this project, you must agree to the DCO. Commits must include a Signed-off-by: header which certifies agreement with the terms of the DCO.

Using -s with git commit will automatically add this header.

What to Expect for the Reviews

We aim to address all PRs in a timely manner. If no one reviews your PR within 5 days, please @-mention one of YuhanLiu11
, Shaoting-Feng or ApostaC.

[gemini-code-assist]

Summary of Changes

Hello @zerofishnoodles, 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 addresses an issue where the liveness probe for the CRD (Custom Resource Definition) was failing when large models were in use. The change modifies a specific configuration parameter to provide more tolerance for startup or processing delays, ensuring the application remains stable and is not prematurely restarted due to transient unresponsiveness caused by model loading.

Highlights

• Liveness Probe Configuration: The FailureThreshold for the liveness probe in operator/internal/controller/vllmruntime_controller.go has been increased from 10 to 100. This change aims to prevent liveness probe failures when dealing with large models, allowing more time for the application to become responsive.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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]

Code Review

This pull request increases the liveness probe failure threshold from 10 to 100 to prevent pod restarts when loading large models. While this addresses the immediate problem, I've raised a concern that such a high threshold could mask real failures and delay recovery. I've suggested alternative approaches, such as increasing the initialDelaySeconds for long startups, and making the probe settings configurable in the CRD for a more flexible long-term solution.

[Shaoting-Feng]

LGTM. But I’m concerned that default.yaml might need frequent changes. Should we delete it from the codebase? cc @royyhuang

[TheCodeWrangler]

If this is actually just trying to resolve the model load time you should only need to do a startup probe and an initial delay seconds.

The gemini warnings on this are quite good. Setting the liveness probe tolerance this high is similar to not having a liveness probe.

[zerofishnoodles]

If this is actually just trying to resolve the model load time you should only need to do a startup probe and an initial delay seconds.

The gemini warnings on this are quite good. Setting the liveness probe tolerance this high is similar to not having a liveness probe.

@TheCodeWrangler This was trying to resolve the varied model load time since we encounter that for some model it only need several minutes, however for big models like qwen-480b and oss-120b, it takes around 30 minutes for model to load.
However, I do think a startup probe would be better.

[zerofishnoodles]

@Shaoting-Feng Could you please take a look at it?

[Shaoting-Feng]

LGTM. But I’m concerned that default.yaml might need frequent changes. Should we delete it from the codebase? I am not familiar with CRD so cc @YuhanLiu11