[Doc] Add troubleshooting section to k8s deployment

[annapendleton]

Essential Elements of an Effective PR Description Checklist

Purpose

Add clear documentation around how to troubleshoot k8s manifest that hits errors with startup or readiness probes that caused issues for starting up gemma-3-1b model with vllm, ref: #17386

(Optional) Documentation Update

Add section in k8s deployment guide for troubleshooting. Add item related to startup and readiness probes.

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

[gemini-code-assist]

Hello @annapendleton, 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!

Summary of Changes

Hello! Gemini here, providing a summary of this pull request to help everyone get up to speed quickly.

This PR, authored by @annapendleton, aims to enhance the vLLM documentation, specifically the guide for deploying vLLM on Kubernetes. The core intent is to add a dedicated troubleshooting section to address common issues encountered during deployment, particularly those related to startup and readiness probe failures. This is motivated by a specific issue (referenced as vllm-project/vllm/issues/17386) where users faced problems starting models like gemma-3-1b due to probe misconfigurations.

The changes primarily involve adding new content to the docs/deployment/k8s.md file to provide clear guidance on diagnosing and mitigating probe failures caused by insufficient failureThreshold values in the Kubernetes manifest.

Highlights

• Documentation Enhancement: Adds a new 'Troubleshooting' section to the Kubernetes deployment guide (docs/deployment/k8s.md).
• Probe Failure Guidance: Provides specific troubleshooting steps for startup or readiness probe failures where the container log shows 'KeyboardInterrupt: terminated', explaining that this is often due to a low failureThreshold and suggesting how to fix it.

Changelog

• docs/deployment/k8s.md
  • Added a new top-level link to a 'Troubleshooting' section in the document's outline.
  • Added a sub-link under 'Troubleshooting' specifically for 'Startup Probe or Readiness Probe Failure, container log contains "KeyboardInterrupt: terminated"'.
  • Changed existing list markers from * to - in the initial outline.
  • Added a new '## Troubleshooting' section near the end of the document.
  • Added a '### Startup Probe or Readiness Probe Failure, container log contains "KeyboardInterrupt: terminated"' subsection within the new troubleshooting section.
  • Provided explanation and mitigation steps for the described probe failure scenario, including identifying symptoms like 'KeyboardInterrupt: terminated' in logs and suggesting increasing the failureThreshold.

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 is currently in preview and 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 to provide feedback.

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 adds a very useful troubleshooting section to the Kubernetes deployment documentation, specifically addressing startup/readiness probe failures leading to KeyboardInterrupt. The explanation is clear, and the suggested mitigation is practical. The changes improve the documentation's helpfulness for users encountering this common issue.

No explicit style guide was provided for Markdown. The review was conducted based on general Markdown best practices, such as consistent list markers and appropriate heading levels. The changes in this PR, including the update of list markers from * to - for consistency, align well with these practices.

Summary of Findings

• Minor Typo: A minor typo (a double space) was observed in docs/deployment/k8s.md on line 366 in the new content: "...by removing the probes...". Due to the review settings to only comment on medium or higher severity issues, a formal review comment was not created for this low-severity typo.

Merge Readiness

The changes are well-implemented and significantly improve the Kubernetes deployment documentation by adding a relevant troubleshooting tip. The PR appears to be in good shape and ready for merging. As a language model, I am not authorized to approve pull requests; this decision should be made by the designated reviewers.

[yewentao256]

Looks good to me

[annapendleton]

@yewentao256 it looks like this PR is stuck on buildkite/ci/pr status being reported, is there a way to retrigger this / see if it's stuck somewhere?

[annapendleton]

@hmellor @yewentao256 any chance we can retry the buildkite/ci/pr? I can't see any logs to debug why this is failing.