Check failed put task count and record metrics by maobaolong · Pull Request #2439 · LMCache/LMCache

maobaolong · 2026-01-19T09:38:14Z

What this PR does / why we need it:

Special notes for your reviewers:

If applicable:

this PR contains user facing changes - docs added
this PR contains unit tests

gemini-code-assist · 2026-01-19T09:38:29Z

Summary of Changes

Hello @maobaolong, 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 enhances the monitoring capabilities of the LMCache remote backend by introducing a new metric to specifically track failures during put operations. It also refines the existing get blocking failed count metric, transitioning it to a cumulative model. This change allows for more consistent and accurate tracking of read failures over time, with health checks now intelligently calculating interval-specific failure rates from this cumulative data, providing a clearer picture of backend health.

Highlights

New Metric for Put Failures: Introduced a new Prometheus metric, lmcache:put_failed_count, to track the number of failed put operations in the remote backend.
Refactored Get Blocking Failed Count: The get blocking failed count metric has been changed from an interval-clearing counter to a cumulative counter. Health checks now calculate interval failures by comparing the current cumulative count with the last observed count.
Updated Health Check Logic: The RemoteBackendHealthCheck now maintains a _last_get_blocking_failed_count to correctly determine the number of get blocking failures within a specific interval without resetting the underlying metric.

🧠 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.

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 introduces metrics for failed put tasks and refactors the existing metric for failed get tasks. A new counter put_failed_count is added to RemoteBackend and exposed via Prometheus. The get_blocking_failed_count is now a cumulative counter, and the health check logic has been updated to calculate the delta between checks, which is a good improvement.

My main feedback is regarding thread safety. The new and existing counters are incremented without a lock, which can lead to race conditions and inaccurate metrics in a multi-threaded environment. I've added suggestions to use the existing self.lock to protect these counter updates.

ApostaC

Otherwise LGTM!

Signed-off-by: baoloongmao <baoloongmao@tencent.com>

chunxiaozheng

lgtm

* Check failed put task count and record metrics Signed-off-by: baoloongmao <baoloongmao@tencent.com> * update naming Signed-off-by: baoloongmao <baoloongmao@tencent.com> * Address comment Signed-off-by: baoloongmao <baoloongmao@tencent.com> --------- Signed-off-by: baoloongmao <baoloongmao@tencent.com> Signed-off-by: DongDongJu <commisori28@gmail.com>

* Check failed put task count and record metrics Signed-off-by: baoloongmao <baoloongmao@tencent.com> * update naming Signed-off-by: baoloongmao <baoloongmao@tencent.com> * Address comment Signed-off-by: baoloongmao <baoloongmao@tencent.com> --------- Signed-off-by: baoloongmao <baoloongmao@tencent.com>

* Check failed put task count and record metrics Signed-off-by: baoloongmao <baoloongmao@tencent.com> * update naming Signed-off-by: baoloongmao <baoloongmao@tencent.com> * Address comment Signed-off-by: baoloongmao <baoloongmao@tencent.com> --------- Signed-off-by: baoloongmao <baoloongmao@tencent.com> Signed-off-by: shaoxiawjc <wjc2800@163.com>

gemini-code-assist Bot reviewed Jan 19, 2026

View reviewed changes

Comment thread lmcache/v1/storage_backend/remote_backend.py

Comment thread lmcache/v1/storage_backend/remote_backend.py

Comment thread lmcache/v1/storage_backend/remote_backend.py

maobaolong force-pushed the robustImprove2 branch 2 times, most recently from 95a4b94 to dfef213 Compare January 25, 2026 01:54

ApostaC approved these changes Jan 26, 2026

View reviewed changes

Comment thread lmcache/v1/storage_backend/remote_backend.py Outdated

maobaolong added 3 commits February 19, 2026 10:57

Check failed put task count and record metrics

19c183d

Signed-off-by: baoloongmao <baoloongmao@tencent.com>

update naming

34f903f

Signed-off-by: baoloongmao <baoloongmao@tencent.com>

Address comment

5894794

Signed-off-by: baoloongmao <baoloongmao@tencent.com>

maobaolong force-pushed the robustImprove2 branch from d752ec6 to 5894794 Compare February 19, 2026 03:04

maobaolong added the full Run comprehensive tests on this PR label Feb 19, 2026

chunxiaozheng approved these changes Feb 19, 2026

View reviewed changes

chunxiaozheng merged commit 379b6be into LMCache:dev Feb 19, 2026
32 of 33 checks passed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Check failed put task count and record metrics#2439

Check failed put task count and record metrics#2439
chunxiaozheng merged 3 commits intoLMCache:devfrom
maobaolong:robustImprove2

maobaolong commented Jan 19, 2026

Uh oh!

gemini-code-assist Bot commented Jan 19, 2026

Uh oh!

gemini-code-assist Bot left a comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

ApostaC left a comment

Uh oh!

Uh oh!

chunxiaozheng left a comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

maobaolong commented Jan 19, 2026

Uh oh!

gemini-code-assist Bot commented Jan 19, 2026

Summary of Changes

Highlights

Footnotes

Uh oh!

gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

Uh oh!

Uh oh!

Uh oh!

ApostaC left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

chunxiaozheng left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants