[BugFix] resource_manager_v1 lock PD

[ST-XX]

Motivation

💡 If this PR is a Cherry Pick, the PR title needs to follow the format by adding the [Cherry-Pick] label at the very beginning and appending the original PR ID at the end. For example, [Cherry-Pick][CI] Add check trigger and logic(#5191)

💡 如若此PR是Cherry Pick，PR标题需遵循格式，在最开始加上[Cherry-Pick]标签，以及最后面加上原PR ID，例如[Cherry-Pick][CI] Add check trigger and logic(#5191)

Modifications

PD分离模式，resource_manager_v1 部分相关函数未添加锁

Usage or Command

PD

Accuracy Tests

测试功能正常
bash -x start_v0_tp1.sh
bash start_v1_tp1_vl.sh

Checklist

• Add at least a tag in the PR title.
  • Tag list: [[FDConfig],[APIServer],[Engine], [Scheduler], [PD Disaggregation], [Executor], [Graph Optimization], [Speculative Decoding], [RL], [Models], [Quantization], [Loader], [OP], [KVCache], [DataProcessor], [BugFix], [Docs], [CI], [Optimization], [Feature], [Benchmark], [Others], [XPU], [HPU], [GCU], [DCU], [Iluvatar], [Metax]]
  • You can add new tags based on the PR content, but the semantics must be clear.
• Format your code, run pre-commit before commit.
• Add unit tests. Please write the reason in this PR if no unit tests.
• Provide accuracy results.
• If the current PR is submitting to the release branch, make sure the PR has been submitted to the develop branch, then cherry-pick it to the release branch with the [Cherry-Pick] PR tag.

[paddle-bot]

Thanks for your contribution!

[codecov-commenter]

Codecov Report

❌ Patch coverage is 0% with 20 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (develop@78adf83). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
fastdeploy/engine/sched/resource_manager_v1.py	0.00%	20 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #5616   +/-   ##
==========================================
  Coverage           ?   66.99%           
==========================================
  Files              ?      347           
  Lines              ?    44454           
  Branches           ?     6831           
==========================================
  Hits               ?    29781           
  Misses             ?    12470           
  Partials           ?     2203           

Flag	Coverage Δ
GPU	66.99% <0.00%> (?)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[juncaipeng]

LGTM

[Copilot]

Pull request overview

This PR addresses a critical thread-safety issue in the resource_manager_v1 module for PD (Prefill-Decode) disaggregation mode. The fix adds missing lock protection to two functions that manage prefilled requests in the decode instance.

Key changes:

• Added lock protection to has_resource_for_prefilled_req() method
• Added lock protection to add_prefilled_request() method with proper early return handling

[Copilot]

Using explicit lock.acquire()/lock.release() pattern is error-prone. If an exception occurs between lines 1120-1142 (before the lock.release() at line 1142), the lock will remain held indefinitely, causing a deadlock. Use a context manager pattern (with self.lock:) instead, as done in has_resource_for_prefilled_req(), to ensure the lock is always released even in exception scenarios.