[Feature] Tracing: Fine-Grained Tracing for Request Latency Part1

[xiaolei373]

Motivation

FastDeploy currently lacks request-level observability mechanisms. Although performance analysis can be performed using profiling tools, they are not suitable for long-term, stable monitoring and introduce significant performance overhead. To help developers diagnose performance bottlenecks and troubleshoot issues more effectively, we have introduced a new request-level end-to-end tracing capability.

Modifications

This update introduces a new Trace utility class and provides a Docker Compose setup for launching Jaeger to visualize tracing data. To reduce the review burden, the feature will be delivered and refined across multiple incremental PRs.

Usage or Command

Accuracy Tests

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 70.17544% with 136 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (develop@c3a8a16). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
fastdeploy/metrics/trace.py	74.04%	71 Missing and 31 partials ⚠️
fastdeploy/engine/common_engine.py	6.25%	15 Missing ⚠️
fastdeploy/entrypoints/openai/api_server.py	40.00%	6 Missing ⚠️
fastdeploy/entrypoints/openai/serving_chat.py	53.84%	5 Missing and 1 partial ⚠️
fastdeploy/output/token_processor.py	63.63%	4 Missing ⚠️
fastdeploy/engine/request.py	33.33%	2 Missing ⚠️
fastdeploy/entrypoints/cli/tokenizer.py	0.00%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #5255   +/-   ##
==========================================
  Coverage           ?   59.21%           
==========================================
  Files              ?      327           
  Lines              ?    40849           
  Branches           ?     6213           
==========================================
  Hits               ?    24188           
  Misses             ?    14782           
  Partials           ?     1879           

Flag	Coverage Δ
GPU	59.21% <70.17%> (?)

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.