[https://nvbugs/5727517][fix] Preserve ip:port for disagg #9859
Conversation
Signed-off-by: Junyi Xu <[email protected]>
|
/bot run |
📝 WalkthroughWalkthroughThe changes enhance socket handling in the disaggregated server initialization. A bound listening socket is created within a context manager before server instantiation. New timeout and metrics parameters are added to OpenAIDisaggServer. GC disable behavior is now conditional. The bound socket is passed to asyncio.run for server startup. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes
Pre-merge checks and finishing touches❌ Failed checks (2 warnings)
✅ Passed checks (1 passed)
✨ Finishing touches
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
tensorrt_llm/commands/serve.py (1)
638-669: Socket binding & GC behavior are sound; refine exception chaining per Ruff hintsThe new pattern of binding a TCP socket in a
withblock and passingsockets=[s]intoasyncio.run(server(...))is a solid match for the updatedOpenAIDisaggServer.__call__and ensures early, explicit bind failures while preserving the configured ip:port. The conditional GC disabling controlled byTRTLLM_DISAGG_SERVER_DISABLE_GC(defaulting to disabled) is also consistent with the accompanying comment and gives an escape hatch if needed.You can tighten the error handling in the bind path and satisfy the Ruff B904/TRY003 hints by chaining the original
OSErrorand shortening the custom message, e.g.:- with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: - try: - s.bind((disagg_cfg.hostname, disagg_cfg.port)) - except OSError as e: - raise RuntimeError( - f"Failed to bind socket to {disagg_cfg.hostname}:{disagg_cfg.port}: {e}" - ) + with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s: + try: + s.bind((disagg_cfg.hostname, disagg_cfg.port)) + except OSError as e: + raise RuntimeError( + f"Failed to bind socket to {disagg_cfg.hostname}:{disagg_cfg.port}" + ) from eThis preserves the original traceback context while keeping the custom message focused.
Please re-run Ruff (or your usual lint pipeline) on this file after applying the change to confirm B904/TRY003 are resolved. As per static analysis hints.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
tensorrt_llm/commands/serve.py(1 hunks)tensorrt_llm/serve/openai_disagg_server.py(2 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: The code developed for TensorRT-LLM should conform to Python 3.8+
Indent Python code with 4 spaces; do not use tabs
Always maintain the namespace when importing in Python, even if only one class or function from a module is used (e.g., usefrom package.subpackage import fooand thenfoo.SomeClass()instead offrom package.subpackage.foo import SomeClass)
Python filenames should use snake_case (e.g.,some_file.py)
Python class names should use PascalCase (e.g.,class SomeClass)
Python function and method names should use snake_case (e.g.,def my_awesome_function():)
Python local variable names should use snake_case, with prefixkfor variable names that start with a number (e.g.,k_99th_percentile = ...)
Python global variables should use upper snake_case with prefixG(e.g.,G_MY_GLOBAL = ...)
Python constants should use upper snake_case (e.g.,MY_CONSTANT = ...)
Avoid shadowing variables declared in an outer scope in Python
Initialize all externally visible members of a Python class in the constructor
For Python interfaces that may be used outside a file, prefer docstrings over comments
Python comments should be reserved for code within a function, or interfaces that are local to a file
Use Google style docstrings for Python classes and functions, which can be parsed by Sphinx
Python attributes and variables can be documented inline with type and description (e.g.,self.x = 5followed by"""<type>: Description of 'x'""")
Avoid using reflection in Python when functionality can be easily achieved without reflection
When using try-except blocks in Python, limit the except clause to the smallest set of specific errors possible instead of catching all exceptions
When using try-except blocks in Python to handle multiple possible variable types (duck-typing), keep the body of the try as small as possible and use the else block to implement the logic
Files:
tensorrt_llm/commands/serve.pytensorrt_llm/serve/openai_disagg_server.py
**/*.{cpp,h,cu,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
All TensorRT-LLM Open Source Software code files should contain an NVIDIA copyright header that includes the current year at the top
Files:
tensorrt_llm/commands/serve.pytensorrt_llm/serve/openai_disagg_server.py
🧬 Code graph analysis (1)
tensorrt_llm/commands/serve.py (3)
tensorrt_llm/executor/rpc/rpc_server.py (1)
bind(91-115)tensorrt_llm/llmapi/disagg_utils.py (1)
parse_metadata_server_config_file(325-333)tensorrt_llm/serve/openai_disagg_server.py (1)
OpenAIDisaggServer(81-242)
🪛 Ruff (0.14.8)
tensorrt_llm/commands/serve.py
642-644: Within an except clause, raise exceptions with raise ... from err or raise ... from None to distinguish them from errors in exception handling
(B904)
642-644: Avoid specifying long messages outside the exception class
(TRY003)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Pre-commit Check
🔇 Additional comments (1)
tensorrt_llm/serve/openai_disagg_server.py (1)
19-20: Socket-aware__call__looks consistent with disagg startup flowAdding the
socketimport and threadingsockets: list[socket.socket] | None = Nonethrough touvicorn.Server(config).serve(sockets=sockets)cleanly supports the pre-bound socket path while remaining backward compatible with existing 2-arg call sites. This aligns with the updateddisaggregatedcommand wiring and preserves the existing host/port behavior whensocketsis left asNone.Please confirm your deployed uvicorn version supports the
socketskeyword onServer.serveand that the disaggregated path has been exercised end‑to‑end in your CI or local tests.Also applies to: 194-200
|
PR_Github #27607 [ run ] triggered by Bot. Commit: |
|
/bot run |
|
PR_Github #27796 [ run ] triggered by Bot. Commit: |
|
PR_Github #27796 [ run ] completed with state |
Signed-off-by: Junyi Xu <[email protected]>
Signed-off-by: Junyi Xu <[email protected]>
4 participants
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.
Description
Do like what we did for agg serve: #9646.
Test Coverage
PR Checklist
Please review the following before submitting your PR:
PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.
PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (see test instructions)
Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
Update tava architecture diagram if there is a significant design change in PR.
The reviewers assigned automatically/manually are appropriate for the PR.
Please check this after reviewing the above items as appropriate for this PR.
GitHub Bot Help
/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...Provide a user friendly way for developers to interact with a Jenkins server.
Run
/bot [-h|--help]to print this help message.See details below for each supported subcommand.
Details
run [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental)]Launch build/test pipelines. All previously running jobs will be killed.
--reuse-test (optional)pipeline-id(OPTIONAL) : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.--disable-reuse-test(OPTIONAL) : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.--disable-fail-fast(OPTIONAL) : Disable fail fast on build/tests/infra failures.--skip-test(OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.--stage-list "A10-PyTorch-1, xxx"(OPTIONAL) : Only run the specified test stages. Examples: "A10-PyTorch-1, xxx". Note: Does NOT update GitHub check status.--gpu-type "A30, H100_PCIe"(OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.--test-backend "pytorch, cpp"(OPTIONAL) : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: Does NOT update GitHub pipeline status.--only-multi-gpu-test(OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.--disable-multi-gpu-test(OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.--add-multi-gpu-test(OPTIONAL) : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline.--post-merge(OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx"(OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx".--detailed-log(OPTIONAL) : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.--debug(OPTIONAL) : Experimental feature. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in thestage-listparameter to access the appropriate container environment. Note: Does NOT update GitHub check status.For guidance on mapping tests to stage names, see
docs/source/reference/ci-overview.mdand the
scripts/test_to_stage_mapping.pyhelper.kill
killKill all running builds associated with pull request.
skip
skip --comment COMMENTSkip testing for latest commit on pull request.
--comment "Reason for skipping build/test"is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.reuse-pipeline
reuse-pipelineReuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.