[https://nvbugs/5594753][fix] fix rpc unique addr related issue #8419

Superjomn · 2025-10-16T07:53:39Z

Summary by CodeRabbit

New Features
- Added get_unique_ipc_addr to the RPC public API for generating unique IPC addresses.
Bug Fixes
- Re-enabled previously skipped test to improve test coverage.
Refactor
- Consolidated internal IPC address generation into a shared utility function.

Description

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
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.

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 the stage-list parameter 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.md
and the scripts/test_to_stage_mapping.py helper.

kill

kill

Kill all running builds associated with pull request.

skip

skip --comment COMMENT

Skip 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-pipeline

Reuse 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.

coderabbitai · 2025-10-16T07:53:55Z

📝 Walkthrough

Walkthrough

Extracts IPC address generation into a shared utility function get_unique_ipc_addr() in the RPC module. Replaces the private gen_uniq_rpc_addr() method in GenerationExecutorRpcProxy with calls to the new shared function. Exports the utility as part of the public RPC API and updates all tests to use it.

Changes

Cohort / File(s)	Summary
Public API Export `tensorrt_llm/executor/rpc/__init__.py`	Adds `get_unique_ipc_addr` to imports from `.rpc_common` and exports it in `__all__` to expose the function as part of the public RPC API.
Core Utility Implementation `tensorrt_llm/executor/rpc/rpc_common.py`	Introduces new `get_unique_ipc_addr()` function that generates a unique IPC address using process ID and current timestamp. Adds `os` module import for process ID retrieval. Returns address in format `ipc:///tmp/rpc_test_{pid}_{timestamp}`.
RPC Proxy Refactoring `tensorrt_llm/executor/rpc_proxy.py`	Removes private static method `gen_uniq_rpc_addr()` from `GenerationExecutorRpcProxy` class. Updates `__init__` to call external `get_unique_ipc_addr()` function instead. Removes now-unused `os` module import.
Test Updates `tests/unittest/executor/test_rpc.py`	Imports `get_unique_ipc_addr` and replaces hardcoded IPC address strings with dynamic address generation. Updates all `RPCClient` and server binding operations to use the dynamically generated address.
RPC Worker Tests `tests/unittest/executor/test_rpc_worker.py`	Replaces import of `GenerationExecutorRpcProxy` with import of `get_unique_ipc_addr` from `rpc_common`. Updates all calls from `GenerationExecutorRpcProxy.gen_uniq_rpc_addr()` to `get_unique_ipc_addr()` in test setup.
RPC Proxy Tests `tests/unittest/executor/test_rpc_proxy.py`	Removes pytest skip marker from `test_tp1`, allowing the test to execute.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Pre-merge checks and finishing touches

❌ Failed checks (2 warnings, 1 inconclusive)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 14.29% which is insufficient. The required threshold is 80.00%.	You can run `@coderabbitai generate docstrings` to improve docstring coverage.
Description Check	⚠️ Warning	The PR description is largely incomplete and does not provide required information from the template. The "Description" section contains only the template placeholder comment with no explanation of the issue or solution, and the "Test Coverage" section is similarly empty with no list of relevant tests. While the PR checklist box is marked as complete, the author has not filled in the substantive sections (Description and Test Coverage) that are necessary for reviewers to understand the motivation and validation of these changes.	Please provide a complete PR description following the repository template. Add a "Description" section that explains the issue being fixed (why unique RPC addresses were needed) and how the new `get_unique_ipc_addr()` function and refactoring addresses it. Add a "Test Coverage" section that lists the relevant tests (such as `test_rpc.py`, `test_rpc_proxy.py`, `test_rpc_worker.py`) that validate the changes. These sections are essential for code review and maintainability.
Title Check	❓ Inconclusive	The PR title `[https://nvbugs/5594753][fix] fix rpc unique addr related issue` follows the correct format with a valid NVBugs ticket ID and type indicator. However, the summary is vague and generic—the phrase "fix rpc unique addr related issue" does not clearly convey what the main change accomplishes. Based on the raw summary, the changes involve extracting RPC address generation into a shared function and refactoring how unique addresses are generated, but the title fails to communicate this specifics clearly enough for developers scanning history to understand the intent.

✨ Finishing touches

📝 Generate docstrings

🧪 Generate unit tests (beta)

Create PR with unit tests
Post copyable unit tests in a comment

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.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

coderabbitai

Actionable comments posted: 0

🧹 Nitpick comments (1)

tests/unittest/executor/test_rpc.py (1)
368-384: Consider using get_unique_ipc_addr() for consistency.

The setup_method in TestRpcTimeout uses a custom address format instead of the newly introduced get_unique_ipc_addr() function. For consistency with the rest of the codebase and to benefit from the centralized address generation logic, consider refactoring this to use the shared utility:

Apply this diff:
     def setup_method(self, method):
         """Setup RPC server and client for timeout tests."""
-        # Use unique address based on the test parameter to avoid socket conflicts
-        test_name = method.__name__
-        self.address = f"ipc:///tmp/rpc_test_timeout_{test_name}_{id(self)}"
+        self.address = get_unique_ipc_addr()
         self.server = RPCServer(self.App())
         self.server.bind(self.address)
         self.server.start()
If the test name in the address is important for debugging, you could enhance get_unique_ipc_addr() to accept an optional prefix parameter, but the current PID + timestamp approach should already provide sufficient uniqueness and debuggability.

📜 Review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 89d03d7 and ddb8722.

📒 Files selected for processing (6)

tensorrt_llm/executor/rpc/__init__.py (1 hunks)
tensorrt_llm/executor/rpc/rpc_common.py (1 hunks)
tensorrt_llm/executor/rpc_proxy.py (2 hunks)
tests/unittest/executor/test_rpc.py (19 hunks)
tests/unittest/executor/test_rpc_proxy.py (0 hunks)
tests/unittest/executor/test_rpc_worker.py (3 hunks)

💤 Files with no reviewable changes (1)

tests/unittest/executor/test_rpc_proxy.py

🧰 Additional context used

📓 Path-based instructions (3)

**/*.{h,hpp,hh,hxx,cpp,cxx,cc,cu,cuh,py}

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

Use only spaces, no tabs; indent with 4 spaces.

Files:

tests/unittest/executor/test_rpc_worker.py
tensorrt_llm/executor/rpc/rpc_common.py
tensorrt_llm/executor/rpc_proxy.py
tests/unittest/executor/test_rpc.py
tensorrt_llm/executor/rpc/__init__.py

**/*.py

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

**/*.py: Python code must target Python 3.8+.
Indent Python code with 4 spaces; do not use tabs.
Maintain module namespace when importing; prefer 'from package.subpackage import foo' then 'foo.SomeClass()' instead of importing the class directly.
Python filenames should be snake_case (e.g., some_file.py).
Python classes use PascalCase names.
Functions and methods use snake_case names.
Local variables use snake_case; prefix 'k' for variables that start with a number (e.g., k_99th_percentile).
Global variables use upper SNAKE_CASE prefixed with 'G' (e.g., G_MY_GLOBAL).
Constants use upper SNAKE_CASE (e.g., MY_CONSTANT).
Avoid shadowing variables from an outer scope.
Initialize all externally visible members of a class in the constructor.
Prefer docstrings for interfaces that may be used outside a file; comments for in-function or file-local interfaces.
Use Google-style docstrings for classes and functions (Sphinx-parsable).
Document attributes and variables inline so they render under the class/function docstring.
Avoid reflection when a simpler, explicit approach suffices (e.g., avoid dict(**locals()) patterns).
In try/except, catch the most specific exceptions possible.
For duck-typing try/except, keep the try body minimal and use else for the main logic.

Files:

tests/unittest/executor/test_rpc_worker.py
tensorrt_llm/executor/rpc/rpc_common.py
tensorrt_llm/executor/rpc_proxy.py
tests/unittest/executor/test_rpc.py
tensorrt_llm/executor/rpc/__init__.py

**/*.{cpp,cxx,cc,h,hpp,hh,hxx,cu,cuh,py}

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

Prepend the NVIDIA Apache-2.0 copyright header with current year to the top of all source files (e.g., .cpp, .h, .cu, .py).

Files:

tests/unittest/executor/test_rpc_worker.py
tensorrt_llm/executor/rpc/rpc_common.py
tensorrt_llm/executor/rpc_proxy.py
tests/unittest/executor/test_rpc.py
tensorrt_llm/executor/rpc/__init__.py

🧬 Code graph analysis (4)

tests/unittest/executor/test_rpc_worker.py (1)

tensorrt_llm/executor/rpc/rpc_common.py (1)

get_unique_ipc_addr (7-15)

tensorrt_llm/executor/rpc_proxy.py (1)

tensorrt_llm/executor/rpc/rpc_common.py (1)

get_unique_ipc_addr (7-15)

tests/unittest/executor/test_rpc.py (2)

tensorrt_llm/executor/rpc/rpc_common.py (1)

get_unique_ipc_addr (7-15)

tensorrt_llm/executor/rpc/rpc_server.py (1)

address (72-74)

tensorrt_llm/executor/rpc/__init__.py (1)

tensorrt_llm/executor/rpc/rpc_common.py (1)

get_unique_ipc_addr (7-15)

🪛 Ruff (0.14.0)

tests/unittest/executor/test_rpc.py

36-36: Local variable server is assigned to but never used