[TRTLLM-7008][fix] cherrypick fix to 1.0 Add automatic shared memory delete if already exist #7433
Conversation
📝 WalkthroughWalkthroughIntroduces environment-driven shared memory naming in MoeLoadBalancer, updates its constructor to accept None for name resolution via TRTLLM_EPLB_SHM_NAME, and hardens SharedMemory creation with FileExistsError handling. Test lists move two online EPLB tests from post_merge to pre_merge in l0_gb200. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
participant U as User Code
participant LB as MoeLoadBalancer
participant ENV as Environment
participant OS as SharedMemory
rect rgba(230,240,255,0.6)
note over LB: Initialization
U->>LB: __init__(shared_memory_base_name=None)
alt shared_memory_base_name is None
LB->>ENV: read TRTLLM_EPLB_SHM_NAME
ENV-->>LB: value or unset
LB->>LB: set shared_memory_base_name = env or "moe_shared"
else name provided
LB->>LB: set shared_memory_base_name = provided
end
end
rect rgba(240,255,240,0.6)
note over LB,OS: finalize_layer_weights -> SharedMemory creation
LB->>OS: create SharedMemory(name, size)
alt FileExistsError raised
LB->>OS: unlink/close existing shared memory
LB->>OS: recreate SharedMemory(name, size)
else success
note over LB: proceed with weight finalization
end
end
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Suggested reviewers
✨ Finishing Touches
🧪 Generate unit tests
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. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR/Issue comments)Type Other keywords and placeholders
Status, Documentation and Community
|
|
/bot run --disable-fail-fast |
|
PR_Github #17182 [ run ] triggered by Bot |
![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 (4)
tensorrt_llm/_torch/modules/fused_moe/moe_load_balancer.py (4)
1-1: Add NVIDIA copyright header.Per repo guidelines, prepend the current-year NVIDIA header.
Apply:
+# Copyright (c) 2025, NVIDIA CORPORATION. All rights reserved. +# SPDX-License-Identifier: Apache-2.0 import os
176-191: Make stale-SHM recovery race-safe; fix log text; use consistent logger; silence resource_tracker.Current unlink-on-exist solves stale segments but can race with another process on the same host. Tighten handling and wording; also unregister to avoid resource_tracker warnings.
Apply:
- try: - shm = shared_memory.SharedMemory(name=shm_name, - create=True, - size=total_size) - except FileExistsError: - tensorrt_llm.logger.warning( - f'Found exist EPLB shared memory name: {shm_name}, unlinking...' - ) - existing_shm = shared_memory.SharedMemory(name=shm_name) - existing_shm.close() - existing_shm.unlink() - shm = shared_memory.SharedMemory(name=shm_name, - create=True, - size=total_size) + try: + shm = shared_memory.SharedMemory(name=shm_name, create=True, size=total_size) + except FileExistsError: + logger.warning(f'Found existing EPLB shared memory: {shm_name}; unlinking stale segment and recreating.') + try: + existing_shm = shared_memory.SharedMemory(name=shm_name) + except FileNotFoundError: + existing_shm = None + else: + tracker_name = existing_shm._name + existing_shm.close() + try: + existing_shm.unlink() + except FileNotFoundError: + pass + else: + resource_tracker.unregister(tracker_name, "shared_memory") + shm = shared_memory.SharedMemory(name=shm_name, create=True, size=total_size)Please confirm CI sets TRTLLM_EPLB_SHM_NAME uniquely per job; otherwise a concurrent job on the same host could unlink a name before peers open it (pre-barrier vs. external job).
693-694: Docstring: mention env variable fallback.Clarify behavior when None so users know to set TRTLLM_EPLB_SHM_NAME.
- shared_memory_base_name: Shared memory base name, will use 'moe_shared' if None + shared_memory_base_name: Shared memory base name. If None, uses env TRTLLM_EPLB_SHM_NAME or falls back to 'moe_shared'.
703-706: Remove accidental double assignment.Minor cleanup; avoids confusion.
- if shared_memory_base_name is None: - shared_memory_base_name = shared_memory_base_name = os.getenv( - 'TRTLLM_EPLB_SHM_NAME') or 'moe_shared' + if shared_memory_base_name is None: + shared_memory_base_name = os.getenv('TRTLLM_EPLB_SHM_NAME') or 'moe_shared'
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (2)
tensorrt_llm/_torch/modules/fused_moe/moe_load_balancer.py(4 hunks)tests/integration/test_lists/test-db/l0_gb200.yml(1 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.{cpp,cc,cxx,cu,h,hpp,hh,hxx,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.{cpp,cc,cxx,cu,h,hpp,hh,hxx,cuh,py}: Use spaces only; no tabs; indent with 4 spaces
Prepend NVIDIA copyright header (current year) to all source files (.cpp, .h, .cu, .py, etc.)
Files:
tensorrt_llm/_torch/modules/fused_moe/moe_load_balancer.py
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: Python code must target Python 3.8+
Indent Python with 4 spaces; no tabs
Preserve module namespaces when importing: from package.subpackage import foo; then call foo.SomeClass() instead of importing the class directly
Python naming: files snake_case; classes PascalCase; functions/methods snake_case; locals snake_case (prefix k_ when starting with a number); globals UPPER_SNAKE_CASE with G_ prefix; constants UPPER_SNAKE_CASE
Avoid shadowing outer-scope variables; initialize all externally visible members in init
Prefer docstrings for interfaces used outside a file; limit comments to function-internal or file-local interfaces
Use Google-style docstrings for classes and functions; document attributes/variables inline so Sphinx can render them
Avoid reflection when simpler alternatives exist; prefer explicit parameters and return dicts over locals()/dynamic tricks
In try/except, catch the narrowest exceptions possible; keep try bodies minimal and use else for the main logic when doing duck-typing checks
Files:
tensorrt_llm/_torch/modules/fused_moe/moe_load_balancer.py
🧠 Learnings (1)
📚 Learning: 2025-07-28T17:06:08.621Z
Learnt from: moraxu
PR: NVIDIA/TensorRT-LLM#6303
File: tests/integration/test_lists/qa/examples_test_list.txt:494-494
Timestamp: 2025-07-28T17:06:08.621Z
Learning: In TensorRT-LLM testing, it's common to have both CLI flow tests (test_cli_flow.py) and PyTorch API tests (test_llm_api_pytorch.py) for the same model. These serve different purposes: CLI flow tests validate the traditional command-line workflow, while PyTorch API tests validate the newer LLM API backend. Both are legitimate and should coexist.
Applied to files:
tests/integration/test_lists/test-db/l0_gb200.yml
⏰ 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)
tests/integration/test_lists/test-db/l0_gb200.yml (1)
36-37: Remove duplicate online_eplb tests and set unique SHM base per CI job
- Remove the two
test_nvfp4_4gpus_online_eplbandtest_bfloat16_4gpus_online_eplbentries from thepost_mergeblock intests/integration/test_lists/test-db/l0_gb200.yml.- In your CI pipeline, export
TRTLLM_EPLB_SHM_NAMEwith a per-job unique suffix (e.g.export TRTLLM_EPLB_SHM_NAME="eplb_${GITHUB_RUN_ID:-local}_$HOSTNAME").⛔ Skipped due to learnings
Learnt from: pengbowang-nv PR: NVIDIA/TensorRT-LLM#7192 File: tests/integration/test_lists/test-db/l0_dgx_b200.yml:56-72 Timestamp: 2025-08-26T09:49:04.956Z Learning: In TensorRT-LLM test configuration files, the test scheduling system handles wildcard matching with special rules that prevent duplicate test execution even when the same tests appear in multiple yaml files with overlapping GPU wildcards (e.g., "*b200*" and "*gb200*").Learnt from: moraxu PR: NVIDIA/TensorRT-LLM#6303 File: tests/integration/test_lists/qa/examples_test_list.txt:494-494 Timestamp: 2025-07-28T17:06:08.621Z Learning: In TensorRT-LLM testing, it's common to have both CLI flow tests (test_cli_flow.py) and PyTorch API tests (test_llm_api_pytorch.py) for the same model. These serve different purposes: CLI flow tests validate the traditional command-line workflow, while PyTorch API tests validate the newer LLM API backend. Both are legitimate and should coexist.
Signed-off-by: Dongxu Yang <[email protected]>
Signed-off-by: Dongxu Yang <[email protected]>
dongxuy04
force-pushed
the
user/dongxuy/fix_wideep_shm_release_1.0
branch
from
f9c7b38 to
b9eca87
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #17200 [ run ] triggered by Bot |
|
PR_Github #17182 [ run ] completed with state |
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (3)
tensorrt_llm/_torch/modules/fused_moe/moe_load_balancer.py (3)
689-694: Docstring: mention the environment resolution path.Clarify that None triggers TRTLLM_EPLB_SHM_NAME fallback.
- shared_memory_base_name: Shared memory base name, will use 'moe_shared' if None + shared_memory_base_name: Shared memory base name. If None, resolves via + os.getenv('TRTLLM_EPLB_SHM_NAME', 'moe_shared').
703-705: Trim/sanitize the resolved base name to avoid accidental whitespace issues.Low-risk robustness improvement.
- self.shared_memory_base_name = shared_memory_base_name or os.getenv( - 'TRTLLM_EPLB_SHM_NAME', 'moe_shared') + self.shared_memory_base_name = ( + shared_memory_base_name + or os.getenv('TRTLLM_EPLB_SHM_NAME') + or 'moe_shared' + ).strip()
176-191: Document per-job uniqueness for shared memory name
No existing docs or tests enforce thatTRTLLM_EPLB_SHM_NAMEmust be unique; update documentation to recommend incorporating a job-specific identifier (e.g.SLURM_JOB_ID) to avoid cross-job collisions, or enhance the unlink logic to only remove shared memory when its size doesn’t matchtotal_size.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (2)
tensorrt_llm/_torch/modules/fused_moe/moe_load_balancer.py(4 hunks)tests/integration/test_lists/test-db/l0_gb200.yml(1 hunks)
🚧 Files skipped from review as they are similar to previous changes (1)
- tests/integration/test_lists/test-db/l0_gb200.yml
🧰 Additional context used
📓 Path-based instructions (2)
**/*.{cpp,cc,cxx,cu,h,hpp,hh,hxx,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.{cpp,cc,cxx,cu,h,hpp,hh,hxx,cuh,py}: Use spaces only; no tabs; indent with 4 spaces
Prepend NVIDIA copyright header (current year) to all source files (.cpp, .h, .cu, .py, etc.)
Files:
tensorrt_llm/_torch/modules/fused_moe/moe_load_balancer.py
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: Python code must target Python 3.8+
Indent Python with 4 spaces; no tabs
Preserve module namespaces when importing: from package.subpackage import foo; then call foo.SomeClass() instead of importing the class directly
Python naming: files snake_case; classes PascalCase; functions/methods snake_case; locals snake_case (prefix k_ when starting with a number); globals UPPER_SNAKE_CASE with G_ prefix; constants UPPER_SNAKE_CASE
Avoid shadowing outer-scope variables; initialize all externally visible members in init
Prefer docstrings for interfaces used outside a file; limit comments to function-internal or file-local interfaces
Use Google-style docstrings for classes and functions; document attributes/variables inline so Sphinx can render them
Avoid reflection when simpler alternatives exist; prefer explicit parameters and return dicts over locals()/dynamic tricks
In try/except, catch the narrowest exceptions possible; keep try bodies minimal and use else for the main logic when doing duck-typing checks
Files:
tensorrt_llm/_torch/modules/fused_moe/moe_load_balancer.py
🧬 Code graph analysis (1)
tensorrt_llm/_torch/modules/fused_moe/moe_load_balancer.py (1)
tensorrt_llm/logger.py (1)
warning(132-133)
⏰ 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
|
PR_Github #17200 [ run ] completed with state |
|
/bot run --disable-fail-fast |
|
PR_Github #17237 [ run ] triggered by Bot |
|
PR_Github #17237 [ run ] completed with state |
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
…delete if already exist (NVIDIA#7433) Signed-off-by: Dongxu Yang <[email protected]> Signed-off-by: Wangshanshan <[email protected]>
Summary by CodeRabbit
New Features
Bug Fixes
Tests
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 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.