[https://nvbugs/5655584][chore] Debug perf problem in CI for 5655584 #9258
Conversation
Signed-off-by: Lizhi Zhou <[email protected]>
reasonsolo
force-pushed
the
debug5655584
branch
from
34d4138 to
efc9766
Compare
Signed-off-by: Lizhi Zhou <[email protected]>
reasonsolo
force-pushed
the
debug5655584
branch
from
efc9766 to
f37e5eb
Compare
|
/bot run --disable-fail-fast --only-multi-gpu-test |
📝 WalkthroughWalkthroughThe changes add performance debugging utilities and extend the disaggregated LLM launch function to optionally collect and surface KV-cache timing metrics and performance data during test execution. Environment variables are wired to propagate perf directories to worker processes. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes
Pre-merge checks and finishing touches❌ Failed checks (2 warnings)
✅ Passed checks (1 passed)
✨ Finishing touches
🧪 Generate unit tests (beta)
Tip 📝 Customizable high-level summaries are now available in beta!You can now customize how CodeRabbit generates the high-level summary in your pull requests — including its content, structure, tone, and formatting.
Example instruction:
Note: This feature is currently in beta for Pro-tier users, and pricing will be announced later. 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: 4
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
tests/integration/defs/accuracy/test_disaggregated_serving.py(7 hunks)
🧰 Additional context used
🧠 Learnings (4)
📓 Common learnings
Learnt from: venkywonka
Repo: NVIDIA/TensorRT-LLM PR: 6029
File: .github/pull_request_template.md:45-53
Timestamp: 2025-08-27T17:50:13.264Z
Learning: For PR templates in TensorRT-LLM, avoid suggesting changes that would increase developer overhead, such as converting plain bullets to mandatory checkboxes. The team prefers guidance-style bullets that don't require explicit interaction to reduce friction in the PR creation process.
📚 Learning: 2025-07-28T17:06:08.621Z
Learnt from: moraxu
Repo: NVIDIA/TensorRT-LLM PR: 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/defs/accuracy/test_disaggregated_serving.py
📚 Learning: 2025-08-13T11:07:11.772Z
Learnt from: Funatiq
Repo: NVIDIA/TensorRT-LLM PR: 6754
File: tests/integration/test_lists/test-db/l0_a30.yml:41-47
Timestamp: 2025-08-13T11:07:11.772Z
Learning: In TensorRT-LLM test configuration files like tests/integration/test_lists/test-db/l0_a30.yml, TIMEOUT values are specified in minutes, not seconds.
Applied to files:
tests/integration/defs/accuracy/test_disaggregated_serving.py
📚 Learning: 2025-09-09T09:40:45.658Z
Learnt from: fredricz-20070104
Repo: NVIDIA/TensorRT-LLM PR: 7645
File: tests/integration/test_lists/qa/llm_function_core.txt:648-648
Timestamp: 2025-09-09T09:40:45.658Z
Learning: In TensorRT-LLM test lists, it's common and intentional for the same test to appear in multiple test list files when they serve different purposes (e.g., llm_function_core.txt for comprehensive core functionality testing and llm_function_core_sanity.txt for quick sanity checks). This duplication allows tests to be run in different testing contexts.
Applied to files:
tests/integration/defs/accuracy/test_disaggregated_serving.py
🧬 Code graph analysis (1)
tests/integration/defs/accuracy/test_disaggregated_serving.py (1)
tests/unittest/llmapi/apps/_test_disagg_serving_multi_nodes.py (1)
env(61-68)
🪛 Ruff (0.14.5)
tests/integration/defs/accuracy/test_disaggregated_serving.py
31-31: PEP 484 prohibits implicit Optional
Convert to T | None
(RUF013)
39-39: PEP 484 prohibits implicit Optional
Convert to T | None
(RUF013)
40-40: PEP 484 prohibits implicit Optional
Convert to T | None
(RUF013)
51-51: Do not catch blind exception: Exception
(BLE001)
53-53: Do not catch blind exception: Exception
(BLE001)
89-89: Do not assert False (python -O removes these calls), raise AssertionError()
Replace assert False
(B011)
154-154: f-string without any placeholders
Remove extraneous f prefix
(F541)
373-373: f-string without any placeholders
Remove extraneous f prefix
(F541)
⏰ 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 (6)
tests/integration/defs/accuracy/test_disaggregated_serving.py (6)
28-29: LGTM!The constant definition is clear and appropriately named for limiting performance metrics collection.
142-143: LGTM!The new parameters are well-designed with safe defaults. The
debug_perfparameter correctly defaults toFalseto avoid impacting existing tests.
147-164: LGTM!The conditional initialization of the performance directory and configuration injection is well-structured. The consistent application of performance settings across all server configurations ensures uniform metric collection.
224-224: LGTM!The refactoring to use
get_worker_env_varsimproves code consistency and ensures proper propagation of the KV cache performance directory to worker processes.
245-245: LGTM!Consistent with the context server changes, properly centralizing environment variable handling.
445-445: Verify if the 5x timeout increase is temporary or permanent.The timeout has been increased from 1800 seconds (30 minutes) to 9000 seconds (2.5 hours). While this may be necessary for debugging performance issues, such a long timeout could significantly impact CI pipeline duration.
Please clarify:
- Is this timeout increase temporary for debugging purposes, or is it intended to be permanent?
- If temporary, consider using a decorator like
@pytest.mark.timeout(DEFAULT_TEST_TIMEOUT * 5, method="thread")only on specific tests that need it- If permanent, document why such a long timeout is necessary for this test class
Signed-off-by: Lizhi Zhou <[email protected]>
|
PR_Github #24874 [ run ] triggered by Bot. Commit: |
|
/bot run --disable-fail-fast --only-multi-gpu-test |
|
PR_Github #24875 [ run ] triggered by Bot. Commit: |
|
PR_Github #24874 [ run ] completed with state |
reasonsolo
changed the title
|
/bot run --stage-list "DGX_H100-2_GPUs-PyTorch-Others-1" |
|
PR_Github #24898 [ run ] triggered by Bot. Commit: |
|
PR_Github #24875 [ run ] completed with state |
|
/bot kill |
Signed-off-by: Lizhi Zhou <[email protected]>
|
/bot run --stage-list "DGX_H100-2_GPUs-PyTorch-Others-1" --debug |
|
PR_Github #24971 [ run ] triggered by Bot. Commit: |
|
PR_Github #24898 [ run ] completed with state |
|
PR_Github #24971 [ run ] completed with state |
3 participants
This PR tries to collect perf metrics data from CI machines, do NOT merge or enable auto-merge.
Summary by CodeRabbit
Release Notes
No user-facing changes in this release.
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
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.
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.