[None][fix] Only Use Throughput Metrics to Check Regression#10404
[None][fix] Only Use Throughput Metrics to Check Regression#10404chenfeiz0326 merged 3 commits intoNVIDIA:mainfrom
Conversation
|
/bot run --disable-fail-fast |
📝 WalkthroughWalkthroughRefactored performance regression detection logic by consolidating regression data handling directly within test data entries instead of using a separate list. Updated function signatures to remove explicit regressive data parameters, with filtering now performed internally. Added metrics-based difference calculation and improved threshold retrieval. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Pre-merge checks and finishing touches❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✨ Finishing touches
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: 1
Fix all issues with AI Agents 🤖
In @tests/integration/defs/perf/open_search_db_utils.py:
- Around line 459-474: The KeyError message references an undefined fallback_key
in _get_threshold_for_metric; define fallback_key as the alternate expected key
(the pre/post-merge counterpart) before raising the error and include it in the
message, e.g. compute fallback_key = f"d_threshold_post_merge_{metric_suffix}"
if is_post_merge is False (and vice versa), then raise the KeyError using both
threshold_key and fallback_key in the message.
🧹 Nitpick comments (1)
tests/integration/defs/perf/open_search_db_utils.py (1)
734-774: LGTM! Signature correctly updated and error handling improved.The function signature has been updated to derive
regressive_data_listfromnew_data_dictby filtering entries whereb_is_regressionis True (lines 739-742). Post-merge regressions now correctly useprint_errorand raiseRuntimeError(lines 767-774), which is appropriately more severe than the warning approach for pre-merge regressions.Optional: Consider using a custom exception class
Per static analysis (TRY003), the long error message on lines 773-774 could be moved to a custom exception class for better error handling practices:
class PostMergeRegressionError(RuntimeError): """Raised when post-merge performance regression is detected.""" def __init__(self, count): super().__init__(f"Found {count} post-merge regression data") self.count = countThen raise it as:
raise PostMergeRegressionError(len(post_merge_regressions))
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
tests/integration/defs/perf/open_search_db_utils.pytests/integration/defs/perf/test_perf_sanity.py
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: 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
Python files should use snake_case naming:some_file.py
Python classes should use PascalCase naming:class SomeClass
Python functions and methods should use snake_case naming:def my_awesome_function():
Python local variables should use snake_case naming:my_variable = ...
Python variable names that start with a number should be prefixed with 'k':k_99th_percentile = ...
Python global variables should use upper snake_case with prefix 'G':G_MY_GLOBAL = ...
Python constants should use upper snake_case naming: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 in Python for classes and functions, which can be parsed by Sphinx
Python attributes and variables can be documented inline with type and description
Avoid using reflection in Python when functionality can be easily achieved without reflection
When using try-except blocks in Python, limit the except to the smallest set of errors possible
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, using the else block for logic
Files:
tests/integration/defs/perf/open_search_db_utils.pytests/integration/defs/perf/test_perf_sanity.py
**/*.{cpp,h,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
All TensorRT-LLM Open Source Software code should contain an NVIDIA copyright header that includes the year of its latest meaningful modification
Files:
tests/integration/defs/perf/open_search_db_utils.pytests/integration/defs/perf/test_perf_sanity.py
🧠 Learnings (1)
📓 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.
🧬 Code graph analysis (2)
tests/integration/defs/perf/open_search_db_utils.py (1)
tests/integration/defs/trt_test_alternative.py (1)
print_error(318-324)
tests/integration/defs/perf/test_perf_sanity.py (1)
tests/integration/defs/perf/open_search_db_utils.py (3)
prepare_regressive_test_cases(492-542)post_new_perf_data(612-631)check_perf_regression(734-778)
🪛 Ruff (0.14.10)
tests/integration/defs/perf/open_search_db_utils.py
472-474: Avoid specifying long messages outside the exception class
(TRY003)
474-474: Undefined name fallback_key
(F821)
773-774: 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 (5)
tests/integration/defs/perf/open_search_db_utils.py (4)
65-71: LGTM! Core change aligning with PR objective.The new
REGRESSION_METRICSconstant correctly restricts regression detection to throughput metrics only (seq, token, total_token, user), which aligns with the PR title "Only Use Throughput Metrics to Check Regression."
477-490: LGTM! Percentage difference calculation is correct.The function correctly handles both MAXIMIZE_METRICS (higher is better) and MINIMIZE_METRICS (lower is better), returning positive percentages for performance improvements and negative for regressions. The zero baseline edge case is handled appropriately.
492-542: LGTM! Correctly implements throughput-only regression checks.The function now updates
new_data_dictentries in place with regression metadata. Importantly, while all metrics are logged ins_regression_info(lines 513-528), onlyREGRESSION_METRICS(throughput metrics) trigger theb_is_regressionflag (lines 530-539), which correctly implements the PR objective.The regression logic is also correct:
- For MAXIMIZE_METRICS: regressive if
new_value < baseline_value * (1 - threshold)- For MINIMIZE_METRICS: regressive if
new_value > baseline_value * (1 + threshold)
612-632: LGTM! Signature correctly updated.The function signature has been updated to remove the
regressive_data_listparameter, which is consistent with the refactoring that embeds regression metadata directly innew_data_dictentries.tests/integration/defs/perf/test_perf_sanity.py (1)
1363-1379: LGTM! Function calls correctly updated.All three function calls have been correctly updated to match the new signatures from
open_search_db_utils.py:
- Line 1364:
prepare_regressive_test_casesnow updatesnew_data_dictin place with no return value- Line 1377:
post_new_perf_datano longer requires theregressive_data_listparameter- Line 1379:
check_perf_regressionderives regression data internally fromnew_data_dict
|
PR_Github #30564 [ run ] triggered by Bot. Commit: |
|
/bot run --disable-fail-fast |
|
PR_Github #30569 [ run ] triggered by Bot. Commit: |
|
PR_Github #30569 [ run ] completed with state
|
|
/bot run --disable-fail-fast |
|
PR_Github #30598 [ run ] triggered by Bot. Commit: |
|
PR_Github #30598 [ run ] completed with state |
…0404) Signed-off-by: Chenfei Zhang <chenfeiz@nvidia.com> Signed-off-by: Daniil Kulko <kulkodaniil@gmail.com>
3 participants
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.
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.
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.