[None][fix] Fix KV cache manager test warnings #9103

Tabrizian · 2025-11-12T20:23:17Z

Summary by CodeRabbit

Tests
- Added explicit validation for cache offload write operations to ensure data integrity during persistence.
- Improved test code consistency and eliminated compiler warnings through refined return value handling.
- Expanded testing infrastructure with additional system-level file operation support capabilities.

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 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.

Tabrizian · 2025-11-12T20:23:55Z

/bot run

coderabbitai · 2025-11-12T20:25:10Z

📝 Walkthrough

Walkthrough

Updated a kvCache manager test file to add explicit write result validation in GDS-offload helper code, replace direct removeSequence calls with static_cast() to silence compiler warnings, and add include directives for fcntl.h and unistd.h.

Changes

Cohort / File(s)	Summary
Test validation and warning suppression `cpp/tests/unit_tests/batch_manager/kvCacheManagerTest.cpp`	Added bytesToWrite computation and assertion to validate written bytes in GDS-offload path; replaced multiple kvCacheManager.removeSequence() calls with static_cast() casts; added fcntl.h and unistd.h includes.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Review the bytesWritten validation logic to ensure the assertion correctly computes and validates expected written bytes
Verify static_cast() changes target all appropriate removeSequence() calls and don't mask unintended warnings
Confirm new include directives don't conflict with existing headers or create unintended dependencies

Pre-merge checks and finishing touches

❌ Failed checks (2 warnings)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The PR description is empty; only the template structure is present with no actual content under Description, Test Coverage sections, or explanation of the changes made.	Add a clear description explaining why the warnings needed fixing, what specific warnings were addressed, and list the relevant test(s) that validate these changes.
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	You can run `@coderabbitai generate docstrings` to improve docstring coverage.

✅ Passed checks (1 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title '[None][fix] Fix KV cache manager test warnings' clearly and specifically identifies the main change: addressing compiler warnings in the KV cache manager test file.

✨ 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

Caution

Some comments are outside the diff and can’t be posted inline due to platform limitations.

⚠️ Outside diff range comments (1)

cpp/tests/unit_tests/batch_manager/kvCacheManagerTest.cpp (1)

208-223: Don’t silently skip failed ::open; make the write robust (loop) and truncate

Right now, if ::open fails, the test silently does nothing. That can hide real failures. Also, a single ::write may write fewer bytes; use a loop. Truncating prevents stale data.

Apply:

-        int fd = ::open(filename.c_str(), O_WRONLY);
-        if (fd >= 0)
-        {
+        int fd = ::open(filename.c_str(), O_WRONLY | O_TRUNC);
+        ASSERT_GE(fd, 0) << "open failed for " << filename << ": " << std::strerror(errno);
             auto poolBlockSize = blockSize / numPools;
             std::vector<T> buffer(poolBlockSize);
             for (int i = 0; i < poolBlockSize; ++i)
             {
                 buffer[i] = i & mask;
             }
-            auto const bytesToWrite = static_cast<size_t>(poolBlockSize) * sizeof(T);
-            auto const written = ::write(fd, buffer.data(), bytesToWrite);
-            EXPECT_EQ(written, static_cast<ssize_t>(bytesToWrite))
-                << "Failed to write pattern to offloaded block file " << filename;
+            auto const bytesToWrite = static_cast<size_t>(poolBlockSize) * sizeof(T);
+            size_t totalWritten = 0;
+            auto const* ptr = reinterpret_cast<char const*>(buffer.data());
+            while (totalWritten < bytesToWrite)
+            {
+                ssize_t rc = ::write(fd, ptr + totalWritten, bytesToWrite - totalWritten);
+                ASSERT_GE(rc, 0) << "write failed for " << filename << ": " << std::strerror(errno);
+                totalWritten += static_cast<size_t>(rc);
+            }
             ::close(fd);
-        }

Note: this uses / added above.

🧹 Nitpick comments (1)

cpp/tests/unit_tests/batch_manager/kvCacheManagerTest.cpp (1)
37-42: POSIX includes: add errno diagnostics and consider guarding for portability

Add and so failures can report strerror(errno).

Optionally guard POSIX-only headers to keep Windows toolchains happy.

Apply:
+#include <cerrno>
+#include <cstring>
-#include <fcntl.h>
+#if defined(__linux__)
+#include <fcntl.h>
 #include <filesystem>
 ...
-#include <unistd.h>
+#include <unistd.h>
+#endif
If you guard the includes, also guard the GDS-only helper definition similarly.

📜 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 8a751a0 and cc9429c.

📒 Files selected for processing (1)

cpp/tests/unit_tests/batch_manager/kvCacheManagerTest.cpp (9 hunks)

🧰 Additional context used

📓 Path-based instructions (5)

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