TRT EP race condition fix during ep compile time#13356
Merged
Conversation
chilo-ms
changed the title
jywu-msft
reviewed
Oct 18, 2022
| } | ||
| trt_context = tensorrt_ptr::unique_pointer<nvinfer1::IExecutionContext>(trt_engine->createExecutionContextWithoutDeviceMemory()); | ||
| } else { | ||
| size_t mem_size = trt_engine->getDeviceMemorySize(); |
Member
There was a problem hiding this comment.
the indentation seems off here?
jywu-msft
approved these changes
Oct 18, 2022
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
TRT EP has the chance to encounter race condition when multiple threads are doing engine serialization/deserialization during EP compile time.
Let's say one thread is serializing the engine and has not yet completely written all the data to file, and at this moment, another thread finds the engine file is existed and begins to deserialize the engine, it will end up deserialize the corrupt file.
The fix is to put a lock around engine deserialization/serialization, engine build and context build.
Motivation and Context
The TensorRT EP Windows CI sometimes fails because of
TensorrtExecutionProviderTest.MultiThreadsTestWithOneSessionSingleThreadInferenceunit test fails (This PR changes the name to SessionCreationWithMultiThreadsAndInferenceWithMultiThreads). It's highly possible due to race condition.The TensorRT CI failure also been reported here