Serialize destruction of the delegate #5996
Closed
Conversation
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/5996
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit e0e1c6f with merge base e540bcb ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D63917052 |
digantdesai
force-pushed
the
export-D63917052
branch
from
2d018f9 to
1ff960a
Compare
digantdesai
added a commit
to digantdesai/executorch-1
that referenced
this pull request
Oct 8, 2024
Summary: When workspace sharing is enabled, if we call `destroy()` from multiple threads it is possible that we enter in `xnn_delete_runtime` from multiple threads. It is not safe to do so, and can cause double free. This serializes the destroy calls for the singleton backend object if/when called multiple times. Not locking in the failure case because we may not have a real memory to free i.e. empty workspace? Differential Revision: D63917052
|
This pull request was exported from Phabricator. Differential Revision: D63917052 |
digantdesai
added a commit
to digantdesai/executorch-1
that referenced
this pull request
Oct 8, 2024
Summary: When workspace sharing is enabled, if we call `destroy()` from multiple threads it is possible that we enter in `xnn_delete_runtime` from multiple threads. It is not safe to do so, and can cause double free. This serializes the destroy calls for the singleton backend object if/when called multiple times. Not locking in the failure case because we may not have a real memory to free i.e. empty workspace? Differential Revision: D63917052
digantdesai
force-pushed
the
export-D63917052
branch
from
1ff960a to
bd5bc8a
Compare
|
This pull request was exported from Phabricator. Differential Revision: D63917052 |
Summary: When workspace sharing is enabled, if we call `destroy()` from multiple threads it is possible that we enter in `xnn_delete_runtime` from multiple threads. It is not safe to do so, and can cause double free. This serializes the destroy calls for the singleton backend object if/when called multiple times. Not locking in the failure case because we may not have a real memory to free i.e. empty workspace? Differential Revision: D63917052
digantdesai
force-pushed
the
export-D63917052
branch
from
bd5bc8a to
e0e1c6f
Compare
|
This pull request was exported from Phabricator. Differential Revision: D63917052 |
GregoryComer
approved these changes
Oct 9, 2024
|
This pull request has been merged in 566902b. |
|
@pytorchbot cherry-pick --onto release/0.4 -c regression |
pytorchbot
pushed a commit
that referenced
this pull request
Oct 10, 2024
Summary: Pull Request resolved: #5996 When workspace sharing is enabled, if we call `destroy()` from multiple threads it is possible that we enter in `xnn_delete_runtime` from multiple threads. It is not safe to do so, and can cause double free. This serializes the destroy calls for the singleton backend object if/when called multiple times. Not locking in the failure case because we may not have a real memory to free i.e. empty workspace? Reviewed By: digantdesai Differential Revision: D63917052 fbshipit-source-id: 61e6b1c54f887a54501a4fd3433f8470e74dbca3 (cherry picked from commit 566902b)
Cherry picking #5996The cherry pick PR is at #6111 and it is recommended to link a regression cherry pick PR with an issue. The following tracker issues are updated: Details for Dev Infra teamRaised by workflow job |
jackzhxng
pushed a commit
that referenced
this pull request
Oct 10, 2024
Serialize destruction of the delegate (#5996) Summary: Pull Request resolved: #5996 When workspace sharing is enabled, if we call `destroy()` from multiple threads it is possible that we enter in `xnn_delete_runtime` from multiple threads. It is not safe to do so, and can cause double free. This serializes the destroy calls for the singleton backend object if/when called multiple times. Not locking in the failure case because we may not have a real memory to free i.e. empty workspace? Reviewed By: digantdesai Differential Revision: D63917052 fbshipit-source-id: 61e6b1c54f887a54501a4fd3433f8470e74dbca3 (cherry picked from commit 566902b) Co-authored-by: Gregory Comer <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Summary:
When workspace sharing is enabled, if we call
destroy()from multiple threads it is possible that we enter inxnn_delete_runtimefrom multiple threads. It is not safe to do so, and can cause double free. This serializes the destroy calls for the singleton backend object if/when called multiple times.Not locking in the failure case because we may not have a real memory to free i.e. empty workspace?
Differential Revision: D63917052