rt: pad the task struct to avoid false sharing #5809
Merged
Conversation
This file contains 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
This change pads the task struct to avoid false sharing. It is possible for these structs to overlap cache lines without this alignment.
carllerche
added
A-tokio
Noah-Kennedy
approved these changes
Jun 21, 2023
There was a problem hiding this comment.
I'll stamp but I agree that we should have @Darksonn weigh in on the repr stuff.
Darksonn
approved these changes
Jun 21, 2023
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Outdated suggestions cannot be applied.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.
This change pads the task struct to avoid false sharing. These structs can overlap cache lines without this alignment.
I avoided adding a
CachePaddedwrapper struct as I am not sure how the padded wrapper struct would impact the pointer stuff we do in the task harness (casting*Headerto*Cellas well as the other pointer math).I'm also not 100% sure what happens when you combine
repr(C)withrepr(align(n))but I would guess (hope) it does the right thing.Thoughts @Darksonn ?
As part of a larger scheduler refactor that I am working on, I have observed false sharing happened and confirmed the false sharing using
perf c2c. Adding the padding here resolves the issue.