opt(s2n-quic-dc): Use RwLock for id/peer maps #2799
Merged
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
boquan-fang
approved these changes
Sep 11, 2025
This uses the parking_lot RwLock which helps ensure fairness and guarantees that writers make forward progress even with a continuous stream of readers. In microbenchmarks, this essentially eliminates futex syscalls on the lock atomic, since readers are able to proceed in parallel. We likely still have cache line contention but that's cheaper than going to sleep on a Mutex and is a larger change to fix. The alignment to 128 bytes should also help with the contention.
Mark-Simulacrum
force-pushed
the
rwlock-maps
branch
from
fea0a82 to
cb713fe
Compare
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Outdated suggestions cannot be applied.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.
Release Summary:
Resolved issues:
n/a
Description of changes:
This uses the parking_lot RwLock which helps ensure fairness and guarantees that writers make forward progress even with a continuous stream of readers.
In microbenchmarks, this essentially eliminates futex syscalls on the lock atomic, since readers are able to proceed in parallel. We likely still have cache line contention but that's cheaper than going to sleep on a Mutex and is a larger change to fix. The alignment to 128 bytes should also help with the contention.
Call-outs:
n/a
Testing:
~All of our tests exercise this code. The change shouldn't be purely about performance.
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.