opt(s2n-quic-dc): Further tweak TCP acceptor concurrency #2829
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
This makes two changes: first, we fix a bug where we were lowering per-acceptor concurrency by total concurrency while the worker count was clamped at 4. This artificially shrunk the worker backlog limits more than it should. Second, we change TCP sockets to have the full-sized backlog (4096 on Linux), which reduces the likelihood that Linux will drop incoming connections during transient spikes, causing overall overload on the system. For systems with high concurrency we were previously configuring very small backlogs (e.g., 32 connections) which can get overwhelmed at high accept rates and end up triggering syn flood protection. The above bug made this worse when we clamped concurrency.
boquan-fang
approved these changes
Sep 25, 2025
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Outdated suggestions cannot be applied.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:
intentionally blank, mostly this is fixing bugs introduced in #2827 (though also improves what happened before that PR, so it's sort of an optimization too).
Resolved issues:
n/a
Description of changes:
This makes two changes: first, we fix a bug where we were lowering per-acceptor concurrency by total concurrency while the worker count was clamped at 4. This artificially shrunk the worker backlog limits more than it should.
Second, we change TCP sockets to have the full-sized backlog (4096 on Linux), which reduces the likelihood that Linux will drop incoming connections during transient spikes, causing overall overload on the system. For systems with high concurrency we were previously configuring very small backlogs (e.g., 32 connections) which can get overwhelmed at high accept rates and end up triggering syn flood protection. The above bug made this worse when we clamped concurrency.
Call-outs:
Testing:
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.