fix(benches): reuse config for handshakes #5319
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
maddeleine
reviewed
May 21, 2025
- odd interaction of setup with shared configs
maddeleine
approved these changes
May 23, 2025
Co-authored-by: maddeleine <[email protected]>
goatgoose
approved these changes
May 27, 2025
Co-authored-by: Sam Clark <[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Outdated suggestions cannot be applied.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.
Description of changes:
We noticed some odd benchmark results from the recent change: #5305 . Notably the benchmark caused the performance of rustls and openssl handshakes to significantly degrade on RSA certs.
This change was ultimately the result of switching to a fresh config for each handshake. This is because the libcrypto EVP_PKEY rsa key will cache/precompute certain parts of the sign operation. This causes the first sign to be slower, later signs to be faster. In TLS, this causes the first handshake to be slower, and subsequent handshakes to be faster.
This PR changes the benchmarking setup to reuse the config across the measured handshakes, as that is a more "customer similar" environment.
Testing:
I remove the pkey_match implementation and observed the same handshake regression in s2n-tls.
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.