Trie hash optimizations #5827
Merged
Trie hash optimizations #5827
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
dvush
requested review from
rkrasiuk,
rakita,
joshieDo and
gakonst
as code owners
|
Depends on alloy-rs/nybbles#1 |
|
cc @DaniPopes this should be in alloy-trie, correct? |
Only the primitives change. If you don't mind you can open a PR to https://github.com/alloy-rs/trie with the prealloc commit @dvush |
DaniPopes
requested changes
Dec 20, 2023
DaniPopes
reviewed
Dec 20, 2023
rkrasiuk
added
C-perf
|
@dvush in any follow-up perf PRs it would be great to see side by side comparison of flamegraphs / benches before and after the change. otherwise, it's tough to verify the performance boost from the changes. even some obvious "improvements" might degrade the performance as we've experienced in the past |
rkrasiuk
approved these changes
Dec 26, 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Outdated suggestions cannot be applied.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 PR improves a performance of the trie when calculating hash.
In my benchmark it reduces time from 100ms to 90ms and this 10ms are more noticeable in implementation that caches db reads for the trie.
The most influential commits are:
This key clone alone is mostly responsible for 10ms drop
Recently hashbrown was removed from the repo and it made all hash maps / sets much slower. Its mostly due to hashbrown using ahash for hashing while std is using siphash. This only changes hashmaps in trie related code but other parts of reth can benefit from it too.
push_branch_nodea bit. (without it about 20% of the method is spent doing this collect) (moved to prealloc children alloy-rs/trie#1)