Repository navigation
DDIR: reuse run descriptor storage in hashed joins - #951
Merged
frankmcsherry merged 1 commit intoOct 19, 2026
Merged
frankmcsherry merged 1 commit into
frankmcsherry merged 1 commit into
Conversation
frankmcsherry
force-pushed
the
ddir-join-run-scratch
branch
from
October 19, 2026 00:26
d596f5b to
1b79e8b
Compare
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Symmetric joins with hashed keys rebuild two run-descriptor lists for every matched key. When a key spans more than four chunks, both lists spill to the heap and allocate again for the next key. Reuse the buffers within each block, clearing their entries while retaining capacity.
The focused regression exercises both key shapes, cancellation, and fewer runs after a spill. The implementation change is confined to the hashed-key walk. This PR is one commit directly on
master-next, changing onlyinteractive/src/corgi/join.rs.Earlier native M4 presentation controls (4096 hashed pair keys, two values/key, eight chunks/side) measured 8,603 → 413 allocation requests/pass and 1,509 → 1,434 ns/key. Those measurements precede this rebase; timings were not rerun for this update. The change removes local allocation while preserving the Corgi comparison calls.
Validation of the rebased change on mini-02, Rust 1.95:
cargo test --locked --offline -p interactive -p ddir-server: 185 passed, five existing ignores.cargo clippy --locked --offline -p interactive -p ddir-server --all-targets: passes with repository warnings.