Repository navigation
Reset visited set to buffer contents when a batch search resumes - #437
Open
yuejiaointel wants to merge 4 commits into
Open
yuejiaointel wants to merge 4 commits into
yuejiaointel wants to merge 4 commits into
Conversation
When the visited-set filter is enabled and a batch iterator resumes with a larger search window, nodes that were visited but later dropped from the buffer stayed marked as visited and could never be re-inserted. With a selective filter this collapsed recall. Add reset_visited_to_contents() to the search buffers and call it in RestartInitializer before sorting. Add a buffer unit test and a C API dynamic filtered-search recall test.
…resume # Conflicts: # include/svs/concurrent/dynamic_search_buffer.h # include/svs/concurrent/iterator.h
yuejiaointel
marked this pull request as ready for review
October 28, 2026 23:00
This branch has not been deployed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem: With the visited set on, a batch iterator that resumes keeps every id it has already seen, including ids that were later dropped from the buffer. Those ids can never be added again, so filtered search at low pass rates loses recall.
Fix: On resume, reset the visited set to the ids still in the buffer (
reset_visited_to_contents()inSearchBufferandMutableBuffer, called inRestartInitializer). It does nothing when the visited set is off. The concurrent index gets the fix through its base classes.Tests: No new tests. Existing
*Dynamic*,*Concurrent*,*Iterator*tests pass (except the unrelated "Binary Reader Iterator" temp-folder failure).🤖 Generated with Claude Code