Refactor bulk quantization writing into a unified class #130354
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
elasticsearchmachine
added
v9.2.0
needs:triage
iverase
approved these changes
Jul 1, 2025
benwtrent
commented
Jul 1, 2025
Comment on lines
-155
to
-162
| writeQuantizedValue(postingsOutput, binaryValue, correction); | ||
| binarizedByteVectorValues.getCorrectiveTerms(ord); | ||
| postingsOutput.writeBytes(binaryValue, 0, binaryValue.length); | ||
| postingsOutput.writeInt(Float.floatToIntBits(correction.lowerInterval())); | ||
| postingsOutput.writeInt(Float.floatToIntBits(correction.upperInterval())); | ||
| postingsOutput.writeInt(Float.floatToIntBits(correction.additionalCorrection())); | ||
| assert correction.quantizedComponentSum() >= 0 && correction.quantizedComponentSum() <= 0xffff; | ||
| postingsOutput.writeShort((short) correction.quantizedComponentSum()); |
Member
Author
There was a problem hiding this comment.
We were actually writing all vectors TWICE in the tail of postings. This (just a tad) negatively impacted recall. This is also why the skew index test started failing as the testing value there apparently relied on this :/
benwtrent
added
auto-merge-without-approval
elasticsearchmachine
added
the
Team:Search Relevance
Collaborator
|
Pinging @elastic/es-search-relevance (Team:Search Relevance) |
mridula-s109
pushed a commit
to mridula-s109/elasticsearch
that referenced
this pull request
Jul 2, 2025
this is a small refactor, laying ground work for more generalized bulk writing. I did some benchmarking and there was no significant performance difference (as expected).
mridula-s109
pushed a commit
to mridula-s109/elasticsearch
that referenced
this pull request
Jul 3, 2025
this is a small refactor, laying ground work for more generalized bulk writing. I did some benchmarking and there was no significant performance difference (as expected).
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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.
this is a small refactor, laying ground work for more generalized bulk writing.
I did some benchmarking and there was no significant performance difference (as expected).