Skip to content

[DiskBBQ] fix computation of scoreDocs #132530

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 7, 2025
Merged

[DiskBBQ] fix computation of scoreDocs #132530

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 16 additions & 17 deletions server/src/main/java/org/elasticsearch/index/codec/vectors/DefaultIVFVectorsReader.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -375,7 +375,7 @@ public int resetPostingsScorer(long offset) throws IOException {
return vectors;
}

float scoreIndividually(int offset) throws IOException {
private float scoreIndividually(int offset) throws IOException {
float maxScore = Float.NEGATIVE_INFINITY;
// score individually, first the quantized byte chunk
for (int j = 0; j < BULK_SIZE; j++) {
Expand Down Expand Up @@ -419,27 +419,25 @@ float scoreIndividually(int offset) throws IOException {
return maxScore;
}

private static int filterDocs(int[] docIds, int offset, IntPredicate needsScoring) {
int filtered = 0;
private static int docToBulkScore(int[] docIds, int offset, IntPredicate needsScoring) {
int docToScore = ES91OSQVectorsScorer.BULK_SIZE;
for (int i = 0; i < ES91OSQVectorsScorer.BULK_SIZE; i++) {
if (needsScoring.test(docIds[offset + i]) == false) {
docIds[offset + i] = -1;
filtered++;
final int idx = offset + i;
if (needsScoring.test(docIds[idx]) == false) {
docIds[idx] = -1;
docToScore--;
}
}
return filtered;
return docToScore;
}

private static int collect(int[] docIds, int offset, KnnCollector knnCollector, float[] scores) {
int scoredDocs = 0;
private static void collectBulk(int[] docIds, int offset, KnnCollector knnCollector, float[] scores) {
for (int i = 0; i < ES91OSQVectorsScorer.BULK_SIZE; i++) {
int doc = docIds[offset + i];
final int doc = docIds[offset + i];
if (doc != -1) {
scoredDocs++;
knnCollector.collect(doc, scores[i]);
}
}
return scoredDocs;
}

@Override
Expand All @@ -449,14 +447,14 @@ public int visit(KnnCollector knnCollector) throws IOException {
int limit = vectors - BULK_SIZE + 1;
int i = 0;
for (; i < limit; i += BULK_SIZE) {
int docsToScore = BULK_SIZE - filterDocs(docIdsScratch, i, needsScoring);
if (docsToScore == 0) {
final int docsToBulkScore = docToBulkScore(docIdsScratch, i, needsScoring);
if (docsToBulkScore == 0) {
continue;
}
quantizeQueryIfNecessary();
indexInput.seek(slicePos + i * quantizedByteLength);
float maxScore = Float.NEGATIVE_INFINITY;
if (docsToScore < BULK_SIZE / 2) {
final float maxScore;
if (docsToBulkScore < BULK_SIZE / 2) {
maxScore = scoreIndividually(i);
} else {
maxScore = osqVectorsScorer.scoreBulk(
Expand All @@ -471,8 +469,9 @@ public int visit(KnnCollector knnCollector) throws IOException {
);
}
if (knnCollector.minCompetitiveSimilarity() < maxScore) {
scoredDocs += collect(docIdsScratch, i, knnCollector, scores);
collectBulk(docIdsScratch, i, knnCollector, scores);
}
scoredDocs += docsToBulkScore;
}
// process tail
for (; i < vectors; i++) {
Expand Down