Skip to content

Fix ivf nodestats impl for getOffHeapByteSize #129259

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 2 commits into from
Jun 11, 2025
Merged

Fix ivf nodestats impl for getOffHeapByteSize #129259

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1f685c9
Fix ivf nodestats impl for getOffHeapByteSize
benwtrent Jun 11, 2025
4249eee
adding test
benwtrent Jun 11, 2025
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
59 changes: 6 additions & 53 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 @@ -11,7 +11,6 @@

import org.apache.lucene.codecs.hnsw.FlatVectorsReader;
import org.apache.lucene.index.FieldInfo;
import org.apache.lucene.index.FloatVectorValues;
import org.apache.lucene.index.SegmentReadState;
import org.apache.lucene.index.VectorSimilarityFunction;
import org.apache.lucene.search.KnnCollector;
Expand All @@ -20,10 +19,12 @@
import org.apache.lucene.util.VectorUtil;
import org.apache.lucene.util.hnsw.NeighborQueue;
import org.apache.lucene.util.quantization.OptimizedScalarQuantizer;
import org.elasticsearch.index.codec.vectors.reflect.OffHeapStats;
import org.elasticsearch.simdvec.ES91OSQVectorsScorer;
import org.elasticsearch.simdvec.ESVectorUtil;

import java.io.IOException;
import java.util.Map;
import java.util.function.IntPredicate;

import static org.apache.lucene.codecs.lucene102.Lucene102BinaryQuantizedVectorsFormat.QUERY_BITS;
Expand All @@ -38,7 +39,7 @@
* Default implementation of {@link IVFVectorsReader}. It scores the posting lists centroids using
* brute force and then scores the top ones using the posting list.
*/
public class DefaultIVFVectorsReader extends IVFVectorsReader {
public class DefaultIVFVectorsReader extends IVFVectorsReader implements OffHeapStats {
Copy link
Contributor

@ChrisHegarty ChrisHegarty Jun 11, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

++ Implementing OffHeapStats is right, until we get to lucene 10.3.

private static final float FOUR_BIT_SCALE = 1f / ((1 << 4) - 1);

public DefaultIVFVectorsReader(SegmentReadState state, FlatVectorsReader rawVectorsReader) throws IOException {
Expand Down Expand Up @@ -163,57 +164,9 @@ static float int4QuantizedScore(
}
}

static class OffHeapCentroidFloatVectorValues extends FloatVectorValues {
private final int numCentroids;
private final IndexInput input;
private final int dimension;
private final float[] centroid;
private final long centroidByteSize;
private int ord = -1;

OffHeapCentroidFloatVectorValues(int numCentroids, IndexInput input, int dimension) {
this.numCentroids = numCentroids;
this.input = input;
this.dimension = dimension;
this.centroid = new float[dimension];
this.centroidByteSize = dimension + 3 * Float.BYTES + Short.BYTES;
}

@Override
public float[] vectorValue(int ord) throws IOException {
if (ord < 0 || ord >= numCentroids) {
throw new IllegalArgumentException("ord must be in [0, " + numCentroids + "]");
}
if (ord == this.ord) {
return centroid;
}
readQuantizedCentroid(ord);
return centroid;
}

private void readQuantizedCentroid(int centroidOrdinal) throws IOException {
if (centroidOrdinal == ord) {
return;
}
input.seek(numCentroids * centroidByteSize + (long) Float.BYTES * dimension * centroidOrdinal);
input.readFloats(centroid, 0, centroid.length);
ord = centroidOrdinal;
}

@Override
public int dimension() {
return dimension;
}

@Override
public int size() {
return numCentroids;
}

@Override
public FloatVectorValues copy() throws IOException {
return new OffHeapCentroidFloatVectorValues(numCentroids, input.clone(), dimension);
}
@Override
public Map<String, Long> getOffHeapByteSize(FieldInfo fieldInfo) {
return Map.of();
}

private static class MemorySegmentPostingsVisitor implements PostingVisitor {
Expand Down