Apache Lucene open-source search software
Optimize ParallelLeafReader to improve term vector fetching efficiency (#14373)
DivyanshIITB9272d4d29a15
diff --git a/lucene/CHANGES.txt b/lucene/CHANGES.txtindex de9ec332aea..4ad08332ec1 100644--- a/lucene/CHANGES.txt+++ b/lucene/CHANGES.txt@@ -35,6 +35,7 @@ Optimizations---------------------* GITHUB#14011: Reduce allocation rate in HNSW concurrent merge. (Viliam Durina)* GITHUB#14022: Optimize DFS marking of connected components in HNSW by reducing stack depth, improving performance and reducing allocations. (Viswanath Kuchibhotla)+* GITHUB#14373: Optimized `ParallelLeafReader` to improve term vector fetching efficiency.Bug Fixes---------------------diff --git a/lucene/core/src/java/org/apache/lucene/index/ParallelLeafReader.java b/lucene/core/src/java/org/apache/lucene/index/ParallelLeafReader.javaindex c3ace74fb5b..d73f111785a 100644--- a/lucene/core/src/java/org/apache/lucene/index/ParallelLeafReader.java+++ b/lucene/core/src/java/org/apache/lucene/index/ParallelLeafReader.java@@ -348,15 +348,24 @@ public class ParallelLeafReader extends LeafReader {@Overridepublic Fields get(int docID) throws IOException {ParallelFields fields = null;- for (Map.Entry<String, LeafReader> ent : tvFieldToReader.entrySet()) {- String fieldName = ent.getKey();- TermVectors termVectors = readerToTermVectors.get(ent.getValue());- Terms vector = termVectors.get(docID, fieldName);- if (vector != null) {++ // Step 2: Fetch all term vectors once per reader+ for (Map.Entry<LeafReader, TermVectors> entry : readerToTermVectors.entrySet()) {+ TermVectors termVectors = entry.getValue();+ Fields docFields = termVectors.get(docID); // Fetch all fields at once++ if (docFields != null) {if (fields == null) {fields = new ParallelFields();}- fields.addField(fieldName, vector);++ // Step 3: Aggregate only required fields+ for (String fieldName : docFields) {+ Terms vector = docFields.terms(fieldName);+ if (vector != null) {+ fields.addField(fieldName, vector);+ }+ }}}