Skip to content

Speed up LuceneTopNSourceOperator #125622

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 5 commits into from
Mar 26, 2025
Merged

Speed up LuceneTopNSourceOperator #125622

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
62c278a
Use TOP_DOCS_WITH_SCORES score mode instead of COMPLETE
ioanatia Mar 25, 2025
02e4574
No need to track total hits when using LuceneTopNSourceOperator
ioanatia Mar 25, 2025
80be339
[CI] Auto commit changes from spotless
Mar 25, 2025
97de011
fix
ioanatia Mar 26, 2025
7b870f7
[CI] Auto commit changes from spotless
Mar 26, 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
8 changes: 4 additions & 4 deletions ...esql/compute/src/main/java/org/elasticsearch/compute/lucene/LuceneTopNSourceOperator.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,8 +43,8 @@
import java.util.function.Function;
import java.util.stream.Collectors;

import static org.apache.lucene.search.ScoreMode.COMPLETE;
import static org.apache.lucene.search.ScoreMode.TOP_DOCS;
import static org.apache.lucene.search.ScoreMode.TOP_DOCS_WITH_SCORES;

/**
* Source operator that builds Pages out of the output of a TopFieldCollector (aka TopN)
Expand All @@ -65,7 +65,7 @@ public Factory(
List<SortBuilder<?>> sorts,
boolean scoring
) {
super(contexts, queryFunction, dataPartitioning, taskConcurrency, limit, scoring ? COMPLETE : TOP_DOCS);
super(contexts, queryFunction, dataPartitioning, taskConcurrency, limit, scoring ? TOP_DOCS_WITH_SCORES : TOP_DOCS);
this.maxPageSize = maxPageSize;
this.sorts = sorts;
}
Expand Down Expand Up @@ -287,7 +287,7 @@ PerShardCollector newPerShardCollector(ShardContext shardContext, List<SortBuild
SortField[] sortFields = sortAndFormats.get().sort.getSort();
if (sortFields != null && sortFields.length == 1 && sortFields[0].needsScores() && sortFields[0].getReverse() == false) {
// SORT _score DESC
return new ScoringPerShardCollector(shardContext, new TopScoreDocCollectorManager(limit, null, limit).newCollector());
return new ScoringPerShardCollector(shardContext, new TopScoreDocCollectorManager(limit, null, 0).newCollector());
} else {
// SORT ..., _score, ...
var sort = new Sort();
Expand All @@ -297,7 +297,7 @@ PerShardCollector newPerShardCollector(ShardContext shardContext, List<SortBuild
l.add(SortField.FIELD_SCORE);
sort = new Sort(l.toArray(SortField[]::new));
}
return new ScoringPerShardCollector(shardContext, new TopFieldCollectorManager(sort, limit, null, limit).newCollector());
return new ScoringPerShardCollector(shardContext, new TopFieldCollectorManager(sort, limit, null, 0).newCollector());
}
}
}
Expand Down
7 changes: 4 additions & 3 deletions .../src/test/java/org/elasticsearch/compute/lucene/LuceneTopNSourceOperatorScoringTests.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,15 +110,16 @@ public Optional<SortAndFormats> buildSort(List<SortBuilder<?>> sorts) {
@Override
protected Matcher<String> expectedToStringOfSimple() {
return matchesRegex(
"LuceneTopNSourceOperator\\[shards = \\[test], maxPageSize = \\d+, limit = 100, scoreMode = COMPLETE, sorts = \\[\\{.+}]]"
"LuceneTopNSourceOperator\\[shards = \\[test], "
+ "maxPageSize = \\d+, limit = 100, scoreMode = TOP_DOCS_WITH_SCORES, sorts = \\[\\{.+}]]"
);
}

@Override
protected Matcher<String> expectedDescriptionOfSimple() {
return matchesRegex(
"LuceneTopNSourceOperator"
+ "\\[dataPartitioning = (DOC|SHARD|SEGMENT), maxPageSize = \\d+, limit = 100, scoreMode = COMPLETE, sorts = \\[\\{.+}]]"
"LuceneTopNSourceOperator\\[dataPartitioning = (DOC|SHARD|SEGMENT), "
+ "maxPageSize = \\d+, limit = 100, scoreMode = TOP_DOCS_WITH_SCORES, sorts = \\[\\{.+}]]"
);
}

Expand Down
4 changes: 2 additions & 2 deletions ...compute/src/test/java/org/elasticsearch/compute/lucene/LuceneTopNSourceOperatorTests.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -114,15 +114,15 @@ public Optional<SortAndFormats> buildSort(List<SortBuilder<?>> sorts) {

@Override
protected Matcher<String> expectedToStringOfSimple() {
var s = scoring ? "COMPLETE" : "TOP_DOCS";
var s = scoring ? "TOP_DOCS_WITH_SCORES" : "TOP_DOCS";
return matchesRegex(
"LuceneTopNSourceOperator\\[shards = \\[test], maxPageSize = \\d+, limit = 100, scoreMode = " + s + ", sorts = \\[\\{.+}]]"
);
}

@Override
protected Matcher<String> expectedDescriptionOfSimple() {
var s = scoring ? "COMPLETE" : "TOP_DOCS";
var s = scoring ? "TOP_DOCS_WITH_SCORES" : "TOP_DOCS";
return matchesRegex(
"LuceneTopNSourceOperator"
+ "\\[dataPartitioning = (DOC|SHARD|SEGMENT), maxPageSize = \\d+, limit = 100, scoreMode = "
Expand Down