Apache Lucene open-source search software
Change `set.removeAll(list)` to `list.forEach(set::remove)` (#13052)
Dmitry Cherniachenko39c10a292912
diff --git a/lucene/CHANGES.txt b/lucene/CHANGES.txtindex f0a5dea07a8..2db6735e644 100644--- a/lucene/CHANGES.txt+++ b/lucene/CHANGES.txt@@ -228,6 +228,8 @@ Optimizationsthis will help boolean queries that consist of a mix OF FILTER clauses andSHOULD clauses. (Adrien Grand)+* GITHUB#13052: Avoid set.removeAll(list) O(n^2) performance trap in the UpgradeIndexMergePolicy (Dmitry Cherniachenko)+Bug Fixes---------------------* GITHUB#12866: Prevent extra similarity computation for single-level HNSW graphs. (Kaival Parikh)diff --git a/lucene/core/src/java/org/apache/lucene/index/UpgradeIndexMergePolicy.java b/lucene/core/src/java/org/apache/lucene/index/UpgradeIndexMergePolicy.javaindex 655d5747ec4..944fd780d8c 100644--- a/lucene/core/src/java/org/apache/lucene/index/UpgradeIndexMergePolicy.java+++ b/lucene/core/src/java/org/apache/lucene/index/UpgradeIndexMergePolicy.java@@ -106,7 +106,11 @@ public class UpgradeIndexMergePolicy extends FilterMergePolicy {// the resulting set contains all segments that are left over// and will be merged to one additional segment:for (final OneMerge om : spec.merges) {- oldSegments.keySet().removeAll(om.segments);+ // om.segments.forEach(::remove) is used here instead of oldSegments.keySet().removeAll()+ // for performance reasons; when om.segments.size() == oldSegments.size()+ // the AbstractSet#removeAll() implementation will iterate the set elements+ // calling list.contains() for each of them, resulting in O(n^2) performance+ om.segments.forEach(oldSegments::remove);}}