feat: soft delete optimize

fudongyingluck · Jun 9, 2023 · d21ae98 · d21ae98
1 parent 5b63a18
commit d21ae98
Show file tree

Hide file tree

Showing 2 changed files with 11 additions and 4 deletions.
diff --git a/lucene/core/src/java/org/apache/lucene/index/MergePolicy.java b/lucene/core/src/java/org/apache/lucene/index/MergePolicy.java
@@ -741,8 +741,16 @@ public boolean useCompoundFile(
    * non-deleted documents is set.
    */
   protected long size(SegmentCommitInfo info, MergeContext mergeContext) throws IOException {
-    long byteSize = info.sizeInBytes();
     int delCount = mergeContext.numDeletesToMerge(info);
+    return size(info, delCount);
+  }
+
+  /**
+   * Return the byte size of the provided {@link SegmentCommitInfo}, pro-rated by percentage of
+   * non-deleted documents is set.
+   */
+  protected final long size(SegmentCommitInfo info, int delCount) throws IOException {
+    long byteSize = info.sizeInBytes();
     assert assertDelCount(delCount, info);
     double delRatio =
         info.info.maxDoc() <= 0 ? 0d : (double) delCount / (double) info.info.maxDoc();

diff --git a/lucene/core/src/java/org/apache/lucene/index/TieredMergePolicy.java b/lucene/core/src/java/org/apache/lucene/index/TieredMergePolicy.java
@@ -295,9 +295,8 @@ private List<SegmentSizeAndDocs> getSortedBySegmentSize(
     List<SegmentSizeAndDocs> sortedBySize = new ArrayList<>();
 
     for (SegmentCommitInfo info : infos) {
-      sortedBySize.add(
-          new SegmentSizeAndDocs(
-              info, size(info, mergeContext), mergeContext.numDeletesToMerge(info)));
+      final int delCount = mergeContext.numDeletesToMerge(info);
+      sortedBySize.add(new SegmentSizeAndDocs(info, size(info, delCount), delCount));
     }
 
     sortedBySize.sort(