Skip to content
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

Jump to bottom

Integrate merge-time index reordering with the intra-merge executor. #13289

Merged
merged 4 commits into from
Sep 12, 2024
Merged

Integrate merge-time index reordering with the intra-merge executor. #13289

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
a327d45
Integrate merge-time index reordering with the intra-merge executor.
jpountz Apr 10, 2024
bc6aee5
Merge branch 'main' into reordering_intra_merge_executor
jpountz Sep 11, 2024
3baa392
Use TaskExecutor's work stealing logic.
jpountz Sep 11, 2024
d54d4d1
Merge remote-tracking branch 'origin/main' into reordering_intra_merg…
jpountz Sep 12, 2024
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
19 changes: 12 additions & 7 deletions lucene/core/src/java/org/apache/lucene/index/IndexWriter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,7 @@
import java.util.Queue;
import java.util.Set;
import java.util.concurrent.ConcurrentLinkedQueue;
import java.util.concurrent.Executor;
import java.util.concurrent.Semaphore;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.atomic.AtomicBoolean;
Expand Down Expand Up @@ -3434,9 +3435,11 @@ public void addIndexesReaderMerge(MergePolicy.OneMerge merge) throws IOException
.map(FieldInfos::getParentField)
.anyMatch(Objects::isNull);

final Executor intraMergeExecutor = mergeScheduler.getIntraMergeExecutor(merge);

if (hasIndexSort == false && hasBlocksButNoParentField == false && readers.isEmpty() == false) {
CodecReader mergedReader = SlowCompositeCodecReaderWrapper.wrap(readers);
DocMap docMap = merge.reorder(mergedReader, directory);
DocMap docMap = merge.reorder(mergedReader, directory, intraMergeExecutor);
if (docMap != null) {
readers = Collections.singletonList(SortingCodecReader.wrap(mergedReader, docMap, null));
}
Expand All @@ -3450,7 +3453,7 @@ public void addIndexesReaderMerge(MergePolicy.OneMerge merge) throws IOException
trackingDir,
globalFieldNumberMap,
context,
mergeScheduler.getIntraMergeExecutor(merge));
intraMergeExecutor);

if (!merger.shouldMerge()) {
return;
Expand Down Expand Up @@ -3928,9 +3931,9 @@ public CodecReader wrapForMerge(CodecReader reader) throws IOException {
}

@Override
public Sorter.DocMap reorder(CodecReader reader, Directory dir)
throws IOException {
return toWrap.reorder(reader, dir); // must delegate
public Sorter.DocMap reorder(
CodecReader reader, Directory dir, Executor executor) throws IOException {
return toWrap.reorder(reader, dir, executor); // must delegate
}

@Override
Expand Down Expand Up @@ -5205,6 +5208,8 @@ public int length() {
mergeReaders.add(wrappedReader);
}

final Executor intraMergeExecutor = mergeScheduler.getIntraMergeExecutor(merge);

MergeState.DocMap[] reorderDocMaps = null;
// Don't reorder if an explicit sort is configured.
final boolean hasIndexSort = config.getIndexSort() != null;
Expand All @@ -5219,7 +5224,7 @@ public int length() {
if (hasIndexSort == false && hasBlocksButNoParentField == false) {
// Create a merged view of the input segments. This effectively does the merge.
CodecReader mergedView = SlowCompositeCodecReaderWrapper.wrap(mergeReaders);
Sorter.DocMap docMap = merge.reorder(mergedView, directory);
Sorter.DocMap docMap = merge.reorder(mergedView, directory, intraMergeExecutor);
if (docMap != null) {
reorderDocMaps = new MergeState.DocMap[mergeReaders.size()];
int docBase = 0;
Expand Down Expand Up @@ -5249,7 +5254,7 @@ public int length() {
dirWrapper,
globalFieldNumberMap,
context,
mergeScheduler.getIntraMergeExecutor(merge));
intraMergeExecutor);
merge.info.setSoftDelCount(Math.toIntExact(softDeleteCount.get()));
merge.checkAborted();

Expand Down
8 changes: 6 additions & 2 deletions lucene/core/src/java/org/apache/lucene/index/MergePolicy.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@
import java.util.concurrent.CancellationException;
import java.util.concurrent.CompletableFuture;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.Executor;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;
import java.util.concurrent.atomic.AtomicLong;
Expand Down Expand Up @@ -292,7 +293,7 @@ final void close(
* Wrap a reader prior to merging in order to add/remove fields or documents.
*
* <p><b>NOTE:</b> It is illegal to reorder doc IDs here, use {@link
* #reorder(CodecReader,Directory)} instead.
* #reorder(CodecReader,Directory,Executor)} instead.
*/
public CodecReader wrapForMerge(CodecReader reader) throws IOException {
return reader;
Expand All @@ -308,9 +309,12 @@ public CodecReader wrapForMerge(CodecReader reader) throws IOException {
*
* @param reader The reader to reorder.
* @param dir The {@link Directory} of the index, which may be used to create temporary files.
* @param executor An executor that can be used to parallelize the reordering logic. May be
* {@code null} if no concurrency is supported.
* @lucene.experimental
*/
public Sorter.DocMap reorder(CodecReader reader, Directory dir) throws IOException {
public Sorter.DocMap reorder(CodecReader reader, Directory dir, Executor executor)
throws IOException {
return null;
}

Expand Down
Loading