Skip to content

perf(index): Use Set instead of ArrayList to reduce memory overhead in key lookup #17774

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

Open
prashantwason wants to merge 1 commit into
base: master
Choose a base branch
from
+6 −6
Open

perf(index): Use Set instead of ArrayList to reduce memory overhead in key lookup #17774

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 2 additions & 3 deletions hudi-client/hudi-client-common/src/main/java/org/apache/hudi/index/HoodieIndexUtils.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,7 +89,6 @@
import java.util.Map;
import java.util.Objects;
import java.util.Set;
import java.util.stream.Collectors;

import static java.util.stream.Collectors.toList;
import static org.apache.hudi.common.config.HoodieMetadataConfig.GLOBAL_RECORD_LEVEL_INDEX_ENABLE_PROP;
Expand Down Expand Up @@ -277,7 +276,7 @@ public static <R> HoodieRecord<R> tagRecord(HoodieRecord<R> record, HoodieRecord
* @return List of pairs of candidate keys and positions that are available in the file
*/
public static List<Pair<String, Long>> filterKeysFromFile(StoragePath filePath,
List<String> candidateRecordKeys,
Set<String> candidateRecordKeys,
HoodieStorage storage) throws HoodieIndexException {
checkArgument(FSUtils.isBaseFile(filePath));
List<Pair<String, Long>> foundRecordKeys = new ArrayList<>();
Expand All @@ -288,7 +287,7 @@ public static List<Pair<String, Long>> filterKeysFromFile(StoragePath filePath,
// Load all rowKeys from the file, to double-confirm
if (!candidateRecordKeys.isEmpty()) {
HoodieTimer timer = HoodieTimer.start();
Set<Pair<String, Long>> fileRowKeys = fileReader.filterRowKeys(candidateRecordKeys.stream().collect(Collectors.toSet()));
Set<Pair<String, Long>> fileRowKeys = fileReader.filterRowKeys(candidateRecordKeys);
foundRecordKeys.addAll(fileRowKeys);
log.info("Checked keys against file {}, in {} ms. #candidates ({}) #found ({})", filePath,
timer.endTimer(), candidateRecordKeys.size(), foundRecordKeys.size());
Expand Down
7 changes: 4 additions & 3 deletions hudi-client/hudi-client-common/src/main/java/org/apache/hudi/io/HoodieKeyLookupHandle.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,8 +31,9 @@
import lombok.extern.slf4j.Slf4j;

import java.io.IOException;
import java.util.ArrayList;
import java.util.HashSet;
import java.util.List;
import java.util.Set;

import static org.apache.hudi.metadata.MetadataPartitionType.BLOOM_FILTERS;

Expand All @@ -43,13 +44,13 @@
public class HoodieKeyLookupHandle<T, I, K, O> extends HoodieReadHandle<T, I, K, O> {

private final BloomFilter bloomFilter;
private final List<String> candidateRecordKeys;
private final Set<String> candidateRecordKeys;
private long totalKeysChecked;

public HoodieKeyLookupHandle(HoodieWriteConfig config, HoodieTable<T, I, K, O> hoodieTable,
Pair<String, String> partitionPathFileIDPair) {
super(config, hoodieTable, partitionPathFileIDPair);
this.candidateRecordKeys = new ArrayList<>();
this.candidateRecordKeys = new HashSet<>();
this.totalKeysChecked = 0;
this.bloomFilter = getBloomFilter();
}
Expand Down
Loading