lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

[HUDI-3281][Performance]Tuning performance of getAllPartitionPaths API in FileSystemBackedTableMetadata (#4643)

Browse Source 
Co-authored-by: yuezhang <yuezhang@freewheel.tv>
This commit is contained in:
YueZhang
2022-01-21 07:47:02 +08:00
committed by GitHub
parent 2071e3bfda
commit 79bf6ab00b
1 changed files with 21 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
hudi-common/src/main/java/org/apache/hudi/metadata/FileSystemBackedTableMetadata.java
View File

@@ -31,12 +31,11 @@ import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Collections;
import java.util.LinkedList;
import java.util.List;
import java.util.Map;
import java.util.concurrent.CopyOnWriteArrayList;
import java.util.stream.Collectors;
public class FileSystemBackedTableMetadata implements HoodieTableMetadata {
@@ -64,45 +63,41 @@ public class FileSystemBackedTableMetadata implements HoodieTableMetadata {
@Override
public List<String> getAllPartitionPaths() throws IOException {
FileSystem fs = new Path(datasetBasePath).getFileSystem(hadoopConf.get());
if (assumeDatePartitioning) {
FileSystem fs = new Path(datasetBasePath).getFileSystem(hadoopConf.get());
return FSUtils.getAllPartitionFoldersThreeLevelsDown(fs, datasetBasePath);
}
List<Path> pathsToList = new LinkedList<>();
List<Path> pathsToList = new CopyOnWriteArrayList<>();
pathsToList.add(new Path(datasetBasePath));
List<String> partitionPaths = new ArrayList<>();
List<String> partitionPaths = new CopyOnWriteArrayList<>();
while (!pathsToList.isEmpty()) {
// TODO: Get the parallelism from HoodieWriteConfig
int listingParallelism = Math.min(DEFAULT_LISTING_PARALLELISM, pathsToList.size());
// List all directories in parallel
List<Pair<Path, FileStatus[]>> dirToFileListing = engineContext.map(pathsToList, path -> {
List<FileStatus[]> dirToFileListing = engineContext.map(pathsToList, path -> {
FileSystem fileSystem = path.getFileSystem(hadoopConf.get());
return Pair.of(path, fileSystem.listStatus(path));
return fileSystem.listStatus(path);
}, listingParallelism);
pathsToList.clear();
// If the listing reveals a directory, add it to queue. If the listing reveals a hoodie partition, add it to
// the results.
dirToFileListing.forEach(p -> {
Option<FileStatus> partitionMetaFile = Option.fromJavaOptional(Arrays.stream(p.getRight()).parallel()
.filter(fs -> fs.getPath().getName().equals(HoodiePartitionMetadata.HOODIE_PARTITION_METAFILE))
.findFirst());
if (partitionMetaFile.isPresent()) {
// Is a partition.
String partitionName = FSUtils.getRelativePartitionPath(new Path(datasetBasePath), p.getLeft());
partitionPaths.add(partitionName);
} else {
// Add sub-dirs to the queue
pathsToList.addAll(Arrays.stream(p.getRight())
.filter(fs -> fs.isDirectory() && !fs.getPath().getName().equals(HoodieTableMetaClient.METAFOLDER_NAME))
.map(fs -> fs.getPath())
.collect(Collectors.toList()));
}
});
// if current dictionary contains PartitionMetadata, add it to result
// if current dictionary does not contain PartitionMetadata, add it to queue
dirToFileListing.stream().flatMap(Arrays::stream).parallel()
.forEach(fileStatus -> {
if (fileStatus.isDirectory()) {
if (HoodiePartitionMetadata.hasPartitionMetadata(fs, fileStatus.getPath())) {
partitionPaths.add(FSUtils.getRelativePartitionPath(new Path(datasetBasePath), fileStatus.getPath()));
} else if (!fileStatus.getPath().getName().equals(HoodieTableMetaClient.METAFOLDER_NAME)) {
pathsToList.add(fileStatus.getPath());
}
} else if (fileStatus.getPath().getName().equals(HoodiePartitionMetadata.HOODIE_PARTITION_METAFILE)) {
String partitionName = FSUtils.getRelativePartitionPath(new Path(datasetBasePath), fileStatus.getPath().getParent());
partitionPaths.add(partitionName);
}
});
}
return partitionPaths;
}