alexeykudinkin commented on code in PR #5829:
URL: https://github.com/apache/hudi/pull/5829#discussion_r894833120
##########
hudi-common/src/main/java/org/apache/hudi/metadata/FileSystemBackedTableMetadata.java:
##########
@@ -82,27 +83,35 @@ public List<String> getAllPartitionPaths() throws
IOException {
int listingParallelism = Math.min(DEFAULT_LISTING_PARALLELISM,
pathsToList.size());
// List all directories in parallel
- List<FileStatus[]> dirToFileListing = engineContext.map(pathsToList,
path -> {
+ List<Pair<Path, FileStatus[]>> dirToFileListing =
engineContext.map(pathsToList, path -> {
FileSystem fileSystem = path.getFileSystem(hadoopConf.get());
- return fileSystem.listStatus(path);
+ return Pair.of(path, fileSystem.listStatus(path));
}, listingParallelism);
pathsToList.clear();
// 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().startsWith(HoodiePartitionMetadata.HOODIE_PARTITION_METAFILE_PREFIX))
{
- String partitionName = FSUtils.getRelativePartitionPath(new
Path(datasetBasePath), fileStatus.getPath().getParent());
- partitionPaths.add(partitionName);
- }
- });
+ engineContext.foreach(dirToFileListing, new
SerializableConsumer<Pair<Path, FileStatus[]>>() {
+ @Override
+ public void accept(Pair<Path, FileStatus[]> p) throws Exception {
+ Option<FileStatus> partitionMetaFile =
Option.fromJavaOptional(Arrays.stream(p.getRight()).parallel()
+ .filter(fileStatus ->
fileStatus.getPath().getName().startsWith(HoodiePartitionMetadata.HOODIE_PARTITION_METAFILE_PREFIX))
+ .findFirst());
+
+ if (partitionMetaFile.isPresent()) {
+ // Is a partition.
+ String partitionName = FSUtils.getRelativePartitionPath(new
Path(datasetBasePath), p.getLeft());
Review Comment:
Please create a separate var for `new Path(datasetBasePath)`. `Path` ctor
has non-trivial amount of overhead
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
