vinothchandar commented on code in PR #5829:
URL: https://github.com/apache/hudi/pull/5829#discussion_r929286057
##########
hudi-common/src/main/java/org/apache/hudi/metadata/FileSystemBackedTableMetadata.java:
##########
@@ -68,41 +68,46 @@ public FileStatus[] getAllFilesInPartition(Path
partitionPath) throws IOExceptio
@Override
public List<String> getAllPartitionPaths() throws IOException {
- FileSystem fs = new Path(datasetBasePath).getFileSystem(hadoopConf.get());
+ Path basePath = new Path(datasetBasePath);
+ FileSystem fs = basePath.getFileSystem(hadoopConf.get());
if (assumeDatePartitioning) {
return FSUtils.getAllPartitionFoldersThreeLevelsDown(fs,
datasetBasePath);
}
List<Path> pathsToList = new CopyOnWriteArrayList<>();
- pathsToList.add(new Path(datasetBasePath));
+ pathsToList.add(basePath);
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<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);
- }
- });
+ dirToFileListing.forEach(p -> {
Review Comment:
don't we have an utilty for this in FSUtils.
##########
hudi-common/src/main/java/org/apache/hudi/metadata/FileSystemBackedTableMetadata.java:
##########
@@ -82,27 +82,31 @@ 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);
- }
- });
+ dirToFileListing.forEach(p -> {
+ Option<FileStatus> partitionMetaFile =
Option.fromJavaOptional(Arrays.stream(p.getRight()).parallel()
+ .filter(fileStatus ->
fileStatus.getPath().getName().equals(HoodiePartitionMetadata.HOODIE_PARTITION_METAFILE_PREFIX))
+ .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(fileStatus -> fileStatus.isDirectory() &&
!fileStatus.getPath().getName().equals(HoodieTableMetaClient.METAFOLDER_NAME))
Review Comment:
is there a follow up JIRA?
##########
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()
Review Comment:
+1 . I think if we simply do the processing we need to do within the single
engineContext.map(..) call, we should be able to solve the original problem in
#4643.
--
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]
