This is an automated email from the ASF dual-hosted git repository.
vhs pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/hudi.git
The following commit(s) were added to refs/heads/master by this push:
new e4bc9851bf58 Explicitly state the spark stage name (#18416)
e4bc9851bf58 is described below
commit e4bc9851bf58ddd189de036137a29e7615828baf
Author: Surya Prasanna <[email protected]>
AuthorDate: Sun Mar 29 23:45:34 2026 -0700
Explicitly state the spark stage name (#18416)
---
.../org/apache/hudi/metadata/FileSystemBackedTableMetadata.java | 9 +++++++--
1 file changed, 7 insertions(+), 2 deletions(-)
diff --git
a/hudi-common/src/main/java/org/apache/hudi/metadata/FileSystemBackedTableMetadata.java
b/hudi-common/src/main/java/org/apache/hudi/metadata/FileSystemBackedTableMetadata.java
index a5c51b594641..2b882977ca8b 100644
---
a/hudi-common/src/main/java/org/apache/hudi/metadata/FileSystemBackedTableMetadata.java
+++
b/hudi-common/src/main/java/org/apache/hudi/metadata/FileSystemBackedTableMetadata.java
@@ -156,12 +156,16 @@ public class FileSystemBackedTableMetadata extends
AbstractHoodieTableMetadata {
needPushDownExpressions = false;
}
+ int recursiveListingStep = 0;
while (!pathsToList.isEmpty()) {
+ recursiveListingStep++;
// TODO: Get the parallelism from HoodieWriteConfig
int listingParallelism = Math.min(DEFAULT_LISTING_PARALLELISM,
pathsToList.size());
+ String recursiveListingJobName =
+ String.format("%s recursive listing step %d",
this.getClass().getSimpleName(), recursiveListingStep);
// List all directories in parallel
- engineContext.setJobStatus(this.getClass().getSimpleName(),
+ engineContext.setJobStatus(recursiveListingJobName,
"Listing all partitions on " + this.tableName
+ " with prefix " + relativePathPrefix);
// Need to use serializable file status here, see HUDI-5936
@@ -183,7 +187,8 @@ public class FileSystemBackedTableMetadata extends
AbstractHoodieTableMetadata {
if (!dirToFileListingPairs.isEmpty()) {
// result below holds a list of pair. first entry in the pair
optionally holds the deduced list of partitions.
// and second entry holds optionally a directory path to be processed
further.
- engineContext.setJobStatus(this.getClass().getSimpleName(),
"Processing listed partitions");
+ engineContext.setJobStatus(recursiveListingJobName,
+ "Processing recursively listed partitions on " + this.tableName);
List<Pair<Option<String>, Option<StoragePath>>> result =
engineContext.map(dirToFileListingPairs,
fileInfoPair -> {