amogh-jahagirdar commented on a change in pull request #4052:
URL: https://github.com/apache/iceberg/pull/4052#discussion_r810399883
##########
File path: aws/src/main/java/org/apache/iceberg/aws/s3/S3FileIO.java
##########
@@ -100,6 +114,66 @@ public void deleteFile(String path) {
client().deleteObject(deleteRequest);
}
+ /**
+ * Deletes the given paths in a batched manner.
+ * <p>
+ * The paths are grouped by bucket, and deletion is triggered when we either
reach the configured batch size
+ * or have a final remainder batch for each bucket.
+ *
+ * @param paths paths to delete
+ */
+ @Override
+ public void deleteFiles(Iterable<String> paths) {
+ SetMultimap<String, String> bucketToObjects =
Multimaps.newSetMultimap(Maps.newHashMap(), Sets::newHashSet);
+ List<String> failedDeletions = Lists.newArrayList();
+ for (String path : paths) {
+ S3URI location = new S3URI(path);
+ String bucket = location.bucket();
+ String objectKey = location.key();
+ Set<String> objectsInBucket = bucketToObjects.get(bucket);
+ if (objectsInBucket.size() == awsProperties.s3FileIoDeleteBatchSize()) {
+ List<String> failedDeletionsForBatch = deleteObjectsInBucket(bucket,
objectsInBucket);
+ failedDeletions.addAll(failedDeletionsForBatch);
+ bucketToObjects.removeAll(bucket);
+ }
+ bucketToObjects.get(bucket).add(objectKey);
+ }
+ // Delete the remainder
+ List<List<String>> remainderFailedObjects = bucketToObjects
+ .asMap()
+ .entrySet()
+ .stream()
+ .map(entry -> deleteObjectsInBucket(entry.getKey(), entry.getValue()))
+ .collect(Collectors.toList());
+
+ remainderFailedObjects.forEach(failedDeletions::addAll);
+ if (!failedDeletions.isEmpty()) {
+ throw new S3BatchDeletionException(String.format("Failed to delete %d
objects. Failed objects: %s",
Review comment:
Yeah totally right on a exploding list, we shouldn't log that. I'll just
log the count
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
