[HADOOP-18739] Parallelize concatenation of distcp chunks of separate files in CopyCommitter

• Type: Improvement
• Status: Open
• Priority: Major
• Resolution: Unresolved
• Affects Version/s: 3.3.6
• Component/s: tools/distcp
• Labels: pull-request-available
• Target Version/s: 3.3.6
• Assignee: Unassigned
• Reporter: Abhay Yadav
• Created: 10/May/23 20:30
• Updated: 10/Jul/23 02:00

Description

While copying a folder containing large files consisting of multiple distcp chunks, copy committer synchronously picks chunks of each file and concatenates them. This part can be improved by parallelizing the concatenation of distcp chunks of separate files. We are able to save 2-3 minutes while copying a folder of 100 GB containing 20 files of 5GB size with this improvement.

Contributing a patch for this.

Issue Links

• links to: GitHub Pull Request #5640