[FLINK-29551] Improving adaptive hash join by using sort merge join strategy per partition instead of all partitions

• Type: Improvement
• Status: Open
• Priority: Major
• Resolution: Unresolved
• Affects Version/s: 1.16.0
• Fix Version/s: 1.20.0
• Component/s: Table SQL / Runtime
• Labels: pull-request-available
• Assignee: Unassigned
• Reporter: dalongliu
• Created: 09/Oct/22 02:27
• Updated: 11/Mar/24 12:44

Description

Currently, regarding adaptive hash join, when falling back to sort-merge join, it sorts all partitions globally, however, due to the keys of each partition are disjoint, we can sort it per partition, which can improve the performance.

Issue Links

• links to: GitHub Pull Request #20996