[SPARK-45606] Release restrictions on multi-layer runtime filter

• Type: New Feature
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Affects Version/s: 4.0.0
• Fix Version/s: 4.0.0
• Component/s: SQL
• Labels: pull-request-available
• Assignee: Jiaan Geng
• Reporter: Jiaan Geng
• Created: 19/Oct/23 07:54
• Updated: 08/Nov/23 11:44
• Resolved: 08/Nov/23 11:44

Description

Before https://issues.apache.org/jira/browse/SPARK-41674, Spark only supports insert runtime filter for application side of shuffle join on single-layer. Considered it's not worth to insert more runtime filter if one side of the shuffle join already exists runtime filter, Spark restricts it.

After https://issues.apache.org/jira/browse/SPARK-41674, Spark supports insert runtime filter for one side of any shuffle join on multi-layer. But the restrictions on multi-layer runtime filter looks outdated.

Issue Links

• links to: GitHub Pull Request #43449