Skip to content

Feature: Radix hash join #7315

Open
Open
@leiysky

Description

@leiysky

Radix hash join is a join algorithm that partitions input data of both sides into small buckets that can fit CPU cache, to improve the performance of hash join.

In opposite to radix hash join, we are using a shared hash table fashion now, which cannot utilize with CPU cache as good as radix hash join but works well with our Processor execution engine.

It will be nice if we can provide an option to use radix hash join in a query.

Metadata

Metadata

Assignees

Labels

A-executorArea: processor and shuffleC-featureCategory: featurestaleIssue has not had recent activity or appears to be solved. Stale issues will be automatically closed

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions