apache / apache/datafusion

[EPIC] (Even More) Grouping / Group By / Aggregation Performance

Open
#7,000 12 comments 0 reactions 0 assignees View on GitHub
enhancement PROPOSAL EPIC
Dominant language
Rust
Stars
9.3k
Forks
2.4k
Avg merge
3d 7h
Merged PRs (30d)
344

Description

### Is your feature request related to a problem or challenge?

Aggregation is a key operation of Analytic engines. DataFusion has made great progress recently (e.g. https://github.com/apache/arrow-datafusion/issues/4973 and https://github.com/apache/arrow-datafusion/issues/6889)

This Epic gathers other potential ways we can improve the performance of aggregation

Core Hash Grouping Algorithm:
- [x] https://github.com/apache/arrow-datafusion/issues/6969
- [x] https://github.com/apache/arrow-datafusion/issues/7064
- [x] https://github.com/apache/arrow-datafusion/issues/9403
- [x] https://github.com/apache/arrow-datafusion/issues/7023
- [x] https://github.com/apache/arrow-datafusion/issues/7095

Specialized Aggregators:
- [x] https://github.com/apache/arrow-datafusion/issues/6906
- [x] https://github.com/apache/arrow-datafusion/issues/5547
- [x] https://github.com/apache/arrow-datafusion/issues/5472
- [ ] https://github.com/apache/arrow-datafusion/issues/7065
- [ ] https://github.com/apache/arrow-datafusion/issues/7066

New features:
- [x] https://github.com/apache/arrow-datafusion/issues/6937
- [ ] https://github.com/apache/arrow-datafusion/issues/9562
- [ ] https://github.com/apache/arrow-datafusion/issues/8699
- [x] https://github.com/apache/arrow-datafusion/issues/8934

Improved partitioning:
- [ ] https://github.com/apache/arrow-datafusion/issues/6928
- [ ] https://github.com/apache/arrow-datafusion/issues/7001
- [ ] https://github.com/apache/arrow-datafusion/issues/6822

### Describe the solution you'd like

_No response_

### Describe alternatives you've considered

_No response_

### Additional context

_No response_

Contributor guide

Open the contributing guide

Research direction

The payload names no files, tests, or entry points. Start by opening the unchecked linked issues 7065, 7066, 9562, 8699, 6928, 7001, and 6822; completion must follow the selected issue's scope and acceptance criteria rather than this umbrella epic.

Written by the indexing model from the issue text.

Assessment

Tech stack
rust, sql
Domain
data-engineering, databases, performance
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.