apache / apache/datafusion

[EPIC] A collection of Memory Accounting Limitations and Improvements

Open
#22,758 18 comments 8 reactions 0 assignees View on GitHub
Dominant language
Rust
Stars
9.3k
Forks
2.4k
Avg merge
3d 7h
Merged PRs (30d)
344

Description

As DataFusion gets used more in production systems there is more of an interest in improving its memory accounting model. This epic lists related issues to try and get some organized discussion going

- [ ] https://github.com/apache/datafusion/issues/20714 from @cetra3
- [ ] https://github.com/apache/datafusion/issues/16841 from @gabotechs
- [ ] https://github.com/apache/datafusion/issues/22723 from @avantgardnerio
- [ ] https://github.com/apache/datafusion/issues/22739 from @avantgardnerio
- [ ] https://github.com/apache/datafusion/issues/14748 from @2010YOUY01
- [ ] https://github.com/apache/datafusion/issues/22757 from @Samyak2
- [ ] https://github.com/apache/datafusion/issues/22526 from @ariel-miculas
- [x] https://github.com/apache/datafusion/issues/16517 from @sfluor
- [ ] https://github.com/apache/datafusion/issues/22861 from @jordepic

Contributor guide

Open the contributing guide

Research direction

Start by reading the linked issues, especially the unchecked items, and review the discussion in this epic. No source files, tests, or implementation entry point are named; completion is not defined beyond organizing discussion and tracking progress on the related memory-accounting limitations.

Written by the indexing model from the issue text.

Assessment

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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.