Consider row-count skew when skipping aggregate repartitioning

未关闭
#27,268 0 条评论 1 个 reaction 已指派 0 人 在 GitHub 查看

维护者通常 1 天内回复

还没有人认领这个 Issue。

评估

难度
4/5
预计耗时
3-5 天
新手友好度
52/100
Issue 类型
功能
描述清晰度
基本清楚
活跃度
活跃
技术栈
rust

调研方向

Start by reading the aggregate repartitioning decision and its tests in DataFusion, then trace how preserve_file_partitions, target_partitions, and per-partition row counts affect the SinglePartitioned plan. Use the skewed four-file benchmark in the issue as a performance reference; done means skew can trigger a shuffle when its load-balancing benefit outweighs the shuffle cost, without regressing balanced inputs.

由索引模型根据 Issue 内容生成。

描述

Skipping aggregate repartitioning can preserve a heavily skewed input layout, leaving most of the grouping work on one worker even when more execution partitions are available.

In Jay's benchmark on #27135, one of four files held 97% of 16M rows. With preserve_file_partitions enabled and mostly unique groups, the SinglePartitioned plan took 4.11 times as long as the shuffle plan at target_partitions=8. The two-argument date_bin showed the same behavior.

Consider per-partition row counts when deciding whether to skip aggregate repartitioning, so a shuffle can still be used when its load-balancing benefit outweighs its cost. Related to #19269, which describes the same trade-off for hash-subset partitioning.

主要语言
Rust
星标
9.6k
派生
2.6k
平均合并
3 天 4 小时
30 天内合并 PR
345

环境准备

在 Codespaces 中打开

在浏览器里用你自己的 GitHub 账号启动这个项目的开发容器。

从这里开始

  1. 先读完整个 Issue,再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库,在一个分支上完成修改。
  4. 提交 Pull Request,并在描述里引用这个 Issue 编号。

apache/datafusion 的其他 Issue

查看 apache/datafusion 的全部 Issue

相似的 Issue

更多 Rust Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。