[ARROW-9707] [Rust] [DataFusion] Re-implement threading model

• Type: Sub-task
• Status: Closed
• Priority: Major
• Resolution: Invalid
• Fix Version/s: 3.0.0
• Component/s: Rust, Rust - DataFusion
• Labels: pull-request-available
• External issue URL: https://github.com/apache/arrow/issues/17305
• Assignee: Andy Grove
• Reporter: Andy Grove
• Created: 12/Aug/20 15:25
• Updated: 11/Jan/23 08:08
• Resolved: 14/Nov/20 16:00

Description

The current threading model is very simple and does not scale. We currently use 1-2 dedicated threads per partition and they all run simultaneously, which is a huge problem if you have more partitions than logical or physical cores.

This task is to re-implement the threading model so that query execution uses a fixed (configurable) number of threads. Work will be broken down into stages and tasks and each in-process executor (running on a dedicated thread) will process its queue of tasks.

This process will be driven by a scheduler.

Issue Links

• relates to: ARROW-10303 [Rust] Parallel type transformation in CSV reader
• links to: GitHub Pull Request #8283