[ARROW-12030] [C++] Change dataset readahead to be based on available RAM/CPU instead of fixed constants/options

• Type: Improvement
• Status: Closed
• Priority: Major
• Resolution: Duplicate
• Component/s: C++
• External issue URL: https://github.com/apache/arrow/issues/27859
• Assignee: Weston Pace
• Reporter: Weston Pace
• Created: 20/Mar/21 02:01
• Updated: 11/Jan/23 08:23
• Resolved: 09/Nov/21 21:31

Description

Right now in the dataset scanning there are a few places where we add readahead.  At each spot we have to pick some max for how much we read ahead.  Instead of trying to figure out some max it might be nicer to base it on the available RAM.

On the other hand, it may be the case that there is some set of nice constants that just always works so this can probably wait until we understand more the memory usage of dataset scanning.

Issue Links

• duplicates: ARROW-14648 [C++][Dataset] Change scanner readahead limits to be based on bytes instead of number of batches