[
https://issues.apache.org/jira/browse/ARROW-12030?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17307360#comment-17307360
]
Weston Pace commented on ARROW-12030:
-------------------------------------
I think it's a problem either way (push vs pull). The problem is just
expressed in different ways and the failure condition is different. If you
have push then you have to explicitly add buffering or else you won't have back
pressure. If you have pull then you have to explicitly add buffering
(readahead) or else you won't have pipeline parallelism.
> [C++] Change dataset readahead to be based on available RAM/CPU instead of
> fixed constants/options
> --------------------------------------------------------------------------------------------------
>
> Key: ARROW-12030
> URL: https://issues.apache.org/jira/browse/ARROW-12030
> Project: Apache Arrow
> Issue Type: Improvement
> Components: C++
> Reporter: Weston Pace
> Assignee: Weston Pace
> Priority: Major
>
> 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.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
