[
https://issues.apache.org/jira/browse/ARROW-2458?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16438366#comment-16438366
]
ASF GitHub Bot commented on ARROW-2458:
---------------------------------------
pitrou commented on issue #1893: ARROW-2458: [Plasma] Use one thread pool per
PlasmaClient
URL: https://github.com/apache/arrow/pull/1893#issuecomment-381332975
In other words, I think the right way of improving the plasma client here
would be to have some global thread pool policy for Arrow. That global policy
can provide two separate thread pools, one for CPU-bound tasks (e.g. memcpy,
hashing or compression) and one for IO-bound tasks (such as file or network
tasks). The CPU-bound threadpool should have, by default, the machine's number
of HW threads (*). The IO-bound threadpool can have a multiple of that number
(e.g. 5x).
(*) e.g. through
http://en.cppreference.com/w/cpp/thread/thread/hardware_concurrency
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
> [Plasma] PlasmaClient uses global variable
> ------------------------------------------
>
> Key: ARROW-2458
> URL: https://issues.apache.org/jira/browse/ARROW-2458
> Project: Apache Arrow
> Issue Type: Improvement
> Components: Plasma (C++)
> Affects Versions: 0.9.0
> Reporter: Philipp Moritz
> Assignee: Philipp Moritz
> Priority: Major
> Labels: pull-request-available
>
> The threadpool threadpool_ that PlasmaClient is using is global at the
> moment. This prevents us from using multiple PlasmaClients in the same
> process (one per thread).
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
