You are viewing a plain text version of this content. The canonical link for it is here.
Posted to jira@arrow.apache.org by "David Li (Jira)" <ji...@apache.org> on 2021/05/13 15:06:00 UTC
[jira] [Updated] (ARROW-12760) [C++][Python][R] S3FileSystem: IO
thread parallelism limited to 8 threads
[ https://issues.apache.org/jira/browse/ARROW-12760?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
David Li updated ARROW-12760:
-----------------------------
Summary: [C++][Python][R] S3FileSystem: IO thread parallelism limited to 8 threads (was: [C++][Python] S3FileSystem: IO thread parallelism limited to 8 threads)
> [C++][Python][R] S3FileSystem: IO thread parallelism limited to 8 threads
> -------------------------------------------------------------------------
>
> Key: ARROW-12760
> URL: https://issues.apache.org/jira/browse/ARROW-12760
> Project: Apache Arrow
> Issue Type: Improvement
> Components: C++, Python, R
> Affects Versions: 4.0.0
> Reporter: Juan Galvez
> Assignee: David Li
> Priority: Major
> Labels: filesystem, performance
> Fix For: 5.0.0
>
>
> On Arrow 4, I'm not able to get more than 8 thread parallelism (for example when N threads call fs.ls() with different paths) for S3FileSystem created with pyarrow, because the default IO context is created with 8 thread limit (hardcoded), and I don't see a way to change this or pass a custom IO context through pyarrow APIs. I believe this affects other Arrow filesystem implementations as well.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)