[
https://issues.apache.org/jira/browse/HADOOP-18347?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17568690#comment-17568690
]
Steve Loughran commented on HADOOP-18347:
-----------------------------------------
makes snese. that bounded pool is fairly bounded across an fs instance, so
could become a bottleneck. time to review the defaults?
> Restrict vectoredIO threadpool to reduce memory pressure
> --------------------------------------------------------
>
> Key: HADOOP-18347
> URL: https://issues.apache.org/jira/browse/HADOOP-18347
> Project: Hadoop Common
> Issue Type: Sub-task
> Components: common, fs, fs/adl, fs/s3
> Reporter: Rajesh Balamohan
> Priority: Major
> Labels: performance
>
> https://github.com/apache/hadoop/blob/trunk/hadoop-tools/hadoop-aws/src/main/java/org/apache/hadoop/fs/s3a/S3AInputStream.java#L964-L967
> Currently, it fetches all the ranges with unbounded threadpool. This will not
> cause memory pressures with standard benchmarks like TPCDS. However, when
> large number of ranges are present with large files, this could potentially
> spike up memory usage of the task. Limiting the threadpool size could reduce
> the memory usage.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
