[
https://issues.apache.org/jira/browse/SPARK-1568?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14212145#comment-14212145
]
Andrew Ash commented on SPARK-1568:
-----------------------------------
[~sams] did you see an improvement when you upgraded to 1.0.0?
I've noticed myself that reading from s3 can be slow, particularly in the
scenario where there are many small files. I think the hadoop S3 adapter makes
many more API calls than is necessary, and that scales on the number of files
you have.
> Spark 0.9.0 hangs reading s3
> ----------------------------
>
> Key: SPARK-1568
> URL: https://issues.apache.org/jira/browse/SPARK-1568
> Project: Spark
> Issue Type: Bug
> Reporter: sam
>
> I've tried several jobs now and many of the tasks complete, then it get stuck
> and just hangs. The exact same jobs function perfectly fine if I distcp to
> hdfs first and read from hdfs.
> Many thanks
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
