[
https://issues.apache.org/jira/browse/SPARK-15247?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15281221#comment-15281221
]
Johnny W. edited comment on SPARK-15247 at 5/12/16 5:28 AM:
------------------------------------------------------------
Takeshi, thanks for your reply. However, I don't think they are relevant,
because even though I have only 1 (very small) file, spark creates n_executors
* n_cores tasks, and this is only true for parquet. This issue has been
confirmed by others from the community:
--
https://www.mail-archive.com/user@spark.apache.org/msg50568.html
Is there any walkaround for this without rebuilding spark?
was (Author: johnnyws):
Takeshi, thanks for your reply. However, I don't think they are relevant,
because even though I have only 1 (very small) file, spark creates n_executors
* n_cores tasks, and this is only true for parquet. This issue has been
confirmed by others from the community:
--
https://www.mail-archive.com/user@spark.apache.org/msg50568.html
Could you try to reproduce? Is there any walkaround for this?
> sqlCtx.read.parquet yields at least n_executors * n_cores tasks
> ---------------------------------------------------------------
>
> Key: SPARK-15247
> URL: https://issues.apache.org/jira/browse/SPARK-15247
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.6.0
> Reporter: Johnny W.
>
> sqlCtx.read.parquet always yields at least n_executors * n_cores tasks, even
> though this is only 1 very small file
> This issue can increase the latency for small jobs.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
