[
https://issues.apache.org/jira/browse/HIVE-19937?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16549601#comment-16549601
]
Sahil Takiar commented on HIVE-19937:
-------------------------------------
Attached an jxray report after applying the patch on a cluster and running the
same test. When comparing the two reports, the overhead from fields in
{{MapWork}} is now gone. There is still a lot of overhead due to duplicate
entires in {{Properties}} objects, I need to fix that. I noticed there is a bit
of overhead in {{ProjectionPusher}} that I plan to fix in the next version of
this patch.
> Intern fields in MapWork on deserialization
> -------------------------------------------
>
> Key: HIVE-19937
> URL: https://issues.apache.org/jira/browse/HIVE-19937
> Project: Hive
> Issue Type: Improvement
> Components: Spark
> Reporter: Sahil Takiar
> Assignee: Sahil Takiar
> Priority: Major
> Attachments: HIVE-19937.1.patch, HIVE-19937.2.patch,
> HIVE-19937.3.patch, post-patch-report.html, report.html
>
>
> When fixing HIVE-16395, we decided that each new Spark task should clone the
> {{JobConf}} object to prevent any {{ConcurrentModificationException}} from
> being thrown. However, setting this variable comes at a cost of storing a
> duplicate {{JobConf}} object for each Spark task. These objects can take up a
> significant amount of memory, we should intern them so that Spark tasks
> running in the same JVM don't store duplicate copies.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
