[
https://issues.apache.org/jira/browse/SPARK-4550?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14304817#comment-14304817
]
Reynold Xin commented on SPARK-4550:
------------------------------------
Sandy,
The proposal seems to assume that objects can be individually serialized
efficiently. That is not the case with Kryo, and I'm not even sure if it is
safe to do that in Java. Do you have any thoughts on this?
> In sort-based shuffle, store map outputs in serialized form
> -----------------------------------------------------------
>
> Key: SPARK-4550
> URL: https://issues.apache.org/jira/browse/SPARK-4550
> Project: Spark
> Issue Type: Improvement
> Components: Shuffle, Spark Core
> Affects Versions: 1.2.0
> Reporter: Sandy Ryza
> Assignee: Sandy Ryza
> Priority: Critical
> Attachments: SPARK-4550-design-v1.pdf
>
>
> One drawback with sort-based shuffle compared to hash-based shuffle is that
> it ends up storing many more java objects in memory. If Spark could store
> map outputs in serialized form, it could
> * spill less often because the serialized form is more compact
> * reduce GC pressure
> This will only work when the serialized representations of objects are
> independent from each other and occupy contiguous segments of memory. E.g.
> when Kryo reference tracking is left on, objects may contain pointers to
> objects farther back in the stream, which means that the sort can't relocate
> objects without corrupting them.
--
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
