[jira] [Commented] (SPARK-1476) 2GB limit in spark for blocks

["Mridul Muralidharan (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/SPARK-1476?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13967419#comment-13967419 ] 

Mridul Muralidharan commented on SPARK-1476:
--------------------------------------------

WIP Proposal:

- All references to ByteBuffer will need to be replaced with Seq[ByteBuffer].
    This applies to definition of a block, memory mapped file segments for a shuffle block, etc.
- All use of byte array backed outputstream will need to be replaced with a aggregating outputstream which writes to multiple boas as and when array limits are hit.


> 2GB limit in spark for blocks
> -----------------------------
>
>                 Key: SPARK-1476
>                 URL: https://issues.apache.org/jira/browse/SPARK-1476
>             Project: Spark
>          Issue Type: Bug
>          Components: Spark Core
>         Environment: all
>            Reporter: Mridul Muralidharan
>            Priority: Critical
>
> The underlying abstraction for blocks in spark is a ByteBuffer : which limits the size of the block to 2GB.
> This has implication not just for managed blocks in use, but also for shuffle blocks (memory mapped blocks are limited to 2gig, even though the api allows for long), ser-deser via byte array backed outstreams (SPARK-1391), etc.
> This is a severe limitation for use of spark when used on non trivial datasets.



--
This message was sent by Atlassian JIRA
(v6.2#6252)