[
https://issues.apache.org/jira/browse/SPARK-13921?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Josh Rosen resolved SPARK-13921.
--------------------------------
Resolution: Fixed
Fix Version/s: 2.0.0
Issue resolved by pull request 11748
[https://github.com/apache/spark/pull/11748]
> Store serialized blocks as multiple chunks in MemoryStore
> ---------------------------------------------------------
>
> Key: SPARK-13921
> URL: https://issues.apache.org/jira/browse/SPARK-13921
> Project: Spark
> Issue Type: Improvement
> Components: Block Manager
> Reporter: Josh Rosen
> Assignee: Josh Rosen
> Fix For: 2.0.0
>
>
> Instead of storing serialized blocks in individual ByteBuffers, the
> BlockManager should be capable of storing a serialized block in multiple
> chunks, each occupying a separate ByteBuffer.
> This change will help to improve the efficiency of memory allocation and the
> accuracy of memory accounting when serializing blocks. Our current
> serialization code uses a {{ByteBufferOutputStream}}, which doubles and
> re-allocates its backing byte array; this increases the peak memory
> requirements during serialization (since we need to hold extra memory while
> expanding the array). In addition, we currently don't account for the extra
> wasted space at the end of the ByteBuffer's backing array, so a 129 megabyte
> serialized block may actually consume 256 megabytes of memory. After
> switching to storing blocks in multiple chunks, we'll be able to efficiently
> trim the backing buffers so that no space is wasted.
> This change is also a prerequisite to being able to cache blocks which are
> larger than 2GB (although full support for that depends on several other
> changes which have not bee implemented yet).
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
