[
https://issues.apache.org/jira/browse/SPARK-7389?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Patrick Wendell resolved SPARK-7389.
------------------------------------
Resolution: Fixed
Fix Version/s: 1.5.0
> Tachyon integration improvement
> -------------------------------
>
> Key: SPARK-7389
> URL: https://issues.apache.org/jira/browse/SPARK-7389
> Project: Spark
> Issue Type: Improvement
> Components: Block Manager
> Reporter: shimingfei
> Assignee: shimingfei
> Fix For: 1.5.0
>
>
> Two main changes:
> 1. Add two functions in ExternalBlockManager, which are putValues and
> getValues, because the implementation may not rely on the putBytes and
> getBytes
> 2. improve Tachyon integration.
> Currently, when putting data into Tachyon, Spark first serialize all data in
> one partition into a ByteBuffer, and then write into Tachyon, this will use
> much memory and increase GC overhead
> when getting data from Tachyon, getValues depends on getBytes, which also
> read all data into On heap byte arry, and result in much memory usage.
> This PR changes the approach of the two functions, make them read / write
> data by stream to reduce memory usage.
> In our testing, when data size is huge, this patch reduces about 30% GC time
> and 70% full GC time, and total execution time reduces about 10%
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
