[
https://issues.apache.org/jira/browse/SPARK-4531?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Xiangrui Meng closed SPARK-4531.
--------------------------------
Resolution: Fixed
Fix Version/s: 1.2.0
Assignee: Davies Liu
> Cache serialized java objects instead of serialized python objects in MLlib
> ---------------------------------------------------------------------------
>
> Key: SPARK-4531
> URL: https://issues.apache.org/jira/browse/SPARK-4531
> Project: Spark
> Issue Type: Improvement
> Components: MLlib, PySpark
> Affects Versions: 1.2.0
> Reporter: Davies Liu
> Assignee: Davies Liu
> Priority: Blocker
> Fix For: 1.2.0
>
>
> The Pyrolite is pretty slow (comparing to the adhoc serializer in 1.1), it
> cause much performance regression in 1.2, because we cache the serialized
> Python object in JVM, deserialize them into Java object in each step.
> We should change to cache the deserialized JavaRDD instead of PythonRDD to
> avoid the deserialization of Pyrolite.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
