Github user rxin commented on the pull request:
https://github.com/apache/spark/pull/12067#issuecomment-207193129
The part I don't get is that even in the RDD case, we'd need to create an
object per row. This is equivalent to the "deserialization" in aggregator,
since they both just call the ctor of the class. Why is RDD faster?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
