Github user JoshRosen commented on the pull request:
https://github.com/apache/spark/pull/5868#issuecomment-98810648
I spent a bunch of time yesterday working on adding external spilling
support to this new sort code (my WIP code is in a separate branch while I
clean it up and add proper tests). Given that external sorting will requires
some changes to interfaces in this patch, I think it might make more sense to
split this into a series of slightly smaller patches:
- Extension of the serializer interface plus tests for the Kryo
serializer's relocatibility property; also, finish verifying that @sryza's
patch can be applied with SQLSerializer2.
- A patch that only adds the external sorter plus test cases.
- A patch that integrates the new sorter into a new `unsafe` shuffle path.
The changes here are also becoming large enough that it's worth posting a
design document; I'll work on doing this today.
---
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]
