Github user sryza commented on the pull request:
https://github.com/apache/spark/pull/5868#issuecomment-98889393
@JoshRosen we've had a PR (#3438) out for a while that seeks to make most
shuffles sort on records. If that is something we choose to go with, heavily
optimizing a map-side shuffle implementation for faster sorting might be not be
a ton of bang for buck. I don't mean to naysay this change, but I think it
could be worth putting together a broader picture of what we want the shuffle
to look like 3 months or a year down the road before optimizing specific
components.
---
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]
