Github user sryza commented on the pull request:
https://github.com/apache/spark/pull/6652#issuecomment-109398051
Also, is there an intuitive justification for why 5 is a good number? It
seems a little weird to me that it's independent of the number of tasks, the
cluster size, and the amount of skew. Have you considered a rule like "if X%
of the data falls on Y% of the nodes, mark those as preferred", where X and Y
could be 80/20 or 70/30?
---
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]
