Github user scwf commented on the issue:
https://github.com/apache/spark/pull/16633
I think the local limit cost is important, we assume recompute partions
number: m, all the partitions: n
m = 1, n =100 is a positive case, but there also cases that m very close to
n(even m = n).
Our customers has this scenario, so i am so care about this issue.
---
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]
