Github user jerryshao commented on the pull request:
https://github.com/apache/spark/pull/6870#issuecomment-116917074
I think the original blacklist mechanism and what @davies did is to avoid
the resubmitted tasks running on the same executors/hosts, which means tasks
should be failed beforehand, then the blacklist mechanism could take effect.
But about the first submitted tasks, current implementation cannot avoid
scheduling tasks on such "bad" executors. This is what this PR addresses about.
The basic idea and algorithm is brought from MR, I think for Spark it also
requires such feature.
---
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]
