Github user mridulm commented on the pull request:
https://github.com/apache/spark/pull/5852#issuecomment-103808828
Any updates on pushing this in ?
Our jobs do not run without using this and setting it to some modest value
like 25.
The performance impact is minimal from our observations (since you are
still having 25 outstanding requests to hosts) - while allowing jobs which fail
earlier to run to completion : particularly in yarn mode where jobs get killed
when memory usage shoots up beyond the container limit and the netty code is
extremely 'generous' with using off heap buffers.
---
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]
