Github user tnachen commented on the pull request:
https://github.com/apache/spark/pull/5597#issuecomment-94918952
It's logged each time we recover resources in Mesos since that's when we
evaluate when the filter should be applied. And yes Mesos needs a positive
value for refuse seconds on the filter.
I think refused resources could be used when later there more resources
available on from the same slave since someone else's task is gone. Also we're
adding capacbility into coarse grained scheduler to launched multiple
executors, and in addition to that we're putting in dynamic allocation into
coarse grained scheduler too.
So we will be using refuse resources more often, but 5 as the default
sounds reasonable to me.
---
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]
