Github user squito commented on the issue:
https://github.com/apache/spark/pull/17619
@andreimaximov that is still sort of the case for all cluster managers.
You shouldn't get starvation, you should see the app actively fail (SPARK-15865
was the main change, though some small follow-on stuff after that). What else
can you do if it seems there is something wrong with every node in your cluster?
But if you're really seeing your app just *hang* in mesos in that situation
-- yeah seems like something needs to be fixed in the spark-mesos interaction.
unfortunately I won't have a clear picture of what needs to change without
spending more time understanding what is there now ...
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
