[GitHub] spark pull request: SPARK-4585. Spark dynamic executor allocation ...

[andrewor14 <gi...@git.apache.org>]

Github user andrewor14 commented on the pull request:

    https://github.com/apache/spark/pull/4051#issuecomment-72530870
  
    Alright, in summary, the proposal here is to default the min to 0 and the max to Int.Max, and add a new `initialExecutors` config that defaults to the min. On second thought I think the max sounds reasonable because the number executors we get is actually limited by the number of pending tasks we get (so it'll never actually ramp up all the way). As for the min, if we do decide to set it to 0 then perhaps we should lower the ramp up interval, though we can do that separately. I just thought the advantage of keeping it at 1 is that we'll always make progress no matter how slowly we ramp it up, though it's not a big enough issue to block this patch.
    
    I'm merging this into master. Thanks for the input everyone.


---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org