[
https://issues.apache.org/jira/browse/SPARK-4940?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15185633#comment-15185633
]
Martin Tapp commented on SPARK-4940:
Any update or anyone working on this issue?
> Support more
[
https://issues.apache.org/jira/browse/SPARK-4940?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15116478#comment-15116478
]
Eron Wright commented on SPARK-4940:
-
Another benefit of maximizing the # of allocated executors is
[
https://issues.apache.org/jira/browse/SPARK-4940?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14971228#comment-14971228
]
Jerry Lam commented on SPARK-4940:
--
I just want to weight in the importance of this issue. My observation
[
https://issues.apache.org/jira/browse/SPARK-4940?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14971416#comment-14971416
]
Martin Tapp commented on SPARK-4940:
No real workaround for now as we need the round-robin strategy.
[
https://issues.apache.org/jira/browse/SPARK-4940?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14971496#comment-14971496
]
Jerry Lam commented on SPARK-4940:
--
Thanks Martin,
Yes, beefing up the executor works but the cluster
[
https://issues.apache.org/jira/browse/SPARK-4940?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14734792#comment-14734792
]
Martin Tapp commented on SPARK-4940:
I see your point and thinking about it, round-robin is excellent
[
https://issues.apache.org/jira/browse/SPARK-4940?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14730911#comment-14730911
]
Martin Tapp commented on SPARK-4940:
My principal use case is to cram as much as possible on the same
[
https://issues.apache.org/jira/browse/SPARK-4940?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14730401#comment-14730401
]
Iulian Dragos commented on SPARK-4940:
--
[~doctapp] I guess there is no perfect scheduling for every
[
https://issues.apache.org/jira/browse/SPARK-4940?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14727171#comment-14727171
]
Martin Tapp commented on SPARK-4940:
I think the resource allocation strategy should be configurable.
[
https://issues.apache.org/jira/browse/SPARK-4940?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=14726784#comment-14726784
]
Iulian Dragos commented on SPARK-4940:
--
Would it make sense to allocate resources in a round-robin
[
https://issues.apache.org/jira/browse/SPARK-4940?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14269038#comment-14269038
]
Gerard Maas commented on SPARK-4940:
I forgot to mention that in the previous example,
[
https://issues.apache.org/jira/browse/SPARK-4940?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14268440#comment-14268440
]
Gerard Maas commented on SPARK-4940:
Hi Tim,
We are indeed using Coarse Grain mode.
[
https://issues.apache.org/jira/browse/SPARK-4940?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14265802#comment-14265802
]
Timothy Chen commented on SPARK-4940:
-
So I assume you're specifiying coarse grain
13 matches
Mail list logo