[ https://issues.apache.org/jira/browse/SPARK-9775?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16522064#comment-16522064 ]
Maxim Gekk commented on SPARK-9775: ----------------------------------- Please, change another related methods like proposed in the PR: https://github.com/apache/spark/pull/21589 > Query Mesos for number of CPUs to set default parallelism > --------------------------------------------------------- > > Key: SPARK-9775 > URL: https://issues.apache.org/jira/browse/SPARK-9775 > Project: Spark > Issue Type: Improvement > Components: Mesos > Affects Versions: 1.4.1 > Reporter: Peder Ås > Priority: Minor > > As highlighted in a TODO on line 400 of MesosSchedulerBackend.scala (at least > on 3ca995b7) we should query the Mesos master and set the default parallelism > based on the number of CPUs available in the cluster (and multiply by two or > three?) > See code in question [here > (gitweb)|https://git-wip-us.apache.org/repos/asf?p=spark.git;a=blob;f=core/src/main/scala/org/apache/spark/scheduler/cluster/mesos/MesosSchedulerBackend.scala;h=3f63ec1c;hb=HEAD#l400]. > This task should also update the documentation [here > (gitweb)|https://git-wip-us.apache.org/repos/asf?p=spark.git;a=blob;f=docs/configuration.md;h=c60dd1;hb=HEAD#l789] > to highlight the fact. -- This message was sent by Atlassian JIRA (v7.6.3#76005) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org