[ https://issues.apache.org/jira/browse/MAPREDUCE-3784?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13199465#comment-13199465 ]
Hudson commented on MAPREDUCE-3784: ----------------------------------- Integrated in Hadoop-Hdfs-trunk-Commit #1721 (See [https://builds.apache.org/job/Hadoop-Hdfs-trunk-Commit/1721/]) MAPREDUCE-3784. Fixed CapacityScheduler so that maxActiveApplications and maxActiveApplicationsPerUser per queue are not too low for small clusters. Contributed by Arun C Murthy. vinodkv : http://svn.apache.org/viewcvs.cgi/?root=Apache-SVN&view=rev&rev=1239971 Files : * /hadoop/common/trunk/hadoop-mapreduce-project/CHANGES.txt * /hadoop/common/trunk/hadoop-mapreduce-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/scheduler/capacity/CSQueueUtils.java * /hadoop/common/trunk/hadoop-mapreduce-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/scheduler/capacity/LeafQueue.java * /hadoop/common/trunk/hadoop-mapreduce-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/test/java/org/apache/hadoop/yarn/server/resourcemanager/scheduler/capacity/TestApplicationLimits.java > maxActiveApplications(|PerUser) per queue is too low for small clusters > ----------------------------------------------------------------------- > > Key: MAPREDUCE-3784 > URL: https://issues.apache.org/jira/browse/MAPREDUCE-3784 > Project: Hadoop Map/Reduce > Issue Type: Bug > Components: mrv2 > Affects Versions: 0.23.0 > Reporter: Ramya Sunil > Assignee: Arun C Murthy > Fix For: 0.23.1 > > Attachments: MAPREDUCE-3784.patch, MAPREDUCE-3784.patch, > MAPREDUCE-3784.patch, MAPREDUCE-3784.patch, MAPREDUCE-3784.patch > > > We ran into this issue while testing on small clusters. > On a 7node cluster with 8G per node, for a queue with absolute capacity 30%, > user limit 100%, maxActiveApplications and maxActiveApplicationsPerUser is > calculated to be 1. > This means that even though the queue has 17GB(0.3*8*7), only 1 user can run > 1 app at a given time queuing up rest of the apps/users. This hurts > performance on small clusters. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira