[ https://issues.apache.org/jira/browse/MAPREDUCE-3859?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13660501#comment-13660501 ]
Arun C Murthy commented on MAPREDUCE-3859: ------------------------------------------ [~sergeant] Sorry! I lost track of this again. Sincere apologies. The same bug exists in CS in YARN: {noformat} Resource currentCapacity = Resources.lessThan(resourceCalculator, clusterResource, usedResources, queueCapacity) ? queueCapacity : Resources.add(usedResources, required); {noformat} Do you mind providing a patch for that too? Something like: {noformat} index 64f7114..7d8800a 100644 --- hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/scheduler/capacity/LeafQueue.java +++ hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/scheduler/capacity/LeafQueue.java @@ -997,7 +997,7 @@ private Resource computeUserLimit(FiCaSchedulerApp application, Resource currentCapacity = Resources.lessThan(resourceCalculator, clusterResource, - usedResources, queueCapacity) ? + Resources.add(usedResources, required), queueCapacity) ? queueCapacity : Resources.add(usedResources, required); // Never allow a single user to take more than the {noformat} Guilty as charged on mocks for testing in YARN... *smile* However, it does result in our tests running in ~20mins rather than 5-6hrs it takes in hadoop-1! > CapacityScheduler incorrectly utilizes extra-resources of queue for > high-memory jobs > ------------------------------------------------------------------------------------ > > Key: MAPREDUCE-3859 > URL: https://issues.apache.org/jira/browse/MAPREDUCE-3859 > Project: Hadoop Map/Reduce > Issue Type: Bug > Components: capacity-sched > Affects Versions: 1.0.0 > Environment: CDH3u1 > Reporter: Sergey Tryuber > Assignee: Sergey Tryuber > Attachments: test-to-fail.patch.txt > > > Imagine, we have a queue A with capacity 10 slots and 20 as extra-capacity, > jobs which use 3 map slots will never consume more than 9 slots, regardless > how many free slots on a cluster. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira