[ https://issues.apache.org/jira/browse/YARN-2498?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14142513#comment-14142513 ]
Sunil G commented on YARN-2498: ------------------------------- Hi [~wangda] Great work Wangda. Very good design to solve the issues. I have few doubts though :) 1. bq. 2G resource in node1 with label x, and queueA has label y, so queueA cannot access node1 A scenario where *node1* has more than 50% (say 60) of cluster resources, and queue A is given 50% in CS. IN that case, is there any chance of under utilization? 2. When two or more nodes are merged to a single resource tree, and if these nodes share some common labels, i could see a common total sum is been finally stored per label in the consolidated tree. Here I feel, we may need to split up the resource of label in each node level. For eg; label *x* and *y* are needed for *queueA*. label *y* and *z* are needed for *queueB*. And if the label *y* is shared between 2 or more nodes, I am not sure whether it will cause some pblm. 3. bq.(container.resource can be used by pendingResourceLeaf) For preemption, we just calculate to match the totalResourceToPreempt from the over utilized queues. But whether this container is from which node, and also under which label, and whether this label is coming under which queue. Do we need to do this check for each container? > [YARN-796] Respect labels in preemption policy of capacity scheduler > -------------------------------------------------------------------- > > Key: YARN-2498 > URL: https://issues.apache.org/jira/browse/YARN-2498 > Project: Hadoop YARN > Issue Type: Sub-task > Components: resourcemanager > Reporter: Wangda Tan > Assignee: Wangda Tan > Attachments: YARN-2498.patch, YARN-2498.patch, YARN-2498.patch, > yarn-2498-implementation-notes.pdf > > > There're 3 stages in ProportionalCapacityPreemptionPolicy, > # Recursively calculate {{ideal_assigned}} for queue. This is depends on > available resource, resource used/pending in each queue and guaranteed > capacity of each queue. > # Mark to-be preempted containers: For each over-satisfied queue, it will > mark some containers will be preempted. > # Notify scheduler about to-be preempted container. > We need respect labels in the cluster for both #1 and #2: > For #1, when there're some resource available in the cluster, we shouldn't > assign it to a queue (by increasing {{ideal_assigned}}) if the queue cannot > access such labels > For #2, when we make decision about whether we need preempt a container, we > need make sure, resource this container is *possibly* usable by a queue which > is under-satisfied and has pending resource. -- This message was sent by Atlassian JIRA (v6.3.4#6332)