[ https://issues.apache.org/jira/browse/YARN-752?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13678445#comment-13678445 ]
Siddharth Seth commented on YARN-752: ------------------------------------- Alright - I guess the node only request will be handled in the other jira to track it. And from Bikas' explanation - that'll require rack resolution in any case. Seems a little strange, but required based on scheduler implementation. If we're always doing the rack lookup, we should change the MR AM avoid rack lookups if possible - may be difficult considering it tracks RACK_LOCAL allocations. Separate jira though. The rack lookup in the patch itself, shouldn't it be adding a rack only once. e.g. ResourceRequest: h1, h2, h3 - numContainers=1 If all of them resolve to the same rack - num containers on the rack would go to 3 after this ? Is that correct behaviour. > In AMRMClient, automatically add corresponding rack requests for requested > nodes > -------------------------------------------------------------------------------- > > Key: YARN-752 > URL: https://issues.apache.org/jira/browse/YARN-752 > Project: Hadoop YARN > Issue Type: Improvement > Components: api, applications > Affects Versions: 2.0.4-alpha > Reporter: Sandy Ryza > Assignee: Sandy Ryza > Attachments: YARN-752-1.patch, YARN-752-1.patch, YARN-752.patch > > > A ContainerRequest that includes node-level requests must also include > matching rack-level requests for the racks that those nodes are on. When a > node is present without its rack, it makes sense for the client to > automatically add the node's rack. -- 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