[ https://issues.apache.org/jira/browse/YARN-4287?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14980886#comment-14980886 ]
MENG DING commented on YARN-4287: --------------------------------- Looking at this issue, I have to admit that I had been frustrated with the existing {{getLocalityWaitFactor}}, and had the same question as [~nroberts]: bq. This made no sense to me - Accept OFF-SWITCH without delay, yet don't accept RACK-LOCAL?? IMHO, although it makes sense to introduce a configurable rack-locality delay, it doesn't help when the cluster is really busy as described in YARN-4189 and YARN-3309. As an interim solution, I am in favor of the YARN-4287-minimal.patch, but I think the default configuration of DEFAULT_RACK_LOCALITY_FULL_RESET should be set to true to be backward compatible. > Capacity Scheduler: Rack Locality improvement > --------------------------------------------- > > Key: YARN-4287 > URL: https://issues.apache.org/jira/browse/YARN-4287 > Project: Hadoop YARN > Issue Type: Improvement > Components: capacityscheduler > Affects Versions: 2.7.1 > Reporter: Nathan Roberts > Assignee: Nathan Roberts > Attachments: YARN-4287-minimal.patch, YARN-4287-v2.patch, > YARN-4287-v3.patch, YARN-4287-v4.patch, YARN-4287.patch > > > YARN-4189 does an excellent job describing the issues with the current delay > scheduling algorithms within the capacity scheduler. The design proposal also > seems like a good direction. > This jira proposes a simple interim solution to the key issue we've been > experiencing on a regular basis: > - rackLocal assignments trickle out due to nodeLocalityDelay. This can have > significant impact on things like CombineFileInputFormat which targets very > specific nodes in its split calculations. > I'm not sure when YARN-4189 will become reality so I thought a simple interim > patch might make sense. The basic idea is simple: > 1) Separate delays for rackLocal, and OffSwitch (today there is only 1) > 2) When we're getting rackLocal assignments, subsequent rackLocal assignments > should not be delayed > Patch will be uploaded shortly. No big deal if the consensus is to go > straight to YARN-4189. -- This message was sent by Atlassian JIRA (v6.3.4#6332)