Does HDP 2.3 support per node label capacity scheduler queues? We'd like to be able to label nodes as "high memory", "dense storage", etc and split the workload within those nodes to maintain SLAs.
Yes, check out http://docs.hortonworks.com/HDPDocuments/HDP2/HDP-2.3.0/bk_yarn_resource_mgt/content/configuring_nod...
View solution in original post
very nicely explained ..link
use case : We have 5 nodes (hostname=h1..h5) in the cluster, each of them has 24G memory, 24 vcores. 1 among the 5 nodes has GPU (assume it’s h5). So admin added GPU label to h5.
Within the GPU labeled node, could I have to separate workloads that I can enforce on that node only?