https://community.cloudera.com/t5/Archives-of-Support-Questions/HDFS-In-Memory-Tier/m-p/166404#M24998 <P>Looking to understand if there are any limits to using Host Groups to define specific machines in a cluster to serve as HDFS in Memory Tier. Cluster has machines that have RAM and SSD, in addition to machines that have RAM and SATA Drives.</P><P>Goal would be to use the in memory tier as storage for Spark data processing pipelines.</P> Tue, 12 Apr 2016 20:07:41 GMT michael_perez 2016-04-12T20:07:41Z https://community.cloudera.com/t5/Archives-of-Support-Questions/HDFS-In-Memory-Tier/m-p/166404#M24998 <P>Looking to understand if there are any limits to using Host Groups to define specific machines in a cluster to serve as HDFS in Memory Tier. Cluster has machines that have RAM and SSD, in addition to machines that have RAM and SATA Drives.</P><P>Goal would be to use the in memory tier as storage for Spark data processing pipelines.</P> Tue, 12 Apr 2016 20:07:41 GMT https://community.cloudera.com/t5/Archives-of-Support-Questions/HDFS-In-Memory-Tier/m-p/166404#M24998 michael_perez 2016-04-12T20:07:41Z https://community.cloudera.com/t5/Archives-of-Support-Questions/HDFS-In-Memory-Tier/m-p/166405#M24999 <P> <A rel="user" href="https://community.cloudera.com/users/321/michaelperez.html" nodeid="321">@michael perez</A> To add to Emil, to isolate CPU and Ram resources enable CPU scheduling. More info <A href="http://hortonworks.com/blog/managing-cpu-resources-in-your-hadoop-yarn-clusters/">here</A>. </P><P>CPU scheduling represents one aspect of YARN resource management capabilities that includes CGroups, node labels, archival storage, and memory as storage. CGroups should be used with CPU scheduling to constrain and manage CPU processes.</P> Tue, 12 Apr 2016 20:33:54 GMT https://community.cloudera.com/t5/Archives-of-Support-Questions/HDFS-In-Memory-Tier/m-p/166405#M24999 sunile_manjee 2016-04-12T20:33:54Z