Home | About | Sematext search-lucene.com search-hadoop.com
NEW: Monitor These Apps!
elasticsearch, apache solr, apache hbase, hadoop, redis, casssandra, amazon cloudwatch, mysql, memcached, apache kafka, apache zookeeper, apache storm, ubuntu, centOS, red hat, debian, puppet labs, java, senseiDB
 Search Hadoop and all its subprojects:

Switch to Threaded View
Hadoop >> mail # user >> Scheduler question


Copy link to this message
-
Scheduler question
Do the Hadoop 2.0 YARN scheduler(s) deal with situations like the following?
Hadoop cluster of 10 nodes, with 8GB each available for containers.  There is only one queue.
Application A requests 100 4GB containers.  It initially, or after a little while, gets 20 containers.
Later, application B requests 1 8GB container.
Suppose that App-A's containers each take a few minutes.  At some point one will complete.  When that happens, will the scheduler immediately allocate another 4GB container to App-A?  If so will App-B ever get its container until App-A is almost done?
Thanks
John

NEW: Monitor These Apps!
elasticsearch, apache solr, apache hbase, hadoop, redis, casssandra, amazon cloudwatch, mysql, memcached, apache kafka, apache zookeeper, apache storm, ubuntu, centOS, red hat, debian, puppet labs, java, senseiDB