Hi guys ! Q> I see that createCache() method of JobInProgress is involved in assignment of input splits across nodes in Hadoop. Which classes are involved in assignment of input splits of jobs to nodes ? I am interested in modifying this assignment policy. How can i do it ?
Q> How can i access the topology information inside the scheduler code ? Q> How do i pass a file to the scheduler code say JobQueueTaskscheduler when i run mumak ? Any help ? Thanks, Arun -- View this message in context: http://lucene.472066.n3.nabble.com/Assignment-of-input-splits-across-nodes-in-Hadoop-tp3514824p3514824.html Sent from the Hadoop lucene-users mailing list archive at Nabble.com.