Hello, I have an access to a hadoop cluster that I don't have control over its configuration. I would like to show a "proof of concept" about hadoop about running a certain program that can be parallelized. For that, I would like to compare the performance of running the program while allowing access to N nodes, N varying from 1 to the number of nodes in the cluster. Is there a way to impose the maximal number of nodes that will be used in a pipes application run with hadoop, without having access to the configuration files for hadoop itself?
Thanks. Jerr. -- View this message in context: http://www.nabble.com/performance-tests-tf4899314.html#a14032840 Sent from the Hadoop Users mailing list archive at Nabble.com.
