Short version: MR provides all the info it can to (about all it's tasks locations) and the YARN scheduler deals with providing good locality with even assignment.
I don't have a handy link to a doc, but here is an ancient version: http://developer.yahoo.com/blogs/hadoop/next-generation-apache-hadoop-mapreduce-scheduler-4141.html You might find a more recent version of one of my talks if you try really hard… *smile* Arun On Oct 5, 2013, at 3:12 PM, John Lilley <[email protected]> wrote: > Is there a description of how MapReduce under Hadoop 2.0 assigns mapper tasks > to preferred nodes? I think that someone on the list mentioned previously > that it attempted to assign “one HDFS block per mapper task”, but given that > there can be multiple block instances per data split, how does MapReduce try > to obtain an even task assignment while optimizing data locality? > Thanks, > John Lilley > Chief Architect, RedPoint Global Inc. > 1515 Walnut Street | Suite 200 | Boulder, CO 80302 > T: +1 303 541 1516 | M: +1 720 938 5761 | F: +1 781-705-2077 > Skype: jlilley.redpoint | [email protected] | www.redpoint.net > -- Arun C. Murthy Hortonworks Inc. http://hortonworks.com/ -- CONFIDENTIALITY NOTICE NOTICE: This message is intended for the use of the individual or entity to which it is addressed and may contain information that is confidential, privileged and exempt from disclosure under applicable law. If the reader of this message is not the intended recipient, you are hereby notified that any printing, copying, dissemination, distribution, disclosure or forwarding of this communication is strictly prohibited. If you have received this communication in error, please contact the sender immediately and delete it from your system. Thank You.
