AnsweredAssumed Answered

How to map the locality of the data with scheduler

Question asked by nagarajubingi on Jul 15, 2012
Latest reply on Jul 19, 2012 by lohit
Hi All,

As part of my investigation on tuning the hadoop, I would like to understand the data locality mapping in scheduler. Since it is difficult to place TB/PB of data on hadoop instance, Is there a provision to fetch data from remote location like S3 or any cloud storage to local hadoop instances and improve/no-compromise on performance aspect.
Please provide the info on this. Thanks in advance.