Hi Praveen and Salil, If the data is being written from one of the cluster nodes then preference would be given for local node irrespective of the Rack being configured. If its written remotely(not from one of cluster nodes) then there is possibility of blocks getting distributed. Further you can think of having some custom BlockPlacementPolicy by extending BlockPlacementPolicydefault and configuring "dfs.block.replicator.classname" if required.
+ Naga ________________________________ From: praveen S [mylogi...@gmail.com] Sent: Tuesday, October 27, 2015 17:44 To: user@hadoop.apache.org Subject: Re: How do I customize data placement on DataNodes (DN) of Hadoop cluster? May be Using rack concept might work On 27 Oct 2015 17:32, "Norah Jones" <nh.jone...@gmail.com<mailto:nh.jone...@gmail.com>> wrote: Hi, Let we change the default block size to 32 MB and replication factor to 1. Let Hadoop cluster consists of 4 DNs. Let input data size is 192 MB. Now I want to place data on DNs as following. DN1 and DN2 contain 2 blocks (32+32 = 64 MB) each and DN3 and DN4 contain 1 block (32 MB) each. Can it be possible? How to accomplish it? Thanks, Salil