You are viewing a plain text version of this content. The canonical link for it is here.

Posted to common-user@hadoop.apache.org by Gang Luo <lg...@yahoo.com.cn> on 2010/05/19 16:16:32 UTC

input split

Hi all,
Does Hadoop pack blocks into input split in a contiguous manner? Assume I got a 2-node cluster, block 1, 3, 5.. locate at node 0, block 2, 4, 6 ... locate at node 1. The size of input split is 2 blocks. will a map task takes block 1 & 2 as input? If so, it is really bad in achieving the data locality. 

Thanks,
-Gang