An efficient Hadoop data replication method design for heterogeneous clusters
Daeshin Park, Kiwook Kang, Jiman Hong, Yookun Cho · 2016
The performance of each datanode in a heterogeneous Hadoop cluster differs, and the number of slots that can be numbered to simultaneously execute tasks differs. For this reason, Hadoop is susceptible to replica placement problems and data replication problems. Because of this, replication problems and allocation problems occur. These problems can deteriorate the performance of Hadoop. In this paper, we summarize existing research to improve data locality, and design a data replication method to solve replication and allocation problems.