The University of Tulsa
Large web-scale applications typically use a distributed platform, like clusters of commodity servers, to achieve scalable and low-cost processing. The MapReduce framework and its open-source implementation, Hadoop, are commonly used to program these applications. Since, these applications scale well with an increased number of servers, the cluster size is an important parameter. Cluster size however is constrained by power consumption. In this paper, the authors present a system that uses low-power CPUs to in-crease the cluster size in a fixed power budget.