Mrbench: A benchmark for mapreduce framework

MapReduce is Google’s programming model for easy development of scalable parallel applications which pro-cess huge quantity of data on many clusters. Due to its conveniency and efficiency, MapReduce is used in various applications (e.g., web search services and on-line analytical processing.) However, there are only few good benchmarks to evaluate MapReduce implementa-tions by realistic testsets. In this paper, we present MRBench that is a bench-mark for evaluating MapReduce systems. MRBench fo-cuses on processing business oriented queries and con-current data modifications. To this end, we build MR-Bench to deal with large volumes of relational data and execute highly complex queries. By MRBench, users can evaluate the performance of MapReduce systems while varying environmental parameters such as data size and the number of (Map/Reduce) tasks. Our ex-tensive experimental results show that MRBench is a useful tool to benchmark the capability of answering critical business questions.