HiBench: A Representative and ComprehensiveHadoop Benchmark Suite

HiBench: A Representative and ComprehensiveHadoop Benchmark Suite

Shengsheng Huang, Jie Huang, Yan Liu, Lan Yi and Jinquan Dai
Intel Asia-Pacific Research and Development Ltd., Shanghai, P.R.China, 200241

I. THE HIBENCH SUITE
MapReduce and its popular open source implementation, Hadoop, are moving toward ubiquitous for Big Data storage and processing. Therefore, it is essential to quantitatively evaluate and characterize the Hadoop deployment through extensive benchmarking. In this paper, we present HiBench [1], a representative and comprehensive benchmark suite for Hadoop, which consists of a set of Hadoop programs including both synthetic micro-benchmarks and real-world applications. Currently the benchmark suite contains ten workloads, classified into four categories, as shown in Table I.

Download Paper (.PDF):hibench-wbdb2012-updated