The Implications from Benchmarking Three Big Data Systems

Abstract: Along with today's data explosion and application diversification, a variety of hardware platforms for big data are emerging, attracting interests from both industry and academia. The existing hardware platforms represent a wide range of implementation approaches, and different hardware platforms have different strengths. In this paper, we conduct comprehensive evaluations on three representative big data systems: Intel Xeon, Atom (low power processors), and many-core Tilera using BigDataBench - a big data benchmark suite. Then we explore the relative performance of the three implementation approaches by running BigDataBench, and provide strong guidance for the big data systems construction. Through our experiments, we have inferred that a big data system based on specific hardware has different performance in the context of different applications and data volumes. When we construct a system, we should take into account not only the performance or energy consumption of the pure hardware, but also the characteristics of applications running on them. Data scale, application type and complexity should be considered comprehensively when researchers or architects plan to choose fundamental components for their big data systems.