Benchmarking Big Data Systems: Introducing TPC Express Benchmark HS

摘要

As Big Data becomes an integral part of enterprise IT ecosystem, many organizations are challenged with metrics and methodologies to benchmark various hardware and software technologies in terms of performance, price-performance and energy efficiency. Continuing its commitment to bring relevant benchmarks to industry, the Transaction Processing Performance (TPC) formed the Big Data committee to develop set of industry standards, and announced its first standard, the TPC Express benchmark HS (TPCx-HS) in August 2014. TPCx-HS enables measurement of both hardware and software including Hadoop Runtime, Hadoop file system API compatible systems and MapReduce layers. The TPCx-HS can be used to asses a broad range of system topologies and implementation methodologies, in a technically rigorous and directly comparable, vendor-neutral manner.