Benchmarking Criteria for A Cloud Data Warehouse

Abstract

The Terasort benchmark and the YCSB benchmark are the two most used cloud computing benchmarks. Despite the fact that these benchmarks are quite helpful, data warehouse systems and associated OLAP technologies were not the focus of their creation. We initially introduce cloud computing and data warehouse systems in this essay. Then, we contend that the TPC-H benchmark, which is the most well- known benchmark for decision support systems, conflicts with the justifications for cloud computing (scalability, elasticity, pay-per-use, fault-tolerance characteristics), and customer relationship management (end- user satisfaction, Quality of Service features). Finally, we propose updated specifications for a benchmark for cloud data warehouse systems. The suggested specifications ought to make it possible to fairly compare the products offered by various cloud system providers.