Abstract

Benchmarking the performance of public cloud providers is a common research topic. Previous research has already ex-tensively evaluated the performance of different cloud plat-forms for different use cases, and under different constraints and experiment setups. In this paper, we present a princi-pled, large-scale literature review to collect and codify ex-isting research regarding the predictability of performance in public Infrastructure-as-a-Service (IaaS) clouds. We for-mulate 15 hypotheses relating to the nature of performance variations in IaaS systems, to the factors of influence of per-formance variations, and how to compare different instance types. In a second step, we conduct extensive real-life ex-perimentation on Amazon EC2 and Google Compute En-gine to empirically validate those hypotheses. At the time of our research, performance in EC2 was substantially less predictable than in GCE. Further, we show that hardware heterogeneity is in practice less prevalent than anticipated by earlier research, while multi-tenancy has a dramatic im-pact on performance and predictability.