Experimental Evaluation of the Performance-Influencing Factors of Virtualized Storage Systems

Abstract

Virtualized cloud environments introduce an additional abstraction layer on top of physical resources enabling their collective use by multiple systems to increase resource efficiency. In I/O-intensive applications, however, the virtualized storage of such shared environments can quickly become a bottleneck and lead to performance and scalability issues. In software performance engineering, application performance is analyzed to assess the non-functional properties taking into account the many performance-influencing factors. In current practice, however, virtualized storage is either modeled as a black-box or tackled with full-blown and fine-granular simulations. This paper presents a systematic performance analysis approach of I/O-intensive applications in virtualized environments. First, we systematically identify storageperformance- influencing factors in a representative storage environment. Second, we quantify them using a systematic experimental analysis. Finally, we extract simple performance analysis models based on regression techniques. Our approach is applied in a real world environment using the state-of-the-art virtualization technology of the IBM System z and IBM DS8700.