Automated Modeling of I/O Performance and Interference Effects in Virtualized Storage Systems

Modern IT systems frequently employ virtualization technology to maximize resource efficiency. By sharing physical resources, however, the virtualized storage used in such environments can quickly become a bottleneck. Performance modeling and evaluation techniques applied prior to system deployment help to avoid performance issues. In current practice, however, modeling I/O performance is usually avoided due to the increasing complexity of modern virtualized storage systems. In this paper, we present an automated modeling approach based on statistical regression techniques to analyze I/O performance and interference effects in the context of virtualized storage systems. We demonstrate our approach in three case studies creating performance models with two I/O benchmarks. The case studies are conducted in a real-world environment based on IBM System z and IBM DS8700 server hardware. Using our approach, we effectively create performance models with excellent prediction accuracy for both I/O-intensive applications and I/O performance interference effects with a mean prediction error up to 7%.