Description

We present a novel performance modeling approach tailored to I/O performance prediction in virtualized environments. The main idea is to identify important performance-influencing factors and to develop storage-level I/O performance models. To increase the practical applicability of these models, we combine the low-level I/O performance models with high-level software architecture models. Our approach is validated in a variety of case studies in state-of-the-art, real-world environments.