Model ensemble tools for self-management in data centers

We introduce Ensemble, a runtime framework and associated tools for building query latency models on-the-fly. These dynamic performance models can be used to support complex, highly dimensional resource allocation, and/or what-if performance inquiry in modern database environments, such as data centers and Clouds. Ensemble combines simple, partially specified, lower-dimensionality models to provide good initial approximations for higher dimensionality, end-to-end query latency models. We perform an experimental evaluation on industry-standard applications running on a multi-tier dynamic content server. We show that the Ensemble on-the-fly modeling framework provides accurate, fast and flexible performance modelling by using partial, lower dimensionality models to approximate end-to-end query latency models.