A Generic Platform for Transforming Monitoring Data into Performance Models

Abstract

The performance of software systems is an ongoing issue in the industry, including the development of corresponding performance models. Recently several approaches for deriving such performance models from monitoring data have been proposed. A current limitation of these approaches is that most of them are bound to certain monitoring tools for providing the data, limiting their applicability.We therefore propose a generic platform for transforming monitoring data into performance models, encapsulating these approaches for deriving performance models. This platform gives the flexibility of exchanging the monitoring tool or the used performance modeling approach, allowing more comprehensive performance analysis without additional manual transformation work. A seamless exchangeability of the performance modeling approach enables the generation of different types of performance models based on the same monitoring data, while the exchangeability of the monitoring tool enables the same approaches to be employed on a wider range of systems, as often the applicability of certain monitoring tools is limited by environmental properties. In addition, the generic nature of the platform aims to support the rapid development of prototypes of new, upcoming ideas within the context of performance modeling based on monitoring data.During our evaluation we examine the quality of our approach in terms of accuracy and scalability. We show that our platform for transforming monitoring data into performance models scales with a very low overhead and that the results of the integrated performance modeling approaches are very accurate in comparison to the results of the non-integrated versions.