Dynamic Derivation of Analytical Performance Models in Autonomic Computing Environments
Mahmoud Awad, Daniel A. Menasc · 2014
Deriving analytical performance models requires intimate knowledge of the architecture and behavior of the computer system being modeled. In autonomic computing environ-ments, this detailed knowledge may not be readily available (or it may be impractical to gather) given the dynamic nature of these environments. In this paper, we present a framework for dynamically deriving and parameterizing performance models in auto-nomic systems. Performance models are derived and parameterized by observing the relationships between a real system’s input and output parameters (average arrival rates and response times for each job class). The paper shows the results of implementing our approach using Apache OFBizTMand highlights the predictive power of the derived model. 1