Utility computing environments provide on-demand IT Services to customers. Such environments are dynamic in nature and continuously adapt to changes in requirements and system state. Errors are an important category of environment state changes as such environments consist of a large number of components, and hence, are subject to errors. In this paper, we propose a framework that applies a model-based approach that enables system administrators to simulate error analyses of utility computing environments. Specifically, the information model-centric framework leverages information about existing service components and their interactions; integrates a variety of error models which are bound to individual components; captures use-case behaviors of IT services; and feeds all this information into a simulation engine. The framework also allows definitions of additional components and their interactions to provide error analysis at a finer granularity and performs service evaluation in hypothetical situations (workloads or equipment changes, use cases, error behaviors). To evaluate the framework, we performed experiments on a virtualized blade-server based environment as the target system. Results show that the framework is effective in analyzing error impacts on IT services, and hence, provides a sound foundation for designing potential error mitigation mechanisms. Publication Info: A shorter version of this paper will be published in the proceedings of IM 2007, 21-25 May 2007, Munich, Germany 10 Pages
PDF
download
878987797
028-85220240
