Techniques and a Framework for Characterizing Computer Systems´ Workloads

The performance of any system cannot be determined without knowing the workload, that is, the set of requests presented to the system. Workload characterization is the process by which we produce models that are capable of describing and reproducing the behavior of a workload. Such models are imperative to any performance related studies such as capacity planning, workload balancing, performance prediction and system tuning. In this paper, we provide a summary and classification of the most common techniques used for characterizing several types of information and commutation systems. Based on analyzing a profusion of case studies, we propose a methodology for workload characterization as a framework. We believe that the described characterization techniques, and the proposed framework give a good introduction to the topic, assist in exploring the different options of characterization tools that can be adopted, and provide general guidelines for deriving a good workload model suitable as an input to performance studies