Generative networkload models for a single server environment

Abstract

Any performance evaluation study requires a concise description of the workload under which the performance of the system is to be evaluated. Also, the repeatability of the experiments for different workload profiles, requires that the workload models generate the workload profiles parametrically. Such a model, should preferably be time-invariant, consistent and generative. We view the networkload as a sequence that can be generated from the rules of a Context Free Grammar (CFG). Our approach combines the established practice of viewing the workload as “consisting of a hierarchy” and the CFG description , to produce a generative networkload model. The networkload model is applied to a SingleServer-MultipleClients network by deriving the networkload model parameters from an operational SingleServer network of personal computers. The time-invariance and generative nature are verified experimentally. The usefulness of such a description of the networkload to study the resource management problems of a network, like the optimal allocation of clients to servers, is explored by using the generative model as input descriptor to a queueing network model of SingleServer network.