WSEAS Transactions on Information Science and Applications
Print ISSN: 1790-0832, E-ISSN: 2224-3402
Volume 14, 2017
A Model for Web Workload Generation Based on Content Classification
Authors: ,
Abstract: Web server performance is tightly bound to the workload the server has to support. Therefore, understanding the nature of the server workload is particularly important in capacity planning and overload control of Web servers. Web performance analysis can be done, a priori, with a synthetic generation of Web system workload. However, performance analysis results depend on the accuracy of this workload. In this paper, we propose and describe a workload-generation model based on group classification of Web server les according to their contents. This model, henceforth referred to as SURGE-CC (SURGE Content Classification), is an extension of the SURGE (Scalable URL Reference Generator) model. SURGE-CC is simple, very easy to understand and, most important of all, can be readily customized for specific applications. The parameter settings in our model allows the influnce of Web server contents on output load to be investigated from both a qualitative and quantitative point of view. The results of a workload-generation tool based on our model implementation show the workload dependence on the nature of the server contents, the model ability to generate self-similar traffic and the accuracy of the synthetic workload. The model was validated by a careful statistical analysis of massive data from several servers, computational simulations and by comparison of results found in literature. We point some future application of the SURGE-CC model and discuss the new investigation branches derived from the novelty of our model approach.
Search Articles
Pages: 49-63
WSEAS Transactions on Information Science and Applications, ISSN / E-ISSN: 1790-0832 / 2224-3402, Volume 14, 2017, Art. #7