Analysis of performance impact of drill-down techniques for web traffic models

Abstract

The performance of Web sites continues to be an important research topic. Such studies are invariably based on the access logs from the servers comprising the Web site. A problem with existing access logs is the coarse granularity of the timestamps, e.g., arrival times. In this study we demonstrate and quantify the significant differences in performance obtained under diverse assumptions about the arrival process of user requests derived from the access logs, where the corresponding user response times can differ by more than an order of magnitude. This motivates the need for a general methodology to construct accurate representations of the actual arrival process of user requests from existing coarse-grained accesslog data. Our analysis of the access logs from representative commercial Web sites illustrates self-similar behavior of the arrival process, and we exploit the properties of these self-similar processes as a theoretical foundation for constructing the arrival process at finer time scales. The advantage of our approach is that it maintains consistency between the properties of the arrival processes at both coarser and finer time scales. In addition, our analysis of the request size distribution from commercial Web sites demonstrates a subexponential, but not heavy-tail (power-law) distribution. Through simulations, we investigate the impact of these different traffic models on the user request response times.