Trace driven simulation of GDSF# and existing caching algorithms for web proxy servers

Web proxy caching is used to improve the performance of the Web infrastructure. It aims to reduce network traffic, server load, and user perceived retrieval delays. The heart of a caching system is its page replacement policy, which needs to make good replacement decisions when its cache is full and a new document needs to be stored. The latest and most popular replacement policies like GDSF use the file size, access frequency, and age in the decision process. The effectiveness of any replacement policy can be evaluated using two metrics: hit ratio (HR) and byte hit ratio (BHR). There is always a trade-off between HR and BHR [1]. In this paper, using three different proxy server logs, we use trace driven analysis to evaluate the effects of different replacement policies on the performance of a Web server. We propose a modification of GDSF policy, GDSF#, which allows augmenting or weakening the impact of size or frequency or both on HR and BHR. Our simulation results show that our proposed replacement policy GDSF# gives close to perfect performance in both the important metrics: HR and BHR.