A quantitative study of Web cache replacement strategies using simulation

Abstract

The Web has become the most important source of information and communication for the world. Proxy servers are used to cache objects with the goals of decreasing network traffic, reducing user perceived lag and loads on origin servers. In this paper, we focus on the cache replacement problem with respect to proxy servers. Despite the fact that some Web 2.0 applications have dynamic objects, most of the Web traffic has static content with file types such as cascading style sheets, javascript files, images, etc. The cache replacement strategies implemented in Squid, a widely used proxy cache software, are no longer considered ‘good enough’ today. Squid’s default strategy is Least Recently Used. While this is a simple approach, it does not necessarily achieve the targeted goals. We simulate 27 proxy cache replacement strategies and analyze them against several important performance measures. Hit rate and byte hit rate are the most commonly used performance metrics in the literature. Hit rate is an indication of user perceived lag, while byte hit rate is an indication of the amount of network traffic. We also introduce a new performance metric, the object removal rate, which is an indication of CPU usage and disk access at the proxy server. This metric is particularly important for busy cache servers or servers with lower processing power. Our study provides valuable insights for both industry and academia. They are especially important for Web proxy cache system administrators; particularly in wireless ad-hoc networks as the caches on mobile devices are relatively small.