Improving proxy cache performance: Analysis of three replacement policies

Web caches are located throughout the Internet, from the user's browser cache through local proxy caches and backbone caches, to the so-called reverse proxy cache located near the origin of the content. Each of these caches serves a different set of users and has slightly different goals. A cache server has a fixed amount of storage. When this storage space fills, the cache must choose a set of objects to evict to make room for newly requested objects. Web cache replacement policy choice affects network bandwidth demand and object hit rate, which affect page load time. Two new policies implemented in the Squid cache server show improvement over the standard mechanism.