Role of Aging, Frequency, and Size in Web Cache Replacement Policies

Abstract

Document caching on is used to improve Web performance. An efficient caching policy keeps popular documents in the cache and replaces rarely used ones. The latest web cache replacement policies incorporate the document size, frequency, and age in the decision process. The recently-proposed and very popular Greedy-Dual-Size (GDS) policy is based on document size and has an elegant aging mechanism. Similarly, the Greedy-Dual-Frequency (GDF) policy takes into account file frequency and exploits the aging mechanism to deal with cache pollution. The efficiency of a cache replacement policy can be evaluated along two popular metrics: file hit ratio and byte hit ratio. Using four different web server logs, we show that GDS-like replacement policies emphasizing size yield the best file hit ratio but typically show poor byte hit ratio, while GDF-like replacement policies emphasizing frequency have better byte hit ratio but result in worse file hit ratio. In this paper, we propose a generalization of Greedy-Dual-Frequency-Size policy which allows to balance the emphasis on size vs. frequency. We perform a sensitivity study to derive the impact of size and frequency on file and byte hit ratio, identifying parameters that aim at optimizing both metrics.