Dynamic information-based scalable hashing on a cluster of web cache servers
Concurrency and Computation: Practice & Experience
DISH: dynamic information-based scalable hashing on a cluster of web cache servers
HPCC'07 Proceedings of the Third international conference on High Performance Computing and Communications
Hi-index | 0.00 |
Internet traffic doubles every three months, with web traffic accounting for more than 75% of the total traffic between major ISP providers. Web caching at proxies can reduce this traffic as well as web user latencies. One way to increase the hit rate of caches is to have caches cooperate using the Internet Cache Protocol or using hash functions. This paper provides an experimental and theoretical analysis of two well known hash based caching schemes. Our paper also proposes a new allocation scheme which improves the performance of one of the analyzed techniques. It reduces the standard deviation of the URLs distribution on caches by a factor greater than two without any increase on the scheme complexity.