Directory Structures for Scalable Internet Caches

Use of Internet caches is a cheap and eeective way to improve performance for all Internet users. Distributed caches ooer the potential to serve larger user communities and to deliver higher hit ratios on shared Web documents. The key to building eeective distributed caches is a directory structure that allows individual caching servers to locate objects cached at neighboring sites, combining them into a logically uniied collective cache. This paper uses Web traces to evaluate a range of alternatives for managing directories in distributed Internet caches. We use trace-driven executions and simulations of prototype caches to compare multicast-based queries of local maps (Harvest) with unicast queries of a global map (CRISP). We then use properties of the traces to predict performance of CRISP variants in which the global map is partitioned or replicated. Finally, we propose a novel lazy CRISP structure based on weakly consistent replication of the most valuable subset of the global map. We show that this scheme combines the best aspects of several distributed cache structures, while maintaining a near-ideal hit ratio.