Summary cache: a scalable wide-area Web cache sharing protocol

TLDR

Sharing caches among Web proxies can reduce traffic and alleviate bottlenecks, but existing protocols impose too much overhead for widespread deployment. This work demonstrates the benefits of cache sharing, quantifies the overhead of current protocols, and introduces a new protocol called summary cache. Summary cache maintains a compact, periodically updated summary of each proxy’s cache directory—only 8 bits per entry—and checks these summaries for potential hits before issuing queries, thereby minimizing protocol traffic. Trace‑driven simulations and a prototype show that summary cache cuts inter‑cache messages by 25–60×, cuts bandwidth by over 50 %, eliminates 30–95 % of protocol CPU load, and preserves cache hit ratios comparable to ICP, enabling scaling to many proxies. This paper revises Fan et al.

Abstract

The sharing of caches among Web proxies is an important technique to reduce Web traffic and alleviate network bottlenecks. Nevertheless it is not widely deployed due to the overhead of existing protocols. In this paper we demonstrate the benefits of cache sharing, measure the overhead of the existing protocols, and propose a new protocol called "summary cache". In this new protocol, each proxy keeps a summary of the cache directory of each participating proxy, and checks these summaries for potential hits before sending any queries. Two factors contribute to our protocol's low overhead: the summaries are updated only periodically, and the directory representations are very economical, as low as 8 bits per entry. Using trace-driven simulations and a prototype implementation, we show that, compared to existing protocols such as the Internet cache protocol (ICP), summary cache reduces the number of intercache protocol messages by a factor of 25 to 60, reduces the bandwidth consumption by over 50%, eliminates 30% to 95% of the protocol CPU overhead, all while maintaining almost the same cache hit ratios as ICP. Hence summary cache scales to a large number of proxies. (This paper is a revision of Fan et al. 1998; we add more data and analysis in this version).