Relais is a replicated directory service that improves Web cachingwithin an organization. Relais connects a distributed set of caches andmirrors, providing the abstraction of a single consistent, shared cache.Relais is based on a replication protocol that exploits the semantics ofuser requests to guarantee cache coherence. The protocol also exploitsthe semantics of origin servers to optimize bandwidth requirements. Atthe entry point for a client, Relais maintains a directory of thecontents of each Relais data provider; this minimizes look-up latency,by making it a local operation. The cost of maintaining the directoriesconsistent is minimized thanks to a weak consistency protocol. Relaishas been prototyped on top of Squid; it has been in daily use for over ayear
展开▼
