The costs and limits of availability for replicated services

Haifeng Yu, Amin Vahdat
2006 ACM Transactions on Computer Systems  
As raw system and network performance continues to improve a t exponential rates, the utility o f m a n y services is increasingly limited by a vailability rather than performance. A k ey approach t o improving availability i n volves replicating the service across multiple, wide-area sites. However, replication introduces well-known tradeo s between service consistency and availability. Thus, this paper explores the bene ts of dynamically trading consistency for availability using a continuous
more » ... consistency model. In this model, applications specify a maximum deviation from strong consistency on a per-replica basis. In this paper, we: i) evaluate availability o f a p r o t o t ype replication system running across the Internet as a function of consistency level, consistency protocol, and failure characteristics, ii) demonstrate that simple optimizations to existing consistency protocols result in signi cant availability i m p r o vements (more than an order of magnitude in some scenarios), iii) use our experience with these optimizations to prove t i g h t upper bounds on the availability of services, and iv) show that maximizing availability t ypically entails remaining as close to strong consistency as possible during times of good connectivity, resulting in a communication versus availability tradeo .
doi:10.1145/1124153.1124156 fatcat:a3uqfzwphvczdjuqbemj3egnbi