StarFish: Highly-Available Block Storage

The world's growing dependency on data increases the need for highly-available data storage. Geographically-dispersed replicas can provide data availability despite a major site failure, and are increasingly affordable given the price-performance trends of storage devices, servers, and high-speed networks. In this light we present StarFish, a block storage system built from commodity computing and networking gear that transparently replicates data over multiple storage sites. StarFish is accessed via a host-site appliance that masquerades as a host-attached storage device, hence it requires no special hardware or software in the host computer. We present a formal analysis that describes the data availability of the StarFish architecture as a function of the replica failure rate, recovery speed, number of replicas, and write quorum size.