Algorithms for Timed Consistency Models (1310.7205v1)

Abstract: One of the major challenges in distributed systems is establishing consistency among replicated data in a timely fashion. While the consistent ordering of events has been extensively researched, the time span to reach a consistent state is mostly considered an effect of the chosen consistency model, rather than being considered a parameter itself. This paper argues that it is possible to give guarantees on the timely consistency of an operation. Subsequent to an update the cloud and all connected clients will either be consistent with the update within the defined upper bound of time or the update will be returned. This paper suggests the respective algorithms and protocols capable of producing such comprehensive Timed Consistency, as conceptually proposed by Torres-Rojas et al. The solution offers business customers an increasing level of predictability and adjustability. The temporal certainty concerning the execution makes the cloud a more attractive tool for time-critical or mission-critical applications fearing the poor availability of Strong Consistency in cloud environments.