Adaptive Consistency Guarantees for Large-Scale Replicated Services

To maintain consistency, designers of replicated services have traditionally been forced to choose from either strong consistency guarantees or none at all. Realizing that a continuum between strong and optimistic consistencies is semantically meaningful for a broad range of network services, previous research has proposed a continuous consistency model for replicated services to support the tradeoff between the guaranteed consistency level, performance and availability. However, to meet changing application needs and to make the model useful for interactive users of large-scale replicated services, the adaptability and the swiftness of inconsistency resolution are important and challenging. This paper presents IDEA (an infrastructure for detection-based adaptive consistency guarantees) for adaptive consistency guarantees of large-scale, Internet-based replicated services. The main functions enabled by IDEA include quick inconsistency detection and resolution, consistency adaptation and quantified consistency level guarantees. Through experimentation on the Planet-Lab, IDEA is evaluated from two aspects: its adaptive consistency guarantees and its performance for inconsistency resolution. Results show that IDEA is able to provide consistency guarantees adaptive to userpsilas changing needs, and it achieves low delay for inconsistency resolution and incurs small communication overhead.