Adaptive control for availability and consistency in distributed key-values stores

Abstract

The CAP theorem says that distributed key-value stores can only provide bounded consistency (C) and availability (A) under the presence of partition (P). Recent work has proposed the ability for applications of such stores to specify either an availability SLA or a consistency SLA. In this paper, we propose an adaptive algorithm that automatically controls the underlying storage system in real-time to meet such an SLA while optimizing the other C/A metric. We also present an implementation of the algorithm based on the popular key-value store Riak. Our experiments with the modified system, under realistic workloads, show that the control technique is able to change the system’s configurations to quickly and stably satisfy the SLAs.