Toward a principled framework for benchmarking consistency

Large-scale key-value storage systems sacrifice consis-tency in the interest of dependability (i.e., partition-tolerance and availability), as well as performance (i.e., latency). Such systems provide eventual consistency, which—to this point—has been difficult to quantify in real systems. Given the many implementations and deployments of eventually-consistent systems (e.g., NoSQL systems), attempts have been made to measure this consistency empirically, but they suffer from impor-tant drawbacks. For example, state-of-the art consistency benchmarks exercise the system only in restricted ways and disrupt the workload, which limits their accuracy. In this paper, we take the position that a consistency benchmark should paint a comprehensive picture of the relationship between the storage system under considera-tion, the workload, the pattern of failures, and the consis-tency observed by clients. To illustrate our point, we first survey prior efforts to quantify eventual consistency. We then present a benchmarking technique that overcomes the shortcomings of existing techniques to measure the consistency observed by clients as they execute the work-load under consideration. This method is versatile and minimally disruptive to the system under test. As a proof of concept, we demonstrate this tool on Cassandra.