TurboKV: Scaling Up The Performance of Distributed Key-Value Stores With In-Switch Coordination

Abstract

The power and flexibility of software-defined networks lead to a programmable network infrastructure in which in-network computation can help accelerating the performance of applications. This can be achieved by offloading some computational tasks to the network. However, what kind of computational tasks should be delegated to the network to accelerate applications performance? In this paper, we propose a way to exploit the usage of programmable switches to scale up the performance of distributed key-value stores. Moreover, as a proof-of-concept, we propose TurboKV, an efficient distributed key-value store architecture that utilizes programmable switches as: 1) partition management nodes to store the key-value store partitions and replicas information; and 2) monitoring stations to measure the load of storage nodes, this monitoring information is used to balance the load among storage nodes. We also propose a key-based routing protocol to route the search queries of clients based on the requested keys to targeted storage nodes. Our experimental results of an initial prototype show that our proposed architecture improves the throughput and reduces the latency of distributed key-value stores when compared to the existing architectures.