Hierarchical Consistent Hashing for Heterogeneous Object-Based Storage

Abstract

Distributed storage systems play an increasingly critical role in data centers to meet the ever-increasing data growth demand. Heterogeneous storage systems, with the coexistence of hard disk drives (HDDs) and solid state drives (SSDs), can be an attractive distributed store solution due to the balanced performance, large capacity, and economic cost. The consistent hashing distribution algorithm that is widely used in distributed storage systems can achieve scalable and flexible mappings, but do not take full advantages of different characteristics of heterogeneous devices. In this research, we propose a hierarchical consistent hashing (HiCH) algorithm to better manage data distribution in a heterogeneous object-based storage system and better explore the potential of heterogeneous devices. HiCH divides heterogeneous storage devices into different buckets and applies separate consistent hashing rings for each bucket. It places data into various hashing rings according to the hotness, access time, and other data access patterns. The evaluation based on the Sheepdog, a distributed objectbased storage system, confirms that HiCH can improve the performance of storage systems, and also make better utilization of heterogeneous storage devices.