Parallel Multi-split Extendible Hashing for Persistent Memory

Abstract

Emerging persistent memory (PM) is a promising technology that provides near-DRAM performance and disk-like durability. However, many data structures designed based on DRAM, such as hash table and B-tree, are sub-optimal for PM. Prior studies have shown that the scalability of hash tables on Intel Optane DC Persistent Memory Modules (DCPMM) degrades significantly due to expensive lock-based concurrency control and massive data movements during rehashing. This paper proposes a lock-free parallel multi-split extendible hashing scheme (PMEH), which eliminates the lock contention overhead, reduces data movements during rehashing, and ensures data consistency. Under the widely used YCSB workloads, the evaluation results show that compared to other state-of-the-art hashing schemes, PMEH is up to 1.38x faster for insertion and up to 1.9x faster for deletion, while reducing 52% extra writes. In addition, PMEH can ensure instant recovery regardless of data size.