SplinterDB

Summary

Modern NVMe solid state drives offer significantly higher bandwidth and lower latency than prior storage devices. Current key-value stores struggle to fully utilize the bandwidth of such devices. This paper presents SplinterDB, a new key-value store explicitly designed for NVMe solid-state-drives.

SplinterDB is designed around a novel data structure (the STB^ε-tree) that exposes I/O and CPU concurrency and reduces write amplification without sacrificing query performance. STB^ε-tree combines ideas from log-structured merge trees and B^ε-trees to reduce write amplification and CPU costs of compaction. The SplinterDB memtable and cache are designed to be highly concurrent and to reduce cache misses.

On a number of micro- and macro-benchmarks, SplinterDB outperforms RocksDB, a state-of-the-art key-value store, by a factor of 6–10x on insertions and 2–2.6x on point queries, while matching RocksDB on small range queries. Furthermore, SplinterDB reduces write amplification by 2x.

Learn more about SplinterDB on VMware's Open Source Blog: Introducing SplinterDB: A High-Performance Key-Value Store

Code

SplinterDB is open source. The code is available on github: https://github.com/vmware/splinterdb.

News

• Our USENIX ATC 2020 paper introduces size-tiered B^ε-trees and SplinterDB, a key-value store that outperforms RocksDB by up to an order of magnitude.