Title: SplinterDB: Closing the Bandwidth Gap on NVMe

Abstract: Key-value stores are a fundamental component to storage systems. Recent advances in storage hardware, especially the advent of NVMe devices, expose new bottlenecks in the design of current key-value stores. We introduce SplinterDB and show how it achieves a 6-9x improvement in the insertion rate over Facebook's RocksDB on NVMe devices, while also improving query performance by 2-2.5x.

Bio: Alex Conway is a PhD student in Computer Science at Rutgers University, advised by Martin Farach-Colton. His research is focused on external memory theory and storage systems. His recent publications include work on high performance key-value stores, file system aging, external memory hash tables and the analysis of storage optimization heuristics.

He is a member of the BetrFS team. BetrFS, a prototype file system, is designed around the principles of write-optimization and is built using variants of Bε-trees.