Back to Search Start Over

KV-Tandem -- a Modular Approach to Building High-Speed LSM Storage Engines

Authors :
Bortnikov, Edward
Azran, Michael
Bornstein, Asa
Dashevsky, Shmuel
Huang, Dennis
Kepten, Omer
Pan, Michael
Sheffi, Gali
Twitto, Moshe
Orzech, Tamar Weiss
Keidar, Idit
Gueta, Guy
Maor, Roey
Dayan, Niv
Publication Year :
2024

Abstract

We present~\emph{KV-Tandem}, a modular architecture for building LSM-based storage engines on top of simple, non-ordered persistent key-value stores (KVSs). KV-Tandem enables advanced functionalities such as range queries and snapshot reads, while maintaining the native KVS performance for random reads and writes. Its modular design offers better performance trade-offs compared to previous KV-separation solutions, which struggle to decompose the monolithic LSM structure. Central to KV-Tandem is~\emph{LSM bypass} -- a novel algorithm that offers a fast path to basic operations while ensuring the correctness of advanced APIs. We implement KV-Tandem in \emph{XDP-Rocks}, a RocksDB-compatible storage engine that leverages the XDP KVS and incorporates practical design optimizations for real-world deployment. Through extensive microbenchmark and system-level comparisons, we demonstrate that XDP-Rocks achieves 3x to 4x performance improvements over RocksDB across various workloads. XDP-Rocks is already deployed in production, delivering significant operator cost savings consistent with these performance gains.

Subjects

Subjects :
Computer Science - Databases

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2411.11091
Document Type :
Working Paper