LearnedKV: Integrating LSM and Learned Index for Superior Performance on Storage

TL;DR

LearnedKV is a new key-value store that combines LSM trees with learned indexes to significantly improve read and write performance on storage devices, using a tiered design and efficient data conversion.

Contribution

It introduces a two-tier design integrating LSM and learned indexes with a non-blocking conversion mechanism, enhancing performance and reducing storage size.

Findings

Up to 4.32x faster reads compared to state-of-the-art solutions.

Up to 1.43x faster writes across diverse workloads.

Robust performance on SSDs and HDDs.

Abstract

We present LearnedKV, a novel tiered key-value store that seamlessly integrates a Log-Structured Merge (LSM) tree with a Learned Index to achieve superior read and write performance on storage systems. While existing approaches use learned indexes primarily as auxiliary components within LSM trees, LearnedKV employs a two-tier design where the LSM tree handles recent write operations while a separate Learned Index accelerates read performance. Our design includes a non-blocking conversion mechanism that efficiently transforms LSM data into a Learned Index during garbage collection, maintaining high performance without interrupting operations. LearnedKV dramatically reduces LSM size through this tiered approach, leading to significant performance gains in both reads and writes. Extensive evaluations across diverse workloads show that LearnedKV outperforms state-of-the-art LSM-based solutions by up to 4.32x for read operations and 1.43x for writes. The system demonstrates robust performance across different data distributions, access patterns, and storage media including both SSDs and HDDs.