LITS: An Optimized Learned Index for Strings (An Extended Version)

TL;DR

LITS introduces a novel learned index for variable-length string keys, combining hash-enhanced prefix tables and local models to significantly outperform traditional string indexes in point operations.

Contribution

The paper presents LITS, a new learned index structure specifically designed for string keys, addressing limitations of existing models with a hybrid approach for improved performance.

Findings

LITS achieves up to 2.43x speedup over HOT for point queries.

LITS outperforms ART by up to 2.27x in point operations.

LITS maintains comparable scan performance to traditional indexes.

Abstract

Index is an important component in database systems. Learned indexes have been shown to outperform traditional tree-based index structures for fixed-sized integer or floating point keys. However, the application of the learned solution to variable-length string keys is under-researched. Our experiments show that existing learned indexes for strings fail to outperform traditional string indexes, such as HOT and ART. String keys are long and variable sized, and often contain skewed prefixes, which make the last-mile search expensive, and adversely impact the capability of learned models to capture the skewed distribution of string keys. In this paper, we propose a novel learned index for string keys, LITS (Learned Index with Hash-enhanced Prefix Table and Sub-tries). We propose an optimized learned model, combining a global Hash-enhanced Prefix Table (HPT) and a per-node local linear model to better distinguish string keys. Moreover, LITS exploits compact leaf nodes and hybrid structures with a PMSS model for efficient point and range operations. Our experimental results using eleven string data sets show that LITS achieves up to 2.43x and 2.27x improvement over HOT and ART for point operations, and attains comparable scan performance.