{\lambda}-Tune: Harnessing Large Language Models for Automated Database System Tuning

TL;DR

{ extbackslash}lambda-Tune is a novel framework that uses Large Language Models to automatically generate and select optimal database configuration scripts, improving robustness and efficiency over previous methods.

Contribution

It introduces a cost-based prompt optimization approach for LLMs to generate comprehensive database tuning configurations, outperforming prior single-parameter tuning methods.

Findings

Outperforms baseline tuning methods on multiple benchmarks.

Reduces reconfiguration overheads and evaluation costs.

Demonstrates robustness across PostgreSQL and MySQL.

Abstract

We introduce {\lambda}-Tune, a framework that leverages Large Language Models (LLMs) for automated database system tuning. The design of {\lambda}-Tune is motivated by the capabilities of the latest generation of LLMs. Different from prior work, leveraging LLMs to extract tuning hints for single parameters, {\lambda}-Tune generates entire configuration scripts, based on a large input document, describing the tuning context. {\lambda}-Tune generates alternative configurations, using a principled approach to identify the best configuration, out of a small set of candidates. In doing so, it minimizes reconfiguration overheads and ensures that evaluation costs are bounded as a function of the optimal run time. By treating prompt generation as a cost-based optimization problem, {\lambda}-Tune conveys the most relevant context to the LLM while bounding the number of input tokens and, therefore, monetary fees for LLM invocations. We compare {\lambda}-Tune to various baselines, using multiple benchmarks and PostgreSQL and MySQL as target systems for tuning, showing that {\lambda}-Tune is significantly more robust than prior approaches.