KnobTree: Intelligent Database Parameter Configuration via Explainable Reinforcement Learning

TL;DR

KnobTree introduces an explainable reinforcement learning framework using a tree-based model and Shapley Values to optimize database parameters, improving transparency, stability, and performance in database tuning.

Contribution

This work presents the first interpretable RL-based framework for database configuration, combining a differential tree model with Shapley Values for parameter importance assessment.

Findings

KnobTree achieves higher transparency and interpretability.

The approach slightly outperforms existing RL tuning algorithms.

Experiments on MySQL and Gbase8s validate effectiveness.

Abstract

Databases are fundamental to contemporary information systems, yet traditional rule-based configuration methods struggle to manage the complexity of real-world applications with hundreds of tunable parameters. Deep reinforcement learning (DRL), which combines perception and decision-making, presents a potential solution for intelligent database configuration tuning. However, due to black-box property of RL-based method, the generated database tuning strategies still face the urgent problem of lack explainability. Besides, the redundant parameters in large scale database always make the strategy learning become unstable. This paper proposes KnobTree, an interpertable framework designed for the optimization of database parameter configuration. In this framework, an interpertable database tuning algorithm based on RL-based differentatial tree is proposed, which building a transparent tree-based model to generate explainable database tuning strategies. To address the problem of large-scale parameters, We also introduce a explainable method for parameter importance assessment, by utilizing Shapley Values to identify parameters that have significant impacts on database performance. Experiments conducted on MySQL and Gbase8s databases have verified exceptional transparency and interpretability of the KnobTree model. The good property makes generated strategies can offer practical guidance to algorithm designers and database administrators. Moreover, our approach also slightly outperforms the existing RL-based tuning algorithms in aspects such as throughput, latency, and processing time.