Relation-Aware Bayesian Optimization of DBMS Configurations Guided by Affinity Scores

TL;DR

This paper introduces RelTune, a relation-aware Bayesian optimization framework for DBMS configuration tuning that models parameter dependencies with GNNs and uses affinity scores for improved performance, achieving faster convergence and better results.

Contribution

RelTune is the first to incorporate relational graphs and GNN-based embeddings into Bayesian optimization for DBMS tuning, addressing parameter dependencies and high-dimensional search challenges.

Findings

RelTune outperforms traditional BO methods in convergence speed.

RelTune achieves higher optimization efficiency across multiple DBMSs.

Experimental results show state-of-the-art performance in diverse scenarios.

Abstract

Database Management Systems (DBMSs) are fundamental for managing large-scale and heterogeneous data, and their performance is critically influenced by configuration parameters. Effective tuning of these parameters is essential for adapting to diverse workloads and maximizing throughput while minimizing latency. Recent research has focused on automated configuration optimization using machine learning; however, existing approaches still exhibit several key limitations. Most tuning frameworks disregard the dependencies among parameters, assuming that each operates independently. This simplification prevents optimizers from leveraging relational effects across parameters, limiting their capacity to capture performancesensitive interactions. Moreover, to reduce the complexity of the high-dimensional search space, prior work often selects only the top few parameters for optimization, overlooking others that contribute meaningfully to performance. Bayesian Optimization (BO), the most common method for automatic tuning, is also constrained by its reliance on surrogate models, which can lead to unstable predictions and inefficient exploration. To overcome these limitations, we propose RelTune, a novel framework that represents parameter dependencies as a Relational Graph and learns GNN-based latent embeddings that encode performancerelevant semantics. RelTune further introduces Hybrid-Score-Guided Bayesian Optimization (HBO), which combines surrogate predictions with an Affinity Score measuring proximity to previously high-performing configurations. Experimental results on multiple DBMSs and workloads demonstrate that RelTune achieves faster convergence and higher optimization efficiency than conventional BO-based methods, achieving state-of-the-art performance across all evaluated scenarios.