ESTune: Bayesian Uncertainty-Guided Early Stopping for Database Configuration Tuning
Proceedings of the ACM on Management of Data · 02.04.2026 · 4 (1) · 1-26
DOI: 10.1145/3786649 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Management of Data, online erschienen am 07.04.2026. Verfasst von Zhongwei Yue und 5 weiteren Autor:innen. Die Arbeit nennt 54 Literaturangaben. Gefördert von: National Natural Science Foundation of China, OceanBase.
Abstract (Originalsprache)
Existing database knob tuning methods evaluate the actual performance of each configuration by fully executing the entire workload. However, our experimental analysis reveals that this exhaustive execution approach significantly limits tuning efficiency, particularly when dealing with underperforming configurations. To address this issue, we propose ESTune, which is designed to early-stop the execution of poorly performing configurations. ESTune approximates the actual performance of these configurations using high-confidence predicted values generated from partially executed workload data and configuration knob settings. This strategy significantly reduces the evaluation time for underperforming configurations while maintaining the overall tuning effectiveness. The high-confidence predicted values are produced by a Hybrid Bayesian Neural Network (HBNN), which models the performance distribution with respect to different knob configurations. To address the challenge of limited training data commonly encountered in database knob tuning, ESTune integrates a Model-Agnostic Meta-Learning (MAML), thereby enhancing the few-shot learning capability of the HBNN. Extensive evaluations on a wide range of workloads consistently demonstrate that ESTune improves the tuning efficiency of existing methods.
Förderung
- National Natural Science Foundation of China
- OceanBase
Zitieren
APA
Yue, Z., Zhu, J., Cai, P., Zhou, X., Xu, Q., & Yang, C. (2026). ESTune: Bayesian Uncertainty-Guided Early Stopping for Database Configuration Tuning. Proceedings of the ACM on Management of Data, 4(1), 1-26. https://doi.org/10.1145/3786649
Vancouver
Yue Z, Zhu J, Cai P, Zhou X, Xu Q, Yang C. ESTune: Bayesian Uncertainty-Guided Early Stopping for Database Configuration Tuning. Proceedings of the ACM on Management of Data. 2026;4(1):1-26. doi:10.1145/3786649
BibTeX
@article{Yue2026,
author = {Yue, Zhongwei and Zhu, Jun-Peng and Cai, Peng and Zhou, Xuan and Xu, Quanqing and Yang, Chuanhui},
title = {ESTune: Bayesian Uncertainty-Guided Early Stopping for Database Configuration Tuning},
journal = {Proceedings of the ACM on Management of Data},
year = {2026},
volume = {4},
number = {1},
pages = {1--26},
doi = {10.1145/3786649}
}
EUVIMED