arXiv：cs.LG· Fangping Lan, Qi Zhang, Eduard Dragut·· 4 小时前AI 评分39
CATune：面向 DBMS 配置调优的结构约束感知贝叶斯优化
CATune: Structural Constraint-Aware Bayesian Optimization for DBMS Configuration Tuning
AI 导读
CATune 是一个约束感知的贝叶斯优化框架，将 DBMS 旋钮间的确定性排序约束建模为搜索域的结构组成部分，在约束一致子空间内进行优化，并用 LLM 解析结合可靠性保障的抽取流程自动发现约束。在 PostgreSQL 和 MySQL 上的 TPC-C 与 TPC-H 实验中，CATune 达到基线最优的速度最高快 12.5 倍，吞吐量最高提升 63.37%。
正文
Abstract:Modern DBMSs expose hundreds of configuration knobs, resulting in a high-dimensional and heterogeneous search space that makes automated tuning costly. Existing ML-based tuning systems typically treat the configuration domain as box-constrained and rely on workload feedback to implicitly capture inter-knob relationships. However, DBMS documentation specifies deterministic knob dependency constraints, particularly ordering constraints, that characterize structurally valid regions of the configuration space. We present CATune, a constraint-aware Bayesian optimization (BO) framework that models deterministic inter-knob ordering constraints as structural components of the search domain. Instead of learning feasibility boundaries through sampled violations, CATune performs optimization within a constraint-consistent subspace. We develop a topology-aware sampling strategy that respects dependency structure during exploration and avoids the inefficiencies of post-hoc constraint handling. To enable automated constraint discovery, we further design a precision-first extraction pipeline that combines LLM-based parsing with reliability safeguards to mitigate hallucinated dependencies. Experiments on PostgreSQL and MySQL using TPC-C and TPC-H workloads show that CATune substantially improves both sample efficiency and final tuning quality across surrogate models and BO frameworks. Under default ranges, CATune reaches the baseline optimum up to 12.5x faster and improves throughput by up to 63.37%. The improvements persist under knowledge-guided reduced ranges and alternative optimization implementations. These results demonstrate that explicitly modeling system-defined deterministic ordering constraints enhances optimization robustness and system stability.
| Comments: | 14 pages including references, 10 figure, 2 tables. Accpeted by PVLDB, Volume 19, 2026 |
| Subjects: | Databases (cs.DB); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.09276 [cs.DB] |
| (or arXiv:2610.09276v1 [cs.DB] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09276 arXiv-issued DOI via DataCite (pending registration) |
|
| Related DOI: | https://doi.org/10.14778/3849398.3849421
DOI(s) linking to related resources |
Submission history
From: Fangping Lan [view email]
[v1]
Wed, 7 Oct 2026 01:14:40 UTC (6,158 KB)
来源：arXiv：cs.LG · arxiv.org