Why Database Manuals Are Not Enough: Efficient and Reliable Configuration Tuning for DBMSs via Code-Driven LLM Agents

TL;DR

This paper introduces SysInsight, a code-driven system that leverages static code analysis and LLM reasoning to extract tuning rules from DBMS source code, significantly improving tuning speed and performance.

Contribution

It presents a novel approach to database tuning by mining configuration insights directly from source code, combining static analysis, LLM reasoning, and rule mining.

Findings

SysInsight converges 7.11 times faster than state-of-the-art methods.

Achieves a 19.9% performance improvement over baseline.

Effectively identifies critical knobs for tuning.

Abstract

Modern database management systems (DBMSs) expose hundreds of configuration knobs that critically influence performance. Existing automated tuning methods either adopt a data-driven paradigm, which incurs substantial overhead, or rely on manual-driven heuristics extracted from database documentation, which are often limited and overly generic. Motivated by the fact that the control logic of configuration knobs is inherently encoded in the DBMS source code, we argue that promising tuning strategies can be mined directly from the code, uncovering fine-grained insights grounded in system internals. To this end, we propose SysInsight, a code-driven database tuning system that automatically extracts fine-grained tuning knowledge from DBMS source code to accelerate and stabilize the tuning process. SysInsight combines static code analysis with LLM-based reasoning to identify knob-controlled execution paths and extract semantic tuning insights. These insights are then transformed into quantitative and verifiable tuning rules via association rule mining grounded in tuning observations. During online tuning, system diagnosis is applied to identify critical knobs, which are adjusted under the rule guidance. Evaluations demonstrate that compared to the SOTA baseline, SysInsight converges to the best configuration on average 7.11X faster while achieving a 19.9% performance improvement.