Why Database Manuals Are Not Enough: Efficient and Reliable Configuration Tuning for DBMSs via Code-Driven LLM Agents
🤖 AI Summary
Modern database management systems (DBMSs) involve numerous configuration parameters, yet existing auto-tuning approaches either rely on high-overhead data-driven strategies or are constrained by coarse-grained manual heuristics, struggling to balance efficiency and accuracy. This work proposes SysInsight, a novel system that, for the first time, leverages DBMS source code as a knowledge source for tuning. By integrating static code analysis, large language model (LLM)-based semantic reasoning, and association rule mining, SysInsight automatically extracts fine-grained, verifiable quantitative tuning rules and combines them with system diagnostics to enable dynamic online tuning. Experimental results demonstrate that SysInsight achieves an average convergence speed 7.11× faster and a 19.9% higher performance gain compared to state-of-the-art methods.
Application Category
📝 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.
Problem
Research questions and friction points this paper is trying to address.
database configuration tuning
DBMS knobs
automated tuning
performance optimization
configuration overhead
Innovation
Methods, ideas, or system contributions that make the work stand out.
code-driven tuning
LLM agents
static code analysis
association rule mining
DBMS configuration
🔎 Similar Papers
2024-04-17Citations: 1
