Automatic Database Configuration Debugging using Retrieval-Augmented Language Models

2024-12-10

arXiv.org

AI Summary

Database configuration tuning remains a critical challenge for DBAs, as existing approaches struggle to simultaneously achieve high diagnostic accuracy and actionable remediation recommendations. This paper proposes the first Retrieval-Augmented Generation (RAG) framework specifically designed for DBMS configuration debugging. It integrates heterogeneous knowledge sources—including historical support tickets, official documentation, and real-time telemetry—enabling natural-language-based interactive diagnosis. By combining domain-specific retrieval over heterogeneous documents with fine-tuned large language model (LLM) reasoning, the framework achieves end-to-end problem localization and executable fix generation. Evaluations on a real-world DBMS configuration debugging dataset demonstrate substantial improvements over state-of-the-art baselines: diagnostic accuracy increases by 23.6%, and recommendation adoption rate reaches 89.4%. To our knowledge, this is the first approach to deliver automated configuration debugging that is simultaneously accurate, interpretable, and operationally executable.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Search and Optimization: Algorithm Configuration

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

Abstract

Database management system (DBMS) configuration debugging, e.g., diagnosing poorly configured DBMS knobs and generating troubleshooting recommendations, is crucial in optimizing DBMS performance. However, the configuration debugging process is tedious and, sometimes challenging, even for seasoned database administrators (DBAs) with sufficient experience in DBMS configurations and good understandings of the DBMS internals (e.g., MySQL or Oracle). To address this difficulty, we propose Andromeda, a framework that utilizes large language models (LLMs) to enable automatic DBMS configuration debugging. Andromeda serves as a natural surrogate of DBAs to answer a wide range of natural language (NL) questions on DBMS configuration issues, and to generate diagnostic suggestions to fix these issues. Nevertheless, directly prompting LLMs with these professional questions may result in overly generic and often unsatisfying answers. To this end, we propose a retrieval-augmented generation (RAG) strategy that effectively provides matched domain-specific contexts for the question from multiple sources. They come from related historical questions, troubleshooting manuals and DBMS telemetries, which significantly improve the performance of configuration debugging. To support the RAG strategy, we develop a document retrieval mechanism addressing heterogeneous documents and design an effective method for telemetry analysis. Extensive experiments on real-world DBMS configuration debugging datasets show that Andromeda significantly outperforms existing solutions.

Problem

• database optimization
• automatic detection
• settings correction

Innovation

• Andromeda
• RAG Strategy
• Advanced Super Language Model