D-Bot: Database Diagnosis System using Large Language Models

TL;DR

D-Bot tackles the scalability and generalization gaps in database diagnosis by combining offline knowledge extraction from diagnosis documents with a prompt-driven LLM workflow, a tree-search reasoning mechanism, and a collaborative multi-LLM architecture. It builds a knowledge-and-tools framework, matches context-specific knowledge and APIs, and uses tree-search and asynchronous collaboration to locate root causes efficiently. Experimental results show D-Bot significantly outperforms traditional baselines and approaches human DBA performance in many scenarios, while enabling diagnosis within minutes. The work demonstrates a practical pathway to automated, generalizable database diagnosis across diverse anomalies and applications.

Abstract

Database administrators (DBAs) play an important role in managing, maintaining and optimizing database systems. However, it is hard and tedious for DBAs to manage a large number of databases and give timely response (waiting for hours is intolerable in many online cases). In addition, existing empirical methods only support limited diagnosis scenarios, which are also labor-intensive to update the diagnosis rules for database version updates. Recently large language models (LLMs) have shown great potential in various fields. Thus, we propose D-Bot, an LLM-based database diagnosis system that can automatically acquire knowledge from diagnosis documents, and generate reasonable and well-founded diagnosis report (i.e., identifying the root causes and solutions) within acceptable time (e.g., under 10 minutes compared to hours by a DBA). The techniques in D-Bot include (i) offline knowledge extraction from documents, (ii) automatic prompt generation (e.g., knowledge matching, tool retrieval), (iii) root cause analysis using tree search algorithm, and (iv) collaborative mechanism for complex anomalies with multiple root causes. We verify D-Bot on real benchmarks (including 539 anomalies of six typical applications), and the results show that D-Bot can effectively analyze the root causes of unseen anomalies and significantly outperforms traditional methods and vanilla models like GPT-4.

Figures (11)

• Figure 1: Database diagnosis is a complex problem mainly handled by human expertise -- (a) example root causes of anomalies in a database vendor; (b) comparison of diagnosis methods; (c) toy example of diagnosing by human DBA; (d) example of diagnosing by machine learning classifier.
• Figure 2: Example of Database Diagnosis.
• Figure 3: Database Diagnosis in D-Bot.
• Figure 4: D-Bot Architecture.
• Figure 5: Document Learning.