LLM As DBA

TL;DR

This paper introduces D-Bot, an LLM-based system that autonomously learns from textual sources to diagnose and optimize large-scale database systems efficiently and effectively.

Contribution

It presents a novel LLM-centric framework for database maintenance, including knowledge detection, root cause analysis, and collaborative diagnosis among multiple LLMs.

Findings

D-Bot can accurately diagnose database issues.

The framework improves maintenance efficiency.

Preliminary results show promising effectiveness.

Abstract

Database administrators (DBAs) play a crucial role in managing, maintaining and optimizing a database system to ensure data availability, performance, and reliability. However, it is hard and tedious for DBAs to manage a large number of database instances (e.g., millions of instances on the cloud databases). Recently large language models (LLMs) have shown great potential to understand valuable documents and accordingly generate reasonable answers. Thus, we propose D-Bot, a LLM-based database administrator that can continuously acquire database maintenance experience from textual sources, and provide reasonable, well-founded, in-time diagnosis and optimization advice for target databases. This paper presents a revolutionary LLM-centric framework for database maintenance, including (i) database maintenance knowledge detection from documents and tools, (ii) tree of thought reasoning for root cause analysis, and (iii) collaborative diagnosis among multiple LLMs. Our preliminary experimental results that D-Bot can efficiently and effectively diagnose the root causes and our code is available at github.com/TsinghuaDatabaseGroup/DB-GPT.