DB-BERT: a Database Tuning Tool that "Reads the Manual"

2021/12/21 by Immanuel Trummer, Trummer, Immanuel · 1 voice · 9 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Databases (cs.DB) #FOS: Computer and information sciences #Machine Learning and Data Classification #Natural Language Processing Techniques #Topic Modeling #cs.AI #cs.CL #cs.DB

paper · pdf · doi:10.48550/arxiv.2112.10925

openalex publication_date 2021/12/21 · arxiv published 2021/12/21 · arxiv updated 2021/12/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

DB-BERT is a database tuning tool that exploits information gained via natural language analysis of manuals and other relevant text documents. It uses text to identify database system parameters to tune as well as recommended parameter values. DB-BERT applies large, pre-trained language models (specifically, the BERT model) for text analysis. During an initial training phase, it fine-tunes model weights in order to translate natural language hints into recommended settings. At run time, DB-BERT learns to aggregate, adapt, and prioritize hints to achieve optimal performance for a specific database system and benchmark. Both phases are iterative and use reinforcement learning to guide the selection of tuning settings to evaluate (penalizing settings that the database system rejects while rewarding settings that improve performance). In our experiments, we leverage hundreds of text documents about database tuning as input for DB-BERT. We compare DB-BERT against various baselines, considering different benchmarks (TPC-C and TPC-H), metrics (throughput and run time), as well as database systems (Postgres and MySQL). In all cases, DB-BERT finds the best parameter settings among all compared methods. The code of DB-BERT is available online at https://itrummer.github.io/dbbert/.

Cited by

• L2T-Tune:LLM-Guided Hybrid Database Tuning with LHS and TD3
• DemoTuner: Efficient DBMS Knobs Tuning via LLM-Assisted Demonstration Reinforcement Learning
• GenDB: The Next Generation of Query Processing -- Synthesized, Not Engineered
• Implementing Semantic Join Operators Efficiently
• SEFRQO: A Self-Evolving Fine-Tuned RAG-Based Query Optimizer
• MCTuner: Spatial Decomposition-Enhanced Database Tuning via LLM-Guided Exploration
• SQLBarber: A System Leveraging Large Language Models to Generate Customized and Realistic SQL Workloads
• LIMAO: A Framework for Lifelong Modular Learned Query Optimization
• In-Context Adaptation to Concept Drift for Learned Database Operations

Discussions

• DB-BERT: a database tuning tool that “reads the Manual” [hn, 1 points, 0 comments]

Related

• DemoTuner: Efficient DBMS Knobs Tuning via LLM-Assisted Demonstration Reinforcement Learning
• Is Large Language Model Good at Database Knob Tuning? A Comprehensive Experimental Evaluation
• λ-Tune: Harnessing Large Language Models for Automated Database System Tuning
• BERT: A Review of Applications in Natural Language Processing and Understanding
• DB-GPT: Empowering Database Interactions with Private Large Language Models