Automatic Database Configuration Debugging using Retrieval-Augmented Language Models

Guardat en:
Dades bibliogràfiques
Publicat a:arXiv.org (Dec 10, 2024), p. n/a
Autor principal: Chen, Sibei
Altres autors: Fan, Ju, Wu, Bin, Tang, Nan, Deng, Chao, Wang, Pengyi, Li, Ye, Tan, Jian, Li, Feifei, Zhou, Jingren, Du, Xiaoyong
Publicat:
Cornell University Library, arXiv.org
Matèries:
Accés en línia:Citation/Abstract
Full text outside of ProQuest
Etiquetes: Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!

MARC

LEADER 00000nab a2200000uu 4500
001 3143055023
003 UK-CbPIL
022 |a 2331-8422 
035 |a 3143055023 
045 0 |b d20241210 
100 1 |a Chen, Sibei 
245 1 |a Automatic Database Configuration Debugging using Retrieval-Augmented Language Models 
260 |b Cornell University Library, arXiv.org  |c Dec 10, 2024 
513 |a Working Paper 
520 3 |a 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. 
653 |a Data base management systems 
653 |a Debugging 
653 |a Questions 
653 |a Performance enhancement 
653 |a Configuration management 
653 |a Large language models 
653 |a Trouble shooting 
653 |a Knobs 
653 |a Documents 
653 |a Troubleshooting 
653 |a Retrieval 
700 1 |a Fan, Ju 
700 1 |a Wu, Bin 
700 1 |a Tang, Nan 
700 1 |a Deng, Chao 
700 1 |a Wang, Pengyi 
700 1 |a Li, Ye 
700 1 |a Tan, Jian 
700 1 |a Li, Feifei 
700 1 |a Zhou, Jingren 
700 1 |a Du, Xiaoyong 
773 0 |t arXiv.org  |g (Dec 10, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3143055023/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2412.07548