GPTuner: An LLM-Based Database Tuning System
Open accessAbstract
Selecting appropriate values for the configurable knobs of Database Management Systems (DBMS) is essential to improve performance. But because the complexity of this task has surpassed the abilities of even the best human experts, the database community turns to machine learning (ML)- based automatic tuning systems. However, these systems still incur significant tuning costs or only yield suboptimal performance, attributable to their overly high reliance on black-box optimization and the lack of integration with domain knowledge, such as DBMS manuals and forum discussions. Hence, we propose GPTuner, a manual-reading database tuning system that extensively leverages domain knowledge to automatically optimize the search space and enhance the runtime feedback-based optimization process. Firstly, we develop a Large Language Model (LLM)-based pipeline to collect and refine heterogeneous knowledge, and propose a prompt ensemble algorithm to unify a structured view of the refined knowledge. Secondly, using the structured knowledge, we (1) design a workload-aware, trainingfree knob selection strategy, (2) develop a search space optimization technique considering the value range of each knob, (3) propose a Coarse-to-Fine Bayesian Optimization Framework to explore the optimized space. Finally, we evaluate GPTuner under different benchmarks (TPC-C and TPC-H), metrics (throughput and latency) and DBMS (PostgreSQL and MySQL). Compared to state-of-the-art methods, GPTuner identifies better configurations in 16x less time on average. Moreover, GPTuner achieves up to 30% performance improvement over the best-performing alternative.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Practical Bayesian Optimization of Machine Learning Algorithms
Snoek, J., Larochelle, H., & Adams, R. P. (2012) · arXiv · doi:10.48550/arxiv.1206.2944 · Cited by 6,691 · see citing works
Feurer, M., & Hutter, F. (2019) · The Springer Series on Challenges in Machine Learning · doi:10.1007/978-3-030-05318-5_1 · Cited by 1,414 · see citing works
Automatic Database Management System Tuning Through Large-scale Machine Learning
Aken, D. V., Pavlo, A., Gordon, G. J., & Zhang, B. (2017) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3035918.3064029 · Cited by 576 · see citing works
Ansel, J., Kamil, S. A., Veeramachaneni, K. K., Ragan‐Kelley, J., Bosboom, J., O’Reilly, U.-M., & Amarasinghe, S. P. (2014) · International Conference on Parallel Architectures and Compilation Techniques (PACT) · doi:10.1145/2628071.2628092 · Cited by 531 · see citing works
Difallah, D. E., Pavlo, A., Curino, C., & Cudré-Mauroux, P. (2013) · Proceedings of the VLDB Endowment · doi:10.14778/2732240.2732246 · Cited by 396 · see citing works
An End-to-End Automatic Cloud Database Tuning System Using Deep Reinforcement Learning
Zhang, J., Liu, Y., Zhou, K., Li, G., Xiao, Z., Cheng, B., Xing, J., Wang, Y., Cheng, T., Liu, L., et al. (2019) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3299869.3300085 · Cited by 331 · see citing works
Self-citationTuning database configuration parameters with iTuned
Duan, S., Thummala, V., & Babu, S. (2009) · Proceedings of the VLDB Endowment · doi:10.14778/1687627.1687767 · Cited by 268 · see citing works
Nargesian, F., Zhu, E., Miller, R. J., Pu, K. Q., & Arocena, P. C. (2019) · Proceedings of the VLDB Endowment · doi:10.14778/3352063.3352116 · Cited by 254 · see citing works
Zhu, Y., Liu, J., Guo, M., Bao, Y., Ma, W., Liu, Z., Song, K., & Yang, Y. (2017) · Symposium on Cloud Computing · doi:10.1145/3127479.3128605 · Cited by 251 · see citing works
Latin hypercube sampling as a tool in uncertainty analysis of computer models
McKay, M. D. (1992) · Winter Simulation Conference · doi:10.1145/167293.167637 · Cited by 245 · see citing works
Few-shot training LLMs for project-specific code-summarization
Ahmed, T., & Devanbu, P. (2022) · Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering · doi:10.1145/3551349.3559555 · Cited by 240 · see citing works
Incremental knowledge base construction using DeepDive
Shin, J., Wu, S., Wang, F., De, C., Zhang, C., & Ré, C. (2015) · Proceedings of the VLDB Endowment · doi:10.14778/2809974.2809991 · Cited by 236 · see citing works
Self-Driving Database Management Systems.
Pavlo, A., Angulo, G. B., Arulraj, J. J. P., Lin, H., Lin, J., Ma, L., Menon, P., Mowry, T. C., Perron, M., Quah, I., et al. (2017) · Conference on Innovative Data Systems Research · Cited by 204 · see citing works
ResTune: Resource Oriented Tuning Boosted by Meta-Learning for Cloud Databases
Zhang, X., Wu, H. L., Chang, Z., Jin, S., Tan, J. R., Li, F., Zhang, T., & Cui, B. (2021) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3448016.3457291 · Cited by 117 · see citing works
Aken, D. V., Yang, D., Brillard, S., Fiorino, A., Zhang, B., Bilien, C., & Pavlo, A. (2021) · Proceedings of the VLDB Endowment · doi:10.14778/3450980.3450992 · Cited by 100 · see citing works
Ask Me Anything: A simple strategy for prompting language modelsPreprint
Arora, S., Narayan, A., Chen, M. F., Orr, L., Guha, N., Bhatia, K., Chami, I., Sala, F., & Ré, C. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2210.02441 · Cited by 84 · see citing works
DB-BERT: A Database Tuning Tool that "Reads the Manual"
Trummer, I. (2022) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3514221.3517843 · Cited by 74 · see citing works
Black or White? How to Develop an AutoTuner for Memory-based Analytics
Kunjir, M., & Babu, S. (2020) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3318464.3380591 · Cited by 73 · see citing works
GPTuner: A Manual-Reading Database Tuning System via GPT-Guided Bayesian Optimization
Lao, J., Wang, Y., Li, Y., Wang, J., Zhang, Y., Cheng, Z., Chen, W., Tang, M., & Wang, J. (2024) · Proceedings of the VLDB Endowment · doi:10.14778/3659437.3659449 · Cited by 73 · see citing works
Self-citationReAcTable: Enhancing ReAct for Table Question Answering
Zhang, Y., Henkel, J., Floratou, A., Cahoon, J., Deep, S., & Patel, J. M. (2024) · Proceedings of the VLDB Endowment · doi:10.14778/3659437.3659452 · Cited by 70 · see citing works
Self-citationMaking Language Models Better Reasoners with Step-Aware Verifier
Li, Y., Lin, Z., Zhang, S., Fu, Q., Chen, B., Lou, J.-G., & Chen, W. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.291 · Cited by 69 · see citing works
Self-citationFacilitating database tuning with hyper-parameter optimization
Zhang, X., Chang, Z., Li, Y., Wu, H. L., Tan, J. R., Li, F., & Cui, B. (2022) · Proceedings of the VLDB Endowment · doi:10.14778/3538598.3538604 · Cited by 65 · see citing works
Self-citationTowards Dynamic and Safe Configuration Tuning for Cloud Databases
Zhang, X., Wu, H. L., Li, Y., Tan, J. R., Li, F., & Cui, B. (2022) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3514221.3526176 · Cited by 63 · see citing works
Self-citationCereda, S., Valladares, S., Cremonesi, P., & Doni, S. (2021) · Proceedings of the VLDB Endowment · doi:10.14778/3457390.3457404 · Cited by 58 · see citing works
Kanellis, K., Ding, C., Kroth, B., Müller, A., Curino, C., & Venkataraman, S. (2022) · Proceedings of the VLDB Endowment · doi:10.14778/3551793.3551844 · Cited by 58 · see citing works
Binding Language Models in Symbolic Languages
Cheng, Z., Xie, T., Shi, P., Li, C., Nadkarni, R., Hu, Y., Xiong, C., Radev, D., Ostendorf, M., Zettlemoyer, L., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.02875 · Cited by 53 · see citing works
Self-citationSkinnerDB: Regret-bounded Query Evaluation via Reinforcement Learning
Trummer, I., Wang, J., Wei, Z., Maram, D., Moseley, S., Jo, S., Antonakakis, J., & Rayabhari, A. (2021) · ACM Transactions on Database Systems · doi:10.1145/3464389 · Cited by 53 · see citing works
Self-citationChatGPT as a Factual Inconsistency Evaluator for Text Summarization
Luo, Z., Xie, Q., & Ananiadou, S. (2023) · arXiv · doi:10.48550/arxiv.2303.15621 · Cited by 53 · see citing works
HUNTER: An Online Cloud Database Hybrid Tuning System for Personalized Requirements
Cai, B., Liu, Y., Zhang, C., Zhang, G.-Y., Zhou, K., Liu, L., Li, C., Cheng, B., Yang, J., & Xing, J. (2022) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3514221.3517882 · Cited by 52 · see citing works
Using probabilistic reasoning to automate software tuning
Sullivan, D. G., Seltzer, M., & Pfeffer, A. (2004) · ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS) · doi:10.1145/1005686.1005739 · Cited by 48 · see citing works
Schema Matching using Pre-Trained Language Models
Zhang, Y., Floratou, A., Cahoon, J., Krishnan, S., Müller, A. C., Banda, D., Psallidas, F., & Patel, J. M. (2023) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde55515.2023.00123 · Cited by 39 · see citing works
Self-citationMake your database system dream of electric sheep
Pavlo, A., Butrovich, M., Ma, L., Menon, P., Lim, W. S., Aken, D. V., & Zhang, W. (2021) · Proceedings of the VLDB Endowment · doi:10.14778/3476311.3476411 · Cited by 32 · see citing works
Demonstrating GPT-DB: Generating Query-Specific and Customizable Code for SQL Processing with GPT-4
Trummer, I. (2023) · Proceedings of the VLDB Endowment · doi:10.14778/3611540.3611630 · Cited by 14 · see citing works
A Demonstration of GPTuner: A GPT-Based Manual-Reading Database Tuning System
Lao, J., Wang, Y., Li, Y., Wang, J., Zhang, Y., Cheng, Z., Chen, W., Zhou, Y., Tang, M., & Wang, J. (2024) · ACM SIGMOD International Conference on Management of Data (SIGMOD) · doi:10.1145/3626246.3654739 · Cited by 6 · see citing works
Self-citationFrom Large Language Models to Databases and Back: A discussion on research and educationPreprint
Amer-Yahia, S., Bonifati, A., Chen, L., Li, G., Shim, K., Xu, J., & Yang, X. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.01388 · Cited by 2 · see citing works
Flagged first, then by citations
Research works printed but not linked: 13
- Jason Ansel, Shoaib Kamil, Kalyan Veeramachaneni, Jonathan Ragan-Kelley, Jeffrey Bosboom, Una-May O'Reilly, and Saman Amarasinghe. Opentuner: An extensible framework for program autotuning. In Proceedings of the 23rd International Conference on Parallel Architectures and Compilation, PACT '14, page 303-316, New York, NY, USA, 2014. Association for Computing Machinery.
- Stefano Cereda, Stefano Valladares, Paolo Cremonesi, and Stefano Doni. Cgptuner: A contextual gaussian process bandit approach for the automatic tuning of it configurations under varying workload conditions. Proc. VLDB Endow., 14(8):1401-1413, apr 2021.
- Benoît Dageville and Mohamed Zait. Sql memory management in oracle9i. In Proceedings of the 28th International Conference on Very Large Data Bases, VLDB '02, page 962-973. VLDB Endowment, 2002.
- Xiang Deng, Prashant Shiralkar, Colin Lockard, Binxuan Huang, and Huan Sun. Dom-lm: Learning generalizable representations for html documents. arXiv preprint arXiv:2201.10608, 2022. · arXiv
- Djellel Eddine Difallah, Andrew Pavlo, Carlo Curino, and Philippe Cudré-Mauroux. Oltp-bench: An extensible testbed for benchmarking relational databases. PVLDB, 7(4):277-288, 2013.
- Konstantinos Kanellis, Ramnatthan Alagappan, and Shivaram Venkataraman. Too many knobs to tune? towards faster database tuning by pre-selecting important knobs. In Proceedings of the 12th USENIX Conference on Hot Topics in Storage and File Systems, HotStorage'20, USA, 2020. USENIX Association.
- Konstantinos Kanellis, Cong Ding, Brian Kroth, Andreas Müller, Carlo Curino, and Shivaram Venkataraman. Llamatune: Sample-efficient dbms configuration tuning. Proc. VLDB Endow., 15(11):2953-2965, jul 2022.
- Yifei Li, Zeqi Lin, Shizhuo Zhang, Qiang Fu, Bei Chen, Jian-Guang Lou, and Weizhu Chen. On the advance of making language models better reasoners. arXiv preprint arXiv:2206.02336, 2022. · arXiv
- Marius Lindauer, Katharina Eggensperger, Matthias Feurer, André Biedenkapp, Difan Deng, Carolin Benjamins, Tim Ruhkopf, René Sass, and Frank Hutter. Smac3: A versatile bayesian optimization package for hyperparameter optimization. Journal of Machine Learning Research, 23(54):1-9, 2022.
- Marius Lindauer, Katharina Eggensperger, Matthias Feurer, André Biedenkapp, Difan Deng, Carolin Benjamins, Tim Ruhkopf, René Sass, and Frank Hutter. Smac3: A versatile bayesian optimization package for hyperparameter optimization. Journal of Machine Learning Research, 23(54):1-9, 2022.
- OpenAI. Gpt-4 technical report. arXiv preprint arXiv:2303.08774, 2023. · arXiv
- Immanuel Trummer. Can deep neural networks predict data correlations from column names? arXiv preprint arXiv:2107.04553, 2021. · arXiv
- Yuqing Zhu, Jianxun Liu, Mengying Guo, Yungang Bao, Wenlong Ma, Zhuoyue Liu, Kunpeng Song, and Yingchun Yang. Bestconfig: Tapping the performance potential of systems via automatic configuration tuning. In Proceedings of the 2017 Symposium on Cloud Computing, SoCC '17, page 338-350, New York, NY, USA, 2017. Association for Computing Machinery.
Cited by
Sorted by citations
AI for science: Progress, challenges, and perspectives
Xu, Y., Shao, Z., Liu, X., Li, Y., An, Z., Fu, C., Huang, C., Zhang, L., Gao, F., Li, J., et al. (2026) · The Innovation · doi:10.1016/j.xinn.2026.101530 · Cited by 3 · see citing works
Self-citationResilient LLM-DBMS Pipelines via Event-Driven Fallback Orchestration
Shahab, E., & Taghipour, S. (2025) · IEEE International Conference on Collaborative Advances in Software and Computing (CASCON) · doi:10.1109/cascon66301.2025.00113 · Cited by 1 · see citing works
HAMMER: An Automatic RAG Tuning System via Hierarchical Memory-Guided Monte Carlo Tree Search
Zhou, Y. K., Wang, Z., & Fang, Y. (2026) · Proceedings of the ACM on Management of Data · doi:10.1145/3802071 · Cited by 1 · see citing works
Large Language Models in Database Management System Optimization: A Survey
Bagui, S. S., Malagutti, M., Morelli, R., & Tamascelli, M. (2026) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3829078 · Cited by 1 · see citing works
Pan, Z., Sun, W., Zhang, Y., Purcell, T., Dong, Y., Yang, C., Zhang, R., Zhou, X., & Xu, J. (2026) · Proceedings of the VLDB Endowment · doi:10.14778/3801059.3801077 · Cited by 1 · see citing works
Self-citationHybrid Evolutionary Bayesian Optimization for Cloud Database Knob Tuning
Deepak, D., & Sheoran, S. K. (2025) · International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO) · doi:10.1109/icrito66076.2025.11241285
KnobTuneX:LLM-Enhanced Automatic Database Tuning via Structured Reasoning*
Yang, J., Zhang, Q., Xu, X., Wu, Y., Zhang, S., & Ding, Z. (2025) · Proceedings · doi:10.1109/icdm65498.2025.00092
Relation-Aware Bayesian Optimization of DBMS Configurations Guided by Affinity ScoresPreprint
Kwon, S., Baek, S., Yang, H., & Park, S. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6365598
MFTune: An Efficient Multi-Fidelity Framework for Spark SQL Configuration Tuning
Xu, B., Tung, L., Wang, Y., Lu, Y., & Cui, B. (2026) · Proceedings of the VLDB Endowment · doi:10.14778/3836663.3836715
Self-citationLakeHelm: Zero-Shot Lakehouse Advisor for Joint Engine-Format Selection and Configuration
Xu, Z., Dong, S., Gong, H., Pham, D., & Ma, L. (2026) · Proceedings of the VLDB Endowment · doi:10.14778/3811243.3811250
TellyTune: Exploring the Limits of LLM-Assisted Tuning for LSM-Based Key-Value Stores
Thakkar, V., Lin, Q., Prasetyo, K. K. A., Wisjnunandono, R. H., Wang, J., Kistijantoro, A. I., Rachmadi, R. F., & Cao, Z. (2026) · ACM International Systems and Storage Conference (SYSTOR) · doi:10.1145/3793230.3839381
Self-citationAutoLiquid: Autonomic Data Layout Optimization for the Databricks Lakehouse
Nakandala, S., Bhanoori, N. R., Zhang, Y., Negi, P., Sharma, A., Liang, E., Jiang, C., Sun, S., Kim, T., Mokhtar, M., et al. (2026) · Proceedings of the VLDB Endowment · doi:10.14778/3827998.3828013
Self-citationFunPilot: Runtime Performance Diagnosis and Remediation for Serverless Applications with LLMs
Lin, C., Wang, Y., & Shahrad, M. (2026) · ACM SIGOPS Asia-Pacific Workshop on Systems (APSys) · doi:10.1145/3838177.3841720
Self-citationTuxBot: Semantic-Aware Online OS Tuning with LLMs
Liargkovas, G., Joshi, M. N., Franke, H., & Kaffes, K. (2026) · ACM SIGOPS Symposium on Operating Systems Principles (SOSP) · doi:10.1145/3830418.3843885
Can LLMs Replace the DBA? Evaluating Ontology-Driven Prompting for Relational Database Tuning Tasks
Leão, E. R., Lifschitz, S., ALMEIDA, A. L. N. D., & Hæusler, E. H. (2026) · Simpósio Brasileiro de Bancos de Dados (SBBD) · doi:10.5753/sbbd.2026.249216
OuterTuning: how are database tuning suggestions in LLMs?
Massena, L. F., & ALMEIDA, A. L. N. D. (2026) · Simpósio Brasileiro de Bancos de Dados (SBBD) · doi:10.5753/sbbd_estendido.2026.249615
Osman, A., Baydan, B., & Yurttakal, A. H. (2026) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.71009
- Authors
- Lao, J., Wang, Y., Li, Y., Wang, J., Zhang, Y., Cheng, Z., Chen, W., Tang, M., & Wang, J.
- Affiliations
- Sichuan University (CN)
- Purdue University West Lafayette (US)
- University of Wisconsin–Madison (US)
- Northwest Normal University (CN)
- ORCID
- Venue
- ACM SIGMOD Record
- Published
- 2025-04-28
- Volume
- 54
- Issue
- 1
- Pages
- 101-110
- ISSN
- 0163-5808 (ISSN-L)
- OpenAlex
- W4409920225
- Cited by
- 17
- References
- 34
- Citations by year
- 2026: 14 · 2025: 3
- FWCI
- 7.19
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- ACM SIGMOD Record (publishedVersion)
- Funders
- National Natural Science Foundation of China (92470204)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Advanced Database Systems and Queries
- Physical Sciences › Computer Science › Computer Networks and Communications › Software System Performance and Reliability
- Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- Keywords
- database performance tuning, large language models, prompt engineering, domain knowledge integration, search space optimization, Bayesian optimization, PostgreSQL, MySQL
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
