VDTuner: Automated Performance Tuning for Vector Data Management Systems
Authors:
- 13 May 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4357-4369
Abstract
Vector data management systems (VDMSs) have become an indispensable cornerstone in large-scale information retrieval and machine learning systems like large language models. To enhance the efficiency and flexibility of similarity search, VDMS exposes many tunable index parameters and system parameters for users to specify. However, due to the inherent characteristics of VDMS, automatic performance tuning for VDMS faces several critical challenges, which cannot be well addressed by the existing auto-tuning methods. In this paper, we introduce VDTuner, a learning-based automatic performance tuning framework for VDMS, leveraging multi-objective Bayesian optimization. VDTuner overcomes the challenges associated with VDMS by efficiently exploring a complex multi-dimensional parameter space without requiring any prior knowledge. Moreover, it is able to achieve a good balance between search speed and recall rate, delivering an optimal configuration. Extensive evaluations demonstrate that VDTuner can markedly improve VDMS performance (14.12% in search speed and 186.38 % in recall rate) compared with default setting, and is more efficient compared with state-of-the-art baselines (up to 3.57 x faster in terms of tuning time). In addition, VDTuner is scalable to specific user preference and cost-aware optimization objective. VDTuner is available online at https://github.com/tiannuo-yanWVDTuner.Keywords
All Related Versions
Funding Information
- National Science Foundation (62293510/62293513,62272252,62272253,62141412)
This publication has 30 references indexed in Scilit:
- Automatic Database Knob Tuning: A SurveyIEEE Transactions on Knowledge and Data Engineering, 2023
- Bayesian Optimization2023
- Adaptive Code Learning for Spark Configuration Tuning2022
- Automatic Performance Tuning for Distributed Data Stream Processing Systems2022
- WATuning: A Workload-Aware Tuning System with Attention-Based Deep Reinforcement LearningJournal of Computer Science and Technology, 2021
- Billion-Scale Similarity Search with GPUsIEEE Transactions on Big Data, 2019
- Approximate Nearest Neighbor Search on High Dimensional Data — Experiments, Analyses, and ImprovementIEEE Transactions on Knowledge and Data Engineering, 2019
- Multi-Objective Bayesian Global Optimization using expected hypervolume improvement gradientSwarm and Evolutionary Computation, 2019
- Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World GraphsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Taking the Human Out of the Loop: A Review of Bayesian OptimizationProceedings of the IEEE, 2015