Bao
Ryan Marcus, Parimarjan Negi, Hongzi Mao et al. · ACM SIGMOD Record · 2022
Recent efforts applying machine learning techniques to query optimization have shown few practical gains due to substantive training overhead, inability to adapt to changes, and poor tail performance. Motivated by these difficulties, we introduce Bao (the Bandit optimizer). Bao takes advantage of the wisdom built into existing query optimizers by providing per-query optimization hints. Bao combines modern tree convolutional neural networks with Thompson sampling, a well-studied reinforcement learning algorithm. As a result, Bao automatically learns from its mistakes and adapts to changes in query workloads, data, and schema. Experimentally, we demonstrate that Bao can quickly learn strategies that improve end-to-end query execution performance, including tail latency, for several workloads containing longrunning queries. In cloud environments, we show that Bao can offer both reduced costs and better performance compared with a commercial system.
Cited by 52 works. doi:10.1145/3542700.3542703
Authors
References
- ON THE LIKELIHOOD THAT ONE UNKNOWN PROBABILITY EXCEEDS ANOTHER IN VIEW OF THE EVIDENCE OF TWO SAMPLES
- The Case for Learned Index Structures
- How good are query optimizers, really?
- Access path selection in a relational database management system
- Proceedings of the 19th International Conference on Extending Database Technology, EDBT
- An end-to-end learning-based cost estimator
- Bao: Making Learned Query Optimization Practical
- Deep unsupervised cardinality estimation
- On predictive modeling for optimizing transaction execution in parallel OLTP systems
- AI Meets AI