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.

由于大量的训练开销、无法适应变化和尾部性能差，最近将机器学习技术应用于查询优化的努力几乎没有显示出实际收益。受这些困难的启发，我们介绍了 Bao（Bandit 优化器）。Bao 通过提供每个查询的优化提示来利用现有查询优化器中内置的智慧。Bao 将现代树卷积神经网络与 Thompson 采样相结合，这是一种经过充分研究的强化学习算法。因此，Bao 会自动从错误中学习并适应查询工作负载、数据和模式的变化。通过实验，我们证明 Bao 可以快速学习提高端到端查询执行性能的策略，包括尾延迟，用于包含长时间运行查询的多个工作负载。在云环境中，