Learned Query Optimizers: Evaluation and Improvement

Artem Mikhaylov, Nina Mazyavkina, Mikhail Salnikov, Ilya Trofimov, Fu Qiang, Evgeny BurnaevIEEE Access 2022 · DOI · OpenReview

Abstract

Query Optimization is considered to be one of the most important challenges in database management. Existing built-in query optimizers are very complex and rely on various approximations and hand-picked rules. The rise of deep learning and deep reinforcement learning has aided many scientific and industrial fields, providing an opportunity to develop a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">learnable query optimizer</i> . In this paper, we analyse and improve the state-of-the-art learned query optimizer, Neo for the JOB benchmark on two database systems: PostgreSQL and Huawei GaussDB. We describe our methods, based on combination of Neo, Tree-Transformers, auxiliary tasks, reward weighting. Combinations of these methods improve latency of the found query execution plans. We also conduct a thorough analysis of the resulting execution plans and devise a set of decision-based rules to indicate the cases when the learned optimizer will outperform the built-in one. We also provide a source code for the proposed methods and experiments. Finally, we provide possible directions for further improvement in this field.
BibTeX
@article{mikhaylov2022learned,
  author = {Artem Mikhaylov and Nina Mazyavkina and Mikhail Salnikov and Ilya Trofimov and Fu Qiang and Evgeny Burnaev},
  title = {{Learned Query Optimizers: Evaluation and Improvement}},
  journal = {IEEE Access},
  year = {2022},
  doi = {10.1109/access.2022.3190376},
}

Loading related content...

Figure