Leveraging query logs and machine learning for parametric query optimization

Kapil Vaidya, Anshuman Dutt, Vivek R. Narasayya, Surajit Chaudhuri

Proceedings of the VLDB Endowment 2021 article cited by 20

importance 4/10 solved Advanced Database Systems and Queries database systems stage: research

Parametric query optimization must cache a small set of plans for parameterized queries and then quickly pick the best cached plan per query instance.

Database query performance directly affects application speed and infrastructure cost at scale.

Machine learning models trained on query logs select the lowest optimizer-estimated-cost cached plan for each query instance, alongside an efficient plan-caching algorithm.

populateCache achieves geometric mean sub-optimality of 1.2 on complex queries with few plans and scales to large query logs.

Extensive experiments on benchmark and real workloads demonstrate low sub-optimality and scalable plan selection.

Venue Proceedings of the VLDB Endowment
Published 2021
Work type article
Authors Kapil Vaidya, Anshuman Dutt, Vivek R. Narasayya, Surajit Chaudhuri
Citations 20 (OpenAlex, at import time)
References 21
Model or method not stated in source
Organization not stated in source
Primary source https://doi.org/10.14778/3494124.3494126
Open access closed
Keywords parametric query optimization, machine learning, query logs, database systems, plan caching
4 / 10

real but narrower advance

Faster parametric query optimization improves database speed and cost, a real but narrow technical advance; abstract reports only benchmark results.

Basis: inferred. Judged from the source text, which gives no explicit scale. Stated scale: not stated in source. Method and limits.

# Paper Year Citations Importance
1 ImageNet classification with deep convolutional neural networks
Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton
2017 106,345
8
2 Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
2016 221,134
8
3 Faster sorting algorithms discovered using deep reinforcement learning
Daniel J. Mankowitz, Andrea Michi, Anton Zhernov, Marco Gelmi, Marco S...
2023 175
8
4 A deep learning‐based approach for software vulnerability detection using code metrics
Fazli Subhan, Xiaoxue Wu, Lili Bo, Xiaobing Sun, Muhammad Rahman
2022 42
7
5 Deep Learning-Based Attack Detection and Classification in Android Devices
Alfonso Gómez, Antonio Muñoz
2023 41
7