research-article

DRLindex: deep reinforcement learning index advisor for a cluster database

Authors:

Eleazar LeadAuthors Info & Claims

IDEAS '20: Proceedings of the 24th Symposium on International Database Engineering & Applications

Article No.: 11, Pages 1 - 8

https://doi.org/10.1145/3410566.3410603

Published: 25 August 2020 Publication History

Abstract

Cloud database providers provision different architectures to guarantee high availability. One of these architectures is a cluster database that consists of several database engine nodes, where data is replicated among the nodes. Although the cloud database providers provide various auto-indexing tools, these tools mostly address characteristics of a database deployed on a single node, not a cluster. It is possible to install an index advisor on each node, which recommends an index set for that node. The problem with this approach is that the current index advisors for a single node aim to minimize the processing cost of the workload; however, on a cluster database, other goals such as load balancing can be considered. Hence, the better solution could be an index advisor which has a comprehensive view of the cluster node.

In this paper, we propose an index advisor for a replicated database on a database cluster for a read-only workload. The advisor considers both query processing cost and load balancing. It utilizes a Deep Reinforcement Learning (DRL) approach in which a DRL agent learns to select a set of index configurations for nodes in a cluster. We describe the components of the DRL-advisor such as the agent, the environment, a set of actions, the reward function, and other modules. Experimental results validate the effectiveness of the algorithm.

References

[1]

Sanjay Agrawal, Surajit Chaudhuri, Lubor Kollár, Arunprasad P. Marathe, Vivek R. Narasayya, and Manoj Syamala. 2004. Database Tuning Advisor for Microsoft SQL Server 2005. In VLDB. 1110--1121.

[2]

Debabrota Basu, Qian Lin, Weidong Chen, Hoang Tam Vo, Zihong Yuan, Pierre Senellart, and Stéphane Bressan. 2015. Cost-model oblivious database tuning with reinforcement learning. In Database and Expert Systems Applications. Springer. 253--268.

[3]

Nicolas Bruno and Surajit Chaudhuri. 2007. An Online Approach to Physical Design Tuning. In Proceedings of the IEEE 23rd International Conference on Data Engineering (ICDE), 826--835.

[4]

Surajit Chaudhuri and Vivek R. Narasayya. 1997. An efficient, cost-driven index selection tool for Microsoft SQL server. In VLDB. 146--155.

[5]

Surajit Chaudhuri and Vivek R. Narasayya. AutoAdmin. 1998. 'What-if' Index Analysis Utility. In Proceedings of the 1998 ACM SIGMOD International Conference on Management of Data. 367--378.

[6]

Mariano P. Consens, Kleoni Ioannidou, Jeff LeFevre, and Neoklis Polyzotis. 2012. Divergent physical design tuning for replicated databases. In Proceedings of the 2012 ACM SIGMOD International Conference on Management of Data. 49--60.

Digital Library

[7]

Debabrata Dash, Neoklis Polyzotis, and Anastasia Ailamaki. 2011. CoPhy: A Scalable, Portable, and Interactive Index Advisor for Large Workloads. PVLDB 4, 6 (2011), 362--372.

Digital Library

[8]

Bailu Ding, Sudipto Das, Ryan Marcus, Wentao Wu, Surajit Chaudhuri, and Vivek R Narasayya. 2019. Ai meets ai: Leveraging query executions to improve index recommendations. In Proceedings of the 2019 ACM SIGMOD International Conference on Management of Data. 1241--1258.

Digital Library

[9]

Viktor Leis, Andrey Gubichev, Atanas Mirchev, Peter Boncz, Alfons Kemper, and Thomas Neumann. 2015. How Good Are Query Optimizers, Really? PVLDB 9, 3 (Nov. 2015), 204--215.

Digital Library

[10]

Gabriel Paludo Licks, Julia Colleoni Couto, Priscilla de Fátima Miehe, Renata De Paris, Duncan Dubugras Ruiz, and Felipe Meneguzzi. 2020. SMARTIX: A database indexing agent based on reinforcement learning. Applied Intelligence, 1--14.

[11]

Lin Ma, Dana Van Aken, Ahmed Hefny, Gustavo Mezerhane, Andrew Pavlo, and Geoffrey J. Gordon. 2018. Query-Based Workload Forecasting for Self-Driving Database Management Systems. In Proceedings of the 2018 ACM SIGMOD International Conference on Management of Data. 631--645.

Digital Library

[12]

Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves et al. 2015. Human-level control through deep reinforcement learning. Nature, vol. 7540. 529--533.

[13]

Ryan Marcus, and Papaemmanouil Olga. 2018. Deep reinforcement learning for join order enumeration. In Proceedings of the First International Workshop on Exploiting Artificial Intelligence Techniques for Data Management. 1--4.

Digital Library

[14]

Tim Kraska, Alex Beutel, Ed H. Chi, Jeffrey Dean, and Neoklis Polyzotis. 2018. The case for learned index structures. In Proceedings of the 2018 ACM SIGMOD International Conference on Management of Data. 489--504.

Digital Library

[15]

Ankur Sharma, Felix Martin Schuhknecht, and Jens Dittrich. 2018. The case for automatic database administration using deep reinforcement learning .arXiv preprint arXiv:1801.05643.

[16]

Karl Schnaitter, Serge Abiteboul, Tova Milo, and Neoklis Polyzotis. On-line index selection for shifting workloads. In IEEE 23rd International Conference on Data Engineering Workshop. 459--468.

[17]

Richard S. Sutton, and Andrew G. Barto. 2018. Reinforcement learning: An introduction. MIT press.

[18]

Quoc Trung Tran, Ivo Jimenez, Rui Wang, Neoklis Polyzotis and Anastasia Ailamaki. 2015. RITA: An Index-Tuning Advisor for Replicated Databases. In Proceedings the 27th International Conference on Scientific and Statistical Database Management, ACM, 1--12.

Digital Library

[19]

Transaction Performance Council. TPC-H Benchmark.

[20]

CloudLab. https://www.cloudlab.us/.

[21]

POWA: PostgreSQL Workload Analyzer (2019). URL http://powa.readthedocs.io

Cited By

Wang ZLiu HLin CBao ZLi GWang T(2024)Leveraging Dynamic and Heterogeneous Workload Knowledge to Boost the Performance of Index AdvisorsProceedings of the VLDB Endowment10.14778/3654621.365463117:7(1642-1654)Online publication date: 1-Mar-2024
https://dl.acm.org/doi/10.14778/3654621.3654631
Wang TYoneki E(2024)IA2Proceedings of the 4th Workshop on Machine Learning and Systems10.1145/3642970.3655839(10-17)Online publication date: 22-Apr-2024
https://dl.acm.org/doi/10.1145/3642970.3655839
Zheng YLin CLyu XZhou XLi GWang T(2024)Robustness of Updatable Learning-based Index Advisors against Poisoning AttackProceedings of the ACM on Management of Data10.1145/36392652:1(1-26)Online publication date: 26-Mar-2024
https://dl.acm.org/doi/10.1145/3639265
Show More Cited By

Index Terms

DRLindex: deep reinforcement learning index advisor for a cluster database
1. Information systems
  1. Data management systems
    1. Database administration
      1. Autonomous database administration

Recommendations

An Index Advisor Using Deep Reinforcement Learning
CIKM '20: Proceedings of the 29th ACM International Conference on Information & Knowledge Management

We study the problem of index selection to maximize the workload performance, which is critical to database systems. In contrast to existing methods, we seamlessly integrate index recommendation rules and deep reinforcement learning, such that we can ...
Budget-aware Index Tuning with Reinforcement Learning
SIGMOD '22: Proceedings of the 2022 International Conference on Management of Data

Index tuning aims to find the optimal index configuration for an input workload. It is a resource-intensive task since it requires making multiple expensive "what-if" calls to the query optimizer to estimate the cost of a query given an index ...
Dynamic allocation in a self-scaling cluster database
Selection of Best Papers of the VLDB Data Management in Grids Workshop (VLDB DMG 2007)

Database systems have been vital for all forms of data processing for a long time. In recent years, the amount of processed data has been growing dramatically, even in small projects. Nevertheless, database management systems tend to be static in terms ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

IDEAS '20: Proceedings of the 24th Symposium on International Database Engineering & Applications

August 2020

252 pages

ISBN:9781450375030

DOI:10.1145/3410566

General Chairs:
Bipin C. Desai
Concordia University, Canada
,
Wan-Sup Cho
Chungbuk National University, Korea

Copyright © 2020 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 25 August 2020

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

IDEAS 2020

IDEAS 2020: 24th International Database Engineering & Applications Symposium

August 12 - 14, 2020

Seoul, Republic of Korea

Acceptance Rates

IDEAS '20 Paper Acceptance Rate 27 of 57 submissions, 47%;

Overall Acceptance Rate 74 of 210 submissions, 35%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

19
Total Citations
View Citations
337
Total Downloads

Downloads (Last 12 months)68
Downloads (Last 6 weeks)9

Reflects downloads up to 27 Jul 2024

Other Metrics

View Author Metrics

Citations

Cited By

Wang ZLiu HLin CBao ZLi GWang T(2024)Leveraging Dynamic and Heterogeneous Workload Knowledge to Boost the Performance of Index AdvisorsProceedings of the VLDB Endowment10.14778/3654621.365463117:7(1642-1654)Online publication date: 1-Mar-2024
https://dl.acm.org/doi/10.14778/3654621.3654631
Wang TYoneki E(2024)IA2Proceedings of the 4th Workshop on Machine Learning and Systems10.1145/3642970.3655839(10-17)Online publication date: 22-Apr-2024
https://dl.acm.org/doi/10.1145/3642970.3655839
Zheng YLin CLyu XZhou XLi GWang T(2024)Robustness of Updatable Learning-based Index Advisors against Poisoning AttackProceedings of the ACM on Management of Data10.1145/36392652:1(1-26)Online publication date: 26-Mar-2024
https://dl.acm.org/doi/10.1145/3639265
Zhou WLin CZhou XLi GWang T(2024)TRAP: Tailored Robustness Assessment for Index Advisors via Adversarial Perturbation2024 IEEE 40th International Conference on Data Engineering (ICDE)10.1109/ICDE60146.2024.00011(42-55)Online publication date: 13-May-2024
https://doi.org/10.1109/ICDE60146.2024.00011
Qi ZZhang HWang HChao Z(2024)ANSWER: Automatic Index Selector for Knowledge GraphsWeb and Big Data10.1007/978-981-97-2390-4_27(393-407)Online publication date: 28-Apr-2024
https://doi.org/10.1007/978-981-97-2390-4_27
Yu WYou JNiu XHe JZhang Y(2023)RBOIRA: Integrating Rules and Reinforcement Learning to Improve Index RecommendationICST Transactions on Scalable Information Systems10.4108/eetsis.3822Online publication date: 18-Sep-2023
https://doi.org/10.4108/eetsis.3822
Turkmen ACan O(2023)An Improved Data Management Approach for IoT-Enabled Smart Healthcare: Integrating Semantic Web and Reinforcement Learning2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC)10.1109/COMPSAC57700.2023.00226(1471-1475)Online publication date: Jun-2023
https://doi.org/10.1109/COMPSAC57700.2023.00226
Khosravi MKaragoz PToroslu I(2023)IndexAI: AI Based Index Selection for NoSQL Databases2023 IEEE International Conference on Big Data (BigData)10.1109/BigData59044.2023.10386521(5818-5825)Online publication date: 15-Dec-2023
https://doi.org/10.1109/BigData59044.2023.10386521
Huang SQin YZhang XTu YLi ZCui B(2023)Survey on performance optimization for database systemsScience China Information Sciences10.1007/s11432-021-3578-666:2Online publication date: 11-Jan-2023
https://doi.org/10.1007/s11432-021-3578-6
Hang HSun J(2023)Enhancing Online Index Tuning with a Learned Tuning DiagnosticDatabase and Expert Systems Applications10.1007/978-3-031-39847-6_14(197-212)Online publication date: 18-Aug-2023
https://doi.org/10.1007/978-3-031-39847-6_14
Show More Cited By

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents