Title :

UDO: Universal Database Optimization using Reinforcement Learning

Author(s) :

Wang, Junxiong [Auteur]
Cornell University [New York]
Trummer, Immanuel [Auteur]
Cornell University [New York]
Basu, Debabrota [Auteur]
Scool [Scool]

Conference title :

Proceedings of the VLDB Endowment

City :

Sydney

Country :

Australie

Start date of the conference :

2022-09

Journal title :

Proceedings of the VLDB Endowment (PVLDB)
Proceedings of the VLDB Endowment

Publisher :

VLDB Endowment

Publication date :

2021-09

English keyword(s) :

Reinforcement learning RL
Monte carlo tree search
Database management system
Query optimization

HAL domain(s) :

Informatique [cs]/Base de données [cs.DB]
Informatique [cs]/Apprentissage [cs.LG]
Informatique [cs]/Intelligence artificielle [cs.AI]

English abstract : [en]

UDO is a versatile tool for offline tuning of database systems for specific workloads. UDO can consider a variety of tuning choices, reaching from picking transaction code variants over index selections up to database ...
Show more >UDO is a versatile tool for offline tuning of database systems for specific workloads. UDO can consider a variety of tuning choices, reaching from picking transaction code variants over index selections up to database system parameter tuning. UDO uses reinforcement learning to converge to near-optimal configurations, creating and evaluating different configurations via actual query executions (instead of relying on simplifying cost models). To cater to different parameter types, UDO distinguishes heavy parameters (which are expensive to change, e.g. physical design parameters) from light parameters. Specifically for optimizing heavy parameters, UDO uses reinforcement learning algorithms that allow delaying the point at which the reward feedback becomes available. This gives us the freedom to optimize the point in time and the order in which different configurations are created and evaluated (by benchmarking a workload sample). UDO uses a cost-based planner to minimize reconfiguration overheads. For instance, it aims to amortize the creation of expensive data structures by consecutively evaluating configurations using them. We evaluate UDO on Postgres as well as MySQL and on TPC-H as well as TPC-C, optimizing a variety of light and heavy parameters concurrently.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL