Hilprecht, Benjamin ; Binnig, Carsten ; Röhm, Uwe (2020)
Learning a Partitioning Advisor for Cloud Databases.
2020 ACM SIGMOD International Conference on Management of Data. virtual Conference (14.06.2020-19.06.2020)
doi: 10.1145/3318464.3389704
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Cloud vendors provide ready-to-use distributed DBMS solutions as a service. While the provisioning of a DBMS is usually fully automated, customers typically still have to make important design decisions which were traditionally made by the database administrator such as finding an optimal partitioning scheme for a given database schema and workload. In this paper, we introduce a new learned partitioning advisor based on Deep Reinforcement Learning (DRL) for OLAP-style workloads. The main idea is that a DRL agent learns the cost tradeoffs of different partitioning schemes and can thus automate the partitioning decision. In the evaluation, we show that our advisor is able to find non-trivial partitionings for a wide range of workloads and outperforms more classical approaches for automated partitioning design.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2020 |
| Autor(en): | Hilprecht, Benjamin ; Binnig, Carsten ; Röhm, Uwe |
| Art des Eintrags: | Bibliographie |
| Titel: | Learning a Partitioning Advisor for Cloud Databases |
| Sprache: | Englisch |
| Publikationsjahr: | 14 Juni 2020 |
| Verlag: | ACM |
| Buchtitel: | SIGMOD '20: Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data |
| Veranstaltungstitel: | 2020 ACM SIGMOD International Conference on Management of Data |
| Veranstaltungsort: | virtual Conference |
| Veranstaltungsdatum: | 14.06.2020-19.06.2020 |
| DOI: | 10.1145/3318464.3389704 |
| Kurzbeschreibung (Abstract): | Cloud vendors provide ready-to-use distributed DBMS solutions as a service. While the provisioning of a DBMS is usually fully automated, customers typically still have to make important design decisions which were traditionally made by the database administrator such as finding an optimal partitioning scheme for a given database schema and workload. In this paper, we introduce a new learned partitioning advisor based on Deep Reinforcement Learning (DRL) for OLAP-style workloads. The main idea is that a DRL agent learns the cost tradeoffs of different partitioning schemes and can thus automate the partitioning decision. In the evaluation, we show that our advisor is able to find non-trivial partitionings for a wide range of workloads and outperforms more classical approaches for automated partitioning design. |
| Freie Schlagworte: | machine learning, database management systems, database tuning |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Data Management (2022 umbenannt in Data and AI Systems) DFG-Sonderforschungsbereiche (inkl. Transregio) DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche > SFB 1053: MAKI – Multi-Mechanismen-Adaption für das künftige Internet DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche > SFB 1053: MAKI – Multi-Mechanismen-Adaption für das künftige Internet > C: Kommunikationsmechanismen DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche > SFB 1053: MAKI – Multi-Mechanismen-Adaption für das künftige Internet > C: Kommunikationsmechanismen > Teilprojekt C2: Informationszentrische Sicht |
| Hinterlegungsdatum: | 21 Apr 2022 09:18 |
| Letzte Änderung: | 21 Apr 2022 09:18 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum