Choosing a cloud DBMS: architectures and tradeoffs
© 2019 VLDB Endowment. As analytic (OLAP) applications move to the cloud, DBMSs have shifted from employing a pure shared-nothing design with locally attached storage to a hybrid design that combines the use of shared-storage (e.g., AWS S3) with the use of shared-nothing query execution mechanisms....
| Hoofdauteurs: | , , , , , , , , |
|---|---|
| Formaat: | Artikel |
| Taal: | English |
| Gepubliceerd in: |
VLDB Endowment
2021
|
| Online toegang: | https://hdl.handle.net/1721.1/132276 |
| _version_ | 1826195407017869312 |
|---|---|
| author | Tan, Junjay Ghanem, Thanaa Perron, Matthew Yu, Xiangyao Stonebraker, Michael DeWitt, David Serafini, Marco Aboulnaga, Ashraf Kraska, Tim |
| author_facet | Tan, Junjay Ghanem, Thanaa Perron, Matthew Yu, Xiangyao Stonebraker, Michael DeWitt, David Serafini, Marco Aboulnaga, Ashraf Kraska, Tim |
| author_sort | Tan, Junjay |
| collection | MIT |
| description | © 2019 VLDB Endowment. As analytic (OLAP) applications move to the cloud, DBMSs have shifted from employing a pure shared-nothing design with locally attached storage to a hybrid design that combines the use of shared-storage (e.g., AWS S3) with the use of shared-nothing query execution mechanisms. This paper sheds light on the resulting tradeoffs, which have not been properly identified in previous work. To this end, it evaluates the TPC-H benchmark across a variety of DBMS offerings running in a cloud environment (AWS) on fast 10Gb+ networks, specifically database-as-a-service offerings (Redshift, Athena), query engines (Presto, Hive), and a traditional cloud agnostic OLAP database (Vertica). While these comparisons cannot be apples-to-apples in all cases due to cloud configuration restrictions, we nonetheless identify patterns and design choices that are advantageous. These include prioritizing low-cost object stores like S3 for data storage, using system agnostic yet still performant columnar formats like ORC that allow easy switching to other systems for different workloads, and making features that benefit subsequent runs like query precompilation and caching remote data to faster storage optional rather than required because they disadvantage ad hoc queries. |
| first_indexed | 2024-09-23T10:12:10Z |
| format | Article |
| id | mit-1721.1/132276 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T10:12:10Z |
| publishDate | 2021 |
| publisher | VLDB Endowment |
| record_format | dspace |
| spelling | mit-1721.1/1322762021-09-21T03:51:53Z Choosing a cloud DBMS: architectures and tradeoffs Tan, Junjay Ghanem, Thanaa Perron, Matthew Yu, Xiangyao Stonebraker, Michael DeWitt, David Serafini, Marco Aboulnaga, Ashraf Kraska, Tim © 2019 VLDB Endowment. As analytic (OLAP) applications move to the cloud, DBMSs have shifted from employing a pure shared-nothing design with locally attached storage to a hybrid design that combines the use of shared-storage (e.g., AWS S3) with the use of shared-nothing query execution mechanisms. This paper sheds light on the resulting tradeoffs, which have not been properly identified in previous work. To this end, it evaluates the TPC-H benchmark across a variety of DBMS offerings running in a cloud environment (AWS) on fast 10Gb+ networks, specifically database-as-a-service offerings (Redshift, Athena), query engines (Presto, Hive), and a traditional cloud agnostic OLAP database (Vertica). While these comparisons cannot be apples-to-apples in all cases due to cloud configuration restrictions, we nonetheless identify patterns and design choices that are advantageous. These include prioritizing low-cost object stores like S3 for data storage, using system agnostic yet still performant columnar formats like ORC that allow easy switching to other systems for different workloads, and making features that benefit subsequent runs like query precompilation and caching remote data to faster storage optional rather than required because they disadvantage ad hoc queries. 2021-09-20T18:21:37Z 2021-09-20T18:21:37Z 2021-01-11T15:10:36Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/132276 en 10.14778/3352063.3352133 Proceedings of the VLDB Endowment Creative Commons Attribution-NonCommercial-NoDerivs License http://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf VLDB Endowment VLDB Endowment |
| spellingShingle | Tan, Junjay Ghanem, Thanaa Perron, Matthew Yu, Xiangyao Stonebraker, Michael DeWitt, David Serafini, Marco Aboulnaga, Ashraf Kraska, Tim Choosing a cloud DBMS: architectures and tradeoffs |
| title | Choosing a cloud DBMS: architectures and tradeoffs |
| title_full | Choosing a cloud DBMS: architectures and tradeoffs |
| title_fullStr | Choosing a cloud DBMS: architectures and tradeoffs |
| title_full_unstemmed | Choosing a cloud DBMS: architectures and tradeoffs |
| title_short | Choosing a cloud DBMS: architectures and tradeoffs |
| title_sort | choosing a cloud dbms architectures and tradeoffs |
| url | https://hdl.handle.net/1721.1/132276 |
| work_keys_str_mv | AT tanjunjay choosingaclouddbmsarchitecturesandtradeoffs AT ghanemthanaa choosingaclouddbmsarchitecturesandtradeoffs AT perronmatthew choosingaclouddbmsarchitecturesandtradeoffs AT yuxiangyao choosingaclouddbmsarchitecturesandtradeoffs AT stonebrakermichael choosingaclouddbmsarchitecturesandtradeoffs AT dewittdavid choosingaclouddbmsarchitecturesandtradeoffs AT serafinimarco choosingaclouddbmsarchitecturesandtradeoffs AT aboulnagaashraf choosingaclouddbmsarchitecturesandtradeoffs AT kraskatim choosingaclouddbmsarchitecturesandtradeoffs |