Workload-Driven Fragment Allocation for Partially Replicated Databases Using Linear Programming
- In replication schemes, replica nodes can process read-only queries on snapshots of the master node without violating transactional consistency. By analyzing the workload, we can identify query access patterns and replicate data depending to its access frequency. In this paper, we define a linear programming (LP) model to calculate the set of partial replicas with the lowest overall memory capacity while evenly balancing the query load. Furthermore, we propose a scalable decomposition heuristic to calculate solutions for larger problem sizes. While guaranteeing the same performance as state-of-the-art heuristics, our decomposition approach calculates allocations with up to 23% lower memory footprint for the TPC-H benchmark.
| Verfasserangaben: | Stefan Halfpap, Rainer SchlosserORCiDGND |
|---|---|
| DOI: | https://doi.org/10.1109/ICDE.2019.00188 |
| ISBN: | 978-1-5386-7474-1 |
| ISBN: | 978-1-5386-7475-8 |
| ISSN: | 1084-4627 |
| ISSN: | 2375-026X |
| ISSN: | 1063-6382 |
| Titel des übergeordneten Werks (Englisch): | 2019 IEEE 35th International Conference on Data Engineering (ICDE) |
| Verlag: | IEEE |
| Verlagsort: | New York |
| Publikationstyp: | Sonstiges |
| Sprache: | Englisch |
| Jahr der Erstveröffentlichung: | 2019 |
| Erscheinungsjahr: | 2019 |
| Datum der Freischaltung: | 05.05.2021 |
| Freies Schlagwort / Tag: | allocation problem; database replication; linear programming |
| Seitenanzahl: | 4 |
| Erste Seite: | 1746 |
| Letzte Seite: | 1749 |
| Organisationseinheiten: | Digital Engineering Fakultät / Hasso-Plattner-Institut für Digital Engineering GmbH |
| DDC-Klassifikation: | 0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 000 Informatik, Informationswissenschaft, allgemeine Werke |
| Peer Review: | Referiert |
