Improving the scalability of geo-replication with reservations

Mahsa Najafzadeh, Marc Shapiro, Valter Balegas, Nuno Preguiça

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Geo-replicated systems improve performance and fault tolerance by replicating data on sites in different physical locations. Because of performance and scalability costs of strong consistency, these systems rely on eventual consistency that improves performance but might violate application invariants. In this work, we exploit reservation techniques to strengthen eventual consistency, by protecting specific invariants without adding synchronization in the critical path. We define a consistency model called RPB that retains the advantages of eventual consistency, while enforcing stronger guarantees, including causality and safety properties.

Original languageEnglish
Title of host publicationProceedings - 2013 IEEE/ACM 6th International Conference on Utility and Cloud Computing, UCC 2013
PublisherIEEE Computer Society
Pages441-445
Number of pages5
ISBN (Print)978-076955152-4
DOIs
Publication statusPublished - 1 Jan 2013
Event2013 IEEE/ACM 6th International Conference on Utility and Cloud Computing, UCC 2013 - Dresden, Saxony, Germany
Duration: 9 Dec 201312 Dec 2013

Conference

Conference2013 IEEE/ACM 6th International Conference on Utility and Cloud Computing, UCC 2013
CountryGermany
CityDresden, Saxony
Period9/12/1312/12/13

    Fingerprint

Keywords

  • commutativity
  • consistency
  • performance
  • reservation

Cite this

Najafzadeh, M., Shapiro, M., Balegas, V., & Preguiça, N. (2013). Improving the scalability of geo-replication with reservations. In Proceedings - 2013 IEEE/ACM 6th International Conference on Utility and Cloud Computing, UCC 2013 (pp. 441-445). [6809446] IEEE Computer Society. https://doi.org/10.1109/UCC.2013.87