Supporting multiple data replication models in distributed transactional memory

João A. Silva, Tiago M. Vale, Ricardo J. Dias, Hervé Paulino, João M. Lourenço

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

2 Citations (Scopus)

Abstract

Distributed transactional memory (DTM) presents itself as a highly expressive and programmer friendly model for concurrency control in distributed programming. Current DTM systems make use of both data distribution and replication as a way of providing scalability and fault tolerance, but both techniques have advantages and drawbacks. As such, each one is suitable for different target applications, and deployment environments. In this paper we address the support of different data replication models in DTM. To that end we propose REDSTM, a modular and non-intrusive framework for DTM, that supports multiple data replication models in a general purpose programming language (Java). We show its application in the implementation of distributed software transactional memories with different replication models, and evaluate the framework via a set of well-known benchmarks, analysing the impact of the different replication models on memory usage and transaction throughput.

Original languageEnglish
Title of host publicationICDCN 2015 - Proceedings of the 16th International Conference on Distributed Computing and Networking
PublisherAssociation for Computing Machinery
Volume04-07-January-2015
ISBN (Electronic)9781450329286
DOIs
Publication statusPublished - 4 Jan 2015
Event16th International Conference on Distributed Computing and Networking, ICDCN 2015 - Goa, India
Duration: 4 Jan 20157 Jan 2015

Conference

Conference16th International Conference on Distributed Computing and Networking, ICDCN 2015
CountryIndia
CityGoa
Period4/01/157/01/15

Keywords

  • Concurrency control
  • Data replication
  • Distributed systems
  • Distributed transactional memory

Fingerprint Dive into the research topics of 'Supporting multiple data replication models in distributed transactional memory'. Together they form a unique fingerprint.

Cite this