{"title":"Managing Data Replication and Placement based on Availability","authors":"Bakhta Meroufel, Ghalem Belalem","doi":"10.1016/j.aasri.2013.10.071","DOIUrl":null,"url":null,"abstract":"<div><p>The replication of data across multiple sites of data grid is an effective solution to achieve good performance in terms of load balancing, response time, and improving data availability. To get the maximum gain that can make the data replication, their placement strategy in the system is critical. This paper proposes a replication strategy based on availability. It proposes also a placement and replacement strategies of replicas that ensures the desired availability with the minimum replicas despite the presence of nodes failures and without overloading the system. The results of our experimentations confirm that the proposed approach reaches its objectives.</p></div>","PeriodicalId":100008,"journal":{"name":"AASRI Procedia","volume":"5 ","pages":"Pages 147-155"},"PeriodicalIF":0.0000,"publicationDate":"2013-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.aasri.2013.10.071","citationCount":"19","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"AASRI Procedia","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2212671613000723","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 19
Abstract
The replication of data across multiple sites of data grid is an effective solution to achieve good performance in terms of load balancing, response time, and improving data availability. To get the maximum gain that can make the data replication, their placement strategy in the system is critical. This paper proposes a replication strategy based on availability. It proposes also a placement and replacement strategies of replicas that ensures the desired availability with the minimum replicas despite the presence of nodes failures and without overloading the system. The results of our experimentations confirm that the proposed approach reaches its objectives.