CFS: A New Dynamic Replication
Strategy for Data Grids
Feras Hanandeh1, Mutaz Khazaaleh2, Hamidah Ibrahim3, and Rohaya Latip3
1Prince Al- Hussein bin Abdullah II Faculty of Information Technology, Hashemite University, Jordan
2Irbid College, Al-Balqa Applied University, Jordan
3Faculty of Computer Science and Information Technology, University Putra Malaysia, Malaysia
1Prince Al- Hussein bin Abdullah II Faculty of Information Technology, Hashemite University, Jordan
2Irbid College, Al-Balqa Applied University, Jordan
3Faculty of Computer Science and Information Technology, University Putra Malaysia, Malaysia
Abstract: Data grids are currently proposed solutions to large scale data management problems including efficient file transfer and replication. Large amounts of data and the world-wide distribution of data stores contribute to the complexity of the data management challenge. Recent architecture proposals and prototypes deal with dynamic replication strategies for a high-performance data grid. This paper describes a new dynamic replication strategy called Constrained Fast Spread (CFS). It aims to alleviate the main problems encountered in the current replication strategies like the negligence of the storage capacity of the nodes. The new CFS strategy enhanced the fast spread strategy by concentrating on the feasibility of replicating the requested replica on each node among the network.
Keywords: Grid computing, dynamic replication strategies.
Received March 1, 2010; accepted May 20, 2010