Abstract

Data grids provide distributed resources for dealing with large scale applications that generate huge volume of data sets. Data replication, a technique much discussed by data grid researchers in past years creates multiple copies of file and stores them in conventional locations to shorten file access times. One of the challenges in data replication is creation of replicas, replica placement and replica selection. Dynamic creation of replicas in a suitable site by data replication strategy can increase the systems performance. When creating replicas a decision has to be made on when to create replicas and which one to be created. This decision is based on popularity of file. Placement of replicas selects the best site where replicas should be placed. Placing the replicas in the appropriate site reduces the bandwidth consumption and reduces the job execution time. Replica selection decides which replica to locate among many replicas. This paper discusses about dynamic creation of replicas, replica placement and replica selection. It is implemented by using a data grid simulator, Optorsim developed by European data grid projects.