Distributed Popularity Based Replica Placement in Data Grid Environments

Data grids support distributed data-intensive applications that need to access massive datasets stored around the world. Ensuring efficient access to such datasets is hindered by the high latencies of wide-area networks. To speed up access, files can be replicated so a user can access a nearby replica. Replication also provides improved availability, decreased bandwidth use, increased fault tolerance, and improved scalability. Since a grid environment is dynamic, resource availability, network latency, and user requests may change. To address these issues a dynamic replica placement strategy that adapts to changing behaviour is needed. In this paper, we introduce a highly distributed replica placement algorithm for hierarchical data grids. Our algorithm exploits data access histories to identify popular files and determines optimal replication locations to improve access performance by minimizing replication overhead (access and update) assuming a given traffic pattern. The problem is formulated using dynamic programming. We evaluate our algorithm using the OptorSim simulator and find that it offers shorter execution time and reduced bandwidth consumption compared to other dynamic replica placement methods.