Improving Job Scheduling Performance with Dynamic Replication Strategy in Data Grids

Dealing with a large amount of data in Data Grids makes the requirement for efficient data access more critical. In this paper, we proposed a new approach to replication problem by organizing the data into several data categories that it belongs to. This organizing will help improving placement strategy of data replication. We studied our approach in combination with scheduling issue and evaluating it through simulation. The result shows that our strategy has improved the scheduling performance by 30%.

[1]  Kavitha Ranganathan,et al.  Simulation Studies of Computation and Data Scheduling Algorithms for Data Grids , 2003, Journal of Grid Computing.

[2]  Ming Tang,et al.  The impact of data replication on job scheduling performance in the Data Grid , 2006, Future Gener. Comput. Syst..

[3]  Floriano Zini,et al.  Evaluating scheduling and replica optimisation strategies in OptorSim , 2003, Proceedings. First Latin American Web Congress.

[4]  Kurt Stockinger,et al.  OptorSim-A Grid Simulator for Studying Dynamic Data Replication Strategies , 2003 .

[5]  Kavitha Ranganathan,et al.  Decoupling computation and data scheduling in distributed data-intensive applications , 2002, Proceedings 11th IEEE International Symposium on High Performance Distributed Computing.

[6]  Boleslaw K. Szymanski,et al.  Simulation of dynamic data replication strategies in Data Grids , 2003, Proceedings International Parallel and Distributed Processing Symposium.

[7]  Shubhashis Sengupta,et al.  Integration of Scheduling and Replication in Data Grids , 2004, HiPC.

[8]  Viktor K. Prasanna,et al.  High Performance Computing - HiPC 2004 , 2004, Lecture Notes in Computer Science.