Given paper contain proposed approached for task scheduling to achieve load balancing which is done on a group of computers. The processor idles due to large set of data, on the multiprocessor computer. Consideration of process data part by dividing them into number of fixed part & merge into single set that as good as previous original data set. Parallelism an approach for doing jobs in amount of time i.e. very fast. The paper contains dynamic approach for process migration using thread level paradigm. Creating a thread of process into number of task, that leads to reduce total execution time of process. An algorithm is used to calculate PCB for decision purpose to achieve load balancing. We are taking CPU and MEMORY parameter in this approach. Fair share approach is considered to allocating task to every processor using preemption strategy. The MPI is used for process communication. This system has defined to reduce total execution time on onboard & between board times. Open knoppix & MOSIX platform (Middleware) are used to show the results. Prime number calculation code is used to show parallel architecture like SIMD computer. Cluster computing is way of resource managing & scheduling strategy.

1. M. Willekk-Lemair and A.P. Reeves, Strategies for dynamic load-balancing on highly parallel computers, IEEE Transaction on Parallel and Distributed Systems, (4)9, September 1993, Pages 979-993.
2. M. Wu and W. Sbu, A load balancing algorithm for n-cube, Proceedings of rhe 1996 Inremarwnal Conference on Parallel Processing, IEEE Computer Society, 1996, Pages 148-155.
3. H. Shan, J.P. Singh, L. Oliker and R. Biswas, “Messge passing and shared address space parallelism on an SMP cluster,” Parallel Computing, vol 29, 2003, pp. 167-186.
4. W. Pan, L. Chan, J. Zhang, Y. Li, L. Wan and F. Xia, “Research on MPI+OpenMP hybrid programming paradigm based on SMP cluster,” Application Research of Computers, vol. 26, 2009, pp. 4492–4594.
5. Calvin Lin, “Priciples of parallel programming,” China machine press, Bejing, 2008.
6. Oren LA’ADAN Amnon BARAK and Amnon SHILOH.Scalable cluster computing with MOSIX for LINUX .InProc.LinuxExpo’99, pages95–100,May1999.
7. Barak, A., Shiloh, A., “ A Distributed Load-Balancing Policyfor a Multiwmputer” , Software-Practice and Eqerience, vol. 5, no 9, September 1985, pp 901-913.
8. Amith R. Mamidala Rahul Kumar Debraj De D. K. Panda Department of Computer Science and Engineering” MPI Collectives on Modern Multicore Clusters: Performance Optimizationsand Communication Characteristics”, Eighth IEEE International Symposium on Cluster Computing and the Grid.
9. Douglis, F., Ousterhout, J, “ Transparent Process Migration: Design Alternatives and the Sprite Implementation” , Soj ware-Practice and Experience, vol. 2, no 8, August 1991, pp 757-785.
10. Walker, B. J., Mathew, R. M., “ Process Migration in AIX’ sTransparent Computing Facility” , IEEE TCOS Newsletter, Winter 1989, vol. 3(l), pp 5-7.
11. Theimer, M., Lantz, K., Cheriton, I)., “ Preemptable Remote Execution Facilities for the V System” , Proc. of the 10th ACM Symposium on OS Principles, December 1985, pp 2- 12.
12. Milojicic, D., Zint, W., Dangel, A., Giese, P., “ Task Migration on the top of the Mach Microkernel” , Proceedings of the third USENIX Mach Symposium, Santa Fe, New Mexico, April 1993, pp 273-290. [ 14] Litzkow, M., Solomon, M., “ Supporting Checkpointing and Process Migration outside the UNIX Kernel” , Proceedings of the USENIX Winter Conference, San Francisco, January 1992, pp 283-290.
13. Alonso, R., Kyrimis, K., “ A Process Migration Implementation for a Unix System” , Proceedings of the USENIX Winter Conference, February 1988, pp 365-372.
14. L. Anand, D. Ghose, and V. Mani, “ELISA: An Estimated Load Information Scheduling Algorithm for Distributed Computing Systems,” Int’l J. Computers and Math. with Applications, vol. 37, no. 8, pp. 57-85, Apr. 1999.
15. J. Krallmann, U. Schwiegelshohn, and R. Yahyapour, “On the Design and Evaluation of Job Scheduling Algorithms,” Proc. Fifth Workshop Job Scheduling Strategies for Parallel Processing, pp. 17-42, 1999.
16. D.G. Feitelson, L. Rudolph, U. Schwiegelshohn, K.C. Sevcik, and P. Wong, “Theory and Practice in Parallel Job Scheduling,” Proc. ThirdWorkshop Job Scheduling Strategies for Parallel Processing, pp. 1- 34, 1997.
17. Nikolaos D. Doulamis, Member, IEEE, Anastasios D. Doulamis, Member, IEEE, Emmanouel A. Varvarigos, and Theodora A. Varvarigou, Member, IEEE ” Fair Scheduling Algorithms in Grids”. IEEE transactions on parallel and distributed systems, vol. 18, no. 11, november 2007

Cluster computing MOSIX MPI load balancing threads Task load. Onboard-time betweenbord time