Open Access Open Access  Restricted Access Subscription or Fee Access

Developing an Effective Computational Cluster using a Novel Job Distribution Tool

N. Balaji, Dr. N. Ramaraj, C. Dhanasekaran

Abstract


The aim of our paper is to develop a tool for creating performance effective computational cluster called TCE (TCE Cluster Engine) tool using JAVA RMI. The Installation of TCE is very simple and easy to launch when compared with the existing tools. The batch jobs and their input data are given to the cluster environment for execution. Finally the result from the execution node will be sent back to the user specified location. Since the incoming batch jobs are distributed in the cluster, thereby distributing the load among several machines in order to increase the throughput of the system. By deploying an application in the created cluster, the performance of TCE is evaluated.

Keywords


Cluster computing, Job distribution, Remote Method Invocation, Resource management, Throughput, job allocation, Queue manager, Linux cluster, Batch job, job scheduler.

Full Text:

PDF

References


M. D. Schroeder, “A state-of-the-art distributed systems and Computing with BOB,” in Distributed Systems, S. Mullende. (Ed.), 2nd edition, Addison-Wesley, 1993, pp. 1-16.

Manish Parashar and Salim Hariri,A. Gaber Mohamed and Geoffrey C. Fox, " A Requirement Analysis for High Performance Distributed Computing over LAN’s",0-8186-2970-3192 SU3.00 Q 1992 IEEE.

William E. Biles,Jack P. C. Kleijnen, “ A java-based simulation manager for optimization and response surface methodology in multi-respone parallel simulation“,Proceedings of the I999 Winter Simulation Conference P. A. Farrington, H. B. Nembhard, D. T. Sturrock, and G. W. Evans, eds.

Stephen S. Yau and Haiqing Ying, A Clustering Algorithm for Object-Oriented Development of Distributed Computing System Software 0-8186-7125-495 $04.00 0 1995 IEEE

Mark A. Baker1, Matthew Groveξ and Aamir Shafiξ,"Parallel and Distributed Computing with Java ", Proceedings of The Fifth International Symposium on Parallel and Distributed Computing (ISPDC'06) 0-7695-2638-1/06 $20.00 © 2006 IEEE.

B. Ghahramani and M. A. Pauley, “Java in high-performance environments,” IEEE Computer, vol. 36, no. 9, pp. 109–111, Sept. 2003.

Java Remote Method Invocation - Distributed Computing for Java: at http://java.sun.com/javase/technologies/core/basic/rmi/whitepaper/index.jsp also, http://courses.dce.harvard.edu/~cscie160/UnitVI.htm

JavaTech: An Introduction to Scientific and Technical Computing withJava–Page-511. http://books.google.co.in/books?id=yL217mej8koC&pg=PA503&dq=rmi+distributed+computing+importance - PPA511,M1

Introduction to Object-oriented Programming through Java - Page 460http://books.google.co.in/books?id=ZC2aa-yqPNEC&pg=PA460&dq=power+of+java+RMI

Head First Java - Page 607by Kathy Sierra, Bert Bates - Computers - 2005 -688-pages. http://books.google.co.in/books?id=uIVJiAPlBq0C&pg=PA607&dq=rmi+distributed+computing+importance - PPA607, M1

Sun Grid Engine information at, http://www.sun.com/software/sge/

Henry Cohn, Robert Kleinberg, Balazs Szegedy, and Chris Umans. Group-theoretic Algorithms for Matrix Multiplication. arΧiv:math.GR/0511460. Proceedings of the 46th Annual Symposium on Foundations of Computer Science, 23-25 October 2005, Pittsburgh, PA, IEEE Computer Society, pp. 379–388.

http://searchdata.ter.techtarget.com/sDefinition/0,,sid80_gci211641,00.html

http://en.wikipedia.org/wiki/Batch_processing

http://en.wikipedia.org/wiki/Cluster_(computing)

http://www.corba.org/

http://en.wikipedia.org/wiki/CORBA

http://www.cro-ngi.hr/index.php?id=1408&L=1

http://en.wikipedia.org/wiki/Job_scheduler

http://en.wikipedia.org/wiki/Shell_script


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.