Sunday 24th of September 2017
 

A MLFQ Scheduling Technique using MMc Queues for Grid Computing


Dharamendra Chouhan, S.M Dilip Kumar and Jerry Antony Ajay

We model the objective function, that the jobs entering the scheduler have a Poissons distribution and the jobs that are sent out from the multilevel feedback scheduler are also distributed as a Poissons distribution. We also assume that the number of CPUs in a processing element is not restricted to one, but rather many CPUs integrated into one PE. Therefore, we assume the M/M/c queue model for our calculations. In Kendall\'s notation, we describes a system where arrivals form a single queue and are governed by a Poisson process, where there are c servers and job service times are exponentially distributed. Gridlets provided by the users are assigned to processing elements (PEs), and gridlets whose remaining service time is shifted between queues of the MLFQ scheduler to be completed. In MLFQ, the total architecture is divided into multiple prioritized queues. This approach provides gridlets which starve in the lower priority queue for long time to get resources. As a result, the response time of the starved gridlets decreases and overall turnaround time of the scheduling process decreases. This scheduling policy is simulated using Alea GridSim toolkit to test the performance. The proposed MLFQ scheduling algorithm works better in most of the scenarios when compared to FCFS and PBS_PRO algorithms.

Keywords: Grid Computing, Job Scheduling, Multilevel Feedback Queue, GridSim.

Download Full-Text


ABOUT THE AUTHORS

Dharamendra Chouhan
Dharamendra Chouhan completed B.E in 1999 and M.E in 2002 from Bangalore University,currently Working as a Assistant Professor.He has published 4 papers in International Journals and Conferences. His Research interest include Grid,Cloud and Ubiquitous Computing.

S.M Dilip Kumar
S. M Dilip Kumar received the B. E (CS&E) degree in 1996 and the M. Tech (CS&E) degree in 2001 from Kuvempu University and Vishweswaraiah Technological University respectively. He obtained the Ph. D degree in Computer Science and engineering from Kuvempu University in April 2010. Currently he is working as Associate Professor in the Department of Computer Science and Engineering, University Visvesvaraya College of Engineering (UVCE), Bangalore University, Bangalore. He is involved in research and teaching B. E and M. E students of Computer Science and Engineering and has more than 13 years of teaching experience and also guiding Ph. D students in Computer Science and Engineering under Bangalore University. He has published 13 papers in International Journals and Conferences. He has also edited two books for the distance education at Kuvempu University. His current research lies in the areas of ad hoc networks, wireless sensor networks,ubiquitous computing and grid computing.

Jerry Antony Ajay
Jerry Antony Ajay is a final year B.E student specializing in computer science and his active research include High Performance computing.He has published 3 papers in International Journals and Conferences.


IJCSI Published Papers Indexed By:

 

 

 

 
About IJCSI

IJCSI is a refereed open access international journal for scientific papers dealing in all areas of computer science research...

Learn more »
Join Us
FAQs

Read the most frequently asked questions about IJCSI.

Frequently Asked Questions (FAQs) »
Get in touch

Phone: +230 911 5482
Email: info@ijcsi.org

More contact details »