Peer to Peer Scheduling in PBS and Implementing Multi-Level Feedback Queues
CH.V.T.E.V.Laxmi1, K.Somasundaran2
1Ch E V T V Laxmi, Research Scholar, Associate Professor, Department of Computer Science Engineering, Raghu Engineering College, Visakhapatnam (Andhra Pradesh), India.
2Dr. K. Somasundaram, Research Supervisor, Professor, Department of Computer Science and Engineering, Jaya Engineering College, Thiruvallur (Tamil Nadu), India.
Manuscript received on 21 July 2013 | Revised Manuscript received on 28 July 2013 | Manuscript published on 30 July 2013 | PP: 22-24 | Volume-2 Issue-3, July 2013 | Retrieval Number: C0674072313/2013©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Grid computing is the federation of pooling resources in order to solve various large problems. Grid computing has gained remarkable importance in the last decade as the resource requirements for large applications increased drastically. Scheduling is the main issue in grid computing and it is the process of making scheduling decisions over multiple grid resources. In this paper we proposed a approach for Portable Batch System (PBS) to implement peer to peer scheduling. This mainly defines that a site can have multiple PBS Pro cluster, each cluster has its server, scheduler and one or more execution systems. This paper focuses on designing of new architecture for Portable Batch System to implement Peer to Peer scheduling system. In this research of Peer to Peer scheduling in PBS we proposed new approach for selecting the jobs from the job pool through ready queue data structure mechanism and we proposed Grid scheduling algorithm Multi Level Feedback Queues Scheduling algorithm for the execution of jobs.
Keywords: Grid Computing, Grid scheduling, Resource discovery, Portable Batch System, Peer to Peer Scheduling, Pro cluster
Scope of the Article: Multi-Agent Systems