Probabilistic load balancing with optimal resources set of nodes in clusters

N. P. Gopalan, Nagarajan Kathiresan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A probability model for task allocation to nodes in a cluster for better CPU utilization and reduces I/O and communication overhead is presented in this paper. For the NP-hard problem of task assignment, load balancing is done with a local and global scheduler (LS and GS). A newly arriving task need not wait at the home node (HN) for the want of resources as GS takes care of it. Using three different queues for the processes, GS assigns the best set of optimal resources at a foreign node (FN) with a minimal transfer cost to the processes. The experimentally simulated results show that the model compares well with the existing models and well suited for time and space sharing systems with minimal I/O overhead and excellent resource utilization.

Original languageEnglish
Title of host publicationAdvances in Computer Science and Eng.: Reports and Monographs; Innovative Applications of Information Technology for the Developing World - Proc. of the 3rd Asian Applied Computing Conf., AACC 2005
Pages45-49
Number of pages5
Volume2
Publication statusPublished - 2007
Externally publishedYes
Event3rd Asian Applied Computing Conference, AACC 2005 - Kathmandu, Nepal
Duration: 10 Dec 200512 Dec 2005

Other

Other3rd Asian Applied Computing Conference, AACC 2005
CountryNepal
CityKathmandu
Period10/12/0512/12/05

    Fingerprint

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems

Cite this

Gopalan, N. P., & Kathiresan, N. (2007). Probabilistic load balancing with optimal resources set of nodes in clusters. In Advances in Computer Science and Eng.: Reports and Monographs; Innovative Applications of Information Technology for the Developing World - Proc. of the 3rd Asian Applied Computing Conf., AACC 2005 (Vol. 2, pp. 45-49)