Offer-based scheduling of deadline-constrained Bag-of-Tasks applications for utility computing systems

  • Authors:

  • Marco A. S. Netto;Rajkumar Buyya

  • Affiliations:

  • Grid Computing and Distributed Systems Laboratory, Department of Computer Science and Software Engineering, The University of Melbourne, Australia;Grid Computing and Distributed Systems Laboratory, Department of Computer Science and Software Engineering, The University of Melbourne, Australia

  • Venue:
  • IPDPS '09 Proceedings of the 2009 IEEE International Symposium on Parallel&Distributed Processing
  • Year:
  • 2009

Quantified Score

Hi-index 0.01

Visualization

Abstract

Metaschedulers can distribute parts of a Bag-of-Tasks (BoT) application among various resource providers in order to speed up its execution. When providers cannot disclose private information such as their load and computing power, which are usually heterogeneous, the metascheduler needs to make blind scheduling decisions. We propose three policies for composing resource offers to schedule deadline-constrained BoT applications. Offers act as a mechanism in which resource providers expose their interest in executing an entire BoT or only part of it without revealing their load and total computing power. We also evaluate the amount of information resource providers need to expose to the metascheduler and its impact on the scheduling. Our main findings are: (i) offer-based scheduling produces less delay for jobs that cannot meet deadlines in comparison to scheduling based on load availability (i.e. free time slots); thus it is possible to keep providers' load private when scheduling multi-site BoTs; and (ii) if providers publish their total computing power they can have more local jobs meeting deadlines.