Authors: Jun Zhang, Chris Phillips
Addresses: School of Electronic Engineering and Computer Science, Queen Mary, University of London, Mile End Road, E1 4NS, London, UK. ' School of Electronic Engineering and Computer Science, Queen Mary, University of London, Mile End Road, E1 4NS, London, UK
Abstract: In a volunteer-based computational grid computing, one big challenge for effective job allocation is resource availability. As resources in this environment are volatile, matching guest jobs to suitable resources is very important. To improve scheduling, especially in terms of avoiding job failures due to resource unavailability, we propose a new job-scheduling algorithm called first-come-first-served plus predictor (FCFSPP). This scheduling algorithm is based on an existing resource availability prediction method that anticipates the future availability of resources to help make reliable job allocation decisions. According to the simulation results, FCFSPP does not only reduce the number of job failures but also maintain acceptable job throughput in volatile volunteer environments by providing reliable job allocation decisions.
Keywords: computational grids; volunteer grids; job scheduling; resource availability prediction; reliable decisions; grid computing; job allocation; guest jobs; simulation; job failures; job throughput.
International Journal of Grid and Utility Computing, 2011 Vol.2 No.1, pp.25 - 32
Received: 09 Jul 2010
Accepted: 21 Oct 2010
Published online: 09 May 2011 *