Title: Improving the MXFT scheduling algorithm for a cloud computing context

Authors: Paul Moggridge; Na Helian; Yi Sun; Mariana Lilley; Vito Veneziano; Martin Eaves

Addresses: School of Computer Science, University of Hertfordshire Hatfield, Hertfordshire, UK ' School of Computer Science, University of Hertfordshire Hatfield, Hertfordshire, UK ' School of Computer Science, University of Hertfordshire Hatfield, Hertfordshire, UK ' School of Computer Science, University of Hertfordshire Hatfield, Hertfordshire, UK ' School of Computer Science, University of Hertfordshire Hatfield, Hertfordshire, UK ' School of Computer Science, University of Hertfordshire Hatfield, Hertfordshire, UK

Abstract: In this paper, the Max-Min Fast Track (MXFT) scheduling algorithm is improved and compared against a selection of popular algorithms. The improved versions of MXFT are called Min-Min Max-Min Fast Track (MMMXFT) and Clustering Min-Min Max-Min Fast Track (CMMMXFT). The key difference is using Min-Min for the fast track. Experimentation revealed that despite Min-Min's characteristic of prioritising small tasks at the expense of overall makespan, the overall makespan was not adversely affected and the benefits of prioritising small tasks were identified in MMMXFT. Experiments were conducted by using a simulator with the exception of one real-world experiment. The real-world experiment identified challenges faced by algorithms which rely on accurate execution time prediction.

Keywords: cloud computing; scheduling algorithms; max-min.

DOI: 10.1504/IJGUC.2019.102711

International Journal of Grid and Utility Computing, 2019 Vol.10 No.6, pp.618 - 638

Received: 01 Dec 2017
Accepted: 27 Feb 2018

Published online: 09 Aug 2019 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article