Research Area:  Cloud Computing

Abstract:

In this work,we present a scheduling mechanism for deadline sensitive task or lease. It is very impelling and challenging to allocate on-demand resources within the deadline rather than rejecting the lease. The work studies the insight of existing backfilling algorithm that is used to schedule deadline sensitive lease in the Open Nebula cloud platform. In backfilling mechanism a lease is selected in First Come First Serve (FCFS) to be backfilled in which some ideal resources can be found out and allocated to other leases. Mainly, the scheduling performance of backfilling algorithm could be better when there are conflicts among the similar leases to backfill. Moreover, backfilling algorithm doesnt allow to schedule a new deadline sensitive task during execution. The proposed work addresses such types of issues and improves the scheduling performances with respect to maximize the task acceptance ratio and reduce the task rejection ratio. Finally, the performances are compared with the existing mechanisms that are quite good.

Keywords:  

Author(s) Name:  Suvendu Chandan Nayak,Sasmita Parida,Chitaranjan Tripathy,Prasant Kumar Pattnaik

Publisher name:  Elsevier

DOI:  10.1016/j.jksuci.2018.10.009

Volume Information:  Volume 2018

Paper Link:   https://www.sciencedirect.com/science/article/pii/S1319157818304270