Paper Info
Title
Allocating qos-constrained workflow-based jobs in a multi-cluster grid through queueing theory approach
Abstract
Clusters are increasingly interconnected to form multi-cluster systems, which are becoming popular for scientific computation. End-users often submit their applications in the form of workflows with certain Quality of Service (QoS) requirements imposed on the workflows. These workflows describe the execution of a complex application built from individual application components, which form the workflow tasks. This paper addresses workload allocation techniques for Grid workflows. We model individual clusters as M/M/k queues and obtain a numerical solution for missed deadlines (failures) of tasks of Grid workflows. The approach is evaluated through an experimental simulation and the results confirm that the proposed workload allocation strategy combined with traditional scheduling algorithms performs considerably better in terms of satisfying QoS requirements of Grid workflows than scheduling algorithms that don't employ such workload allocation techniques.
Year
DOI
Venue
2006
10.1007/11946441_48
ISPA
Keywords
Field
DocType
qos-constrained workflow-based job,individual cluster,traditional scheduling algorithm,proposed workload allocation strategy,grid workflows,complex application,workload allocation technique,individual application component,multi-cluster grid,k queue,experimental simulation,queueing theory approach,qos requirement,quality of service,scheduling algorithm,satisfiability,queueing theory,scientific computing
Computer science,Parallel algorithm,Workload,Scheduling (computing),Quality of service,Real-time computing,Queueing theory,Workflow,Grid,Computer cluster,Distributed computing
Conference
Volume
ISSN
ISBN
4330
0302-9743
3-540-68067-5
Citations 
PageRank 
References 
3
0.51
12
Authors
2
Name
Order
Citations
PageRank
Yash Patel1294.60
John Darlington219127.97