Toward Practical Multi-workflow Scheduling in Cluster and Grid Environments

TOWARD PRACTICAL MULTI-WORKFLOW SCHEDULING IN CLUSTER ANDGRID ENVIRONMENTS byZHIFENG YUMay 2009 Advisor: Dr. Weisong ShiMajor: Computer ScienceDegree: Doctor of PhilosophyWorkflow applications are gaining popularity in recent years because of the prevalence ofcluster and Grid environments. Many algorithms have been developed ever since, howevertwo fundamental challenges in this area, i.e., dynamic resource and dynamic workload, arenot well addressed. In cluster and Grid environments, resources may be contributed andcontrolled by different virtual organizations and shared by a variety of users who in turn sub-mit various kinds of applications. Resources are heterogeneous under different ownership,their availability varies over time and may fail in a high rate. On the other hand, resourcesare shared and hence competed among many applications with various computation require-ments. Existing static algorithms are designed to schedule a single workflow application,without considering other workloads and any resource competition in the system. Hencestatic approaches are not utilized widely in practice despite its known advantages. Dynamicscheduling approaches can handle the dynamic workload and resources practically by naturebut their effectiveness has yet to optimize as they do not have a global view of workflowapplication and scheduling decision is made nearsighted locally.In this dissertation, as an effort toward practically scheduling workflow applicationsin cluster and Grid environments, a failure aware dynamic scheduling strategy for multipleworkflow applications is proposed. The approach makes scheduling decision only when a task