A new resource mapping technique for Grid workflows in advance reservation environments

Abstract

Advance reservation can ensure the future availability of the Grid's heterogeneous resources and help a scheduler to produce better schedules. We propose a new resource mapping technique for jobs of a Grid workflow in an advance reservation environment. Using the Dynamic Critical Path for Grid (DCP-G) scheduling algorithm's job selection method, our proposed technique considers the conditional mapping of parent and child jobs to the same resource, trying to minimise the communication duration between jobs and thus optimising workflow completion time. For a number of different workflows, the schedules computed by our technique are compared with those computed by DCP-G, a workflow scheduling algorithm that is known to outperform many other popular scheduling heuristics. The results show that our proposed resource mapping technique yields improved schedules along with the significant improvement in the CPU time as the size of the workflow increases.

Resource Management for Business Process Scheduling in the Presence of Availability Constraints

“…In Russell et al [2005], a novel framework of resource patterns for workflow resource management is proposed. Some approaches such as Ashraf and Erlebach [2010], Decker and Schneider [2007], and Langguth and Schuldt [2010] consider resource reservation when scheduling the workflow/business processes. In contrast, the second category is to plan resource for certain number of workflow instances at the build time.…”

“…Another category is workflow scheduling/planning, which considers the workflow structure in resource allocation. Yu et al in Yu and Buyya [2005] compared some significant workflow scheduling algorithms and systems [Ashraf and Erlebach 2010;Decker and Schneider 2007;Langguth and Schuldt 2010;Senkul and Toroslu 2005;Yarkhan and Dongarra 2002;Yu and Buyya 2006] under the Grid environment. These approaches mainly deal with the run-time workflow scheduling problems.…”

Load Balancing in Partner-Based Scheduling Algorithm for Grid Workflow

“…Partner Based Dynamic Critical Path for Grid (PDCPG), proposed in [6], is based on Dynamic Critical Path for Grid (DCPG) for AR environment. For job selection, it uses same technique as of DCPG.…”

“…For efficient execution of workflow good scheduling heuristics are trivial. Partner Based Dynamic Critical Path for Grids (PDCPG) proposed in [6], is one of the proposed algorithms for advance reservation environment in Grid and is based on Dynamic Critical Path for Grids (DCPG) [7].www.ijacsa.thesai.org order to minimize the communication involved to transfer required files of the child jobs. This may lead the overall Grid to an un-balanced state in which some of the resources are highly utilized while others remain under-utilized.…”