A unified resource scheduling framework for heterogeneous computing environments
- 20 January 2003
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
A major challenge in Metacomputing Systems (Computational Grids) is to effectively use their shared resources, such as compute cycles, memory, communication network, and data repositories, to optimize desired global objectives. In this paper we develop a unified framework for resource scheduling in metacomputing systems where tasks with various requirements are submitted from participant sites. Our goal is to minimize the overall execution time of a collection of application tasks. In our model, each application task is represented by a Directed Acyclic Graph (DAG). A task consists of several subtasks and the resource requirements are specified at subtask level. Our framework is general and it accommodates emerging notions of Quality of Service (QoS) and advance resource reservations. In this paper, we present several scheduling algorithms which consider compute resources and data repositories that have advance reservations. As shown by our simulationresults, it is advantageous to schedule the system resources in a unified manner rather than scheduling each type of resource separately. Our algorithms have at least 30% improvement over the separated approach with respect to completion time.Keywords
This publication has 15 references indexed in Scilit:
- SmartNet: a scheduling framework for heterogeneous computingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A taxonomy for describing matching and scheduling heuristics for mixed-machine heterogeneous computing systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Scheduling resources in multi-user, heterogeneous, computing environments with SmartNetPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Dynamic, competitive scheduling of multiple DAGs in a distributed heterogeneous environmentPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Task Matching and Scheduling in Heterogeneous Computing Environments Using a Genetic-Algorithm-Based ApproachJournal of Parallel and Distributed Computing, 1997
- Scheduling from the perspective of the applicationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Heterogeneous computing: challenges and opportunitiesComputer, 1993
- Allocating modules to processors in a distributed systemIEEE Transactions on Software Engineering, 1989
- A taxonomy of scheduling in general-purpose distributed computing systemsIEEE Transactions on Software Engineering, 1988
- Heuristic Algorithms for Scheduling Independent Tasks on Nonidentical ProcessorsJournal of the ACM, 1977