Providing non-trivial QoS for grid application under meeting local job's QoS requirements and local scheduling strategy of grid site
is an important objective and a new issue of task scheduling in service grid environment. A resource dynamic performance evaluation method is presented and two performance metrics are obtained. Based on resource availability characteristic of a grid site
probability theory is employed to evaluate the average capacity of a resource. Several states for grid sites are labeled
and the conception of entropy in thermodynamics is used to describe the uncertainty of the resource. Then
a performance-evaluation-based meta-task scheduling algorithm is proposed. On the basis of extended and revised gridSim
the algorithm is implemented and compared with two related existing algorithms. The experiment results show that the proposed algorithm outperforms the existing ones on both aspects of the service deny rate and the grid task makespan.
关键词
Keywords
references
FOSTER I, KESSELMAN C, NICK M, et al. The physiology of the grid: an open grid services architecture for distributed systems integration [EB/OL]. [2006-12-10]. http:∥www.globus.org/research/papers/ogsa.pdf.
HU Chunming, HUAI Jinpeng. A service oriented grid architecture with end to end quality of service [J]. Journal of Software, 2006, 17(6): 1448-1458.
SUN Xianhe, WU Ming. Quality of service of grid computing: resource sharing[C]∥6th International Conference on Grid and Cooperative Computing. Los Alamitos, CA, USA: IEEE Computer Society, 2007:395-402.
FUJIMOTO N, HAGIHARA K. A comparison among grid scheduling algorithms for independent coarse-grained tasks [C]∥Proceedings of the 2004 International Symposium on Applications and the Internet Workshops. Los Alamitios, CA, USA: IEEE Computer Society, 2004: 674-680.
TOPCUOGLU H, HARIRI S, WU M Y. Performance-effective and low-complexity task scheduling for heterogeneous computing [J]. IEEE Transactions on Parallel and Distributed Systems, 2002, 13(3): 260-274.
DONG Fangpeng, AKL S G. An adaptive double-layer workflow scheduling approach for grid computing [C]∥21st International Symposium on High Performance Computing Systems and Applications. Los Alamitos, CA, USA: IEEE Computer Society, 2007: 1-7.
WU Ming, SUN Xianhe. Grid harvest service: a performance system of grid computing [J]. Journal of Parallel and Distributed Computing, 2006, 66(10): 1322-1337.
ADZIGOGOV L, SOLDATOS J, POLYMENAKOS L. EMPEROR: an OGSA grid meta-scheduler based on dynamic resource predictions [J]. Journal of Grid Computing, 2005, 3(1): 19-37.
GAO Zhan, LUO Siwei, DING Ding. A scheduling mechanism considering simultaneous running of grid tasks and local tasks in the computational grid [C]∥2007 International Conference on Multimedia and Ubiquitous Engineering. Los Alamitos, CA, USA: IEEE Computer Society, 2007: 1100-1105.
DONG Fangpeng, AKL S G. PFAS: a resource-performance-fluctuation-aware workflow scheduling algorithm for grid computing[C]∥21st Parallel and Distributed Processing Symposium. Los Alamitos, CA, USA: IEEE Computer Society, 2007: 1-9.
MUTKA M W, LIVNY M. The available capacity of a privately owned workstation environment [J]. Performance Evaluation, 1991, 12(4): 269-284.
SULISTIO A, PODUVALY G, BUYYA R, et al. Constructing a grid simulation with differentiated network service using gridsim [C]∥Proceeding of 6th International Conference on Internet Computing. Las Vegas, Nevada, USA: CSREA Press, 2005: 437-444.
HE Xiaoshan, SUN Xianhe. QoS guided min-min heuristic for grid task scheduling [J]. Journal of Computer Science and Technology, 2003, 18(4): 442-445.