用户名: 密码: 验证码:
基于多Agent的网格监控的研究与实现
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
网格计算研究的基本目的是实现最大范围内的计算资源共享,并提供协同计算能力;网格是把广域网上大量分布、异构资源进行整合,实现统一视图和统一访问接口的基础设施。资源信息服务在网格中具有重要地位,其作用是感知和监控异构资源,并为上层应用提供资源信息,从而为资源调度和选择系统策略提供依据。
     本文在深入研究网格监控相关技术的基础上,提出了基于多Agent的网格监控系统模型,并设计了一种基于多Agent的网格监控系统原型。该系统根据网格应用系统的一般特点采用层次架构,其基本架构遵循全球网格论坛提出的网格监控架构GMA。在系统的研究中引入了多Agent系统中多个Agent间的协作技术,解决了网格资源的动态性、可扩展性和异构性。在此系统的监控服务设计中,运用目前网格研究中的体系架构规范——Web服务资源架构(WSRF)构建网格监控服务,从而为与其他网格监控系统的互操作提供了统一的访问接口。
     实验结果表明:基于多Agent的网格监控系统能够有效地收集监控数据并为用户提供实时的网格监控服务,其功能和性能均达到了设计要求。
As an up-to-date realm of computer science research, grid computing technology focuses on sharing of resources and cooperating of computing. The Grid is a basic information infrastructure which integrates a mass of heterogeneous resources distributed in wide area network, and constitutes a virtual organization with uniform interface and user view. The resource information service, perceiving and monitoring the heterogeneous resources, plays a key role in Grid technology. The resource scheduler and the system strategy selecting should work according to the resource information provided by the service.
     Based on studying grid monitoring technologies in depth, the grid monitoring system model based on multi-agent is proposed, and a new grid monitoring system prototype based on multi-agent is designed. It adopts hierarchical architecture according to usual grid architectures. Its basic architecture is accordance with Grid Monitoring Architecture (GMA), which is proposed by Global Grid Forum. In the research of system, collaboration technologies in multi-agent systems are used to solve dynamic, expand and heterogeneousness of grid resources. In the design of system monitoring service, Web Service Resource Framework (WSRF) is used to create a universal interface to facilitate the cooperation of different grid monitoring systems.
     The experiment results show that system can collect monitor data of grid resource and provide users grid monitor service more efficiently and easily, its functions and performance all meet the design requirements.
引文
[1]都志辉,陈渝,刘鹏.网格计算.北京:清华大学出版社,2002:3-12,21.
    [2]Ian Foster.What is the Grid? A Three Point Checklist.http://www.grid.today.com/02/0722/100136.html,2002.
    [3]Zhao Ying,Zhou WanLei.Self-Adaptive Clock Synchronization for Computational Grid.Computer Science and Technology.2003.18(4):434-441.
    [4]I Foster,C Kesselman,G Tsudik,S Tuecke.A security architecture for computational grids.In Proc 5~(th)ACM Conference on Computer and Communications Security Conference,1998:83-92.
    [5]Ian Foster.Internet Computing and the Emerging Grid.Nature Web Matters,http://www.nature.com/nature/webmatters/grid/grid.html,2000.
    [6]Andrerson E.Extensible,Scalable Monitoring for Clusters of Computers.In:proceedings of the 11~(th)systems administration conference LISA'97,San Diego,CA,1997.10:10-16.
    [7]R Buyya.PARMON:A Portable and Scalable Monitoring System for Clusters.Software-practice and Experience,2000.30:1-17.
    [8]桂小林.网格技术导论.北京:北京邮电大学出版社.2005:44-45,207-238.
    [9]桂小林,钱德沛.基于INTERNET的网格计算模型研究.西安交通大学学报,2001,35(10):8-11
    [10]胡春明,怀进鹏,孙海龙.基于Web服务的网格体系结构及其支撑环境研究.软件学报,2004,15(7):1064-1073
    [11]Gabrielle Allen,Thomas Dramlitsch,Ian Foster,Nick Karonis,Matei Ripeanu,Ed Seidel,Brian Toonen.Supporting Efficient Execution in Heterogeneous Distributed Computing Environments with Cactus and Globus.Supercomputing,2001:1-25.
    [12]S Brunett,D.Davis,T.Gottschalk,P.Messina,C.Kesselman.Implementing Distributed Synthetic Forces Simulations in Metacomputing Environments.IPPS/SPDP'98 Heterogeneous Computing Workshop,1998.
    [13]Gabrielle Allen,E.Seidel,John Shalf,Scientific Computing on the Grid,Byte,Spring 2002.
    [14]Tierney B.et al.The NetLogger Methodology for High Performance Distributed Systems Performance Analysis.In:Proc.Of IEEE High Performance Distributed Comparing.July 1998.28-31.
    [15]Allcock W.at al.GridMapper:A Tool for Visualizing the Behavior of Large-Scale Distributed Systems.In:11~(th)IEEE Intl.Symposium on High Performance Distributed Computing HPDC-1120002(HPDC'02)P.179.
    [16]Wolski R.Spring N T.H ayes J.The Network Weather Service A Distributed Resource Performance Forecasting Service for Metacomputing.Future Generation Computing System,1999 http://nws.npaci.edu/
    [17]Lee D W.Dongarra J J.Rnmakrishna R S.VisPerf:Monitoring Tool for Grid Computing.Workshop on Grid Computing(submitted),Baltimore,MD.Nov.2002.
    [18]I Foster,C Kesselman,S Tuecke.The Anatomy of the Grid:Enabling Scalable Virtual Organizations.International Journal of Supercomputer Applications,2001.15(3):1-25.
    [19]I Foster,C Kesselman.Globus:A Metacomputing Infrastructure Toolkit.International Journal of Supercomputer Applications,1997.11(2):115-128.
    [20]SUN ONE.http://wwws.sun.com/software/sunone/
    [21]WSDL,http://www.w3.org/TR/wsdl/
    [22]UDDI.http://www.uddi.org/
    [23]Globus Toolkit 3.0.http://www.globus.org/ogsa/releases/alpha/
    [24]Fisher S.Relational Grid Monitoring Architecture http://hepunx.rl.ac.uk/Grid/wp3/release.html
    [25]Brian Tierney,Ruth Aydt,Dan Gunter,et al.A Grid monitoring Architecture,Global Grid Forum Working Draft.
    [26]庞丽萍,董兴昌,邹德清,金海.基于UDDI的两级网格服务注册系统.计算机工程与科学,2004,26(11):80-8
    [27]Thomas Sandholm,Jarek Gawor.Globus Toolkit 3 Core-A Grid Service container Framework,July 2003.http://www-unix.gobus.org/toolkit/3.0/ogsa/docs/gt3_core.pdf
    [28]陈昕.基于开放网格服务架构的网格Portal的研究和设计(硕士论文).May 2003.
    [29]S Gullapalli,K Czajkowski,C kesselman.Grid Notification Frame.Globus Grid Forum Draft,2001.
    [30]R.Butler,D.Engert,I.Foster,C.Kesselman,S.Tuecke,J.Volmer,V.Welch.A National-Scale Authentication Infrastructure.IEEE Computer,33(12):60-66, 2000.
    [31]Gridftp.Available from http://www.globus.org/dataGrid/Gridftp.html
    [32]Index Service:http://www-unix.globus.org/toolkit/docs/3.2/infosvcs/ws/index.html
    [33]Steve Fisher.Relational Model for Information and Monitoring.http://www.ggfl.nl/abstracts/PERF/Relational/Model.pdf 2001-02.
    [34]Tienrey B.Aydt R.Gunter D.et al.A Grid Monitoring Architecture.In:Performance Working Group of Global Grid Forum 2002.
    [35]Baker M.Ong H.Smith G.A Prototype Grid-site Monitoring System.http://homer.csm.port.ac.uk/publications/technical/reports/Grid/DSGmonitoringpdf/
    [36]T.Finin,R.Frichard,D.McKay,R.McEntire.KQML as an Agent Communication Language[C].In:Proceedings of the Third International Conference on information and Knowledge Management(CIKM'94):ACM Press,1994:1-8.
    [37]I Foster,C Kesselman,S Tuecke.The Anatomy of the Grid:Enabling Scalable Virtual Organizations[J].International Journal of Supercomputer Applications,2001,15(3):1-24.
    [38]D.Beckett and B.McBride.RDF/XML Syntax Specification(Revised).W3C Recommandation,http://www.w3.orgr/TR/rdf-syntax-grammar,2004.
    [39]X.Zhang and J.Schopf.Performance Analysis of the Globus Toolkit Monitoring and Discovery Service[C].Proceedings of the International Workshop on Middleware Performance(MP 2004),2004.
    [40]I.Foster,J.Frey,S.Graham et al.Modeling Stateful Resources in Web Services.http://www-106.ibm.com/developerworks/library/WS-Resource/ws-modelingres ources.pdf,2004.
    [41]F.Bellifemine,G.Caire,A.Poggi and G.Rimassa.JADE:A White Paper.http://jade.cselt.it/papers/2003/WhitePaperJADEEXP.pdf,2003.
    [42]田鸣华.网格环境下资源监控系统的研究与实现[D].湖南:国防科技大学,2005.
    [43]B.Tierney,R.Aydt,D.Gunter et al.A Grid Monitoring Architecture.http://www-didc.lbl.gov/GGF-PERF/GMA-WG/papers/GWD-GP-16-2.pdf,2002.
    [44]J.Schopf.Distributed Monitoring and Information Services for the Grid. http://www.mcs.anl.gov/schopf/Talks/mds4-bath-septO5.ppt,2005.
    [45]M.A.Baker,G.C.Smith.GridRM:an extensible resource monitoring system [C].In:Proceedings of the IEEE International Cluster Computing Conference,2003:207-214.
    [46]A.Hawkeye.Monitoring and Management Tool for Distributed Systems.http://www.cs.wisc.edu/condor/hawkeve,2003.
    [47]Z.Balaton,G.Gombas.Resource and job monitoring in the grid[C].In:Proceedings of the Ninth International Euro-Par Conference,vol.2790 of Lecture Notes in Computer Science[C].Austria:Springer-Verlag,Klagenfurt,2003:404-411.
    [48]B.Tienrey,D.Gunter.NetLogger:a toolkit for distributed system performance tuning and debugging[C],In:Proceedings of the IFIP/IEEE Eighth Intenrational Symposium on Integrated Network Management(IM 2003),vol.246 of IFIP Conference Proceedings.Kluwer,2003:97-100.
    [49]R.Wolski,N.Spring,J.Hayes.The network weather service:a distributed resource performance forecasting service for metacomputing[J].Jounral of Future Generation Computer System,1999,15(5/6):757-768.
    [50]Joshy Joseph,Craig Fellenstein.Grid Computing.清华大学出版社,2005,196-213

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700