网格环境下信息服务与任务调度的仿真
|
摘要
网格是构筑在互联网上的一组新兴技术，可以为人们提供更多的资源、功能和交互性。传统互联网实现了计算机硬件的连通，Web实现了网页的连通，而网格试图实现互联网上所有资源的全面连通。它要把整个互联网整合成一台巨大的超级计算机，实现计算资源、存储资源、通信资源、软件资源、信息资源、知识资源的全面共享。
信息服务和任务调度是网格计算的关键技术之一，信息服务的作用是管理网格计算环境中各种资源的信息，任务调度的作用是根据当前系统的负载情况，对系统内的任务进行调度，提高系统的运行效率。一旦得到相关的资源信息，下一步就是调度要在这些资源上运行的任务。
本文在普通任务调度算法的基础上提出了近视眼任务调度算法，并对近视眼任务调度算法进行仿真实现和性能分析。在仿真实现过程中采用面向对象技术进行系统需求、分析、设计和实现，采用UML作为建模语言。整个仿真系统对近视眼任务调度算法进行了有效地分析，并且系统结构清晰，易于维护。
Grid computing is a group of new technology based on Internet, and it can provides more resources, function and inter-operation for people. Traditional internet realized the communication of computer hardware, and Web realized the communication of Home Page, and grid computing try to realize the communication of all resources on Internet, Grid computing think to merge all Internet into a super computer, and realize the share of computing resource, storage resource, communication resource, software resource, information resource and knowledge resource.
Information service and task schedule is one of the most important techniques in grid computing. The function of information service is to manage information of all resources in grid environment, and the function of task schedule is to schedule the tasks according to the balance of system and to improve the efficiency of system. As soon as the resource information has been gotten, the next is to schedule the tasks that should be running on these resources.
In this paper, myopic task schedule algorithm has been developed based on original task schedule algorithm, and its behavior has been simulated and its efficiency has been analyzed. Object-Oriented technique has been adopted to analyze, design and realize the simulation system, and UML has been adopted as modeling language. The simulation system has analyzed myopic task schedule algorithm efficiently, and this system's structure is legible to read and easy to maintain.
信息服务和任务调度是网格计算的关键技术之一，信息服务的作用是管理网格计算环境中各种资源的信息，任务调度的作用是根据当前系统的负载情况，对系统内的任务进行调度，提高系统的运行效率。一旦得到相关的资源信息，下一步就是调度要在这些资源上运行的任务。
本文在普通任务调度算法的基础上提出了近视眼任务调度算法，并对近视眼任务调度算法进行仿真实现和性能分析。在仿真实现过程中采用面向对象技术进行系统需求、分析、设计和实现，采用UML作为建模语言。整个仿真系统对近视眼任务调度算法进行了有效地分析，并且系统结构清晰，易于维护。
Grid computing is a group of new technology based on Internet, and it can provides more resources, function and inter-operation for people. Traditional internet realized the communication of computer hardware, and Web realized the communication of Home Page, and grid computing try to realize the communication of all resources on Internet, Grid computing think to merge all Internet into a super computer, and realize the share of computing resource, storage resource, communication resource, software resource, information resource and knowledge resource.
Information service and task schedule is one of the most important techniques in grid computing. The function of information service is to manage information of all resources in grid environment, and the function of task schedule is to schedule the tasks according to the balance of system and to improve the efficiency of system. As soon as the resource information has been gotten, the next is to schedule the tasks that should be running on these resources.
In this paper, myopic task schedule algorithm has been developed based on original task schedule algorithm, and its behavior has been simulated and its efficiency has been analyzed. Object-Oriented technique has been adopted to analyze, design and realize the simulation system, and UML has been adopted as modeling language. The simulation system has analyzed myopic task schedule algorithm efficiently, and this system's structure is legible to read and easy to maintain.
引文
[1] 都志辉，陈渝，刘鹏．网格计算．北京：清华大学出版社．2002
[2] Bruce EcheI．Java编程思想．北京：机械工业出版社．2002
[3] I. Foster, C. Kesselman, S. Tuecke. The Anatomy of the Grid. International J. Supercomputer Applications. 2001
[4] I. Foster, C. Kesselman, J. Nick, S. Tuecke. The Physiology of the Grid. Global Grid Forum. 2002
[5] Karl Czajkowski, Ian Foster, Nicholas Karonis, Carl Kesselman,Stuart Martin, Warren Smith, Steven Tuecke.A Resource Management Architecture for Metacomputing Systems.pdf
[6] Carl Kesselman, Ian Foster, Klara Nahrstedt.A Distributed Resource Management Architecture that Supports Advance Reservations and Co-Allocation.pdf
[7] http://www.cactuscode.org/Presentations
[9] http://mkp.com/grids/
[10] Thomas Dramlitsch,Supporting Efficient Execution inHeterogeneous Distributed Computing Envirments with Catus and Globus,2001
[11] http://www.gridforum.org
[12] http://www.ccgrid.org
[13] http://www.gridhome.com.cn
[14] http://www.globus.org
[15] Gregor von Laszewski and lan Foster,Mathematics and Computer Science Division,Argonne National Laboratory, Argonne,Usage of LDAP in Globus.pdf
[16] Karl Czajkowski, Ian Foster, Carl Kesselman. Resource Co-Allocation in Computational Grids.pdf
[17] Warren Smith, Ian Foster, Valerie Taylory.Scheduling with Advanced Reservations.pdf
[18] Karl Czajkowskiy,Steven Fitzgerald, Ian Foster, Carl Kesselmany.Grid Information Services for Distributed Resource Sharing.pdf
[19] Donald McMullen,Randall Bramley, et al Xport Collaboratory for X-ray Cryatallography, http://www.iumsc, Indiana.edu/Xport/xport demo talk.pkf
[20] http://www.globus.org/cog/
[21] Science Portals Project, http://www.extreme.indiana.edu/an/
[22] The DOE Common Component Architecture Project,http://www.extreme.indiana.edu/～gannon/cca report.html
[23] The Common Component Architecture Toolkit Project, http://www.extreme.indiana.edu/ccat/
[24] The XCAT Project, http://www.extreme.indiana.edu/xcat/
[25] SF-Express Application, http://www.globus.org/research/applications/sfexpress.html
[26] HPSS World Wide Web Site, http://www.sdsc.edu/hpss/
[27] http://go4.163.com/xxys/ycyl/ycyl.htm
[28] http://www.netdoctor.com.cn/telemed/index.php?ps operate=showarticle
[29] http://www.imageing-nsmc.com.cn/telmedicine/tel.htm
[30] http://www.netdoctor.com.cn/telemed/indes.php
[31] http://www.escience.cam.ac.uk/projects/telemed.html
[32] I. Foster and C. Kesselman. The Grid: Blueprint for a New Computing Infrastructure. San Fransisco, CA: Morgan Kaufmann, 1999
[34] W.Allcock,A.Chervenak, I.Foster, C.Desselman,C.Salisbury, S.Tuecke.The Data Grid:Towards an Architecture for the Distributed Management and Analysis of Large Scientific Datasets.Journal of Network and Computer Applications,2001
[35] Jason Leigh,Thomas A.DeFanti,Andrew E.Johnson,Maxine D.Brown,and Daniel J.Sandin,Global Tele-Immersion:Better Than Being There,appeared in proceedings of 7th International Conference on Artificial Reality and Tele-Existence.Tokyo,Japan,Dec3-5,1997
[36] Johnson.A.E,Leigh.J,and DeFanti.T.Multi-Disciplinary EXPERIENCES with CAVERNsoft Tele-Immersive Applications. Proc.of Fourth International Conference on Virtual System and Multimedia,November 1998
[37] 吴际，金茂中．UML面向对象分析．北京航空航天大学出版社．2001
[38] 冯玉琳，黄涛．网络分布式计算和软件工程．科学出版社．2003
[39] 周之英．现代软件工程(上)．科学出版社．2001
[40] 周之英．现代软件工程(中)．科学出版社．2001
[41] 周之英．现代软件工程(下)．科学出版社．2001
[42] Lethbridge．T．C，张红光．面向对象软件工程．机械工业出版社．2003
[43] 伯格．Java与分布式系统．机械工业出版社．2003
[44] 里德，郭旭．JAVA与UML协同应用开发．清华大学出版社．2003
[45] 克罗恩克．数据库处理．基础、设计与实现．电子工业出版社．2003
[46] www.51cmm.com
[47] www.csdn.net
[48] www.chinajavaworld.com
[49] Brian Knight，李明，欧刚宁．SQL Server 2000高级DBA指南．清华大学出版社．2003
[50] 王庆建，董征宇．SQL Server 2000数据库管理与开发．电子工业出版社．2003
[51] Sterens，Pooley，包晓露，赵晓玲．使用UML——关于对象和组件软件工程．人民邮电出版社．2003
[2] Bruce EcheI．Java编程思想．北京：机械工业出版社．2002
[3] I. Foster, C. Kesselman, S. Tuecke. The Anatomy of the Grid. International J. Supercomputer Applications. 2001
[4] I. Foster, C. Kesselman, J. Nick, S. Tuecke. The Physiology of the Grid. Global Grid Forum. 2002
[5] Karl Czajkowski, Ian Foster, Nicholas Karonis, Carl Kesselman,Stuart Martin, Warren Smith, Steven Tuecke.A Resource Management Architecture for Metacomputing Systems.pdf
[6] Carl Kesselman, Ian Foster, Klara Nahrstedt.A Distributed Resource Management Architecture that Supports Advance Reservations and Co-Allocation.pdf
[7] http://www.cactuscode.org/Presentations
[9] http://mkp.com/grids/
[10] Thomas Dramlitsch,Supporting Efficient Execution inHeterogeneous Distributed Computing Envirments with Catus and Globus,2001
[11] http://www.gridforum.org
[12] http://www.ccgrid.org
[13] http://www.gridhome.com.cn
[14] http://www.globus.org
[15] Gregor von Laszewski and lan Foster,Mathematics and Computer Science Division,Argonne National Laboratory, Argonne,Usage of LDAP in Globus.pdf
[16] Karl Czajkowski, Ian Foster, Carl Kesselman. Resource Co-Allocation in Computational Grids.pdf
[17] Warren Smith, Ian Foster, Valerie Taylory.Scheduling with Advanced Reservations.pdf
[18] Karl Czajkowskiy,Steven Fitzgerald, Ian Foster, Carl Kesselmany.Grid Information Services for Distributed Resource Sharing.pdf
[19] Donald McMullen,Randall Bramley, et al Xport Collaboratory for X-ray Cryatallography, http://www.iumsc, Indiana.edu/Xport/xport demo talk.pkf
[20] http://www.globus.org/cog/
[21] Science Portals Project, http://www.extreme.indiana.edu/an/
[22] The DOE Common Component Architecture Project,http://www.extreme.indiana.edu/～gannon/cca report.html
[23] The Common Component Architecture Toolkit Project, http://www.extreme.indiana.edu/ccat/
[24] The XCAT Project, http://www.extreme.indiana.edu/xcat/
[25] SF-Express Application, http://www.globus.org/research/applications/sfexpress.html
[26] HPSS World Wide Web Site, http://www.sdsc.edu/hpss/
[27] http://go4.163.com/xxys/ycyl/ycyl.htm
[28] http://www.netdoctor.com.cn/telemed/index.php?ps operate=showarticle
[29] http://www.imageing-nsmc.com.cn/telmedicine/tel.htm
[30] http://www.netdoctor.com.cn/telemed/indes.php
[31] http://www.escience.cam.ac.uk/projects/telemed.html
[32] I. Foster and C. Kesselman. The Grid: Blueprint for a New Computing Infrastructure. San Fransisco, CA: Morgan Kaufmann, 1999
[34] W.Allcock,A.Chervenak, I.Foster, C.Desselman,C.Salisbury, S.Tuecke.The Data Grid:Towards an Architecture for the Distributed Management and Analysis of Large Scientific Datasets.Journal of Network and Computer Applications,2001
[35] Jason Leigh,Thomas A.DeFanti,Andrew E.Johnson,Maxine D.Brown,and Daniel J.Sandin,Global Tele-Immersion:Better Than Being There,appeared in proceedings of 7th International Conference on Artificial Reality and Tele-Existence.Tokyo,Japan,Dec3-5,1997
[36] Johnson.A.E,Leigh.J,and DeFanti.T.Multi-Disciplinary EXPERIENCES with CAVERNsoft Tele-Immersive Applications. Proc.of Fourth International Conference on Virtual System and Multimedia,November 1998
[37] 吴际，金茂中．UML面向对象分析．北京航空航天大学出版社．2001
[38] 冯玉琳，黄涛．网络分布式计算和软件工程．科学出版社．2003
[39] 周之英．现代软件工程(上)．科学出版社．2001
[40] 周之英．现代软件工程(中)．科学出版社．2001
[41] 周之英．现代软件工程(下)．科学出版社．2001
[42] Lethbridge．T．C，张红光．面向对象软件工程．机械工业出版社．2003
[43] 伯格．Java与分布式系统．机械工业出版社．2003
[44] 里德，郭旭．JAVA与UML协同应用开发．清华大学出版社．2003
[45] 克罗恩克．数据库处理．基础、设计与实现．电子工业出版社．2003
[46] www.51cmm.com
[47] www.csdn.net
[48] www.chinajavaworld.com
[49] Brian Knight，李明，欧刚宁．SQL Server 2000高级DBA指南．清华大学出版社．2003
[50] 王庆建，董征宇．SQL Server 2000数据库管理与开发．电子工业出版社．2003
[51] Sterens，Pooley，包晓露，赵晓玲．使用UML——关于对象和组件软件工程．人民邮电出版社．2003