地震资料分布数据管理平台研究与实现
|
摘要
利用数据网格技术实现海量地震资料并行处理需要解决动态、自治、异构的高性能计算系统之间的分布数据管理问题。根据石油领域资源现状,将该领域高性能资源划分为不同的虚拟社区,并建立分布数据管理体系结构,详细描述元数据模型与副本定位算法等关键技术。实现并部署了基于Web portal的地震资料数据管理平台,系统运行稳定、可操作性强、可扩展性好。
Parallel processing of massive seismic data with data grid technology has to resolve distribute data management problem between dynamic,autonomous,heterogeneous high-performance computing systems.The high performance resources in petroleum industry are divided into different virtual communities according to the status quo of the resource characteristics.Distributed data management architecture is established as well.The key technologies including metadata model and replica location algorithm are expatiated.The Web portal-based seismic data management platform is implemented and deployed,the system runs stably,and has good operability and scalability.
Parallel processing of massive seismic data with data grid technology has to resolve distribute data management problem between dynamic,autonomous,heterogeneous high-performance computing systems.The high performance resources in petroleum industry are divided into different virtual communities according to the status quo of the resource characteristics.Distributed data management architecture is established as well.The key technologies including metadata model and replica location algorithm are expatiated.The Web portal-based seismic data management platform is implemented and deployed,the system runs stably,and has good operability and scalability.
引文
[1]张军华,仝兆岐.地震资料处理中的并行计算机技术[J].物探化探计算技术,2002,24(1):31-36.
[2]Ian Foster,Carl Kesselman.Globus:A Metacomputing InfrastructureToolkit[J].The International Journal of Supercomputer Applicationsand High Performance Computing,1997,11(2):115-128.
[3]Grimshaw A S,Natrajan A.Legion:Lessons Learned Building a GridOperating System[J].Proceedings of the IEEE,2005,93(3):589-603.
[4]Streit A,Erwin D,Lippert Th,et al.Unicore-From project results to pro-duction grids[M]//Advances in Parallel Computing:Grid Computingand New Frontiers of High Performance Processing.Elsevier Science2005,14:357-376.
[5]Keith Seymour,Asim YarKhan,Sudesh Agrawal,et al.NetSolve:GridEnabling Scientific Computing Environments[M]//Advances in Paral-lel Computing:Grid Computing and New Frontiers of High PerformanceProcessing.Elsevier Science 2005,14:33-51.
[6]William Allcock,John Bresnahan,Rajkumar Kettimuthu,et al.The Glo-bus Striped GridFTP Framework and Server[C]//SC’05:Proceedingsof the 2005 ACM/IEEE conference on Supercomputing.
[7]Ann Chervenak,Ewa Deelman,Ian Foster,et al.Giggle:A Frameworkfor Constructing Scalable Replica Location Services[C]//Proceedingsof the 2002 ACM/IEEE conference on Supercomputing.IEEE Comput-er Society Press,Los Alamitos,CA,USA,2002.
[8]Foster I.Globus Toolkit Version 4:Software for Service-Oriented Sys-tems[C]//IFIP International Conference on Network and ParallelComputing,Springer-Verlag LNCS 3779,2006:2-13.
[9]Siamak Hassanzadeh,Charles C Mosher,Calvin L Joyner.Scalable par-allel seismic processing[J].The Leading Edge,1996,15(12):1363-1366.
[10]周奇年,陈玲玲,李革.云计算与云数据管理[J].电信科学,2010,8A:57-61.
[11]Ian Foster,Carl Kesselman,Steven Tuecke.The anatomy of the grid:Enabling scalable virtual organizations[J].Int’l Journal of Supercom-puter Applications,2001,15(3):200-222.
[2]Ian Foster,Carl Kesselman.Globus:A Metacomputing InfrastructureToolkit[J].The International Journal of Supercomputer Applicationsand High Performance Computing,1997,11(2):115-128.
[3]Grimshaw A S,Natrajan A.Legion:Lessons Learned Building a GridOperating System[J].Proceedings of the IEEE,2005,93(3):589-603.
[4]Streit A,Erwin D,Lippert Th,et al.Unicore-From project results to pro-duction grids[M]//Advances in Parallel Computing:Grid Computingand New Frontiers of High Performance Processing.Elsevier Science2005,14:357-376.
[5]Keith Seymour,Asim YarKhan,Sudesh Agrawal,et al.NetSolve:GridEnabling Scientific Computing Environments[M]//Advances in Paral-lel Computing:Grid Computing and New Frontiers of High PerformanceProcessing.Elsevier Science 2005,14:33-51.
[6]William Allcock,John Bresnahan,Rajkumar Kettimuthu,et al.The Glo-bus Striped GridFTP Framework and Server[C]//SC’05:Proceedingsof the 2005 ACM/IEEE conference on Supercomputing.
[7]Ann Chervenak,Ewa Deelman,Ian Foster,et al.Giggle:A Frameworkfor Constructing Scalable Replica Location Services[C]//Proceedingsof the 2002 ACM/IEEE conference on Supercomputing.IEEE Comput-er Society Press,Los Alamitos,CA,USA,2002.
[8]Foster I.Globus Toolkit Version 4:Software for Service-Oriented Sys-tems[C]//IFIP International Conference on Network and ParallelComputing,Springer-Verlag LNCS 3779,2006:2-13.
[9]Siamak Hassanzadeh,Charles C Mosher,Calvin L Joyner.Scalable par-allel seismic processing[J].The Leading Edge,1996,15(12):1363-1366.
[10]周奇年,陈玲玲,李革.云计算与云数据管理[J].电信科学,2010,8A:57-61.
[11]Ian Foster,Carl Kesselman,Steven Tuecke.The anatomy of the grid:Enabling scalable virtual organizations[J].Int’l Journal of Supercom-puter Applications,2001,15(3):200-222.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心