基于MPI的分布式数据处理系统
|
摘要
为简化江门中微子实验的离线数据处理流程,减少资源消耗,提出一种在分布式计算环境中进行数据处理的通用软件系统。基于信息传递接口实现节点间的通信与数据交换,使用Master/Worker架构对计算作业生命周期进行管理,包括计算作业拆分、计算资源分配以及计算任务执行与监控。测试结果表明,该系统具有良好的可扩展性,其产生的数据与人工逐步执行作业脚本运行模拟软件产生的数据一致。
In order to simplify the off-line data processing flow of Jiangmen Underground Neutrino Observation(JUNO) and reduce resource consumption,a general software system is proposed to process data in distributed computing environment.Based on Message Passing Interface(MPI),communication and data exchange between nodes are realized.Master/Worker architecture is used to manage the life cycle of computing jobs,including computing job splitting,computing resource allocation,computing task execution and monitoring.Test results show that the proposed system has good scalability,and the data generated by the system is consistent with the data generated by manual step-by-step execution of job scripts to run simulation software.
In order to simplify the off-line data processing flow of Jiangmen Underground Neutrino Observation(JUNO) and reduce resource consumption,a general software system is proposed to process data in distributed computing environment.Based on Message Passing Interface(MPI),communication and data exchange between nodes are realized.Master/Worker architecture is used to manage the life cycle of computing jobs,including computing job splitting,computing resource allocation,computing task execution and monitoring.Test results show that the proposed system has good scalability,and the data generated by the system is consistent with the data generated by manual step-by-step execution of job scripts to run simulation software.
引文
[1] DJURCIC Z,GUARINO V,CABRERA A,et al.JUNO conceptual design report[EB/OL].[2018-03-20].https://arxiv.org/vc/arxiv/papers/1508/1508.07166v1.pdf.
[2] AN Fengpeng,AN Guangpeng,AN Qi,et al.Neutrino physics with JUNO[J].Journal of Physics G:Nuclear and Particle Physics,2016,43(3):030401.
[3] WANG Zhimin.JUNO central detector and its prototyping[J].Journal of Physics:Conference Series,2016,718(6):062075.
[4] MOSCICKI J T.Diane-distributed analysis environment for grid-enabled simulation and analysis of physics data[C]//Proceedings of 2003 IEEE Nuclear Science Symposium.Washington D.C.,USA:IEEE Press,2003:1617-1620.
[5] ILCDirac for ILC users [EB/OL].[2018-03-20].http://flcwiki.desy.de/ILCDirac.
[6] HUANG Xingtao,LI Tao,ZOU Jiaheng,et al.Offline data processing software for the JUNO experiment[EB/OL].[2018-03-15].https://indico.cern.ch/event/432527/con tributions/1072223/con tribution.pdf.
[7] 李腾.江门中微子实验离线软件系统的设计与开发[D].济南:山东大学,2017.
[8] ZOU J H,HUANG Xiangjie,LI W D,et al.SNiPER:an offline software framework for non-collider physics experiments[J].Journal of Physics:Conference Series,2015,664(7):072053.
[9] LIN Tao,ZOU Jiaheng,LI Weidong,et al.The application of SNiPER to the JUNO simulation[J].Journal of Physics:Conference Series,2017,898(4):042029.
[10] LI Teng,XIA Xin,HUANG Xingtao,et al.Design and development of JUNO event data model[J].Chinese Physics C,2017,41(6):066201.
[11] CLARKE L,GLENDINNING I,HEMPEL R.The MPI message passing interface standard[M]//DECKER K M,REHMANN R M.Programming environments for massively parallel distributed systems.Berlin,Germany:Springer,1994:213-218.
[12] LUSK E,GROPP W.The MPI message-passing interface standard:overview and status[J].Advances in Parallel Computing,1995,10(6):265-269.
[13] GROPP W,LUSK E,DOSS N,et al.MPICH:a high-performance,portable implementation for the MPI message-passing interface[J].Parallel Computing,1998,22(6):789-828.
[14] 鄢锋,桂卫华,胡志坤,等.一种网络节点通信控制的心跳模型[J].信息与控制,2008,37(5):524-528.
[15] THAIN D,TANNENBAUM T,LIVNY M.Distributed computing in practice:the condor experience[J].Concurrency and Computation Practice and Experience,2005,17(2-4):323-356.
[2] AN Fengpeng,AN Guangpeng,AN Qi,et al.Neutrino physics with JUNO[J].Journal of Physics G:Nuclear and Particle Physics,2016,43(3):030401.
[3] WANG Zhimin.JUNO central detector and its prototyping[J].Journal of Physics:Conference Series,2016,718(6):062075.
[4] MOSCICKI J T.Diane-distributed analysis environment for grid-enabled simulation and analysis of physics data[C]//Proceedings of 2003 IEEE Nuclear Science Symposium.Washington D.C.,USA:IEEE Press,2003:1617-1620.
[5] ILCDirac for ILC users [EB/OL].[2018-03-20].http://flcwiki.desy.de/ILCDirac.
[6] HUANG Xingtao,LI Tao,ZOU Jiaheng,et al.Offline data processing software for the JUNO experiment[EB/OL].[2018-03-15].https://indico.cern.ch/event/432527/con tributions/1072223/con tribution.pdf.
[7] 李腾.江门中微子实验离线软件系统的设计与开发[D].济南:山东大学,2017.
[8] ZOU J H,HUANG Xiangjie,LI W D,et al.SNiPER:an offline software framework for non-collider physics experiments[J].Journal of Physics:Conference Series,2015,664(7):072053.
[9] LIN Tao,ZOU Jiaheng,LI Weidong,et al.The application of SNiPER to the JUNO simulation[J].Journal of Physics:Conference Series,2017,898(4):042029.
[10] LI Teng,XIA Xin,HUANG Xingtao,et al.Design and development of JUNO event data model[J].Chinese Physics C,2017,41(6):066201.
[11] CLARKE L,GLENDINNING I,HEMPEL R.The MPI message passing interface standard[M]//DECKER K M,REHMANN R M.Programming environments for massively parallel distributed systems.Berlin,Germany:Springer,1994:213-218.
[12] LUSK E,GROPP W.The MPI message-passing interface standard:overview and status[J].Advances in Parallel Computing,1995,10(6):265-269.
[13] GROPP W,LUSK E,DOSS N,et al.MPICH:a high-performance,portable implementation for the MPI message-passing interface[J].Parallel Computing,1998,22(6):789-828.
[14] 鄢锋,桂卫华,胡志坤,等.一种网络节点通信控制的心跳模型[J].信息与控制,2008,37(5):524-528.
[15] THAIN D,TANNENBAUM T,LIVNY M.Distributed computing in practice:the condor experience[J].Concurrency and Computation Practice and Experience,2005,17(2-4):323-356.