基于容器的脉冲星数据处理软件部署与测试  

Deployment and Testing of Pulsar Data Processing Software Based on Container

作　　者：冶鑫晨 张海龙[1,2,3,4] 王杰 张萌[1,2] 张亚州 王万琼[1] 李嘉 杜旭 Ye Xinchen;Zhang Hailong;Wang Jie;Zhang Meng;Zhang Yazhou;Wang Wanqiong;Li Jia;Du Xu(Xinjiang Astronomical Observatory,Chinese Academy of Sciences,Urumqi 830011,China;University of Chinese Academy of Sciences,Beijing 100049,China;Key Laboratory of Radio Astronomy,Chinese Academy of Sciences,Nanjing 210033,China;National Astronomical Data Center,Beijing 100101,China)

机构地区：[1]中国科学院新疆天文台,新疆乌鲁木齐830011 [2]中国科学院大学,北京100049 [3]中国科学院射电天文重点实验室,江苏南京210033 [4]国家天文科学数据中心,北京100101

出　　处：《天文研究与技术》2023年第2期154-164,共11页Astronomical Research & Technology

基　　金：国家重点研发计划(2021YFC2203502,2022YFF0711502);国家自然科学基金(12173077,12003062,11873082,11803080);新疆维吾尔自治区天山创新团队计划(2022D14020);中国科学院青年创新促进会;国家重点研发计划(2018YFA0404704);国家天文科学数据中心;中国科学院天文台站设备更新及重大仪器设备运行专项经费资助.

摘　　要：随着天文观测技术的飞速发展,天文数据处理软件日趋复杂,天文数据处理环境的部署与管理日渐繁琐。利用容器技术将脉冲星数据处理环境封装成容器镜像并建立私有镜像库,科研人员可以根据数据处理需求选择镜像,实现数据处理环境的快速部署。利用实体计算机、虚拟机和容器中对脉冲星基带数据进行相干消色散处理,对比不同平台的资源利用率与数据处理效率。实验结果表明,容器的性能与实体计算机相近;在多任务并发的数据处理测试中,容器的资源分配更加合理,相较虚拟机可以提高计算资源利用效率。在新疆天文台脉冲星数据处理服务器上实现了基于容器的数据处理架构部署,设计并开发了容器管理图形用户界面,通过优化多用户登录、身份验证、数据卷挂载管理等功能,提高利用容器技术进行天文数据处理的效率。With the rapid development of astronomical observation technology,astronomical data processing software has become increasingly complex,and it is challenging to deploy the software environment.Container technology is used for packaging the pulsar data processing environment to images by applying hierarchical encapsulation.According to the data processing requirements,a private library of images is established,and the users can select the images according to the data processing mode.The hardware environment,the traditional virtual machine environment,and the container environment perform coherent dedispersion for pulsar baseband data.The resource utilization and data processing efficiency of different platforms are compared.Experimental results show that the performance of the container is similar to the physical machine.In multi-threaded parallel processing,the resource allocation of the container is more reasonable and can improve the efficiency of service resource utilization.The container-based data processing architecture is implemented on Xinjiang Astronomical Observatory pulsar data processing server,and the container management graphical user interfaces are designed and developed.Through optimizing functions such as multi-user login,authentication and data volume mount,the efficiency of astronomical data processing using container technology is improved.

关 键 词：脉冲星 数据处理 容器 虚拟化 

分 类 号：P111.44[天文地球—天文学]