其他知识库

平方公里阵望远镜(SKA)即将开始建设,各子工作包也将进入关键设计评估阶段。基于云与容器技术是当前SKA科学数据处理器(SDP)未来可能采用的平台技术。本文针对SDP超大规模海量数据处理中所面临的天文应用软件快速部署、运行与实测要求,充分考虑了天文应用软件运行环境复杂,云计算环境下超大规模计算集群部署困难等问题,系统研究并给出了一种使用Docker技术的天文应用软件通用自动部署方法,论文以目前较为常用的可见度函数校准软件SAGECaL为例,首先分析了SAGECaL的相关特性和分布式部署方面存在的困难,进而给出了基于Docker容器技术的SAGECaL分布式集群的自动部署方法。实验结果表明,本文所提出的自动部署方法极大地提高了SAGECaL分布式集群的部署效率,满足了项目组承担SKA-SDP相关测试工作中所需要的基础平台部署与切换等需求。同时,本工作也为其它天文软件在云端的快速部署与执行提供了有益的思路。 

The Square Kilometer Array(SKA) is under construction. And each sub-work package will also enter the critical design evaluation phase. The cloud-based and container-based technologies are the platform  technologies that SKA Scientific Data Processor (SDP) may adopt in the future. This paper is aimed at the rapid deployment, operation and measurement requirements of astronomical application software faced by SDP ultra-large-scale massive data processing. It fully considers the complex operation environment of astronomical application software and the difficulty in deploying ultra-large-scale computing clusters in cloud computing environment. For this reason, a general automatic deployment method for astronomical application using Docker technology is systematically studied and presented. The paper takes SAGECaL, a calibration software commonly used for visibility function as an example.Firstly, the characteristics of SAGECaL and the difficulties in distributed deployment are analyzed. The automatic deployment method of SAGECaL distributed cluster based on Docker container technology is given. The experimental results show that the automatic deployment method proposed in this paper greatly improves the deployment efficiency of SAGECaL distributed cluster, and meets the needs of the
project team to undertake the deployment and switching of the basic platform required for SKA-SDP related testing. At the same time, this work also provides useful ideas for the rapid deployment and implementation of other astronomical software in the cloud.