大规模在线实训环境下的快速容器并发启动研究
Research on Container Concurrent Initiation under Large-Scale Online Training Environment
DOI: 10.12677/CSA.2021.111012, PDF,    国家自然科学基金支持
作者: 毕枫林*, 田春岐, 唐 骏：同济大学，电子与信息工程学院，上海；王 伟#：华东师范大学，数据科学与工程学院，上海
关键词: Docker；虚拟化技术；并发；容器；通信方式；Docker； Virtualization Technology； Concurrent； Container； Communication Mode
摘要: 随着在线教育业务的快速增长，需要越来越多的技术来支撑在线教育的不同场景。本文进行了在大规模在线实训环境下的虚拟化技术的可行性探索，得出了容器技术符合在线实训环境的需求的结果，并且得出以下结论：1) 确定数学模型来选择与Docker通信的最佳方式；2) 对大规模在线实训环境下的容器并发启动场景进行了研究，总结出了CPU是影响容器并发启动时延的主要因素；3) 容器镜像大小对容器并发启动影响较小；4) 容器并发启动性能消耗主要阶段在容器启动阶段。
Abstract: With the rapid growth of online education, more and more technologies are needed to support different scenarios of online education. This paper explores the feasibility of virtualization technology in large-scale online training environment, and concludes that container technology meets the requirements of online training environment. The following conclusions are drawn: 1) the mathematical model is determined to choose the best way of communication with Docker; 2) the container concurrent startup scenario under large-scale online training environment is studied, and it is concluded that CPU is the main factor affecting the container concurrent startup delay; 3) the container image size has little influence on the container concurrent startup; 4) the container concurrent startup performance consumption is mainly in the container startup stage.
文章引用：毕枫林, 田春岐, 王伟, 唐骏. 大规模在线实训环境下的快速容器并发启动研究[J]. 计算机科学与应用, 2021, 11(1): 101-112. https://doi.org/10.12677/CSA.2021.111012

参考文献

[1] Docker, M.D. (2014) Lightweight Linux Containers for Consistent Development and Deployment. Linux Journal, 2014, Article No. 2.
[2] Akkus, I.E., Chen, R., Rimac, I., et al. (2018) SAND: Towards High-Performance Serverless Com-puting. 2018 USENIX Annual Technical Conference, Boston, 11-13 July 2018, 923-935.
[3] Xu, Y., Mahendran, V. and Radhakrishnan, S. (2016) SDN Docker: Enabling Application Auto-Docking/Undocking in Edge Switch. 2016 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), San Francisco, 10-14 April 2016, 864-869. [Google Scholar] [CrossRef] 
[4] Azab, A. (2017) Enabling Docker Containers for High-Performance and Many-Task Computing. 2017 IEEE International Conference on Cloud Engineering, Vancouver, 4-7 April 2017, 279-285. [Google Scholar] [CrossRef] 
[5] Kovács, Á. (2017) Comparison of Different Linux Containers. 2017 40th International Conference on Telecommunications and Signal Processing (TSP), Barcelona, 5-7 July 2017, 47-51. [Google Scholar] [CrossRef] 
[6] Bernstein, D. (2014) Containers and Cloud: From LXC to Docker to Kubernetes. IEEE Cloud Computing, 1, 81-84. [Google Scholar] [CrossRef] 
[7] Paolino, M., Hanmayun, M.M. and Raho, D. (2014) A Performance Analysis of ARM Virtual Machines Secured Using Selinux. Cyber Security and Privacy Forum, Springer, Cham, 28-36.
[8] Kratzke, N. (2014) A Lightweight Virtualization Cluster Reference Architecture Derived from Open Source PaaS Platforms. Open Journal of Mobile Computing and Cloud Computing, 1, 17-30. [Google Scholar] [CrossRef] 
[9] Madhavapeddy, A., Mortier, R., Rotsos, C., et al. (2013) Unikernels: Library Operating Systems for the Cloud. ACM SIGARCH Computer Architecture News, 41, 461-472. [Google Scholar] [CrossRef] 
[10] Eiras, R.S.V., Couto, R.S. and Rubinstein, M.G. (2016) Perfor-mance Evaluation of a Virtualized HTTP Proxy in KVM and Docker. 2016 7th International Conference on the Network of the Future (NOF), Buzios, 16-18 November 2016, 1-5. [Google Scholar] [CrossRef] 
[11] Joy, A.M. (2015) Performance Comparison between Linux Containers and Virtual Machines. International Conference on Advances in Computer Engineering and Applications, Ghaziabad, 19-20 March 2015, 342-346. [Google Scholar] [CrossRef] 
[12] Seo, K.-T., Hwang, H.-S., Moon, I.-Y., Kwon, O.-Y. and Kim, B.-J. (2014) Performance Comparison Analysis of Linux Container and Virtual Machine for Building Cloud. Ad-vanced Science and Technology Letters, 66, 105-111. [Google Scholar] [CrossRef] 
[13] Xavier, B. and Jersak, L. (2016) Time Provisioning Evaluation of KVM, Docker and Unikernels in a Cloud Platform. 2016 16th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid), Cartagena, 16-19 May 2016, 277-280. [Google Scholar] [CrossRef] 
[14] Oakes, E., Yang, L., Zhou, D., Houck, K., Harter, T., Arpaci-Dusseau, A. and Arpaci-Dusseau, R. (2018) SOCK: Rapid Task Provisioning with Serverless-Optimized Con-tainers. USENIX Annual Technical Conference, Boston, 11-13 July 2018, 57-70.
https://www.usenix.org/conference/atc18/presentation/oakes
[15] Harter, T., Salmon, B., Liu, R., Arpaci-Dusseau, A.C. and Arpaci-Dusseau, R.H. (2016) Slacker: Fast Distribution with Lazy Docker Containers. Proceedings of the 14th Usenix Conference on File and Storage Technologies, Santa Clara, 22-25 February 2016. 181-195.
https://www.usenix.org/conference/fast16/technical-sessions/presentation/harter
[16] Rizki, R., Rakhmatsyah, A. and Nugroho, M.A. (2016) Performance Analysis of Container-Based Hadoop Cluster: OpenVZ and LXC. 2016 4th In-ternational Conference on Information and Communication Technology, Bandung, 25-27 May 2016, 1-4. [Google Scholar] [CrossRef] 
[17] Felter, W., Ferreira, A., Rajamony, R. and Rubio, J. (2015) An Updated Performance Comparison of Virtual Machines and Linux Containers. 2015 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), Philadelphia, 29-31 March 2015, 171-172. [Google Scholar] [CrossRef] 
[18] Xie, B., Sun, G. and Ma, G. (2017) Docker Based Overlay Network Performance Evaluation in Large Scale Streaming System. Proceedings of 2016 IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, Xi’an, 3-5 October 2016, 366-369. [Google Scholar] [CrossRef] 
[19] 李巍, 赵永彬, 王鸥, 等. 基于Macvlan的Docker容器网络架构研究[J]. 机械设计与制造, 2017(5): 270-272.
[20] 王志伟, 杨超. 基于流量控制的Docker容器网络带宽控制机制[J]. 计算机应用, 2019(12): 3628-3632.
[21] 张礼庆, 郭栋, 吴绍岭, 等. 一种最大化内存共享与最小化运行时环境的超轻量级容器[J]. 计算机研究与发展, 2019, 56(7): 1545-1555.
[22] 张可颖, 彭丽苹, 吕晓丹, 等. 开源云上的Kubernetes弹性调度[J]. 计算机技术与发展, 2019, 29(2): 109-114.
[23] 谢晓兰, 张征征, 王建伟, 等. 基于三次指数平滑法和时间卷积网络的云资源预测模型[J]. 通信学报, 2019, 40(8): 143-150.
[24] Paraiso, F., Chal-lita, S., Al-Dhuraibi, Y., et al. (2016) Model-Driven Management of Docker Containers. 2016 IEEE 9th International Conference on cloud Computing (CLOUD), San Francisco, 27 June-2 July 2016, 718-725. [Google Scholar] [CrossRef] 
[25] Smith, S. (2015) On-Demand Activation of Docker Containers with System.
https://blog.developer.atlassian.com/docker-systemd-socket-activation
[26] https://docs.docker.com/engine/api/v1.38/#operation/ImageList
[27] https://hub.docker.com