一种大规模容器镜像分发加速模型及其实现方法
A Large-Scale Container Image Distribution Acceleration Model and its Implementation Method
DOI: 10.12677/CSA.2020.1012237, PDF,   
作者: 潘 瑭：同济大学，电子与信息工程学院，上海
关键词: 容器；Docker；镜像分发；传输加速；Container； Docker； Image Distribution； Transportation Acceleration
摘要: 云计算逐渐成为一种主流的基础服务，容器由于其轻便型是目前云计算之中最常使用的一种虚拟化抽象。基于镜像这样的模板容器可以迅速部署应用在云服务器上。然而现有的容器引擎在大规模镜像分发时容器会产生冷启动时间过长的问题。本文分析并验证了影响Docker容器冷启动的关键因素，提出了一种大规模容器镜像分发加速模型。通过以文件为粒度的延迟加载，以及按使用顺序的文件分层，加快了镜像的传输速度，进而加速容器启动。基于该模型，实现了镜像分发系统D4C (Doing Deft Distribution of Docker Container)。并从容器冷启动时间、启动镜像大小、网络传输量三个方面进行测试，验证了D4C在这几个方面的优势。
Abstract: Cloud computing has gradually become a mainstream basic service, and containers are currently the most commonly used virtualization abstraction in cloud computing due to their lightness. Based on such template containers, applications can be quickly deployed on cloud servers. However, the existing container engine will have a long cold start time when the container is expanded and distributed. The key factors affecting the cold start of Docker containers are analyzed and verified here, and an expanded container stack acceleration model is proposed. By taking the file as the model, the distributed system D4C (Deft distribution to Docker containers) is realized. Tests were conducted in terms of container cold start time, boot image size, and network transmission volume to verify the advantages of D4C in these aspects.
文章引用：潘瑭. 一种大规模容器镜像分发加速模型及其实现方法[J]. 计算机科学与应用, 2020, 10(12): 2257-2269. https://doi.org/10.12677/CSA.2020.1012237

参考文献

[1] Sharma, P., Chaufournier, L., Shenoy, P., et al. (2016) Containers and Virtual Machines at Scale: A Comparative Study. In: Proceedings of the 17th International Middleware Conference, ACM, Article No. 1. [Google Scholar] [CrossRef] 
[2] Merkel, D. (2014) Docker: Lightweight Linux Containers for Con-sistent Development and Deployment. Linux Journal, 239, 2.
[3] Harter, T., Salmon, B., Liu, R., et al. (2016) Slacker: Fast Distribution with Lazy Docker Containers. 14th USENIX Conference on File and Storage Technologies (FAST’16), Santa Clara, 22-25 February 2016, 181-195.
[4] Burns, B., Grant, B., Oppenheimer, D., et al. (2016) Borg, Omega, and Kubernetes: Lessons Learned from Three Container-Management Systems over a Decade. Queue, 14, No. 1. [Google Scholar] [CrossRef] 
[5] Reich, J., Laadan, O., Brosh, E., et al. (2012) VMTorrent: Scalable P2P Virtual Machine Streaming. CoNEXT, 12, 289-300. [Google Scholar] [CrossRef] 
[6] Chowdhury, M., Zaharia, M., Ma, J., et al. (2011) Managing Data Transfers in Computer Clusters with Orchestra. ACM SIGCOMM Computer Communication Review, 41, 98-109. [Google Scholar] [CrossRef] 
[7] Wang, K.J., Yang, Y., Li, Y., et al. (2017) FID: A Faster Image Distribution System for Docker Platform. 2017 IEEE 2nd International Workshops on Foundations and Applications of Self* Systems (FAS* W), Tucson, 18-22 September 2017, 191-198. [Google Scholar] [CrossRef] 
[8] Nathan, S., Ghosh, R., Mukherjee, T., et al. (2017) CoMICon: A Co-Operative Management System for Docker Container Images. 2017 IEEE International Conference on Cloud Engi-neering (IC2E), Vancouver, 4-7 April 2017, 116-126. [Google Scholar] [CrossRef] 
[9] Liang, M., Shen, S., Li, D., et al. (2016) HDID: An Efficient Hybrid Docker Image Distribution System for Datacenters. In: Zhang, L. and Xu, C., Eds., Software Engineering and Method-ology for Emerging Domains. NASAC 2016. Communications in Computer and Information Science, Vol. 675, Springer, Singapore, 179-194. [Google Scholar] [CrossRef] 
[10] Tarasov, V., Rupprecht, L., Skourtis, D., et al. (2017) In Search of the Ideal Storage Configuration for Docker Containers. 2017 IEEE 2nd International Workshops on Founda-tions and Applications of Self* Systems (FAS* W), Tucson, 18-22 September 2017, 199-206. [Google Scholar] [CrossRef] 
[11] Nguyen, T.L., Nou, R. and Lebre, A. (2019) YOLO: Speeding up VM and Docker Boot Time by Reducing I/O Operations. In: Yahyapour, R., Ed., Euro-Par 2019: Parallel Processing. Euro-Par 2019. Lecture Notes in Computer Science, Vol 11725, Springer, Cham, 273-287. [Google Scholar] [CrossRef] 
[12] Hardi, N., Blomer, J., Ganis, G. and Popescu, R. (2018) Making Containers Lazy with Docker and CernVM-FS. Journal of Physics: Conference Series, 1085, 032019. [Google Scholar] [CrossRef] 
[13] Cheng, Y., Gupta, A. and Butt, A.R. (2015) An In-Memory Object Caching Framework with Adaptive Load Balancing. In: Proceedings of the Tenth European Confer-ence on Computer Systems, ACM, Article No. 4. [Google Scholar] [CrossRef] 
[14] Anwar, A., Cheng, Y., Gupta, A., et al. (2015) Taming the Cloud Object Storage with Mos. In: Proceedings of the 10th Parallel Data Storage Workshop, ACM, 7-12. [Google Scholar] [CrossRef] 
[15] Butt, A.R., Gniady, C. and Hu, Y.C. (2005) The Performance Im-pact of Kernel Prefetching on Buffer Cache Replacement Algorithms. ACM SIGMETRICS Performance Evaluation Re-view, 33, 157-168. [Google Scholar] [CrossRef] 
[16] Cao, P., Felten, E.W., Karlin, A.R., et al. (1996) Implementation and Performance of Integrated Application-Controlled File Caching, Prefetching, and Disk Scheduling. ACM Transac-tions on Computer Systems (TOCS), 14, 311-343. [Google Scholar] [CrossRef] 
[17] De, P., Gupta, M., Soni, M., et al. (2012) Caching VM Instances for Fast VM Provisioning: A Comparative Evaluation. European Conference on Parallel Processing. In: Kaklamanis, C., Pa-patheodorou, T. and Spirakis, P.G., Eds., Euro-Par 2012 Parallel Processing. Euro-Par 2012. Lecture Notes in Com-puter Science, Vol 7484, Springer, Berlin, Heidelberg, 325-336. [Google Scholar] [CrossRef] 
[18] Zhang, Z., Li, D. and Wu, K. (2016) Large-Scale Virtual Ma-chines Provisioning in Clouds: Challenges and Approaches. Frontiers of Computer Science, 10, 2-18. [Google Scholar] [CrossRef] 
[19] Razavi, K., Van Der Kolk, G. and Kielmann, T. (2015) Prebaked µVMs: Scalable, Instant VM Startup for IaaS Clouds. 2015 IEEE 35th International Conference on Distributed Compu-ting Systems, Columbus, 29 June-2 July, 245-255. [Google Scholar] [CrossRef] 
[20] Anwar, A., Mohamed, M., Tarasov, V., et al. (2018) Improving Docker Registry Design Based on Production Workload Analysis. 16th USENIX Conference on File and Storage Tech-nologies (FAST ’18), Oakland, February 2018, 265-278.
[21] Littley, M., Anwar, A., Fayyaz, H., et al. (2019) Bolt: Towards a Scalable Docker Registry via Hyperconvergence. 2019 IEEE 12th International Conference on Cloud Com-puting (CLOUD), Milan, 8-13 July 2019, 358-366. [Google Scholar] [CrossRef] 
[22] Du, L., Wo, T., Yang, R. and Hu, C.M. (2017) Cider: A Rapid Docker Container Deployment System through Sharing Network Storage. 2017 IEEE 19th International Conference on High Performance Computing and Communications; IEEE 15th International Conference on Smart City; IEEE 3rd In-ternational Conference on Data Science and Systems (HPCC/SmartCity/DSS), Bangkok, 18-20 December 2017, 332-339. [Google Scholar] [CrossRef] 
[23] Zheng, C., Rupprecht, L., Tarasov, V., et al. (2018) Wharf: Sharing Docker Images in a Distributed File System. In: Proceedings of the ACM Symposium on Cloud Compu-ting, ACM, 174-185. [Google Scholar] [CrossRef] 
[24] Thalheim, J., Bhatotia, P., Fonseca, P., et al. (2018) Cntr: Lightweight OS Containers. 2018 USENIX Annual Technical Conference (USENIXATC’18), Boston, 11-13 July 2018, 199-212.
[25] Zhao, N., Tarasov, V., Anwar, A., et al. (2019) Slimmer: Weight Loss Secrets for Docker Registries. 2019 IEEE 12th International Conference on Cloud Computing (CLOUD), Milan, 8-13 July 2019, 517-519. [Google Scholar] [CrossRef]