异构云计算平台业务迁移

doi:10.11959/j.issn.2096-3750.2020.00161

物联网学报 ›› 2020, Vol. 4 ›› Issue (4): 79-90.doi: 10.11959/j.issn.2096-3750.2020.00161

异构云计算平台业务迁移

魏峰¹,丁飞²(),焦鹏举¹,李杨¹,陈焱山¹,张登银²

¹ 中移（苏州）软件技术有限公司，江苏苏州 215000
² 南京邮电大学江苏省宽带无线通信和物联网重点实验室，江苏南京 210003

修回日期:2020-02-14 出版日期:2020-12-30 发布日期:2020-12-14
作者简介:魏峰（1989- ），男，山西汾阳人，中移（苏州）软件技术有限公司研发工程师，主要研究方向为OpenStack、迁移上云的设计和研发|丁飞（1981- ），男，江苏泰兴人，博士，南京邮电大学物联网学院副教授，主要研究方向为物联网与信息系统、异构网络融合技术、信息处理与大数据|焦鹏举（1989- ），男，河南汝州人，中移（苏州）软件技术有限公司研发工程师，主要研究方向为OpenStack、弹性计算、虚拟化、分布式存储的设计和开发|李杨（1985- ），女，内蒙古通辽人，中移（苏州）软件技术有限公司项目经理、高级信息系统项目管理师、中级通信工程师，主要研究方向为云平台建设和项目管理|陈焱山（1988- ），男，安徽太湖人，中移（苏州）软件技术有限公司研发工程师，主要研究方向为软件定义统一存储系统和数据备份开发|张登银（1964- ），男，江苏靖江人，博士，南京邮电大学物联网学院院长、研究员，主要研究方向为信息网络、智能信号处理、物联网与无线通信
基金资助:
教育部中国移动科研基金资助项目(MCM20170205);工业和信息化部通信软科学研究项目(2019-R-26);江苏省“六大人才高峰”资助项目(DZXX-008);南京邮电大学科研基金资助项目(NY217146);南京邮电大学科研基金资助项目(NY220028)

Service migration of heterogeneous cloud computing platform

Feng WEI¹,Fei DING²(),Pengju JIAO¹,Yang LI¹,Yanshan CHEN¹,Dengyin ZHANG²

¹ China Mobile (Suzhou) Software Technology Co.,Ltd.,Suzhou 215000,China
² Jiangsu Key Laboratory of Broadband Wireless Communication and Internet of Things,Nanjing University of Posts and Telecommunications,Nanjing 210003,China

Revised:2020-02-14 Online:2020-12-30 Published:2020-12-14
Supported by:
The Research Foundation of Ministry of Education-China Mobile(MCM20170205);The Communication Science Research Project of Ministry of Industry and Information Technology of China(2019-R-26);The “Six Talent Peaks”Research Foundation of Jiangsu Province(DZXX-008);The NUPTSF(NY217146);The NUPTSF(NY220028)

摘要/Abstract

摘要：

随着5G通信技术、“互联网+”和物联网的快速发展，云计算作为基于互联网的虚拟资源管理和分布式计算的技术模式，以动态按需和可度量的方式为用户提供服务，将业务平台迁移至云计算平台可实现快速部署业务，有效节约了业务创新及运营成本。所提方案在研究基于云计算平台的业务迁移技术的基础上，以中国移动基于OpenStack的云计算架构为例，对离线迁移、基于平台功能在线迁移、基于块级别在线业务迁移和基于文件级别在线业务迁移等主流业务迁移方案的技术原理和关键点进行分析，同时给出了通用业务迁移流程和方法，最后通过实际平台对3类在线业务迁移方案进行实验验证，分析各方案的技术优势及适用场景，从而指导未来业务迁移的生产实践。

关键词: 云计算, 业务迁移, 异构平台

Abstract:

With the rapid development of 5G communication technology,Internet+ and the Internet of things (IoT),cloud computing as an Internet-based virtual resource management and a distributed computing technology,provides services to users in a dynamic,on-demand and measurable manner.The solution of migrating the service platform to the cloud computing platform can realize rapid service deployment and effectively save service innovation and operating cost.With the research of the cloud computing platform-based service migration technology,the China Mobile’s OpenStack-based cloud computing architecture was taken as an example.The technical principles and core points of the mainstream service migration schemes were analyzed,such as offline migration,online migration based on platform functions,online service migration based on the agent block level and online service migration based on agent file level.The general service migration process and method were also given.Finally,three types of online migration schemes were experimentally verified through the actual platform.The technical advantages and adaptation scenarios were analyzed separately to guide the production practice of future business migration.

Key words: cloud computing, service migration, heterogeneous platform

中图分类号:

TP316

魏峰,丁飞,焦鹏举,李杨,陈焱山,张登银. 异构云计算平台业务迁移[J]. 物联网学报, 2020, 4(4): 79-90.

Feng WEI,Fei DING,Pengju JIAO,Yang LI,Yanshan CHEN,Dengyin ZHANG. Service migration of heterogeneous cloud computing platform[J]. Chinese Journal on Internet of Things, 2020, 4(4): 79-90.

图/表 15

图1

表1

表2

图2

图3

图4

图5

图6

图7

图8

表3

图9

图10

图11

表4

参考文献 36

[27]	AWASTHI A , GUPTA R . Multiple hypervisor based OpenStack cloud and VM migration[C]// International Conference-Cloud System and Big Data Engineering(Confluence). IEEE, 2016: 130-134.
[28]	LUO Y W , ZHANG B B , WANG X L ,et al. Live and incremental whole-system migration of virtual machines using block-bitmap[C]// IEEE International Conference on Cluster Computing(ICCC). IEEE, 2008: 99-106.
[29]	HAO W , THURAISINGHAM B M , YEN I L . Dynamic service and data migration in the clouds[C]// International Computer Software and Applications Conference. 2009(2): 134-139.
[30]	AMORETTI M , LAGHI M C , TASSONI F ,et al. Service migration within the cloud:code mobility in SP2A[C]// International Conference on High Performance Computing and Simulation(HPCS). IEEE, 2010: 196-202.
[31]	SIM K M . Agent-based cloud computing[J]. IEEE Transactions on Services Computing, 2012,5(4): 564-577.
[32]	JAHANI A , DERAKHSHAN F , KHANLI L M . Arank:a multi-agent based approach for ranking of cloud computing services[J]. Scalable Computing, 2017,18(2): 105-116.
[33]	FERNANDO D L P , SARA R G , PABLO C ,et al. Survey of agent-based cloud computing applications[C]// Future Generation Computer Systems. 2019(100): 223-236.
[34]	胡荣辉 . 基于云计算平台的虚拟机部署及迁移策略研究[D]. 南京:南京邮电大学, 2017.
[1]	工业和信息化部电信研究院. 云计算白皮书[S]. 2012.
	Telecommunication Research Institute of the Ministry of Industry and Information Technology. Cloud computing white paper[S]. 2012.
[2]	中国信息通信研究院. 云计算发展白皮书[S]. 2019.
	China Academy of Information and Communications Technology. White paper on cloud computing development[S]. 2019.
[3]	WANG K . Migration strategy of cloud collaborative computing for delay-sensitive industrial IoT applications in the context of intelligent manufacturing[J]. Computer Communications, 2020(150): 413-420.
[4]	PATEL Y S , PAGE A , NAGDEV M ,et al. On demand clock synchronization for live VM migration in distributed cloud data centers[J]. Journal of Parallel and Distributed Computing, 2020(138): 15-31.
[5]	宋富洪, 邢焕来, 潘炜 . 一种面向移动云计算的多目标任务卸载算法[J]. 物联网学报, 2019,3(3): 41-49.
	SONG F H , XING H L , PAN W . Multi-objective task offloading algorithm for mobile cloud computing[J]. Chinese Journal on Internet of Things, 2019,3(3): 41-49.
[6]	JOSE C , FRANCISCO D , ERNESTO P . Live migration of trans-cloud applications[J]. Computer Standards and Interfaces, 2020(69): 1-14.
[7]	LOYD W J , PALLICKARA S , DAVID O ,et al. Migration of multi-tier applications to infrastructure-as-a-service clouds:an investigation using kernel based virtual machines[C]// IEEE/ACM International Conference on Grid Computing. IEEE, 2011: 137-144.
[8]	LOYD W , PALLICKARA S , DAVID O ,et al. Performance implications of multi-tier application deployments on infrastructure-as-a- service clouds:towards performance modeling[J]. Future Generation Computer Systems, 2013,29(5): 1254-1264.
[9]	REN S Y , HE L G , ZHU H Z ,et al. Developing power-aware scheduling mechanisms for computing systems virtualized by Xen[J]. Concurrency Computation, 2017,29(3).
[34]	HU R H . Research on virtual machine deployment and migration strategy based on cloud computing platform[D]. Nanjing:Nanjing University of Posts and Telecommunications, 2017.
[35]	郭静 . 面向私有云的业务迁移部署方法研究[J]. 中国电子科学研究院学报, 2016,11(2): 191-198.
[10]	MICHAEL C . VMware opens,reinforces hybrid-cloud migration software[J]. Network World, 2019
[11]	CHAE M , LEE H , LEE K . A performance comparison of Linux containers and virtual machines using docker and KVM[J]. Cluster Computing, 2019,(22): 1765-1775.
[35]	GUO J . Research on system migration and deployment method for private cloud[J]. Journal of China Academy of Electronics and Information Technology, 2016,11(2): 191-198.
[36]	黄秋兰, 李海波, 石京燕 ,等. 基于Openstack的高能物理虚拟计算集群系统及应用[J]. 计算机科学, 2017,44(10): 59-63.
[12]	DIALLO M H , AUGUST M , HALLMAN R ,et al. Automigrate:a framework for developing intelligent,self-managing cloud services with maximum availability[J]. Cluster Computing, 2017,20(3): 1995-2012.
[13]	WANG W Y , JIANG Y C , WU W W . Multiagent-based resource allocation for energy minimization in cloud computing systems[J]. IEEE Transactions on Systems,Man,and Cybernetics:Systems, 2017,47(2): 205-220.
[14]	BELLO M , . Cloud-based conversational agents for user acquisition and engagement[C]// International Conference on Cloud Computing and Services Science. IEEE, 2019: 528-534.
[15]	SADOOGHI I , HERNANDEZ M J , LI T L ,et al. Understanding the performance and potential of cloud computing for scientific applications[J]. IEEE Transactions on Cloud Computing, 2017,5(2): 358-371.
[16]	CARVER B , ESPOSITO T , LYKE J . Cloud-based computation and networking for space[C]// International Society for Optical Engineering (SPIE). 2018: 1-16.
[17]	富宇, 卢士达, 王宝来 ,等. 基于异构平台的开源VIRT-V2V虚拟化迁移自动化实现的研究[J]. 电力信息与通信技术, 2019,17(6): 63-68.
	FU Y , LU S D , WANG B L ,et al. Research on implementation of open source VIRT-V2V virtualization migration automation based on heterogeneous platform[J]. Electric Power Information and Communication Technology, 2019,17(6): 63-68.
[18]	LI B G , SHU J W , ZHENG W M . Design and implementation of a storage virtualization system based on SCSI target simulator in SAN[J]. Tsinghua Science and Technology, 2005,10(1): 122-127.
[19]	刘禹燕, 牛保宁 . 半虚拟化框架 Virtio 的网络请求性能优化[J]. 小型微型计算机系统, 2018,1(1): 105-110.
	LIU Y Y , NIU B N . Optimizing network performance of para-virtualization virtio frametwork[J]. Journal of Chinese Mini-Micro Computer Systems, 2018,1(1): 105-110.
[20]	陈睦, 黄黎明, 李先锋 . 云计算中虚拟机磁盘迁移时机优化策略[J]. 计算机工程与设计, 2014,2(2): 525-530.
	CHEN M , HUANG L M , LI X F . Disk migration timing optimization mechanism in cloud computing[J]. Computer Engineering and Design, 2014,2(2): 525-530.
[21]	HE S , HU C M , SHI B ,et al. Optimizing virtual machine live migration without shared storage in hybrid clouds[C]// IEEE International Conference on High Performance Computing and Communications,14th IEEE International Conference on Smart City and 2nd IEEE International Conference on Data Science and Systems (HPCC/ SmartCity/DSS). IEEE, 2016: 921-928.
[22]	KARGATZIS D , SOTIRIADIS S , PETRAKIS E G M . Virtual machine migration in heterogeneous clouds:from OpenStack to VMWare[C]// 38th IEEE Sarnoff Symposium. IEEE, 2017: 1-6.
[23]	陈雯倩 . 基于云平台的虚拟机快照存储备份技术研究[D]. 重庆:重庆大学, 2018.
	CHEN W Q . Research on virtual machine snapshot storage and backup technology based on cloud platform[D]. Chongqing:Chongqing University, 2018.
[24]	邵曦煜, 李京, 周志强 . 一种Ceph块设备跨集群迁移算法[J]. 中国科学技术大学学报, 2018,48(9): 748-754.
	SHAO X Y , LI J , ZHOU Z Q . Migration algorithm for Ceph block device cross clusters[J]. Journal of University of Science and Technology of China, 2018,48(9): 748-754.
[25]	周林 . OpenStack和Ceph结合的云存储设计与实现[D]. 南京:南京邮电大学, 2018.
	ZHOU L . Design and implementation of cloud storage based on OpenStack and Ceph[D]. Nanjing:Nanjing University of Posts and Telecommunications, 2018.
[26]	武义涵, 黄罡, 张颖 ,等. 一种基于模型的云计算容错机制开发方法[J]. 计算机研究与发展, 2016,53(1): 138-154.
	WU Y H , HUANG G , ZHANG Y ,et al. A model-based fault tolerance mechanism development approach for cloud computing[J]. Journal of Computer Research and Development, 2016,53(1): 138-154.
[36]	HUANG Q L , LI H B , SHI J Y ,et al. Openstack-based virtualized computing cluster and application for high energy physics[J]. Computer Science, 2017,44(10): 59-63.

迁移方式	业务相关	停服时长	增量迁移	侵入性	影响程度
离线迁移	业务无关	数据/带宽	否	否	大
基于平台功能在线迁移	业务无关	分钟级	是	否	小
基于块级别在线业务迁移	业务无关	分钟级	是	是	小
基于文件级别在线业务迁移	业务无关	分钟级	是	是	小

迁移方式	适合业务场景
离线迁移	测试环境、准生产环境
基于平台功能在线迁移	源平台为VMware、Hyper-V
基于块级别在线业务迁移	源端除物理机以外的生产环境，业务为数据库
基于文件级别在线业务迁移	源端为物理机或其他虚拟化平台，且此工具支持磁盘缩容

业务系统	虚拟机名称	虚拟机地址
	CRM01	192.168.1.1
	CRM02	192.168.1.2
CRM系统	CRM03	192.168.1.3
	CRM04	192.168.1.4
	CRM05	192.168.1.5
	CRM06	192.168.1.6

技术方案	方案优势	非适用场景
基于平台功能的迁移	不用侵入系统，避免用户信息的泄露，更安全可靠	① 不适合实施精确的流量控制，流量控制的粒度是每个批次，不能到达每台虚拟机② 该功能严重依赖平台的负载，如在VMware vcenter忙时，则快照功能处理较慢③ 只支持特定平台
基于块级别在线业务迁移	① 迁移速率较快，停服时间相对较短② 流量控制可以到每台虚拟机的粒度	① 需要侵入源服务器② 不支持磁盘缩容
基于文件级别在线业务迁移	① 流量控制可以到每台虚拟机的粒度② 支持磁盘缩容，适合源端为物理机的场景	需要侵入源服务器

异构云计算平台业务迁移

Service migration of heterogeneous cloud computing platform

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 15

参考文献 36

相关文章 4

Metrics

推荐阅读 0

[1]	宋富洪,邢焕来,潘炜. 一种面向移动云计算的多目标任务卸载算法[J]. 物联网学报, 2019, 3(3): 41-49.
[2]	柴天佑,丁进良,徐泉,岳恒. 基于物联网的选矿制造执行系统技术[J]. 物联网学报, 2018, 2(1): 1-16.
[3]	丁恩杰,胡青松. 矿山物联网顶层设计思路[J]. 物联网学报, 2018, 2(1): 69-75.
[4]	周雷雷,江伟,王猛,杜诗研. 智慧园区规划方案探讨[J]. 物联网学报, 2017, 1(3): 72-76.