云平台中虚拟机部署的关键问题研究
|
摘要
云计算课题是当今工业界和学术界的研究热点，云计算通过虚拟化技术大大提高了数据中心的资源利用率并降低了运营成本。云服务提供商按照用户的需求提供平台服务，软件服务和基础设施服务，其中云平台下虚拟机的部署是实现云计算中基础设施即服务IaaS (Infrastructure as a Service)的基础。用户可以根据需要来选择资源并希望得到更好的服务质量，云服务提供商则考虑自身利益需要尽量降低运营成本，在云计算环境下如何高效的和合理的部署虚拟机成为本文的研究重点。本文分析了当前流行的虚拟机部署策略及其相关改进方法并分析了当前云计算的研究人员针对虚拟机部署机制的研究工作。在此基础上，本文研究了虚拟机镜像的定制方法，设计了以性能能耗比作为评价标准的虚拟机部署的位置选择策略以及研究了虚拟机部署机制的关键问题。
本文主要贡献有：
(1)通过LFS (Linux From Scratch)定制虚拟机镜像。为用户提供定制接口，云提供商可以动态的更新为用户提供的服务和应用，云平台根据用户的需求生成相应的需求配置文件，并生成脚本实现虚拟机镜像的自动生成。通过LFS定制的虚拟机镜像明显减小了系统镜像的大小，在开机速度上也有很大幅度的提高，并为后续的部署过程减少系统开销和通信开销。
(2)针对虚拟机部署过程中的位置选择策略进行了研究。本文提出了一种通过分布式并行遗传算法来实现云平台中虚拟机部署的位置选择策略DPGA (Distributed ParallelGenetic Algorithm of Placement Strategy for Virtual Machines Deployment on CloudPlatform)。DPGA以在保证系统性能的前提下尽量减少能耗开销为目的，为了提高初始种群的覆盖率，在解空间中松散的和平均的选择初始种群，采用自适应交叉率的多点交叉方法和自适应变异率的多点变异方法，分两个阶段使用遗传算法来获得更好的更精确的解。通过DPGA实现的部署策略相比于其他方法能明显提高性能能耗比，并较其他方法更为稳定。
(3)针对虚拟机部署机制进行了研究。本文提出了一种针对定制虚拟机的部署方法DCVM (Deployment of Customized Virtual Machine)。部署通过之前LFS方法定制的虚拟机镜像，从根本上减少了部署过程的系统开销和通信开销。DCVM结合了虚拟机动态迁移机制中一些方法的优点，使用了pre-copy和post-copy算法并结合了增量压缩机制，通过组播机制进行部署。DCVM明显缩短了总的部署时间，减少了部署过程中的数据传输量，实现了在云计算环境下虚拟机的快速部署。
Cloud computing is at the forefront of information technology. Cloud platform provideslots of computing resources and software resources. In order to provide better infrastructureservice and to improve the utilization rate of resources, virtualization technology has beenapplied in the cloud-computing field, through which, cloud provider can offer servicesaccording to users’ needs. Because of the development of the technology like Vmware, Xen,some researchers and industrial enterprises have got innovation progress on cloud computingand its applications. In the wake of development in virtualization technology, underlyinghardware furnishes more and more support for virtualization. Virtualization technologybecome the important basis of cloud computing.
Virtual machine (VM) technology, as the most important part of virtualizationtechnology, has already been used widely in cloud computing. User experience of operatingon physical machine is the same as operating on a virtual one, so through virtualizationtechnology, we can devise one physical machine into several individual “ones” on the cloudplatform. People can set up several independent VMs on one physical machine, then installdifferent operating systems, services and applications. This makes virtualization technology tobe more compatibility, flexibility and security in cloud computing application.
These strengths of VM can also be brought out in its deployment, migration andmanagement under cloud computing environment. Some key issues of cloud computing, likeload balancing, task scheduling and fault-tolerant etc. are partially resolved because of VMtechnology. The “green cloud” aimed at energy saving of data center, which attractstremendous attention, also need the technology related to VM. Lots of VM techniques havebeen applied intensively on cloud computing, but comparing to other issues, more researchesand optimizations on the deployment, migration and management of VM have yet to be done.These issues seriously impact the whole performance of cloud platform. How to customizeVM image efficiently, to reduce deployment, migration time and to deploy and migrate VMreasonably are the main issues in current research of cloud computing.
This paper is focused on the customization, deployment strategy and deploymentmechanism of VM in cloud computing. Some researches related to the subject are alreadystarted, but they still need to be optimized and worked on.
(1) In the matter of customization of VM image, considering of the security, most of theVM images used Linux kernel. However, the fact that traditional VM images are too big andtake a lot of system resources. It will impact the performance of the deployment process, sothe images need slim down. Linux kernel tailoring is the main solution to reduce the size of operating system in today’s world. However, Linux kernel tailoring takes more time tocustomize under cloud computing environment. It mainly used in embedded system and someparticular domain, besides, users’ requirements are different from each other under cloudcomputing environment. Therefore, it can’t satisfy users’needs flexibly and it isn’t convenientto be applied in customization of VM image under cloud computing environment.
(2) On the issue of the placement strategy of VMs deployment, most of currentresearches didn’t pay attention to the placement problem in the process of VMs deployment.They used relatively easy strategy in deployment, and only focused on the location of VMmigration after deployment. If they had done, the migration frequency of cloud center wouldbe greatly reduced, so that the energy consumption could be reduced too. There are manyplacement strategies to select the VMs place, among which heuristic algorithm is widely usedin this kind of issue. But when cloud platform have a certain size, and a number of VMs todeploy, traditional heuristic algorithm is difficult to find a good place efficiently with anaffordable system expenses.
(3) In the deployment mechanism, dynamic migration mechanism is the main method.There are three mainstream mechanism of VM migration: Pre-copy algorithm, Post-copyalgorithm and the hybrid memory copy algorithm which mixes the previous two. All thesethree methods can realize the deployment of VMs and many improved methods have beenproposed to increase the performance of deployment. But there is still a lot of improvementspace in deployment performance and efficiency. Pre-copy algorithm must transfer mountainsof redundant dirty pages in iterative process, which will cause the process to transfer moredata and to take more bandwidth. Post-copy algorithm maybe cause long downtime whichwill delay the whole deployment time and take more computing resources. Mixed memorycopy algorithm with Pre-copy and Post-copy can make up the shortfall of the first twomethods in some degree, but deployment performances still need improvement.
Aiming at the issues presented above, this paper studies the VM image customizationwith LFS. We study and design a placement strategy of VMs deployment which is sensitive toenergy consumption. Besides, it improves the hybrid memory copy algorithm in combiningwith the incremental compressing method and uses multicast technology to improve theefficiency of deployment process. Main contributions are as follow:
1. Using LFS technology to customize VM image according users’ needs. We create userinterface through which users can send their requirements information. Cloud platformprovides management interface of applications and system components, moreover, it generatethe script program related to the automatic installation of applications and system components.Cloud platform generate the configuration file after receiving users’ information. Thecustomization process of VM image search the minimum matching image according to theconfiguration file and do the incremental installation. The obtained image is the exactly onerequired by users and it will be saved on cloud platform for future customization uses. Theuse of LFS greatly reduces the system size and the resources consumption on the premise that users’ requirements are satisfied. Moreover, the boot speed has been seriously raised while thesystem cost and network overhead significantly decrease.
2. Taking performance per watt as the standard for evaluating the placement strategy ofVMs deployment. The placement strategy in traditional VMs deployment process didn’tconsider the performance and energy consumption issues of cloud center. This paper proposesa new distributed parallel genetic algorithm (DPGA) for deploying a number of VMs inlarge-scale cloud center by using DVFS technology, meanwhile taking QoS of users andenergy saving of cloud platform in consideration. This algorithm can be separated into twostages. Firstly, considering the coverage rate of solution space, we select initial populationsdispersedly and averagely. Then the genetic algorithm executes parallelly and distributedly onthe selected hosts. The algorithm executing in each host will get an optimal solution. Secondly,we take the solutions obtained in the first stage as initial population and begin the geneticalgorithm procedure of second stage. The optimal solution obtained in the second stage is thefinal solution of DPGA. Through DPGA, cloud center can reduce energy consumptionsignificantly in condition of users’ QoS. In addition, it can ensure the high efficiency underdifferent demand.
3. Research on dynamic deployment mechanism of VMs. We proposed a new VMsdeployment mechanism DCVM with the combination of pre-copy algorithm and post-copyalgorithm. First of all, copy the metadata from the source VM to the target VMs. Then thesource VM pushes memory pages to the target VMs at regular time, the target VMs takesmissing pages from source VM during its boot process. Finally, the source VM stops to pushall memory pages remaining. DCVM transfers metadata and memory pages by multicasttechnology. Multicast technology can transfer data to all target VMs at once and can realizepage prefetching of target VMs. The incremental compressing technology is used in thememory pages transfer process for incremental compressing the dirty pages. Firstly, deal withthe dirty pages with the temporary saved memory pages by XOR operation to get incrementdata of memory dirty pages. Then, compress the increment data which is easy to compress byXBRLE algorithm, and multicast the compressed data to target VMs. The target VM restoresthe memory data according to the information of incremental compressed data. Theincremental compressing technology can reduce the network overhead obviously indeployment process. DCVM increase VM deployment efficiency significantly while thesystem cost decrease in the process.
本文主要贡献有：
(1)通过LFS (Linux From Scratch)定制虚拟机镜像。为用户提供定制接口，云提供商可以动态的更新为用户提供的服务和应用，云平台根据用户的需求生成相应的需求配置文件，并生成脚本实现虚拟机镜像的自动生成。通过LFS定制的虚拟机镜像明显减小了系统镜像的大小，在开机速度上也有很大幅度的提高，并为后续的部署过程减少系统开销和通信开销。
(2)针对虚拟机部署过程中的位置选择策略进行了研究。本文提出了一种通过分布式并行遗传算法来实现云平台中虚拟机部署的位置选择策略DPGA (Distributed ParallelGenetic Algorithm of Placement Strategy for Virtual Machines Deployment on CloudPlatform)。DPGA以在保证系统性能的前提下尽量减少能耗开销为目的，为了提高初始种群的覆盖率，在解空间中松散的和平均的选择初始种群，采用自适应交叉率的多点交叉方法和自适应变异率的多点变异方法，分两个阶段使用遗传算法来获得更好的更精确的解。通过DPGA实现的部署策略相比于其他方法能明显提高性能能耗比，并较其他方法更为稳定。
(3)针对虚拟机部署机制进行了研究。本文提出了一种针对定制虚拟机的部署方法DCVM (Deployment of Customized Virtual Machine)。部署通过之前LFS方法定制的虚拟机镜像，从根本上减少了部署过程的系统开销和通信开销。DCVM结合了虚拟机动态迁移机制中一些方法的优点，使用了pre-copy和post-copy算法并结合了增量压缩机制，通过组播机制进行部署。DCVM明显缩短了总的部署时间，减少了部署过程中的数据传输量，实现了在云计算环境下虚拟机的快速部署。
Cloud computing is at the forefront of information technology. Cloud platform provideslots of computing resources and software resources. In order to provide better infrastructureservice and to improve the utilization rate of resources, virtualization technology has beenapplied in the cloud-computing field, through which, cloud provider can offer servicesaccording to users’ needs. Because of the development of the technology like Vmware, Xen,some researchers and industrial enterprises have got innovation progress on cloud computingand its applications. In the wake of development in virtualization technology, underlyinghardware furnishes more and more support for virtualization. Virtualization technologybecome the important basis of cloud computing.
Virtual machine (VM) technology, as the most important part of virtualizationtechnology, has already been used widely in cloud computing. User experience of operatingon physical machine is the same as operating on a virtual one, so through virtualizationtechnology, we can devise one physical machine into several individual “ones” on the cloudplatform. People can set up several independent VMs on one physical machine, then installdifferent operating systems, services and applications. This makes virtualization technology tobe more compatibility, flexibility and security in cloud computing application.
These strengths of VM can also be brought out in its deployment, migration andmanagement under cloud computing environment. Some key issues of cloud computing, likeload balancing, task scheduling and fault-tolerant etc. are partially resolved because of VMtechnology. The “green cloud” aimed at energy saving of data center, which attractstremendous attention, also need the technology related to VM. Lots of VM techniques havebeen applied intensively on cloud computing, but comparing to other issues, more researchesand optimizations on the deployment, migration and management of VM have yet to be done.These issues seriously impact the whole performance of cloud platform. How to customizeVM image efficiently, to reduce deployment, migration time and to deploy and migrate VMreasonably are the main issues in current research of cloud computing.
This paper is focused on the customization, deployment strategy and deploymentmechanism of VM in cloud computing. Some researches related to the subject are alreadystarted, but they still need to be optimized and worked on.
(1) In the matter of customization of VM image, considering of the security, most of theVM images used Linux kernel. However, the fact that traditional VM images are too big andtake a lot of system resources. It will impact the performance of the deployment process, sothe images need slim down. Linux kernel tailoring is the main solution to reduce the size of operating system in today’s world. However, Linux kernel tailoring takes more time tocustomize under cloud computing environment. It mainly used in embedded system and someparticular domain, besides, users’ requirements are different from each other under cloudcomputing environment. Therefore, it can’t satisfy users’needs flexibly and it isn’t convenientto be applied in customization of VM image under cloud computing environment.
(2) On the issue of the placement strategy of VMs deployment, most of currentresearches didn’t pay attention to the placement problem in the process of VMs deployment.They used relatively easy strategy in deployment, and only focused on the location of VMmigration after deployment. If they had done, the migration frequency of cloud center wouldbe greatly reduced, so that the energy consumption could be reduced too. There are manyplacement strategies to select the VMs place, among which heuristic algorithm is widely usedin this kind of issue. But when cloud platform have a certain size, and a number of VMs todeploy, traditional heuristic algorithm is difficult to find a good place efficiently with anaffordable system expenses.
(3) In the deployment mechanism, dynamic migration mechanism is the main method.There are three mainstream mechanism of VM migration: Pre-copy algorithm, Post-copyalgorithm and the hybrid memory copy algorithm which mixes the previous two. All thesethree methods can realize the deployment of VMs and many improved methods have beenproposed to increase the performance of deployment. But there is still a lot of improvementspace in deployment performance and efficiency. Pre-copy algorithm must transfer mountainsof redundant dirty pages in iterative process, which will cause the process to transfer moredata and to take more bandwidth. Post-copy algorithm maybe cause long downtime whichwill delay the whole deployment time and take more computing resources. Mixed memorycopy algorithm with Pre-copy and Post-copy can make up the shortfall of the first twomethods in some degree, but deployment performances still need improvement.
Aiming at the issues presented above, this paper studies the VM image customizationwith LFS. We study and design a placement strategy of VMs deployment which is sensitive toenergy consumption. Besides, it improves the hybrid memory copy algorithm in combiningwith the incremental compressing method and uses multicast technology to improve theefficiency of deployment process. Main contributions are as follow:
1. Using LFS technology to customize VM image according users’ needs. We create userinterface through which users can send their requirements information. Cloud platformprovides management interface of applications and system components, moreover, it generatethe script program related to the automatic installation of applications and system components.Cloud platform generate the configuration file after receiving users’ information. Thecustomization process of VM image search the minimum matching image according to theconfiguration file and do the incremental installation. The obtained image is the exactly onerequired by users and it will be saved on cloud platform for future customization uses. Theuse of LFS greatly reduces the system size and the resources consumption on the premise that users’ requirements are satisfied. Moreover, the boot speed has been seriously raised while thesystem cost and network overhead significantly decrease.
2. Taking performance per watt as the standard for evaluating the placement strategy ofVMs deployment. The placement strategy in traditional VMs deployment process didn’tconsider the performance and energy consumption issues of cloud center. This paper proposesa new distributed parallel genetic algorithm (DPGA) for deploying a number of VMs inlarge-scale cloud center by using DVFS technology, meanwhile taking QoS of users andenergy saving of cloud platform in consideration. This algorithm can be separated into twostages. Firstly, considering the coverage rate of solution space, we select initial populationsdispersedly and averagely. Then the genetic algorithm executes parallelly and distributedly onthe selected hosts. The algorithm executing in each host will get an optimal solution. Secondly,we take the solutions obtained in the first stage as initial population and begin the geneticalgorithm procedure of second stage. The optimal solution obtained in the second stage is thefinal solution of DPGA. Through DPGA, cloud center can reduce energy consumptionsignificantly in condition of users’ QoS. In addition, it can ensure the high efficiency underdifferent demand.
3. Research on dynamic deployment mechanism of VMs. We proposed a new VMsdeployment mechanism DCVM with the combination of pre-copy algorithm and post-copyalgorithm. First of all, copy the metadata from the source VM to the target VMs. Then thesource VM pushes memory pages to the target VMs at regular time, the target VMs takesmissing pages from source VM during its boot process. Finally, the source VM stops to pushall memory pages remaining. DCVM transfers metadata and memory pages by multicasttechnology. Multicast technology can transfer data to all target VMs at once and can realizepage prefetching of target VMs. The incremental compressing technology is used in thememory pages transfer process for incremental compressing the dirty pages. Firstly, deal withthe dirty pages with the temporary saved memory pages by XOR operation to get incrementdata of memory dirty pages. Then, compress the increment data which is easy to compress byXBRLE algorithm, and multicast the compressed data to target VMs. The target VM restoresthe memory data according to the information of incremental compressed data. Theincremental compressing technology can reduce the network overhead obviously indeployment process. DCVM increase VM deployment efficiency significantly while thesystem cost decrease in the process.
引文
[1] J. G. Park, J. M. Kim, H. Choi, Y. C. Woo. Virtual Machine Migration in Self-managingVirtualized Server Environments[C]. Proceedings of the11th international conference onAdvanced Communication Technology. Dublin, Ireland: IEEE Press,2009,2077-2083.
[2] Krishnan, H. Amur, A. Gavrilovska, K. Schwan. VM Power Metering: Feasibility andChallenges[C]. Proceedings of the Second Green Metrics Workshop, in conjunction withSIGMETRICS'10. New York, USA: ACM Press, June14,2010,56-60.
[3] T. Wood, P. Shenoy, A. Venkataramani, M. Yousif. Black-box and Gray-box Strategies forVirtual Machine Migration[C]. Proceeding of the4th USENIX conference on NetworkedSystems Design&Implementation, Cambridge, UK: MA,2007,1-14.
[4] Wikipedia. John McCarthy (computer scientist)[EB/OL].(2008-10-07)[2008-12-10].http://en.wikipedia.org/wiki/John_McCarthy_(computer_scientist).
[5] IBM. Google and IBM announced university initiative to address internetscale computingchallenges [EB/OL].(2007-10-08)[2008-10-15] http://www-03.ibm.com/press/us/en/pressrelease/22414.wss.
[6] WANG Li-zhe, TAO Jie, KUNZE M. Scientific cloud computing: early definition andexperience[C]. Proc of the10th IEEE International Conference on High PerformanceComputing and Communications.2008:825-830.
[7] Barroso LA, Dean J, Holzle U. Web search for a planet: The Google cluster architecture.IEEE Micro,2003,23(2):2228.
[8] IBM. IBM cloud computing.http://www.ibm.com/cloud-computing/.
[9] Amazon. Amazon elastic compute cloud (Amazon EC2).2009. http://aws.amazon.com/ec2/.
[10]BRYANTRE. Data-intensive supercomputing: The case for DISC, CMU-CS-07-128[R].Pittsburgh, PA, USA: CarnegieMellon University, Department of Computer Science,2007.
[11]Nathan Regola, Jean-Christophe Ducom. Recommendations for VirtualizationTechnologies in High Performance Computing[C].2010IEEE second InternationalConference on Cloud Computing Technology and Science.2010:409-416.
[12]Hao Sun, Kento Aida. AHybrid and secure Mechanism to Execute Parameter SurveyApplications on Local and Public Cloud Resources[C].2010IEEE Second InternationalConference on Cloud Computing Technology and Science.2010:118-126.
[13]Kim Hyunjoo, El-Khamra Yaakoub, Jha Shantenu, Parashar Manish. Exploringapplication and infrastructure adaptation on hybrid grid-cloud infrastructure[C]. HPDC2010Proceedings of the19th ACM International Symposium on High PerformanceDistributed Computing.2010:402-412.
[14]Garey Michael R, Johnson David S. Computers and intractability-a guide to the theory ofnp-completeness[M]. San Francisco: W H Freeman Co,1979.
[15]Clark C, Fraser K, Hand S, et al. Live migration of virtual machines[C]. Proceedings ofthe Second Symposium on Networked Systems Design and Implementation (NSDI’05).Boston: USENIX ASSOC.2005:273-286.
[16]Nelson M, Lim B, Hutchins G. Fast transparent migration for virtual machines[C].Proceedings of the USENIX Annual Technical Conference (USENIX’05). Anaheim:USENIX ASSOC.2005:391-394.
[17]Michael R Hines, Umesh Deshpande, Kartik Gopalan. Post-copy live migration of virtualmachines[J]. ACM SIGOPS Operating Systems Review.2009:14-26.
[18]Michael R Hines, Kartik Gopalan. Post-Copy Based Live Virtual Machine MigrationUsing Adaptive Pre-Paging and Dynamic Self-Ballooning[C]. Proc. of the2009ACMSIGPLAN/SIGOPS International Conf. on Virtual Execution Environments.2009:51-60.
[19]Ori Ben-Yitzhak, Irit Goft, et al. An algorithm for parallel incremental compaction[C].ACM SIGPLAN Notices-MSP2002and ISMM2002(Proceedings of the3rdinternational symposium on Memory management).2003:100-105.
[20]H Jin, L Deng, S Wu, X Shi and X Pan. Live Virtual Machine Migration with AdaptiveMemory Compression[C]. Proc. of International Conf. on Cluster Computing andWorkshops (CLUSTER '09).2009:1-10.
[21]P Sv rd, B Hudzia, J Tordsson. Evaluation of Delta Compression Techniques for EfficientLive Migration of Large Virtual Machine[C]. Proc. of the2011ACM SIGPLAN/SIGOPSInternational Conf. on Virtual Execution Environments.2011:111-120.
[22]Gharachorloo K, Lenoski D, Laudon J, et al. Memory Consistency and Event Ordering inScalable Shared-memory Multiprocessors[C]. Proc of the17th International Symposiumon Computer Architecture, Seattle.1990:15-26.
[23]Gu Y F, Chen Z L. Approach to Tailoring Embedded Linux[J]. MINI-MICRO SYSTEMS,2003,24(9):1697-1700.
[24]Cheng Y L, Fang S H. Research and implementation of application-oriented embeddedLinux tailoring methods [J]. Computer Engineering and Design,2009,11:022.
[25]Wang L, Zhu S W, Yu J F. Transplant and Tailor of gSOAP Based on Embedded Linux[J].Applied Mechanics and Materials,2013,303:2445-2448.
[26]Tao L Y, Xu H J. Analysis of LFS Installation[J]. Computer Era,2007(9):54-56.
[27]Wang Y, Wang C L. Principle Analysis of Linux Operating System Build by LFS[J].Software Guide,2010(005).
[28]Cardosa M, Korupolu M R, Singh A. Shares and utilities based power consolidation invirtualized server environments[C]. Integrated Network Management,2009. IM'09.IFIP/IEEE International Symposium on. IEEE,2009:327-334.
[29]Grit L, Irwin D, Yumerefendi A, et al. Virtual machine hosting for networked clusters:Building the foundations for autonomic orchestration[C]. Proceedings of the2ndInternational Workshop on Virtualization Technology in Distributed Computing. IEEEComputer Society,2006:7.
[30]Machida F, Kim D S, Park J S, et al. Toward optimal virtual machine placement andrejuvenation scheduling in a virtualized data center[C]. Software Reliability EngineeringWorkshops,2008. ISSRE Wksp2008. IEEE International Conference on. IEEE,2008:1-3.
[31]Kochut A. On impact of dynamic virtual machine reallocation on data centerefficiency[C]. Modeling, Analysis and Simulation of Computers and TelecommunicationSystems,2008. MASCOTS2008. IEEE International Symposium on. IEEE,2008:1-8.
[32]Viswanathan B, Verma A, Dutta S. Cloudmap: Workload-aware placement in privateheterogeneous clouds[C]. Network Operations and Management Symposium (NOMS),2012IEEE. IEEE,2012:9-16.
[33]Bobroff N, Kochut A, Beaty K. Dynamic placement of virtual machines for managing slaviolations[C]. Integrated Network Management,2007. IM'07.10th IFIP/IEEEInternational Symposium on. IEEE,2007:119-128.
[34]Wang M, Meng X, Zhang L. Consolidating virtual machines with dynamic bandwidthdemand in data centers[C]. INFOCOM,2011Proceedings IEEE. IEEE,2011:71-75.
[35]Chaisiri S, Lee B S, Niyato D. Optimal virtual machine placement across multiple cloudproviders[C]. Services Computing Conference,2009. APSCC2009. IEEE Asia-Pacific.IEEE,2009:103-110.
[36]Bichler M, Setzer T, Speitkamp B. Capacity planning for virtualized servers[C].Workshop on Information Technologies and Systems (WITS), Milwaukee, Wisconsin,USA. sn,2006,1.
[37]Speitkamp B, Bichler M. A mathematical programming approach for server consolidationproblems in virtualized data centers[J]. Services Computing, IEEE Transactions on,2010,3(4):266-278.
[38]Van H N, Tran F D, Menaud J M. Performance and power management for cloudinfrastructures[C]. Cloud Computing (CLOUD),2010IEEE3rd International Conferenceon. IEEE,2010:329-336.
[39]Hermenier F, Lorca X, Menaud J M, et al. Entropy: a consolidation manager forclusters[C]. Proceedings of the2009ACM SIGPLAN/SIGOPS international conferenceon Virtual execution environments. ACM,2009:41-50.
[40]Greenberg A, Hamilton J R, Jain N, et al. VL2: a scalable and flexible data centernetwork[C]. ACM SIGCOMM Computer Communication Review. ACM,2009,39(4):51-62.
[41]Zhang Y, Su A J, Jiang G. Understanding data center network architectures in virtualizedenvironments: A view from multi-tier applications[J]. Computer Networks,2011,55(9):2196-2208.
[42]Al-Fares M, Loukissas A, Vahdat A. A scalable, commodity data center networkarchitecture[C]. ACM SIGCOMM Computer Communication Review. ACM,2008,38(4):63-74.
[43]Clos C. A Study of Non‐Blocking Switching Networks[J]. Bell System TechnicalJournal,1953,32(2):406-424.
[44]Hou W, Guo L, Wei X, et al. Multi-granularity and robust grooming in power-andport-cost-efficient IP over WDM networks[J]. Computer Networks,2012,56(10):2383-2399.
[45]Cuomo F, Cianfrani A, Polverini M, et al. Network pruning for energy saving in theInternet[J]. Computer Networks,2012,56(10):2355-2367.
[46]Heller B, Seetharaman S, Mahadevan P, et al. ElasticTree: Saving Energy in Data CenterNetworks[C]. NSDI.2010,10:249-264.
[47]Shang Y, Li D, Xu M. Energy-aware routing in data center network[C]. Proceedings ofthe first ACM SIGCOMM workshop on Green networking. ACM,2010:1-8.
[48]Mahadevan P, Banerjee S, Sharma P, et al. On energy efficiency for enterprise and datacenter networks[J]. Communications Magazine, IEEE,2011,49(8):94-100.
[49]Fang W, Liang X, Li S, et al. VMPlanner: Optimizing virtual machine placement andtraffic flow routing to reduce network power costs in cloud data centers[J]. ComputerNetworks,2012.
[50]Meng X, Pappas V, Zhang L. Improving the scalability of data center networks withtraffic-aware virtual machine placement[C]. INFOCOM,2010Proceedings IEEE. IEEE,2010:1-9.
[51]McGeer R, Mahadevan P, Banerjee S. On the complexity of power minimization schemesin data center networks[C]. Global Telecommunications Conference (GLOBECOM2010),2010IEEE. IEEE,2010:1-5.
[52]Mann V, Kumar A, Dutta P, et al. VMFlow: leveraging VM mobility to reduce networkpower costs in data centers[M]. NETWORKING2011. Springer Berlin Heidelberg,2011:198-211.
[53]Guo Y, Stolyar A L, Walid A. Shadow-routing based dynamic algorithms for virtualmachine placement in a network cloud[C]. INFOCOM,2013Proceedings IEEE. IEEE,2013:620-628.
[54]Steiner M, Gaglianello B G, Gurbani V, et al. Network-aware service placement in adistributed cloud environment[J]. ACM SIGCOMM Computer Communication Review,2012,42(4):73-74.
[55]Buyya R, Yeo C S, Venugopal S, et al. Cloud computing and emerging IT platforms:Vision, hype, and reality for delivering computing as the5th utility[J]. Future Generationcomputer systems,2009,25(6):599-616.
[56]Liu J, Zhao F, Liu X, et al. Challenges towards elastic power management in internet datacenters[C]. Distributed Computing Systems Workshops,2009. ICDCS Workshops'09.29th IEEE International Conference on. IEEE,2009:65-72.
[57]Meijer G I. Cooling energy-hungry data centers[J]. Science,2010,328(5976):318-319.
[58]Fakhim B, Behnia M, Armfield S W, et al. Cooling solutions in an operational data centre:A case study[J]. Applied thermal engineering,2011,31(14):2279-2291.
[59]Verma A, Ahuja P, Neogi A. pMapper: power and migration cost aware applicationplacement in virtualized systems[M]. Middleware2008. Springer Berlin Heidelberg,2008:243-264.
[60]Dong J, Jin X, Wang H, et al. Energy-Saving Virtual Machine Placement in Cloud DataCenters[C]. Cluster, Cloud and Grid Computing (CCGrid),201313th IEEE/ACMInternational Symposium on. IEEE,2013:618-624.
[61]Kantarci B, Foschini L, Corradi A, et al. Inter-and-intra data center VM-placement forenergy-efficient large-Scale cloud systems[C]. Globecom Workshops (GC Wkshps),2012IEEE. IEEE,2012:708-713.
[62]Abdelsalam H S, Maly K, Mukkamala R, et al. Analysis of energy efficiency in clouds[C].Future Computing, Service Computation, Cognitive, Adaptive, Content, Patterns,2009.COMPUTATIONWORLD'09. Computation World. IEEE,2009:416-421.
[63]Jung G, Hiltunen M A, Joshi K R, et al. Mistral: Dynamically managing power,performance, and adaptation cost in cloud infrastructures[C]. Distributed ComputingSystems (ICDCS),2010IEEE30th International Conference on. IEEE,2010:62-73.
[64]Srikantaiah S, Kansal A, Zhao F. Energy aware consolidation for cloud computing[C].Proceedings of the2008conference on Power aware computing and systems. USENIXAssociation,2008,10.
[65]Li B, Li J, Huai J, et al. Enacloud: An energy-saving application live placement approachfor cloud computing environments[C]. Cloud Computing,2009. CLOUD'09. IEEEInternational Conference on. IEEE,2009:17-24.
[66]Gao Y, Guan H, Qi Z, et al. A multi-objective ant colony system algorithm for virtualmachine placement in cloud computing[J]. Journal of Computer and System Sciences,2013,79(8):1230-1242.
[67]Békési J, Galambos G, Kellerer H. A5/4linear time bin packing algorithm[J]. Journal ofComputer and System Sciences,2000,60(1):145-160.
[68]E. Feller, L. Rilling, C. Morin, Energy-aware ant colony based workload placement inclouds[C]. Proceedings of the IEEE/ACM International Conference on Grid Computing(GRID),2011, pp.26–33.
[69]Davis L. Genetic algorithms and simulated annealing[J].1987.
[70]De Jong K A. Genetic algorithms: A10year perspective[C]. Proceedings of anInternational Conference on Genetic Algorithms and Their Applications.1985,1(6):9-177.
[71]Goldberg D E. Genetic algorithms in search, optimization, and machine learning[M].Reading Menlo Park: Addison-wesley,1989.
[72]Koza J R, Rice J P. Genetic generation of both the weights and architecture for a neuralnetwork[C]. Neural Networks,1991. IJCNN-91-Seattle International Joint Conference on.IEEE,1991,2:397-404.
[73]H. Andres Lagar-Cavilla, Joseph A. Whitney, Adin Scannell, Philip Patchin, Stephen M.Rumble, Eyal de Lara, Michael Brudno, M. Satyanarayanan. SnowFlock: Rapid VirtualMachine Cloning for Cloud Computing[C]. EuroSys09Proceedings of the4th ACMEuropean conference on Computer systems.2009.
[74]Lagar-Cavilla HA, Whitney JA, Bryant R, et al. SnowFlock: Virtual Machine Cloning asa First-Class Cloud Primitive[J]. ACM Transactions on Computer Systems (TOCS). Vol.29, No.2,2011:1-45.
[75]Vrable M, Ma J, Chen J, et al. Scalability, fidelity and containment in the Potemkinvirtual honeyfarm[C]. Proc20th Symposium on Operating Systems Principles (SOSP).2005:148-162.
[76]Wu XX, Shen ZM, Wu R, Lin YF. Jump-start Cloud: Efficient Deployment Frameworkfor Large-scale Cloud Applications[J]. CONCURRENCY AND COMPUTATION-PRACTICE&EXPERIENCE.2012:2120-2137.
[77]Schmidt Matthias, Fallenbeck Niels, Smith Matthew, Freisleben Bernd. Efficientdistribution of virtual machines for cloud computing[C]. Proceedings of the18thEuromicro Conference on Parallel, Distributed and Network-Based Processing.2010:567-574.
[78]Gerard Beekmans. Linux From Scratch. http://www.linuxfromscratch.org/lfs/view/stable/,2007.1.
[79]AA Fr hlich, W Schr der-Preikschat. Tailor-made operating systems for embeddedparallel applications[J]. Lecture Notes in Computer Science.1999:1361-1373.
[80]Hasan MZ, Sotirios SG. Customized kernel execution on reconfigurable hardware forembedded applications[J]. Microprocessors and Microsystems.2008:211-220.
[81]Montgomery J, Brewster GB, Yee WG. A customized Linux Kernel for ProvidingNotification of Pending Financial Transaction Information[C].7th IEEE ConsumerCommunications and Networking Conference.2010:1021-1022.
[82]APP-V [EB/OL]. http://www.microsoft.com/app-v.
[83]ThinApp [EB/OL]. http://www.vmware.com/products/thinapp/.
[84]XenApp [EB/OL]. http://www.citrix.com/xenapp.
[85]Zhang Han-ying, Wu Qing-bo, Tan Yu-song. On-demand Customized Virtual MachineInstance System[J]. COMPUTER TECHNOLOGY AND DEVELOPMENT. Vol.23, NO.4,2013:1-10.
[86]Ertl M A, Gregg D, Krall A, et al. Vmgen: A Generator of Efficient Virtual MachineInterpreters[J]. Software-Practice&Experience,2002,32(3):265-294.
[87]Ertl M A, Gregg D. The Structure and Performance of Efficient Interpreters[C]. MProc ofthe2004Workshop on Interpreters, Virtual Machines and Emulators,2004.
[88]Ouyang Xing-ming, Zhu Jin-yin. An Implementation Approach to Custom-Built VirtualMachines and Their Dynamic Optimization[J]. COMPUTER ENGINEERING&SCIENCE. Vol.30, NO.1,2008:129-141.
[89]GNU Binutils. http://en.wikipedia.org/wiki/GNU_Binutils.
[90]Nakajima J, Lin Q, Yang S, et al. Optimizing Virtual Machines Using HybridVirtualization[C]. Proc. Of the2011ACM Symposium on Applied Computing (SAC’11).2011:573-578.
[91]Barham P, Dragovic B, Fraser K, et al. Xen and the art of virtualization[C]. New York,USA: Proceedings of the19th ACM Symposium on Operating Systems Principles,2003.
[92]Amdahl G M. Validity of the single processor approach to achieving large scalecomputing capabilities[C]. Proceedings of the April18-20,1967, spring joint computerconference. ACM,1967:483-485.
[93]Gustafson J L. Reevaluating Amdahl's law[J]. Communications of the ACM,1988,31(5):532-533.
[94]Sun X H, Ni L M. Scalable problems and memory-bounded speedup[R]. INSTITUTEFOR COMPUTER APPLICATIONS IN SCIENCE AND ENGINEERING HAMPTONVA,1992.
[95]Tordsson J, Montero R S, Moreno-Vozmediano R, et al. Cloud brokering mechanisms foroptimized placement of virtual machines across multiple providers[J]. Future GenerationComputer Systems,2012,28(2):358-367.
[96]Wang W, Chen H, Chen X. An Availability-Aware Virtual Machine Placement Approachfor Dynamic Scaling of Cloud Applications[C]. Ubiquitous Intelligence&Computingand9th International Conference on Autonomic&Trusted Computing (UIC/ATC),20129th International Conference on. IEEE,2012:509-516.
[97]Yusoh Z I M, Tang M. A penalty-based genetic algorithm for the composite SaaSplacement problem in the cloud[C]. Evolutionary Computation (CEC),2010IEEECongress on. IEEE,2010:1-8.
[98]Ni Z W, Pan X F, Wu Z J. An Ant Colony Optimization for the Composite SaaSPlacement Problem in the Cloud[J]. Applied Mechanics and Materials,2012,130:3062-3067.
[99]Yusoh Z I M, Tang M. A cooperative coevolutionary algorithm for the composite SaaSplacement problem in the cloud[M]. Neural Information Processing. Theory andAlgorithms. Springer Berlin Heidelberg,2010:618-625.
[100] Wang H, Xu W, Wang F, et al. A Cloud-Computing-Based Data Placement Strategy inHigh-Speed Railway[J]. Discrete Dynamics in Nature and Society,2012,2012.
[101] Yuan D, Yang Y, Liu X, et al. A data placement strategy in scientific cloud workflows[J].Future Generation Computer Systems,2010,26(8):1200-1214.
[102] Guo L, He Z, Zhao S, et al. Multi-objective Optimization for Data Placement Strategyin Cloud Computing[M]. Information Computing and Applications. Springer BerlinHeidelberg,2012:119-126.
[103] Ding J, Han H Y, Zhou A H. A Data Placement Strategy for Data-Intensive CloudStorage[J]. Advanced Materials Research,2012,354:896-900.
[104] von Laszewski G, Wang L, Younge A J, et al. Power-aware scheduling of virtualmachines in dvfs-enabled clusters[C]. Cluster Computing and Workshops,2009.CLUSTER'09. IEEE International Conference on. IEEE,2009:1-10.
[105] Ge R, Feng X, Cameron K W. Performance-constrained distributed dvs scheduling forscientific applications on power-aware clusters[C]. Proceedings of the2005ACM/IEEEconference on Supercomputing. IEEE Computer Society,2005:34.
[106] Piao J T, Yan J. A network-aware virtual machine placement and migration approach incloud computing[C]. Grid and Cooperative Computing (GCC),20109th InternationalConference on. IEEE,2010:87-92.
[107] Hsu C H, Kremer U, Hsiao M. Compiler-directed dynamic frequency and voltagescheduling[M]. Power-Aware Computer Systems. Springer Berlin Heidelberg,2001:65-81.
[108] Srinivas M, Patnaik L M. Adaptive probabilities of crossover and mutation in geneticalgorithms[J]. Systems, Man and Cybernetics, IEEE Transactions on,1994,24(4):656-667.
[109] Calheiros R N, Ranjan R, Beloglazov A, et al. CloudSim: a toolkit for modeling andsimulation of cloud computing environments and evaluation of resource provisioningalgorithms[J]. Software: Practice and Experience,2011,41(1):23-50.
[110] Beloglazov A, Buyya R. Optimal online deterministic algorithms and adaptiveheuristics for energy and performance efficient dynamic consolidation of virtualmachines in Cloud data centers[J]. Concurrency and Computation: Practice andExperience,2012,24(13):1397-1420.
[111] SPECpower_ssj2008. http://www.spec.org/power_ssj2008/results/res2013q4/power_ssj2008-20130909-00633.html,2013.
[112] SPECpower_ssj2008. http://www.spec.org/power_ssj2008/results/res2012q4/power_ssj2008-20121031-00573.html,2012.
[113] SPECpower_ssj2008. http://www.spec.org/power_ssj2008/results/res2011q4/power_ssj2008-20111018-00402.html,2011.
[114] SPECpower_ssj2008. http://www.spec.org/power_ssj2008/results/res2010q3/power_ssj2008-20100727-00277.html,2010.
[115] SPECpower_ssj2008. http://www.spec.org/power_ssj2008/results/res2013q2/power_ssj2008-20130605-00611.html,2013.
[116] SPECpower_ssj2008. http://www.spec.org/power_ssj2008/results/res2013q2/power_ssj2008-20130607-00613.html,2013.
[117] MathWorks T. Matlab[J]. The MathWorks, Natick, MA,2004.
[118] P Sv rd, J Tordsson, B Hudzia, E Elmroth. High performance live migration throughdynamic page transfer reordering and compression[C]. Proc. of the3rd IEEEInternational Conf. on Cloud Computing Technology and Science.2011:542-548.
[119] H Jin, W Gao, S Wu, X Shi, X Wu, F Zhou. Optimizing the live migration of virtualmachine by CPU scheduling[J]. Journal of Network and Computer Applications. Vol.34,No.4,2011:1088-1096.
[120] Laurikainen R, Laitinen J, Lehtovuori P, Nurminen JK. Improving the Efficiency ofDeploying Virtual Machines in a Cloud Environment[C].2012INTERNATIONALCONFERENCE ON CLOUD AND SERVICE COMPUTING (CSC).2012:232-239.
[2] Krishnan, H. Amur, A. Gavrilovska, K. Schwan. VM Power Metering: Feasibility andChallenges[C]. Proceedings of the Second Green Metrics Workshop, in conjunction withSIGMETRICS'10. New York, USA: ACM Press, June14,2010,56-60.
[3] T. Wood, P. Shenoy, A. Venkataramani, M. Yousif. Black-box and Gray-box Strategies forVirtual Machine Migration[C]. Proceeding of the4th USENIX conference on NetworkedSystems Design&Implementation, Cambridge, UK: MA,2007,1-14.
[4] Wikipedia. John McCarthy (computer scientist)[EB/OL].(2008-10-07)[2008-12-10].http://en.wikipedia.org/wiki/John_McCarthy_(computer_scientist).
[5] IBM. Google and IBM announced university initiative to address internetscale computingchallenges [EB/OL].(2007-10-08)[2008-10-15] http://www-03.ibm.com/press/us/en/pressrelease/22414.wss.
[6] WANG Li-zhe, TAO Jie, KUNZE M. Scientific cloud computing: early definition andexperience[C]. Proc of the10th IEEE International Conference on High PerformanceComputing and Communications.2008:825-830.
[7] Barroso LA, Dean J, Holzle U. Web search for a planet: The Google cluster architecture.IEEE Micro,2003,23(2):2228.
[8] IBM. IBM cloud computing.http://www.ibm.com/cloud-computing/.
[9] Amazon. Amazon elastic compute cloud (Amazon EC2).2009. http://aws.amazon.com/ec2/.
[10]BRYANTRE. Data-intensive supercomputing: The case for DISC, CMU-CS-07-128[R].Pittsburgh, PA, USA: CarnegieMellon University, Department of Computer Science,2007.
[11]Nathan Regola, Jean-Christophe Ducom. Recommendations for VirtualizationTechnologies in High Performance Computing[C].2010IEEE second InternationalConference on Cloud Computing Technology and Science.2010:409-416.
[12]Hao Sun, Kento Aida. AHybrid and secure Mechanism to Execute Parameter SurveyApplications on Local and Public Cloud Resources[C].2010IEEE Second InternationalConference on Cloud Computing Technology and Science.2010:118-126.
[13]Kim Hyunjoo, El-Khamra Yaakoub, Jha Shantenu, Parashar Manish. Exploringapplication and infrastructure adaptation on hybrid grid-cloud infrastructure[C]. HPDC2010Proceedings of the19th ACM International Symposium on High PerformanceDistributed Computing.2010:402-412.
[14]Garey Michael R, Johnson David S. Computers and intractability-a guide to the theory ofnp-completeness[M]. San Francisco: W H Freeman Co,1979.
[15]Clark C, Fraser K, Hand S, et al. Live migration of virtual machines[C]. Proceedings ofthe Second Symposium on Networked Systems Design and Implementation (NSDI’05).Boston: USENIX ASSOC.2005:273-286.
[16]Nelson M, Lim B, Hutchins G. Fast transparent migration for virtual machines[C].Proceedings of the USENIX Annual Technical Conference (USENIX’05). Anaheim:USENIX ASSOC.2005:391-394.
[17]Michael R Hines, Umesh Deshpande, Kartik Gopalan. Post-copy live migration of virtualmachines[J]. ACM SIGOPS Operating Systems Review.2009:14-26.
[18]Michael R Hines, Kartik Gopalan. Post-Copy Based Live Virtual Machine MigrationUsing Adaptive Pre-Paging and Dynamic Self-Ballooning[C]. Proc. of the2009ACMSIGPLAN/SIGOPS International Conf. on Virtual Execution Environments.2009:51-60.
[19]Ori Ben-Yitzhak, Irit Goft, et al. An algorithm for parallel incremental compaction[C].ACM SIGPLAN Notices-MSP2002and ISMM2002(Proceedings of the3rdinternational symposium on Memory management).2003:100-105.
[20]H Jin, L Deng, S Wu, X Shi and X Pan. Live Virtual Machine Migration with AdaptiveMemory Compression[C]. Proc. of International Conf. on Cluster Computing andWorkshops (CLUSTER '09).2009:1-10.
[21]P Sv rd, B Hudzia, J Tordsson. Evaluation of Delta Compression Techniques for EfficientLive Migration of Large Virtual Machine[C]. Proc. of the2011ACM SIGPLAN/SIGOPSInternational Conf. on Virtual Execution Environments.2011:111-120.
[22]Gharachorloo K, Lenoski D, Laudon J, et al. Memory Consistency and Event Ordering inScalable Shared-memory Multiprocessors[C]. Proc of the17th International Symposiumon Computer Architecture, Seattle.1990:15-26.
[23]Gu Y F, Chen Z L. Approach to Tailoring Embedded Linux[J]. MINI-MICRO SYSTEMS,2003,24(9):1697-1700.
[24]Cheng Y L, Fang S H. Research and implementation of application-oriented embeddedLinux tailoring methods [J]. Computer Engineering and Design,2009,11:022.
[25]Wang L, Zhu S W, Yu J F. Transplant and Tailor of gSOAP Based on Embedded Linux[J].Applied Mechanics and Materials,2013,303:2445-2448.
[26]Tao L Y, Xu H J. Analysis of LFS Installation[J]. Computer Era,2007(9):54-56.
[27]Wang Y, Wang C L. Principle Analysis of Linux Operating System Build by LFS[J].Software Guide,2010(005).
[28]Cardosa M, Korupolu M R, Singh A. Shares and utilities based power consolidation invirtualized server environments[C]. Integrated Network Management,2009. IM'09.IFIP/IEEE International Symposium on. IEEE,2009:327-334.
[29]Grit L, Irwin D, Yumerefendi A, et al. Virtual machine hosting for networked clusters:Building the foundations for autonomic orchestration[C]. Proceedings of the2ndInternational Workshop on Virtualization Technology in Distributed Computing. IEEEComputer Society,2006:7.
[30]Machida F, Kim D S, Park J S, et al. Toward optimal virtual machine placement andrejuvenation scheduling in a virtualized data center[C]. Software Reliability EngineeringWorkshops,2008. ISSRE Wksp2008. IEEE International Conference on. IEEE,2008:1-3.
[31]Kochut A. On impact of dynamic virtual machine reallocation on data centerefficiency[C]. Modeling, Analysis and Simulation of Computers and TelecommunicationSystems,2008. MASCOTS2008. IEEE International Symposium on. IEEE,2008:1-8.
[32]Viswanathan B, Verma A, Dutta S. Cloudmap: Workload-aware placement in privateheterogeneous clouds[C]. Network Operations and Management Symposium (NOMS),2012IEEE. IEEE,2012:9-16.
[33]Bobroff N, Kochut A, Beaty K. Dynamic placement of virtual machines for managing slaviolations[C]. Integrated Network Management,2007. IM'07.10th IFIP/IEEEInternational Symposium on. IEEE,2007:119-128.
[34]Wang M, Meng X, Zhang L. Consolidating virtual machines with dynamic bandwidthdemand in data centers[C]. INFOCOM,2011Proceedings IEEE. IEEE,2011:71-75.
[35]Chaisiri S, Lee B S, Niyato D. Optimal virtual machine placement across multiple cloudproviders[C]. Services Computing Conference,2009. APSCC2009. IEEE Asia-Pacific.IEEE,2009:103-110.
[36]Bichler M, Setzer T, Speitkamp B. Capacity planning for virtualized servers[C].Workshop on Information Technologies and Systems (WITS), Milwaukee, Wisconsin,USA. sn,2006,1.
[37]Speitkamp B, Bichler M. A mathematical programming approach for server consolidationproblems in virtualized data centers[J]. Services Computing, IEEE Transactions on,2010,3(4):266-278.
[38]Van H N, Tran F D, Menaud J M. Performance and power management for cloudinfrastructures[C]. Cloud Computing (CLOUD),2010IEEE3rd International Conferenceon. IEEE,2010:329-336.
[39]Hermenier F, Lorca X, Menaud J M, et al. Entropy: a consolidation manager forclusters[C]. Proceedings of the2009ACM SIGPLAN/SIGOPS international conferenceon Virtual execution environments. ACM,2009:41-50.
[40]Greenberg A, Hamilton J R, Jain N, et al. VL2: a scalable and flexible data centernetwork[C]. ACM SIGCOMM Computer Communication Review. ACM,2009,39(4):51-62.
[41]Zhang Y, Su A J, Jiang G. Understanding data center network architectures in virtualizedenvironments: A view from multi-tier applications[J]. Computer Networks,2011,55(9):2196-2208.
[42]Al-Fares M, Loukissas A, Vahdat A. A scalable, commodity data center networkarchitecture[C]. ACM SIGCOMM Computer Communication Review. ACM,2008,38(4):63-74.
[43]Clos C. A Study of Non‐Blocking Switching Networks[J]. Bell System TechnicalJournal,1953,32(2):406-424.
[44]Hou W, Guo L, Wei X, et al. Multi-granularity and robust grooming in power-andport-cost-efficient IP over WDM networks[J]. Computer Networks,2012,56(10):2383-2399.
[45]Cuomo F, Cianfrani A, Polverini M, et al. Network pruning for energy saving in theInternet[J]. Computer Networks,2012,56(10):2355-2367.
[46]Heller B, Seetharaman S, Mahadevan P, et al. ElasticTree: Saving Energy in Data CenterNetworks[C]. NSDI.2010,10:249-264.
[47]Shang Y, Li D, Xu M. Energy-aware routing in data center network[C]. Proceedings ofthe first ACM SIGCOMM workshop on Green networking. ACM,2010:1-8.
[48]Mahadevan P, Banerjee S, Sharma P, et al. On energy efficiency for enterprise and datacenter networks[J]. Communications Magazine, IEEE,2011,49(8):94-100.
[49]Fang W, Liang X, Li S, et al. VMPlanner: Optimizing virtual machine placement andtraffic flow routing to reduce network power costs in cloud data centers[J]. ComputerNetworks,2012.
[50]Meng X, Pappas V, Zhang L. Improving the scalability of data center networks withtraffic-aware virtual machine placement[C]. INFOCOM,2010Proceedings IEEE. IEEE,2010:1-9.
[51]McGeer R, Mahadevan P, Banerjee S. On the complexity of power minimization schemesin data center networks[C]. Global Telecommunications Conference (GLOBECOM2010),2010IEEE. IEEE,2010:1-5.
[52]Mann V, Kumar A, Dutta P, et al. VMFlow: leveraging VM mobility to reduce networkpower costs in data centers[M]. NETWORKING2011. Springer Berlin Heidelberg,2011:198-211.
[53]Guo Y, Stolyar A L, Walid A. Shadow-routing based dynamic algorithms for virtualmachine placement in a network cloud[C]. INFOCOM,2013Proceedings IEEE. IEEE,2013:620-628.
[54]Steiner M, Gaglianello B G, Gurbani V, et al. Network-aware service placement in adistributed cloud environment[J]. ACM SIGCOMM Computer Communication Review,2012,42(4):73-74.
[55]Buyya R, Yeo C S, Venugopal S, et al. Cloud computing and emerging IT platforms:Vision, hype, and reality for delivering computing as the5th utility[J]. Future Generationcomputer systems,2009,25(6):599-616.
[56]Liu J, Zhao F, Liu X, et al. Challenges towards elastic power management in internet datacenters[C]. Distributed Computing Systems Workshops,2009. ICDCS Workshops'09.29th IEEE International Conference on. IEEE,2009:65-72.
[57]Meijer G I. Cooling energy-hungry data centers[J]. Science,2010,328(5976):318-319.
[58]Fakhim B, Behnia M, Armfield S W, et al. Cooling solutions in an operational data centre:A case study[J]. Applied thermal engineering,2011,31(14):2279-2291.
[59]Verma A, Ahuja P, Neogi A. pMapper: power and migration cost aware applicationplacement in virtualized systems[M]. Middleware2008. Springer Berlin Heidelberg,2008:243-264.
[60]Dong J, Jin X, Wang H, et al. Energy-Saving Virtual Machine Placement in Cloud DataCenters[C]. Cluster, Cloud and Grid Computing (CCGrid),201313th IEEE/ACMInternational Symposium on. IEEE,2013:618-624.
[61]Kantarci B, Foschini L, Corradi A, et al. Inter-and-intra data center VM-placement forenergy-efficient large-Scale cloud systems[C]. Globecom Workshops (GC Wkshps),2012IEEE. IEEE,2012:708-713.
[62]Abdelsalam H S, Maly K, Mukkamala R, et al. Analysis of energy efficiency in clouds[C].Future Computing, Service Computation, Cognitive, Adaptive, Content, Patterns,2009.COMPUTATIONWORLD'09. Computation World. IEEE,2009:416-421.
[63]Jung G, Hiltunen M A, Joshi K R, et al. Mistral: Dynamically managing power,performance, and adaptation cost in cloud infrastructures[C]. Distributed ComputingSystems (ICDCS),2010IEEE30th International Conference on. IEEE,2010:62-73.
[64]Srikantaiah S, Kansal A, Zhao F. Energy aware consolidation for cloud computing[C].Proceedings of the2008conference on Power aware computing and systems. USENIXAssociation,2008,10.
[65]Li B, Li J, Huai J, et al. Enacloud: An energy-saving application live placement approachfor cloud computing environments[C]. Cloud Computing,2009. CLOUD'09. IEEEInternational Conference on. IEEE,2009:17-24.
[66]Gao Y, Guan H, Qi Z, et al. A multi-objective ant colony system algorithm for virtualmachine placement in cloud computing[J]. Journal of Computer and System Sciences,2013,79(8):1230-1242.
[67]Békési J, Galambos G, Kellerer H. A5/4linear time bin packing algorithm[J]. Journal ofComputer and System Sciences,2000,60(1):145-160.
[68]E. Feller, L. Rilling, C. Morin, Energy-aware ant colony based workload placement inclouds[C]. Proceedings of the IEEE/ACM International Conference on Grid Computing(GRID),2011, pp.26–33.
[69]Davis L. Genetic algorithms and simulated annealing[J].1987.
[70]De Jong K A. Genetic algorithms: A10year perspective[C]. Proceedings of anInternational Conference on Genetic Algorithms and Their Applications.1985,1(6):9-177.
[71]Goldberg D E. Genetic algorithms in search, optimization, and machine learning[M].Reading Menlo Park: Addison-wesley,1989.
[72]Koza J R, Rice J P. Genetic generation of both the weights and architecture for a neuralnetwork[C]. Neural Networks,1991. IJCNN-91-Seattle International Joint Conference on.IEEE,1991,2:397-404.
[73]H. Andres Lagar-Cavilla, Joseph A. Whitney, Adin Scannell, Philip Patchin, Stephen M.Rumble, Eyal de Lara, Michael Brudno, M. Satyanarayanan. SnowFlock: Rapid VirtualMachine Cloning for Cloud Computing[C]. EuroSys09Proceedings of the4th ACMEuropean conference on Computer systems.2009.
[74]Lagar-Cavilla HA, Whitney JA, Bryant R, et al. SnowFlock: Virtual Machine Cloning asa First-Class Cloud Primitive[J]. ACM Transactions on Computer Systems (TOCS). Vol.29, No.2,2011:1-45.
[75]Vrable M, Ma J, Chen J, et al. Scalability, fidelity and containment in the Potemkinvirtual honeyfarm[C]. Proc20th Symposium on Operating Systems Principles (SOSP).2005:148-162.
[76]Wu XX, Shen ZM, Wu R, Lin YF. Jump-start Cloud: Efficient Deployment Frameworkfor Large-scale Cloud Applications[J]. CONCURRENCY AND COMPUTATION-PRACTICE&EXPERIENCE.2012:2120-2137.
[77]Schmidt Matthias, Fallenbeck Niels, Smith Matthew, Freisleben Bernd. Efficientdistribution of virtual machines for cloud computing[C]. Proceedings of the18thEuromicro Conference on Parallel, Distributed and Network-Based Processing.2010:567-574.
[78]Gerard Beekmans. Linux From Scratch. http://www.linuxfromscratch.org/lfs/view/stable/,2007.1.
[79]AA Fr hlich, W Schr der-Preikschat. Tailor-made operating systems for embeddedparallel applications[J]. Lecture Notes in Computer Science.1999:1361-1373.
[80]Hasan MZ, Sotirios SG. Customized kernel execution on reconfigurable hardware forembedded applications[J]. Microprocessors and Microsystems.2008:211-220.
[81]Montgomery J, Brewster GB, Yee WG. A customized Linux Kernel for ProvidingNotification of Pending Financial Transaction Information[C].7th IEEE ConsumerCommunications and Networking Conference.2010:1021-1022.
[82]APP-V [EB/OL]. http://www.microsoft.com/app-v.
[83]ThinApp [EB/OL]. http://www.vmware.com/products/thinapp/.
[84]XenApp [EB/OL]. http://www.citrix.com/xenapp.
[85]Zhang Han-ying, Wu Qing-bo, Tan Yu-song. On-demand Customized Virtual MachineInstance System[J]. COMPUTER TECHNOLOGY AND DEVELOPMENT. Vol.23, NO.4,2013:1-10.
[86]Ertl M A, Gregg D, Krall A, et al. Vmgen: A Generator of Efficient Virtual MachineInterpreters[J]. Software-Practice&Experience,2002,32(3):265-294.
[87]Ertl M A, Gregg D. The Structure and Performance of Efficient Interpreters[C]. MProc ofthe2004Workshop on Interpreters, Virtual Machines and Emulators,2004.
[88]Ouyang Xing-ming, Zhu Jin-yin. An Implementation Approach to Custom-Built VirtualMachines and Their Dynamic Optimization[J]. COMPUTER ENGINEERING&SCIENCE. Vol.30, NO.1,2008:129-141.
[89]GNU Binutils. http://en.wikipedia.org/wiki/GNU_Binutils.
[90]Nakajima J, Lin Q, Yang S, et al. Optimizing Virtual Machines Using HybridVirtualization[C]. Proc. Of the2011ACM Symposium on Applied Computing (SAC’11).2011:573-578.
[91]Barham P, Dragovic B, Fraser K, et al. Xen and the art of virtualization[C]. New York,USA: Proceedings of the19th ACM Symposium on Operating Systems Principles,2003.
[92]Amdahl G M. Validity of the single processor approach to achieving large scalecomputing capabilities[C]. Proceedings of the April18-20,1967, spring joint computerconference. ACM,1967:483-485.
[93]Gustafson J L. Reevaluating Amdahl's law[J]. Communications of the ACM,1988,31(5):532-533.
[94]Sun X H, Ni L M. Scalable problems and memory-bounded speedup[R]. INSTITUTEFOR COMPUTER APPLICATIONS IN SCIENCE AND ENGINEERING HAMPTONVA,1992.
[95]Tordsson J, Montero R S, Moreno-Vozmediano R, et al. Cloud brokering mechanisms foroptimized placement of virtual machines across multiple providers[J]. Future GenerationComputer Systems,2012,28(2):358-367.
[96]Wang W, Chen H, Chen X. An Availability-Aware Virtual Machine Placement Approachfor Dynamic Scaling of Cloud Applications[C]. Ubiquitous Intelligence&Computingand9th International Conference on Autonomic&Trusted Computing (UIC/ATC),20129th International Conference on. IEEE,2012:509-516.
[97]Yusoh Z I M, Tang M. A penalty-based genetic algorithm for the composite SaaSplacement problem in the cloud[C]. Evolutionary Computation (CEC),2010IEEECongress on. IEEE,2010:1-8.
[98]Ni Z W, Pan X F, Wu Z J. An Ant Colony Optimization for the Composite SaaSPlacement Problem in the Cloud[J]. Applied Mechanics and Materials,2012,130:3062-3067.
[99]Yusoh Z I M, Tang M. A cooperative coevolutionary algorithm for the composite SaaSplacement problem in the cloud[M]. Neural Information Processing. Theory andAlgorithms. Springer Berlin Heidelberg,2010:618-625.
[100] Wang H, Xu W, Wang F, et al. A Cloud-Computing-Based Data Placement Strategy inHigh-Speed Railway[J]. Discrete Dynamics in Nature and Society,2012,2012.
[101] Yuan D, Yang Y, Liu X, et al. A data placement strategy in scientific cloud workflows[J].Future Generation Computer Systems,2010,26(8):1200-1214.
[102] Guo L, He Z, Zhao S, et al. Multi-objective Optimization for Data Placement Strategyin Cloud Computing[M]. Information Computing and Applications. Springer BerlinHeidelberg,2012:119-126.
[103] Ding J, Han H Y, Zhou A H. A Data Placement Strategy for Data-Intensive CloudStorage[J]. Advanced Materials Research,2012,354:896-900.
[104] von Laszewski G, Wang L, Younge A J, et al. Power-aware scheduling of virtualmachines in dvfs-enabled clusters[C]. Cluster Computing and Workshops,2009.CLUSTER'09. IEEE International Conference on. IEEE,2009:1-10.
[105] Ge R, Feng X, Cameron K W. Performance-constrained distributed dvs scheduling forscientific applications on power-aware clusters[C]. Proceedings of the2005ACM/IEEEconference on Supercomputing. IEEE Computer Society,2005:34.
[106] Piao J T, Yan J. A network-aware virtual machine placement and migration approach incloud computing[C]. Grid and Cooperative Computing (GCC),20109th InternationalConference on. IEEE,2010:87-92.
[107] Hsu C H, Kremer U, Hsiao M. Compiler-directed dynamic frequency and voltagescheduling[M]. Power-Aware Computer Systems. Springer Berlin Heidelberg,2001:65-81.
[108] Srinivas M, Patnaik L M. Adaptive probabilities of crossover and mutation in geneticalgorithms[J]. Systems, Man and Cybernetics, IEEE Transactions on,1994,24(4):656-667.
[109] Calheiros R N, Ranjan R, Beloglazov A, et al. CloudSim: a toolkit for modeling andsimulation of cloud computing environments and evaluation of resource provisioningalgorithms[J]. Software: Practice and Experience,2011,41(1):23-50.
[110] Beloglazov A, Buyya R. Optimal online deterministic algorithms and adaptiveheuristics for energy and performance efficient dynamic consolidation of virtualmachines in Cloud data centers[J]. Concurrency and Computation: Practice andExperience,2012,24(13):1397-1420.
[111] SPECpower_ssj2008. http://www.spec.org/power_ssj2008/results/res2013q4/power_ssj2008-20130909-00633.html,2013.
[112] SPECpower_ssj2008. http://www.spec.org/power_ssj2008/results/res2012q4/power_ssj2008-20121031-00573.html,2012.
[113] SPECpower_ssj2008. http://www.spec.org/power_ssj2008/results/res2011q4/power_ssj2008-20111018-00402.html,2011.
[114] SPECpower_ssj2008. http://www.spec.org/power_ssj2008/results/res2010q3/power_ssj2008-20100727-00277.html,2010.
[115] SPECpower_ssj2008. http://www.spec.org/power_ssj2008/results/res2013q2/power_ssj2008-20130605-00611.html,2013.
[116] SPECpower_ssj2008. http://www.spec.org/power_ssj2008/results/res2013q2/power_ssj2008-20130607-00613.html,2013.
[117] MathWorks T. Matlab[J]. The MathWorks, Natick, MA,2004.
[118] P Sv rd, J Tordsson, B Hudzia, E Elmroth. High performance live migration throughdynamic page transfer reordering and compression[C]. Proc. of the3rd IEEEInternational Conf. on Cloud Computing Technology and Science.2011:542-548.
[119] H Jin, W Gao, S Wu, X Shi, X Wu, F Zhou. Optimizing the live migration of virtualmachine by CPU scheduling[J]. Journal of Network and Computer Applications. Vol.34,No.4,2011:1088-1096.
[120] Laurikainen R, Laitinen J, Lehtovuori P, Nurminen JK. Improving the Efficiency ofDeploying Virtual Machines in a Cloud Environment[C].2012INTERNATIONALCONFERENCE ON CLOUD AND SERVICE COMPUTING (CSC).2012:232-239.