支持Live迁移机制的动态虚拟集群研究
|
摘要
虚拟集群是云计算环境中支持并行应用程序的基础,是虚拟化基础设施建设的重要组成。本文重点关注广域网环境下动态虚拟集群的相关问题,研究动态虚拟集群架构、虚拟集群创建和运行过程的动态性问题以及虚拟集群环境中典型应用的资源调度问题。
本文建立了广域网环境下的虚拟化基础设施,支持动态虚拟集群；提出了虚拟集群Live迁移机制,支持虚拟集群运行过程中的整体迁移；提出了虚拟网络映射算法,解决虚拟集群创建过程中的动态资源选择问题；结合虚拟集群自动配置方法,建立了虚拟集群动态部署框架；以数据密集型应用为例研究虚拟集群环境典型应用的资源调度问题。本文的主要贡献有：
1.进行虚拟集群Live迁移研究。提出了一个广域网环境下的支持虚拟集群Live迁移的虚拟化基础设施(Live-migration-enabled Virtual Infrastructure, LimeVI)。LimeVI通过混合式虚拟网络支持广域网环境下的动态虚拟集群(Elastic Virtual Cluser),支持并行应用程序。研究了虚拟集群并发Live迁移机制,包括动态虚拟路由系统、数据缓存机制和虚拟集群并发Live迁移协议(Concurrent Live Migration Protocol, CLIMP)。迁移过程保持了虚拟集群通信状态一致性、支持虚拟集群并发迁移、对并行应用程序透明。
2.进行虚拟集群动态部署研究。提出了虚拟网络映射算法(Virtual Network Embedding-VF, VNE-VF),解决虚拟集群创建过程中的动态资源选择问题,重点强调虚拟网络和物理网络的拓扑感知思想。在虚拟化基础设施基础上建立了一个虚拟集群动态部署框架,结合虚拟作业模型(Virtual Job Model)进行虚拟集群自动配置。
3.进行数据密集型应用调度研究。提出了一个支持作业截止时间的等待调度算法(Deadline-enabled Delay, DLD)。该算法面向云计算环境和大规模数据处理,着重体现了计算任务和数据资源之间的依赖关系、作业间的资源竞争以及作业截止时间约束,优化了云计算环境中数据密集型作业的调度。
4.对虚拟化基础设施(LimeVI)、虚拟集群动态部署框架以及相应的协议和调度算法进行了原型实现；通过实验分析验证了本文研究的一系列方法的有效性和先进性。
Research on Elastic Virutal Cluster Supporting Live Migration
With the increasing demands on large-scale applications, High Performance Computing (HPC) developed rapidly. The cloud computing technology based on new generation virtualization technology has become one of the most popular topics in HPC community. This dissertation focuses on the key issue of the building of infrastructure as a service (IaaS) in cloud computing environment, as well as facing the demand of high performance applications, also research on dynamic virtual clusters.
Cloud systems are usually based on virtualization technologies and virtual infrastructures. The virtualization technology emerged in the1960s. With the prompt development of computer science and technology, virtualization technology is developing from traditional OS-level virtualization to new generation distributed virtualization technology, such as virtual network, virtual cluster and virtual resource manager. Among which, virtual cluster is an important foundation of high performance application and important component of virtual infrastructure.
Virtualization technologies effectively separated hardware and software system, enhanced the flexibility, security and usability of Clouds. It benefits the dynamic nature of the virtual cluster at the same time. The dynamic nature of the virtual cluster is mainly reflected in two aspects of creating and running. In the creation process of virtual cluster, dynamic generation of virtual cluster according to user requirements and system resource status is virtual cluster dynamic deployment. During the operation of virtual cluster, due to system resource management requirements (such as load balancing and fault tolerance, etc.), the virtual cluster needs to be dynamically adjusted, which is virtual cluster live migration. Therefore, this article focuses on the research of the dynamic nature issues in the creating and running of the virtual cluster.
At the same time, virtual cluster services the high performance application. Along with the increasing emphasis on data importance, the research focusing on data intensive application is becoming popular topic of the high performance application area. This article is based on the research of dynamic virtual cluster and used data intensive application as example to research on typical parallel application resource scheduling issue.
At this stage, the following research work related to this article has several shortcomings:
(1) The researches focusing on virtual cluster live migration are insufficient. Existing work can support sole virtual machine live migration, but does not support the migration of the overall virtual cluster; it has package loss problem in the migration process, which leads to runtime error of parallel application, and does not support virtual cluster live migration; supports LAN Live migration, does not support WAN live migration.
(2) The study on dynamic deployment of virtual cluster is insufficient. One difficulty of the virtual cluster dynamic deployment is the resource selection of virtual cluster, which is virtual network mapping issue. Existing virtual network mapping study does not consider the communication requirements of parallel jobs. In addition, the evaluation of resources does not emphasized enough on topological properties of the physical network, which leads to waste of resources and poor mapping quality.
(3) Existing works are not adequate concerning dynamic resource availability, resource competition and service quality, which lead to insufficient scheduling results.
Under these circumstances, this article focuses on related questions of dynamic virtual cluster, research dynamic virtual cluster architecture under WAN environment, the dynamic issue of the creating and running of virtual cluster, as well as the typical application resource scheduling issue in virtual cluster. The main contributions of this dissertation are:
1. Research on virtual cluster live migration. A Live-migration-enabled Virtual Infrastructure (LimeVI) is proposed to support virtual cluster live migration under WAN environment. LimeVI is based on hybrid virtual network to support Elastic Virtual Cluster (EVC) over WAN and parallel application. A virtual cluster live migration mechanism is proposed, which includes a dynamic virtual network routing system, a data buffering mechanism and a Concurrent Live Migration Protocol (CLIMP) for virtual clusters. This mechanism is able to keep the consistencies of virtual cluster topology and message status, which keep the migration process complete transparent from parallel applications.
2. Research on dynamic virtual cluster resource scheduling. A virtual network embedding algorithm (VNE-VF) is proposed to solve dynamic resource selection problem in the creation process of virtual cluster, emphasize the topologies of both virtual cluster and physical network. Create a virtual cluster dynamic deployment framework and combined with the virtual operating model (VJM) to achieve virtual cluster dynamic deployment.
3. Research on data-intensive application scheduling. A Deadline-enabled Delay (DLD) scheduling algorithm is proposed to solve the problem of data-intensive job scheduling. The algorithm is focusing on cloud computing environments and large-scale data processing. DLD is based on a resource availability estimation method and emphasized the dependencies between jobs and data, the resource competition between jobs and job deadline constraints in order to optimize the scheduling of data-intensive operations in the cloud computing environment.
Through the prototype implementation and verification of the virtualization infrastructure (LimeVI), the virtual cluster scheduling framework, and the corresponding protocol and algorithm, a serious of tests is conducted to construct with the following conclusions:
1. The virtual infrastructure proposed (LimeVI) expands to WAN environment. It through hybrid virtual network to provide users with isolated virtual network, customized and separated virtual clusters. Parallel applications executes on virtual clusters in this system. The hybrid virtual network of LimeVI provides better network traffic performance, virtual clusters support parallel applications. It consists of hybrid virtual network, data buffering mechanism and virtual cluster migration mechanism, also supports virtual cluster live migration from system structure level. LimeVI supports cross-LAN virtual cluster live migration; CLIMP supports concurrent virtual cluster live migrations. Virtual cluster migrations does not have data package loss issue; does not affect the implementation of the parallel applications; transparent to the user application. Therefore, support overall migration of the parallel application runtime environment.
2. VNE-VF scheduling algorithm embodies topology-aware feature, which emphasis the parallel job communication needs and topology of physical network. This algorithm is based on the (sub) graph isomorphism algorithm to solve the virtual cluster resource selection problem, reducing the waste of resources, with higher quality of scheduling results. Formed dynamic deployment framework, automatic configuration of the virtual cluster based on virtual job model (VJM), and support the request for the on-demand dynamic deployment of virtual cluster resource demand.
3. The DLD scheduling algorithm is based on the resource availability estimation and job delay. Appropriate delays can improve data locality and reduce job completion time. It supports job deadline constraints and improves system service quality.
本文建立了广域网环境下的虚拟化基础设施,支持动态虚拟集群；提出了虚拟集群Live迁移机制,支持虚拟集群运行过程中的整体迁移；提出了虚拟网络映射算法,解决虚拟集群创建过程中的动态资源选择问题；结合虚拟集群自动配置方法,建立了虚拟集群动态部署框架；以数据密集型应用为例研究虚拟集群环境典型应用的资源调度问题。本文的主要贡献有：
1.进行虚拟集群Live迁移研究。提出了一个广域网环境下的支持虚拟集群Live迁移的虚拟化基础设施(Live-migration-enabled Virtual Infrastructure, LimeVI)。LimeVI通过混合式虚拟网络支持广域网环境下的动态虚拟集群(Elastic Virtual Cluser),支持并行应用程序。研究了虚拟集群并发Live迁移机制,包括动态虚拟路由系统、数据缓存机制和虚拟集群并发Live迁移协议(Concurrent Live Migration Protocol, CLIMP)。迁移过程保持了虚拟集群通信状态一致性、支持虚拟集群并发迁移、对并行应用程序透明。
2.进行虚拟集群动态部署研究。提出了虚拟网络映射算法(Virtual Network Embedding-VF, VNE-VF),解决虚拟集群创建过程中的动态资源选择问题,重点强调虚拟网络和物理网络的拓扑感知思想。在虚拟化基础设施基础上建立了一个虚拟集群动态部署框架,结合虚拟作业模型(Virtual Job Model)进行虚拟集群自动配置。
3.进行数据密集型应用调度研究。提出了一个支持作业截止时间的等待调度算法(Deadline-enabled Delay, DLD)。该算法面向云计算环境和大规模数据处理,着重体现了计算任务和数据资源之间的依赖关系、作业间的资源竞争以及作业截止时间约束,优化了云计算环境中数据密集型作业的调度。
4.对虚拟化基础设施(LimeVI)、虚拟集群动态部署框架以及相应的协议和调度算法进行了原型实现；通过实验分析验证了本文研究的一系列方法的有效性和先进性。
Research on Elastic Virutal Cluster Supporting Live Migration
With the increasing demands on large-scale applications, High Performance Computing (HPC) developed rapidly. The cloud computing technology based on new generation virtualization technology has become one of the most popular topics in HPC community. This dissertation focuses on the key issue of the building of infrastructure as a service (IaaS) in cloud computing environment, as well as facing the demand of high performance applications, also research on dynamic virtual clusters.
Cloud systems are usually based on virtualization technologies and virtual infrastructures. The virtualization technology emerged in the1960s. With the prompt development of computer science and technology, virtualization technology is developing from traditional OS-level virtualization to new generation distributed virtualization technology, such as virtual network, virtual cluster and virtual resource manager. Among which, virtual cluster is an important foundation of high performance application and important component of virtual infrastructure.
Virtualization technologies effectively separated hardware and software system, enhanced the flexibility, security and usability of Clouds. It benefits the dynamic nature of the virtual cluster at the same time. The dynamic nature of the virtual cluster is mainly reflected in two aspects of creating and running. In the creation process of virtual cluster, dynamic generation of virtual cluster according to user requirements and system resource status is virtual cluster dynamic deployment. During the operation of virtual cluster, due to system resource management requirements (such as load balancing and fault tolerance, etc.), the virtual cluster needs to be dynamically adjusted, which is virtual cluster live migration. Therefore, this article focuses on the research of the dynamic nature issues in the creating and running of the virtual cluster.
At the same time, virtual cluster services the high performance application. Along with the increasing emphasis on data importance, the research focusing on data intensive application is becoming popular topic of the high performance application area. This article is based on the research of dynamic virtual cluster and used data intensive application as example to research on typical parallel application resource scheduling issue.
At this stage, the following research work related to this article has several shortcomings:
(1) The researches focusing on virtual cluster live migration are insufficient. Existing work can support sole virtual machine live migration, but does not support the migration of the overall virtual cluster; it has package loss problem in the migration process, which leads to runtime error of parallel application, and does not support virtual cluster live migration; supports LAN Live migration, does not support WAN live migration.
(2) The study on dynamic deployment of virtual cluster is insufficient. One difficulty of the virtual cluster dynamic deployment is the resource selection of virtual cluster, which is virtual network mapping issue. Existing virtual network mapping study does not consider the communication requirements of parallel jobs. In addition, the evaluation of resources does not emphasized enough on topological properties of the physical network, which leads to waste of resources and poor mapping quality.
(3) Existing works are not adequate concerning dynamic resource availability, resource competition and service quality, which lead to insufficient scheduling results.
Under these circumstances, this article focuses on related questions of dynamic virtual cluster, research dynamic virtual cluster architecture under WAN environment, the dynamic issue of the creating and running of virtual cluster, as well as the typical application resource scheduling issue in virtual cluster. The main contributions of this dissertation are:
1. Research on virtual cluster live migration. A Live-migration-enabled Virtual Infrastructure (LimeVI) is proposed to support virtual cluster live migration under WAN environment. LimeVI is based on hybrid virtual network to support Elastic Virtual Cluster (EVC) over WAN and parallel application. A virtual cluster live migration mechanism is proposed, which includes a dynamic virtual network routing system, a data buffering mechanism and a Concurrent Live Migration Protocol (CLIMP) for virtual clusters. This mechanism is able to keep the consistencies of virtual cluster topology and message status, which keep the migration process complete transparent from parallel applications.
2. Research on dynamic virtual cluster resource scheduling. A virtual network embedding algorithm (VNE-VF) is proposed to solve dynamic resource selection problem in the creation process of virtual cluster, emphasize the topologies of both virtual cluster and physical network. Create a virtual cluster dynamic deployment framework and combined with the virtual operating model (VJM) to achieve virtual cluster dynamic deployment.
3. Research on data-intensive application scheduling. A Deadline-enabled Delay (DLD) scheduling algorithm is proposed to solve the problem of data-intensive job scheduling. The algorithm is focusing on cloud computing environments and large-scale data processing. DLD is based on a resource availability estimation method and emphasized the dependencies between jobs and data, the resource competition between jobs and job deadline constraints in order to optimize the scheduling of data-intensive operations in the cloud computing environment.
Through the prototype implementation and verification of the virtualization infrastructure (LimeVI), the virtual cluster scheduling framework, and the corresponding protocol and algorithm, a serious of tests is conducted to construct with the following conclusions:
1. The virtual infrastructure proposed (LimeVI) expands to WAN environment. It through hybrid virtual network to provide users with isolated virtual network, customized and separated virtual clusters. Parallel applications executes on virtual clusters in this system. The hybrid virtual network of LimeVI provides better network traffic performance, virtual clusters support parallel applications. It consists of hybrid virtual network, data buffering mechanism and virtual cluster migration mechanism, also supports virtual cluster live migration from system structure level. LimeVI supports cross-LAN virtual cluster live migration; CLIMP supports concurrent virtual cluster live migrations. Virtual cluster migrations does not have data package loss issue; does not affect the implementation of the parallel applications; transparent to the user application. Therefore, support overall migration of the parallel application runtime environment.
2. VNE-VF scheduling algorithm embodies topology-aware feature, which emphasis the parallel job communication needs and topology of physical network. This algorithm is based on the (sub) graph isomorphism algorithm to solve the virtual cluster resource selection problem, reducing the waste of resources, with higher quality of scheduling results. Formed dynamic deployment framework, automatic configuration of the virtual cluster based on virtual job model (VJM), and support the request for the on-demand dynamic deployment of virtual cluster resource demand.
3. The DLD scheduling algorithm is based on the resource availability estimation and job delay. Appropriate delays can improve data locality and reduce job completion time. It supports job deadline constraints and improves system service quality.
引文
[1]Lamia Youseff, Maria Butrico, Dilma Da Silva. Toward a Unified Ontology of Cloud Computing [C]. Proceedings of2008Grid Computing Environments Workshop, pp.1-10, Austin, TX, November2008.[2]Michael Armbrust, Armando Fox, Rean Griffith, etc. Above the Clouds:A Berkeley View of Cloud Computing, Technical Report No. UCB/EECS-2009-28[R]. Electrical Engineering and Computer Sciences University of California at Berkeley,2009.[3]Borja Sotomayor, Ruben S. Montero, Ignacio M. Llorente and Ian Forster. Virtual Infrastructure Management in Private and Hybrid Clouds [J]. IEEE Internet Computing,2009,13(5):14-22.[4]Xiaohui Wei, Hongliang Li, Liang Hu, Qingnan Guo, Na Jiang. LimeVI:A Platform for Virtual Cluster Live Migration over WAN [J]. International Journal of Computer Systems Science and Engineering (CSSE),2011,26(5):353-364.[5]Takahiro Hirofuchi, Takeshi Yokoi, Tadashi Ebara, etc. A Multi-Site Virtual Cluster System for Wide Area Networks [C]. Proceedings of LASCO'08,2008.[6]Paul Ruth, Phil McGachey, Dongyan Xu. VioCluster:Virtualization for Dynamic Computational Domains [C]. Proceedings of IEEE ICCC'05, pp.1-10, Burlington, MA, United states, Sep.2005.[7]Masaki Tatezono, Naoya Maruyama and Satoshi Matsuoka. Making Wide-Area, Multi-site MPI Feasible Using Xen VM [C]. Proceedings of ISPA'06, LNCS4331, pp.387-396,2006.[8]Wesley Emeneker, Dan Stanzione. Dynamic Virtual Clustering [C]. Proceedings of IEEE ICCC'07, pp.84-90, Austin, TX, US, September2007.[9]D. Nurmi, R. Wolski, C. Grzegorczyk, G. Obertelli, etc. The Eucalyptus Open-Source Cloud Computing System [C]. Proceedings of9th IEEE/ACM International Symposium on Cluster Computing and the Grid, CCGrid2009, IEEE Computer Society, pp.124-131, Shanghai, China, May18-21,2009.[10]K. Keahey, I. Foster, T. Freeman, X. Zhang. Virtual Workspaces:Achieving Quality of Service and Quality of Life on the Grid [J]. Scientific Programming,13(4):265-276,2005.[11]Franco Travostinoa, Paul Daspit, Leon Gommansc, Chetan Jog, etc. Seamless live migration of virtual machines over the MAN/WAN [J]. Future Generation Computer Systems. Elsevier, October,2006,22(8):901-907.[12]William Voorsluys, James Broberg, Srikumar Venugopal and Rajkumar Buyya. Cost of Virtual Machine Live Migration in Clouds:A Performance Evaluation [J]. Lecture Notes in Computer Science,2009, Vol5931/2009:254-265, Springer.[13]Michael Kozuch and M. Satyanarayanan. Internet Suspend/Resume [C]. Proceedings of Fourth IEEE Workshop on Mobile Computing Systems and Applications, WMCSA'02, August,2002, pp.40-46.[14]Ramesh Chandra, Nickolai Zeldovich, Constantine Sapuntzakis, Monica S. Lam. The Collective:A Cache-Based System Management Architecture [C]. Proceedings of2nd Symposium on Networked Systems Design&Implementation, NSDI'05,2005, pp.259-272.[15]Yingwei Luo, Binbin Zhang, Xiaolin Wang, Zhenlin Wang, Yifeng Sun, Haogang Chen). Live and Incremental Whole-System Migration of Virtual Machines Using Block-Bitmap [C]. Proceedings of2008IEEE International Conference on Cluster Computing, Tsukuba, Japan, October,2008, pp.99-106.[16]Robert Bradford, Evangelos Kotsovinos, Anja Feldmann, Harald Schioberg. Live Wide-Area??Migration of Virtual Machines with local persistent state.3rd international conference on Virtual execution environments [C]. Proceedings of VEE'07, SanDiego, California, USA, June13-15,2007, pp.169-179.[17]Takahiro Hirofuchi, Hidemoto Nakada, Hirotaka Ogawa, et al. A Live Storage Migration Mechanism over WAN and it's Performance Evaluation [C]. Proceedings of3rd international workshop on Virtualization technologies in distributed computing, VTDC'09, June15,2009, Barcelona, Spain, pp.67-74.[18]Xuxian Jiang, Dongyan Xu (2005). VIOLIN:Virtual Internetworking on OverLay Infrastructure [J]. Lecture Notes in Computer Science, Springer, vol.3358, pp.973-946.[19]Paul Ruth, Xuxian Jiang, Dongyan Xu and Sebastien Goasguen. Virtual distributed environments in a shared infrastructure [J]. COMPUTER, IEEE COMPUTER SOC,38(5):63-69.[20]Virtual machine mobility with vmware VMotion and cisco data center interconnect technologies [OL]. http://www.cisco.com/en/US/solutions/collateral/ns340/ns517/ns224/ns836/white_paper_c11-557822. pdf, September2009.[21]Christopher Clark, Keir Fraser, Steven Hand. Live Migration of Virtual Machines [C]. Proceedings of2nd conference on Symposium on Networked Systems Design and Implementation,2005, vol.2, pp.273-286.[22]M. Nelson, B.H. Lim, G. Hutchins. Fast transparent migration for virtual machines [C]. Proceedings of USENIX Annual Technical Conference,2005, page:391-394.[23]Hai Jin, Li Deng, Song Wu, Xuanhua Shi, Xiaodong Pan. Live Virtual Machine Migration with Adaptive Memory Compression [C]. Proceedings of IEEE International Conference on Cluster Computing, ICCC, New Orleans, LA, United states,2009.[24]Michael R. Hines, Umesh Deshpande, and Kartik Gopalan. Post-Copy Live Migration of Virtual Machines [J]. ACM SIGOPS Operating Systems Review, July2009,43(3):14-36.[25]A. Sundararaj, A. Gupta, P. Dinda, Dynamic Topology Adaptation of Virtual Networks of Virtual Machines, Proceedings of the Seventh Workshop on Languages, LCR2004, Houston, TX, USA, October22-23,2004.[26]A. Rezmerita, T. Morlier, V. Neri, F. Cappello. Private Virtual Cluster:Infrastructure and Protocol for Instant Grids [C]. Proceedings of Euro-Par2006. LNCS, vol.4128, page:393-404. Springer, Heidelberg,2006.[27]M.A. Murphy, S. Goasguen. Virtual Organization Clusters:Self-provisioned clouds on the grid [J]. Future Generation Computer Systems, Elsevier2010, doi:10.1016/j.future.2010.02.011.[28]M. Tsugawa, Jose A. B. Fortes. A Virtual Netowk (ViNe) Architecture for Grid Computing [C]. Proceedings of Parallel and Distributed Processing Symposium,2006, page:10.[29]A.Sundararaj, P. Dinda. Towards Virtual Networks for Virtual Machine Grid Computing [C]. Proceedings of the third conference on Virtual Machine Research and Technology Symposium, San Jose, California, United states,2004.[30]VMotion website [OL]. http://www.vmware.com/products/vc/vmotion.html[31]Stuart Hacking, Benoit Hudzia. Improving the Live Migration Process of Large Enterprise Applications [C]. Proceedings of VTDC'09, pp.51-58, Barcelona, Spain, June15,2009.[32]Haikun Liu, HaiJin, Xiaofei Liao, Liting Hu, Chen Yu. Live Migration of Virtual Machine Based on Full System Trace and Replay [C]. Proceedings of ACM HPDC09, pp.101-110,2009.[33]Jing Xu, Sumalatha Adabala, Jose A. B. Fortes. Towards autonomic virtual applications in the in-vigo system [C]. Proceedings of2nd International Conference on Autonomic Computing, ICAC2005,??Seattle, WA, United states, June13-16,2006, pp.15-26.[34]Michael J. Litzkow, Miron Livny and Matt W. Mutka. Condor-A Hunter of Idle Workstations [C]. Proceedings of International Conference on Distributed Computing Systems, San Jose, CA, UNITED STATES,1988, vol.8, pp.104-111.[35]G. Stellner. CoCheck:Checkpointing and process migration for MPI [C]. Proceedings of International Parallel Processing Symposium, Honolulu, Hawaii, UNITED STATES,1996, pp.526-531.[36]G. Bosilca, A. Bouteiller, F. Cappello, S. Djilali, G. F. Magniette, V. N'eri, A. Selikhov. MPICH-V: Toward a scalable fault tolerant MPI for volatile nodes [J]. Proceedings of2002ACM/IEEE conference on Supercomputing, Ohio, UNITED STATES,2002, pp.1-18.[37]Rajanikanth Batchu, Yoginder S. Dandass, Anthony Skjellum, Murali Beddhu. MPI/FT:A Model-Based Approach to Low-Overhead Fault Tolerant Message-Passing Middleware [J]. Cluster Computing,7(4):303-315,2004.[38]Xiaohui Wei, Hongliang Li, Dexiong Li. MPICH-G-DM:An Enhanced MPICH-G with Supporting Dynamic Job Migration [C]. Proceedings of4th ChinaGrid Annual Conference, ChinaGrid2009, Yantai, China,2009, pp.67-76.[39]Woo Namyoon, Jung Hyungsoo, Yeom Heon Young, Park Taesoon, Park Hyungwoo. MPICH-GF: Transparent Checkpointing and Rollback-Recovery for Grid-enabled MPI Processes [J]. IEICE Transactions on Information and Systems, E87-D(7):1820-1828.[40]Jeffrey Dean and Sanjay Ghemawat. Mapreduce:Simplified Data Processing on Large Clusters [C]. Proceedings of the6th Symposium on Operating Systems Design and Implementation, San Francisco, CA,pp.137-150,2004.[41]Jeffrey Dean. Experiences with MapReduce, an abstraction for large-scale computation [C]. Proceedings of the15th International Conference on Parallel Architectures and Compilation Techniques. ACM New York, NY, USA,2006.[42]S. Ghemawat, H. Gobioff, and S.-T. Leung. The Google File System [C]. Proceedings of SOSP2003, pp.29-43,2003.[43]T. White. Hadoop:The Definitive Guide [M]. O'Reilly,2009.[44]HDFS Architecture [OL]. http://hadoop.apache.org/core/docs/current/hdfs_design.html[45]Zhaohui Ding, Xiaohui Wei, etc. Implement the Grid Workflow Scheduling for Data Intensive Applications with CSF4[C]. Proceedings of Fourth IEEE International Conference on eScience, Indiana, U.S.,7-12Dec.2008, IEEE CS Press, pp.563-569.[46]Jianhua Jiang, Gaochao Xu, Xiaohui Wei. An Enhanced Data-aware Scheduling Algorithm for Batch-mode Dataintensive Jobs on Data Grid [C]. Proceedings of2006International Conference on Hybrid Information Technology, Vol.1, pp.257-262, Cheju Island, Korea,9-11November2006.[47]D. Thain, T. Tannenbaum, and M. Livny. Distributed computing in practice:the Condor experience [J]. Concurrency and Computation Practice and Experience,17(2-4):323-356,2005.[48]Matei Zaharia, Dhruba Borthakur, Joydeep Sen Sarma. Delay Scheduling:A Simple Technique for Achieving Locality and Fairness in Cluster Scheduling [C]. Proceedings of EuroSys'10, April13-16,2010, Paris, France.[49]Xiaohong Zhang, Zhiyong Zhong, etc. Improving Data Locality of MapReduce by Scheduling in Homogeneous Computing Environments [C]. Proceedings of Ninth IEEE International Symposium on Parallel and Distributed Processing with Applications, pp.120-126.[50]S. Seo, I. Jang, K. Woo, I. Kim, J.-S. Kim and S. Maeng.Hpmr:Prefetching and pre-shuffling in shared mapreduce computation environment [C]. Proceedings of CLUSTER'10, pp.1-8,2009.[51]Jiong Xie, Shu Yin, Xiaojun Ruan, etc. Improving MapReduce Performance through Data Placement in Heterogeneous Hadoop Clusters [C]. Proceedings of2010IEEE International Symposium onParallel&Distributed Processing, pp.1-8, Atlanta, Georgia, April,2010.[52]Yuan Luo, Zhenhua Guo, Yiming Sun, Beth Plale, Judy Qiu, Wilfred Li. A Hierarchical Framework for Cross-Domain MapReduce Execution [C]. Proceedings of the second international workshop on emerging computational methods for the life sciences (ECMLS11). ACM, New York, NY, USA,2011, pp.15-22. DOI=10.1145/1996023.1996026.[53]Jeff A. Stuart and John D. Owens. Multi-GPU MapReduce on GPU Clusters [C]. Proceedings of2011IEEE International Parallel&Distributed Processing Symposium, pp.1068-1079,2011.[54]Feng Ji and Xiaosong Ma. Using Shared Memory to Accelerate MapReduce on Graphics Processing Units [C]. Proceedings of2011IEEE International Parallel&Distributed Processing Symposium, pp.805-816,2011.[55]Hyunseok Chang, MuraliKodialam, Ramana Rao Kompella, etc. Scheduling in MapReduce-like Systems for Fast CompletionTime [C]. Proceedings of INFOCOM2011, pp.3074-3082.[56]Zhaohui Ding, Xiaohui Wei, Wilfred W Li, etc. Customized Plug-in Modules in Metascheduler CSF4for Life Sciences Applications [J]. Jounral of New Generation Computing,25(4):373-394, Aug.2007.[57]K. Kc and K. Anyanwu. Scheduling Hadoop jobs to meet deadlines [C]. Proceedings of2nd IEEE International Conference on Cloud Computing Technology and Science (CloudCom),2010, pp.388-392.[58]J. Polo, D. Carrera, Y. Becerra, J. Torres, E. Ayguade and, M. Steinder and I. Whalley In Performance-driven task co-scheduling for Mapreduce environments [C]. Proceedings of Network Operations and Management Symposium (NOMS), IEEE,2010, pp.373-380.[59]Xiaohui Wei, Haibin Wang, Hongliang Li, Lei Zou. Dynamic deployment and management of elastic virtual clusters [C]. Proceedings of20116th Annual ChinaGrid Conference, ChinaGrid2011, pp.35-41, August22-23,2011, Dalian, China.[60]Zhaohui Ding, Xiaohui Wei, Da Ma etc. VJM-A Deadlock Free Resource Co-allocation Model for Cross Domain Parallel Jobs [C]. Proceedings of High Performance Computing Asia2007, Korea, Sep9-12,2007.[61]Xiaohui Wei, Zhaohui Ding. A Novel Grid Resource Co-Allocation Model for Parallel Jobs [C]. Proceedings of GDC2008, Sanya, China,2008, IEEE CS Press.[62]Y Zhu and M. Ammar. Algorithms for assigning substrate network resources to virtual network components. In Proc. IEEE INFOCOM,2006.[63]Minlan Yu, Yung Yi, Jennifer Rexford and Mung Chiang. Rethinking Virtual Network Embedding: Substrate Support for Path Splitting and Migration [J]. ACM SIGCOMM Computer Communication Review Volume38Issue2, April2008.[64]J. Fan and M. Ammar. Dynamic Topology Configuration in Service Overlay Networks:A Study of Reconfiguration Policies [C]. Proceedings of IEEE INFOCOM,2006.[65]J. Lu and J. Turner. Efficient mapping of virtual networks onto a shared substrate [J]. Department of Computer Science and Engineering, Washington University in St. Louis, Technical Report WUCSE-2006,35,2006.[66]Chowdhury N.M.M.K, Rahman M.R and Boutaba R. Virtual Network Embedding with Coordinated Node and Link Mapping [C]. Proceedings of IEEE INFOCOM,2009.[67]Jens Lischka and Holger Karl. A virtual network mapping algorithm based on subgraph isomorphism??detection [C]. Proceedings of Pattern Analysis and Machine Intelligence the1st ACM workshop on virtualized infrastructure systems and architectures pages81-88, ACM,2009.[68]Cordella L.P., Foggia P., Sansone C., Vento M. A (sub)graph isomorphism algorithm for matching large graphs [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,26(10):1367-1372, Oct.2004.[69]W.-L. Yeow, C. Westphal, and U. Kozat. Designing and embedding reliable virtual infrastructures [J]. Proceedings of ACM VISA,2010, pp.33-40.[70]Nabeel Farooq Butt, Mosharaf Chowdhury and Raouf Boutaba. Topology-Awareness and Reoptimization Mechanism for Virtual Network Embedding [C]. In Networking2010:9th International IFIP TC6Networking Conference, Chennai, India, May11-15,2010, pp.27-39.[71]E. Zegura, K. Calvert, and S. Bhattacharjee. How to model an Internetwork [C]. Proceedings of IEEE INFOCOM,1996, pp.594-602
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |