Modern datacenter servers hosting popular Internet services face significant and multi-facet challenges in performance and power control. The user-perceived performance is the result of a complex interaction of comple...Modern datacenter servers hosting popular Internet services face significant and multi-facet challenges in performance and power control. The user-perceived performance is the result of a complex interaction of complex workloads in a very complex underlying system. Highly dynamic and bursty workloads of Internet services fluctuate over multiple time scales, which has a significant impact on processing and power demands of datacenter servers. High-density servers apply virtualization technology for capacity planning and system manageability. Such virtuMized computer systems are increasingly large and complex. This paper surveys representative approaches to autonomic performance and power control on virtualized servers, which control the quality of service provided by virtualized resources, improve the energy efficiency of the underlying system, and reduce the burden of complex system management from human operators. It then presents three designed self-adaptive resource management techniques based on machine learning and control for percentile-based response time assurance, non-intrusive energy-efficient performance isolation, and joint performance and power guarantee on virtualized servers. The techniques were implemented and evaluated in a testbed of virtualized servers hosting benchmark applications. Finally, two research trends are identified and discussed for sustainable cloud computing in green datacenters.展开更多
基于Matlab Web Server和WWW构建了空间虚拟实验室(VLSP),并简单介绍了数据分析系统。通过一个具体的电流片结构分析事例阐述了电流片结构分析模块的具体实现。应用该系统具体分析了2003年8月6日Cluster卫星观测到的重联耗散区附近的电...基于Matlab Web Server和WWW构建了空间虚拟实验室(VLSP),并简单介绍了数据分析系统。通过一个具体的电流片结构分析事例阐述了电流片结构分析模块的具体实现。应用该系统具体分析了2003年8月6日Cluster卫星观测到的重联耗散区附近的电流片结构。该系统具有良好的实用性和可扩展性,极大地方便了科研人员的研究工作。展开更多
通过在Hyper-V Server 2008 R2上部署虚拟服务器实例,就虚拟机图形化管理、虚拟机性能规划及对Linux的支持等方面进行了探索,并对提供相同服务的虚拟服务器及真实服务器的性能进行了比较;结果显示,虚拟机的CPU、内存性能要优于真实服务...通过在Hyper-V Server 2008 R2上部署虚拟服务器实例,就虚拟机图形化管理、虚拟机性能规划及对Linux的支持等方面进行了探索,并对提供相同服务的虚拟服务器及真实服务器的性能进行了比较;结果显示,虚拟机的CPU、内存性能要优于真实服务器,其网络性能相近,虚拟硬盘的性能虽有所不及,但可通过采用不同的存储方案获得提升。研究表明,使用Hyper-V Server 2008 R2虚拟化技术整合多个服务器是可行的。展开更多
简要介绍了Matlab 6.0中提供的Matlab Web Server组件的构成和功能,及其利用该组件实现网络虚拟实验平台的原理。具体叙述了利用Flash技术来模拟真实实验场景和Dreamweaver软件制作美观便利的实验界面网页的方法,以及最终如何实现和Mat...简要介绍了Matlab 6.0中提供的Matlab Web Server组件的构成和功能,及其利用该组件实现网络虚拟实验平台的原理。具体叙述了利用Flash技术来模拟真实实验场景和Dreamweaver软件制作美观便利的实验界面网页的方法,以及最终如何实现和Matlab的结合,借助其强大的计算绘图等功能完成实验内容的步骤和过程。展开更多
A hybrid distributed virtual environment （DVE） architecture is presented by importing a peer-to-peer （P2P） idea into the traditional client/server （C/S） architecture to improve the DVE system＇s scalability. The...A hybrid distributed virtual environment （DVE） architecture is presented by importing a peer-to-peer （P2P） idea into the traditional client/server （C/S） architecture to improve the DVE system＇s scalability. The mathematical model of the overload of the center server was built and a series of simulation experiments were performed to validate the conclusions. When the client number increases to a certain value, the hybrid architecture can reduce server overload with some special clients （temp servers） selected with a certain heuristic strategy. With this architecture, the DVE system can support more system clients with the same server hardware than the C/S architecture can. The server overload ＂pulse＂ phenomena causing by the exiting of the temp server can be resolved by adopting a more optimized temp server selecting strategy and by reducing the child client capability of the temp server. By combining the advantages of the C/S architecture and the P2P architecture, the hybrid DVE architecture can effectively improve the scalability of the DVE system. This is validated by theoretical analysis and simulation experiments.展开更多
基金supported in part by the National Science Foundation of USA under Grant Nos.CNS-0844983(CAREER Award)and CNS-1217979the National Natural Science Foundation of China under Grant No.61328203
文摘Modern datacenter servers hosting popular Internet services face significant and multi-facet challenges in performance and power control. The user-perceived performance is the result of a complex interaction of complex workloads in a very complex underlying system. Highly dynamic and bursty workloads of Internet services fluctuate over multiple time scales, which has a significant impact on processing and power demands of datacenter servers. High-density servers apply virtualization technology for capacity planning and system manageability. Such virtuMized computer systems are increasingly large and complex. This paper surveys representative approaches to autonomic performance and power control on virtualized servers, which control the quality of service provided by virtualized resources, improve the energy efficiency of the underlying system, and reduce the burden of complex system management from human operators. It then presents three designed self-adaptive resource management techniques based on machine learning and control for percentile-based response time assurance, non-intrusive energy-efficient performance isolation, and joint performance and power guarantee on virtualized servers. The techniques were implemented and evaluated in a testbed of virtualized servers hosting benchmark applications. Finally, two research trends are identified and discussed for sustainable cloud computing in green datacenters.
文摘基于Matlab Web Server和WWW构建了空间虚拟实验室(VLSP),并简单介绍了数据分析系统。通过一个具体的电流片结构分析事例阐述了电流片结构分析模块的具体实现。应用该系统具体分析了2003年8月6日Cluster卫星观测到的重联耗散区附近的电流片结构。该系统具有良好的实用性和可扩展性,极大地方便了科研人员的研究工作。
文摘通过在Hyper-V Server 2008 R2上部署虚拟服务器实例,就虚拟机图形化管理、虚拟机性能规划及对Linux的支持等方面进行了探索,并对提供相同服务的虚拟服务器及真实服务器的性能进行了比较;结果显示,虚拟机的CPU、内存性能要优于真实服务器,其网络性能相近,虚拟硬盘的性能虽有所不及,但可通过采用不同的存储方案获得提升。研究表明,使用Hyper-V Server 2008 R2虚拟化技术整合多个服务器是可行的。
文摘简要介绍了Matlab 6.0中提供的Matlab Web Server组件的构成和功能,及其利用该组件实现网络虚拟实验平台的原理。具体叙述了利用Flash技术来模拟真实实验场景和Dreamweaver软件制作美观便利的实验界面网页的方法,以及最终如何实现和Matlab的结合,借助其强大的计算绘图等功能完成实验内容的步骤和过程。
文摘A hybrid distributed virtual environment （DVE） architecture is presented by importing a peer-to-peer （P2P） idea into the traditional client/server （C/S） architecture to improve the DVE system＇s scalability. The mathematical model of the overload of the center server was built and a series of simulation experiments were performed to validate the conclusions. When the client number increases to a certain value, the hybrid architecture can reduce server overload with some special clients （temp servers） selected with a certain heuristic strategy. With this architecture, the DVE system can support more system clients with the same server hardware than the C/S architecture can. The server overload ＂pulse＂ phenomena causing by the exiting of the temp server can be resolved by adopting a more optimized temp server selecting strategy and by reducing the child client capability of the temp server. By combining the advantages of the C/S architecture and the P2P architecture, the hybrid DVE architecture can effectively improve the scalability of the DVE system. This is validated by theoretical analysis and simulation experiments.
