远程控制系统中Web服务器的请求调度算法研究
|
摘要
互联网的广泛普及，特别是万维网的迅猛发展，使基于Web的远程控制技术成为远程控制领域新的发展方向和研究热点。在基于Web的远程控制系统中，Web服务器是关键部件之一，直接影响着远程控制系统能否快速、准确、可靠地完成控制任务。而且，随着光纤、新一代交换机等宽带技术在互联网领域的广泛应用，网速越来越快。与之相对，Web服务器逐渐成为基于Web的远程控制系统的性能瓶颈。Web服务器性能的提升主要依靠提高硬件性能和改进Web服务器软件的请求调度算法。为了提高Web服务器的硬件性能，人们开始把多核处理器应用于Web服务器。多核处理器在Web服务器中的应用改变了传统Web服务器软件的运行环境，也产生了新的请求调度问题。因此，本课题提出了适用于多核Web服务器的动态请求调度算法，并对多核Web服务器的建模、多核Web服务器的“乒乓”效应等问题进行了研究。所做主要工作如下：
（1）建立了多核Web服务器的排队网络模型。在对Web服务器的研究过程中，为了分析Web服务器的性能，已经出现了许多使用排队网络理论或Petri网理论对Web服务器建立的数学解析模型。但是这些已建立的Web服务器的性能模型大多是针对单核处理器的。因此，本课题在详细分析Web服务器动态请求处理过程的基础上，依据排队网络理论，建立了多核Web服务器的排队网络模型。该排队网络模型使用泊松过程请求流作为输入流，但也对自相似请求流的情况进行了讨论。
（2）研究了多核处理器的“乒乓”效应问题。多核处理器在一个芯片上集成多个处理器核心的同时，也改变了处理器的缓存结构。多核处理器往往有多级缓存，这样就产生了缓存一致性的问题。而缓存的一致性问题往往会引起处理器核心之间的“乒乓”效应，这会严重影响多核处理器的性能。本课题在对现有操作系统的线程调度算法和典型的片上多核处理器的缓存结构进行研究的基础之上，尝试使用操作系统提供的进程/线程硬亲和性的方法消除多核处理器的“乒乓”效应问题。为了验证此方法，进行了仿真实验，实验结果证明了此方法的有效性。
（3）提出了多核Web服务器中的动态请求调度算法。在对Web服务器动态请求处理过程进行深入研究之后，为了消除多核处理器中存在的“乒乓”效应问题，在充分考虑了动态请求服务时间的分布特点的基础上，本课题提出了针对多核Web服务器的动态请求调度算法。新的动态请求调度算法先对动态请求进行分类，然后进入不同的动态请求队列，而且将为同一类动态请求提供服务的服务线程分配至同一个处理器核心以避免“乒乓”效应。此外，为了保持各处理器核心之间的负载均衡，使用遗传算法规划出最佳的服务线程分配方案。
（4）进行了多核Web服务器中动态请求调度算法的仿真实验。在新的动态请求调度算法的基础上，本课题开发了仿真Web服务器，泊松过程和自相似动态请求流的生成器，并使用这些工具进行了仿真实验。实验测量出了新算法的响应时间分布、平均响应时间、丢包率等关键的性能参数，并且同常用的短作业优先和先到先服务等请求调度策略的性能进行了对比。
With the rapidly development of Internet and WWW, the web-basedremote control technology become a new orientation of development andhot research topic of the remote control field. Web server is the keycomponent for web-based remote control system, and decides whetherremote control system could accomplish a task quickly, accurately, andreliably. Furthermore, with the widely application of fiber and newgeneration switch in the Internet filed, the speed of network is more andmore quick. On the contrary, web server becomes the performancebottleneck of the web-based remote control system. The performance ofweb server relies on the performance of hardware and request schedulingalgorithm in web server software. In order to improve the performance ofweb server hardware, multi-core CPU is applied to web server. Theapplication of multi-core CPU to web server changes the runningenvironment of traditional web server software, and leads to new requestscheduling problems. So this paper proposed a new dynamic requestscheduling algorithm for multi-core web server, and studied the modelingof multi-core web server and ping-pong effect of multi-core web server. The research items are as follows:
(1) Constructing the queueing network model for multi-core webserver. In order to analyze the performance of web server, there have beenmany performance models for web server based on queueing networktheory and Petri theory. But these performance models of web server arejust for the single-core web server. To evaluate the performance ofmulti-core web server, the thesis constructed the queueing network modelfor multi-core web server on the basis of the analysis of requestscheduling process and queueing network theory. The model uses Poissonprocess as input arrival process. At the same time, the model discusses theself-similar arrival process as well.
(2) Studying the ping-pong effect of multi-core CPU. As it integratedmulti processing cores into one chip, multi-core CPU changed thestructure of caches too. There are usually multi-level caches in multi-coreCPU, which would lead to the problem of cache coherence. The problemof cache coherence is liable to cause the ping-pong effect betweenprocessor cores, which will greatly reduce the performance of multi-coreCPU. According to the research of threads scheduling policies of currentO/S and the cache structure of multi-core CPU, this thesis tried toeliminate the ping-pong effect by means of threads/processes hard affinitymethods provided by O/S. For validating the method, we do a simulationexperiment, and the experiment results proved that it is an effective method that eliminates the ping-pong effect by means of the affinity ofthreads/processes.
(3) Proposing a dynamic request scheduling algorithm for multi-coreweb server. After making a thorough study in the process of handlingdynamic requests, in order to eliminate the ping-pong effect in multi-coreCPU, a new dynamic request scheduling algorithm is proposed accordingthe service time distribution of dynamic requests. The new algorithmclassifies the dynamic requests, and then the dynamic requests enter intothe different dynamic request queues. The threads that served for thesame dynamic request queue are assigned to the same processor core.Moreover, to keep the load balance between processor cores, the bestthreads assignment policy is calculated by means of Genetic Algorithm.
(4) Conducting the simulation experiment based on the new dynamicrequest scheduling algorithm in multi-core web server. The simulationweb sever was developed on the basis of the new dynamic requestscheduling algorithm in multi-core web server. Furthermore, wedeveloped the sending module of Poisson arrival process and self-similararrival process. With the help of these tools, we conducted a series ofsimulation experiments. We measured the key indices of performance,such as response time distribution, mean response time, dropped rate andso on. At the same time, we do the simulation experiments based onshortest-job-first and first-come-first-served policies respectively, and compared their performance to the new dynamic request schedulingalgorithm.
（1）建立了多核Web服务器的排队网络模型。在对Web服务器的研究过程中，为了分析Web服务器的性能，已经出现了许多使用排队网络理论或Petri网理论对Web服务器建立的数学解析模型。但是这些已建立的Web服务器的性能模型大多是针对单核处理器的。因此，本课题在详细分析Web服务器动态请求处理过程的基础上，依据排队网络理论，建立了多核Web服务器的排队网络模型。该排队网络模型使用泊松过程请求流作为输入流，但也对自相似请求流的情况进行了讨论。
（2）研究了多核处理器的“乒乓”效应问题。多核处理器在一个芯片上集成多个处理器核心的同时，也改变了处理器的缓存结构。多核处理器往往有多级缓存，这样就产生了缓存一致性的问题。而缓存的一致性问题往往会引起处理器核心之间的“乒乓”效应，这会严重影响多核处理器的性能。本课题在对现有操作系统的线程调度算法和典型的片上多核处理器的缓存结构进行研究的基础之上，尝试使用操作系统提供的进程/线程硬亲和性的方法消除多核处理器的“乒乓”效应问题。为了验证此方法，进行了仿真实验，实验结果证明了此方法的有效性。
（3）提出了多核Web服务器中的动态请求调度算法。在对Web服务器动态请求处理过程进行深入研究之后，为了消除多核处理器中存在的“乒乓”效应问题，在充分考虑了动态请求服务时间的分布特点的基础上，本课题提出了针对多核Web服务器的动态请求调度算法。新的动态请求调度算法先对动态请求进行分类，然后进入不同的动态请求队列，而且将为同一类动态请求提供服务的服务线程分配至同一个处理器核心以避免“乒乓”效应。此外，为了保持各处理器核心之间的负载均衡，使用遗传算法规划出最佳的服务线程分配方案。
（4）进行了多核Web服务器中动态请求调度算法的仿真实验。在新的动态请求调度算法的基础上，本课题开发了仿真Web服务器，泊松过程和自相似动态请求流的生成器，并使用这些工具进行了仿真实验。实验测量出了新算法的响应时间分布、平均响应时间、丢包率等关键的性能参数，并且同常用的短作业优先和先到先服务等请求调度策略的性能进行了对比。
With the rapidly development of Internet and WWW, the web-basedremote control technology become a new orientation of development andhot research topic of the remote control field. Web server is the keycomponent for web-based remote control system, and decides whetherremote control system could accomplish a task quickly, accurately, andreliably. Furthermore, with the widely application of fiber and newgeneration switch in the Internet filed, the speed of network is more andmore quick. On the contrary, web server becomes the performancebottleneck of the web-based remote control system. The performance ofweb server relies on the performance of hardware and request schedulingalgorithm in web server software. In order to improve the performance ofweb server hardware, multi-core CPU is applied to web server. Theapplication of multi-core CPU to web server changes the runningenvironment of traditional web server software, and leads to new requestscheduling problems. So this paper proposed a new dynamic requestscheduling algorithm for multi-core web server, and studied the modelingof multi-core web server and ping-pong effect of multi-core web server. The research items are as follows:
(1) Constructing the queueing network model for multi-core webserver. In order to analyze the performance of web server, there have beenmany performance models for web server based on queueing networktheory and Petri theory. But these performance models of web server arejust for the single-core web server. To evaluate the performance ofmulti-core web server, the thesis constructed the queueing network modelfor multi-core web server on the basis of the analysis of requestscheduling process and queueing network theory. The model uses Poissonprocess as input arrival process. At the same time, the model discusses theself-similar arrival process as well.
(2) Studying the ping-pong effect of multi-core CPU. As it integratedmulti processing cores into one chip, multi-core CPU changed thestructure of caches too. There are usually multi-level caches in multi-coreCPU, which would lead to the problem of cache coherence. The problemof cache coherence is liable to cause the ping-pong effect betweenprocessor cores, which will greatly reduce the performance of multi-coreCPU. According to the research of threads scheduling policies of currentO/S and the cache structure of multi-core CPU, this thesis tried toeliminate the ping-pong effect by means of threads/processes hard affinitymethods provided by O/S. For validating the method, we do a simulationexperiment, and the experiment results proved that it is an effective method that eliminates the ping-pong effect by means of the affinity ofthreads/processes.
(3) Proposing a dynamic request scheduling algorithm for multi-coreweb server. After making a thorough study in the process of handlingdynamic requests, in order to eliminate the ping-pong effect in multi-coreCPU, a new dynamic request scheduling algorithm is proposed accordingthe service time distribution of dynamic requests. The new algorithmclassifies the dynamic requests, and then the dynamic requests enter intothe different dynamic request queues. The threads that served for thesame dynamic request queue are assigned to the same processor core.Moreover, to keep the load balance between processor cores, the bestthreads assignment policy is calculated by means of Genetic Algorithm.
(4) Conducting the simulation experiment based on the new dynamicrequest scheduling algorithm in multi-core web server. The simulationweb sever was developed on the basis of the new dynamic requestscheduling algorithm in multi-core web server. Furthermore, wedeveloped the sending module of Poisson arrival process and self-similararrival process. With the help of these tools, we conducted a series ofsimulation experiments. We measured the key indices of performance,such as response time distribution, mean response time, dropped rate andso on. At the same time, we do the simulation experiments based onshortest-job-first and first-come-first-served policies respectively, and compared their performance to the new dynamic request schedulingalgorithm.
引文
[1]云利军,孙鹤旭,雷兆明,王炜.运动控制网络的研究现状及发展趋势[J].控制工程,2006,13(4):289-293
[2]马龙昌.基于Web的远程监控系统的研究与应用[D].西安:长安大学,2009
[3]林海.浏览器/服务器应用开发[M].北京：科学出版社,2001
[4] Young C, Juang W L, Michael J D. Real-time intranet-controlled virtual instrumentmultiple-circuit power monitoring [J]. IEEE Transcations on Instrumentation andMeasurement,2000,49(3):579-584
[5] JimHenry. Engineering on the web [EB/OL]. http://chem.engr.utc.edu
[6] Bradford Robotic Telescope [EB/OL]. http://www.telescope.org/
[7] Shuanghua Yang, Chengwei Dai, Roger PK. Remote maintenance of control systemperformance over the Internet [J]. Control Engineering Practice,2007,15(5):533-544
[8] Brady K, Tarn T J. Internet-based remote teleoperation [C]. In: IEEE Internationalconference on robotics&automation. Leuven,1998,65-70
[9] Backes PG, Tso K S, Tharp G.K. Mars pathfinder mission Internet-based operationsusing WITS [C]. In: IEEE International conference on Robotics&Automation. SanFrancisco,2000,2025-2032
[10] Eric P, John C. Delivering real reality to the world wide web via telerobotics [C]. In:IEEE International conference on Robotics&automation. Minneapolis,1996.1694-1699
[11] Taylor K, Dalton B, Trevelyan J. Web-based tele-robotics [J]. Robotica,1999,17(1):49-57
[12]聂雪媛,时忠民,黄映城,丁桦,耿丽.基于B/S的海洋平台远程监控系统设计[J].微计算机信息,2007,05X:1-3
[13]祁享年,蒋梁中.基于Web的广域污染源水质自动监控系统研究[J].仪器仪表学报,2008,29(1):120-123
[14]李云,陈刚,魏泽峰.基于Web铁路信号电源的远程监控系统的设计与实现[J].铁路计算机应用,2007,16(8):49-52
[15]陆璐,刘发贵.基于Web的远程监控系统[M].北京:清华大学出版社,2008.61-63
[16]姚念民,郑名扬,鞠九滨.基于流水线的高性能Web服务器[J].软件学报,2003,14(6):1127-1133
[17]王彬蔚.网络中的服务质量(Qos)的研究[D].成都:电子科技大学,2002
[18] Kirubanand V B, Palaniammal S. Distributed Data Transaction of an Apache Web ServerUsing bulk service rule [J]. International Journal of Computer Application,2011,24(8):1-4
[19]罗红兵,张宝印,曹立强.利用作业可塑性改进结合回填FCFS策略的性能[J]，计算机工程与应用,2007,43(24):41-46
[20] Abdouni Khayari R E, Musovic A, Lehmann A, Fellinger P. A workload based adaptivescheduling algorithm for web server [C]. In: Proceedings of the2009Spring SimulationMulticonference. San Diego: SCSI,2009
[21] Abdouni Khayari R E. Class-based weighted fair queueing: Validation and comparisonby trace-driven simulation [J]. International Journal of Communication Systems,2005,18:975-994
[22] Fiorini P, Oboe R. Internet-based teleroboties: Problems and approaches [C]. In:International Conference ofAdvanced Robotics (Icar’97), Monterey:1997
[23] Talyor K, Dalton B. Issues in Internet Telerobotics [C]. In: Int.Conf on Field and ServiceRobtics. Canberra:Australian Robot Association,1997,151-157
[24] Multi-Core from Intel-Products and Platforms [EB/OL]. http://www.intel.com/multi-core/products.htm
[25] AMD Multi-Core Products [EB/OL]. http://multicore.amd.com/en/Products
[26] Kongetira P, Aingaran K., Olukotun K. Niagara: a32-way multithreaded sparc processor[J]. IEEE Micro,2005,25:21-29
[27] World Wide Web Consortium [EB/OL]. http://www.w3c.org
[28] RFC1738. Uniform Resource Locators (URL)[S].1994
[29]李军,徐玖平.运筹学--非线性系统优化[M].北京:科学出版社,2003.35-62.
[30]刘嘉馄.应用随机过程[M].北京:科学出版社,2006
[31]孙荣恒,李建平.排队论基础[M].北京:北京科技出版社,2002
[32]陆传赉.排队论[M].北京:北京邮电学院出版社,1994
[33]唐应辉.排队论-基础与分析技术[M].北京:北京科学出版社,2006
[34]孙荣恒.随机过程及其应用[M].北京:清华大学出版社,2004
[35][美]华兴.排队论与随机服务系统[M].上海:上海翻译出版公司,1987
[36]高世泽.概率统计引论[M].重庆:重庆大学出版社,2000
[37] Slothouber L P. A model of web server performance [C]. In: Proceedings of the FifthInternational World Wide Web Conference,1996.
[38] Nunez-Queija R. Processor-Sharing models for integrated-services networks [D].Eindhoven: Eindhoven university of technology,2000
[39] Rolia J A, Sevcik K C. The method of Layers [J]. IEEE Transactions on SoftwareEngineering,1995,21(8):689-700
[40] Ramesh S, Perros H G. A multilayer client-server queueing network model withsynchronous and asynchronous messages [J]. IEEE Transactions on SoftwareEngineering,2000,26(11):1086-1100
[41] Dilley J, Friedrich R, Jin T. Web server performance measurement and modelingtechniques [J]. Perform. Eval,1998,33(1):5-26
[42] Heidemann J, Obraczka K, Touch J. Modeling the performance of HTTP over severaltransport protocols [J]. IEEE/ACM Trans,1997,5(5):616-630
[43] Kamra A, Misra V, Nahum E M. Yaksha: a self-tuning controller for managing theperformance of3-tiered web sites [C]. In: Twlefth IEEE International workshop onquality of service,2004:47-56
[44] Wells L, Christensen S, Kristensen L M. Simulation based performance analysis of Webservers [C]. In:9thInternational workshop on Petri Nets and performance models,2001:59-68
[45] Liu X, Heo J, Sha L. Modeling3-tiered Web applications [C]. In:13th IEEEInternational Symposium on Modeling, Analysis, and Simulation of Computer andTelecommunication System,2005:307-310
[46] Van Der Mei R D, Hariharan R, Reeser P K. Web Server performance modeling [J].Telecommunication Systems,2001,16(3):361-378
[47] Cao J, Andersson M, Nyberg C. Web server performance modeling using anM/G/1/K*PS queue [C]. In:10th International Conference on Telecommunications,2003,2:1501-1506.
[48] Intel corporation terascale computing [EB/OL]. http://www.intel.com/research/platform/terascale/index.htm
[49] Multi-core processor-the next evolution in computing [EB/OL]. http://www.amd.com
[50]鲁建壮,王志英,张春元.面向SCMP的多线程前瞻控制分析与设计[J].计算机工程与科学,2006,28(10):128-130
[51]宋风龙,刘志勇,范东睿,张军超,余磊.一种片上众核结构共享Cache动态隐式隔离机制研究[J].计算机学报,2009,32(10):1896-1904
[52] El-Moursy A, Garg R, Albonesi D H, Dwarkadas S. Compatible Phase Co-Schedulingon a CMP of Multi-Threaded Processors [C]. In: Proceeding20th IEEE InternationalParallel&Distributed Processing Symposium,2006,1-10
[53] Suh T, Blough D M, Lee H H S. Supporting Cache Coherence in HeterogeneousMultiprocessor System [C]. In: Proceeding of Design, Automation and Test in EuropeConference and Exhibition,2004,1150-1155
[54] Sorin D J, Plakal M, Codon A E, Hill M D, Martin M M K, Wood D A. Specifying andverifying a broadcast and a multicast snooping cache coherence protocol [J]. Parallel andDistributed Systems,2002,13(6):556-578
[55] Hennessy J L, Patterson D A. Computer Architecture: A Quantitative Approach [M].LosAltos: Morgan Kaufmann Publishers,2002
[56]赵钊,蒋烈辉,赵秋霞,刘辉,刘振国.基于排队论的多核处理器总线急用延时分析[J].计算机工程,2008,34(21):232-235
[57]曹非,刘志勇.环连接CMP的缓存一致性协议[J].计算机研究与发展,2009,46(z2):209-215
[58]刘峰，焦容.一种改进的监视Cache协议算法[J].小型微型计算机系统,1999,20(3):222-224
[59]肖立权,周兴铭.多处理机Cache一致性的软件实现算法，计算机工程与科学，1994,16(2):64-70
[60] Jingren Zhou, John Cieslewicz, Kenneth A. Ross, Mihir Shah. Improving DatabasePerformance on Simultaneous Multithreading Processors[C]. In: Proceeding of the31stInternational Conference on Very Large Databases,VLDB Endowment,2005,49-60
[61] Bingsheng He, Yinan Li, Qiong Luo, Dongqing Yang. EaseDB: A Cache-ObliviousIn-Memory Query Processor[C]. In: Proceedings of the2007ACM SIGMODinternational conference on Management of data, New York: ACM Press,2007,1064-1066
[62] John Cieslewicz, Kenneth A.Ross. Adaptive aggregation on chip multiprocessors[C]. In:Proceeding of the33rd International Conference on Very Large Databases, New York:ACM Press,2007:339-350
[63] John Cieslewicz, Kenneth A.Ross, Ioannis Giannakakis. Parallel buffer for chipmultiprocessors[C]. In:3th International Workshop on Data Management on NewHardware, NewYork:ACM Press,2007, Article No.2.
[64] Suh G E, Rudolph L, Devadas S. Dynamic Partitioning of Shared Cache Memory [J].Journal of Supercomputer,2004,28(1):7-26
[65] Planas M M, Cazorla F, Ramirez A, Valero M. Explaining Dynamic Cache PartitioningSpeed Ups [J]. IEEE Computer Architecture Letter,2007,6(1):1-4
[66] Denning P.J. Thrashing: its causes and prevention[C]. In: Proceedings of the December9-11,1968, fall joint computer conference, part I,1968,915-922
[67] Fedorova A, Seltzer M, Small C, Nussbaum D. Performance of multithreaded chipmultiprocessors and implications for operation system design [C]. In: Proceeding of2005USENIX Technical Conference,2006,395-398
[68] Fedorova A, Seltzer M, Smith M D. Improving Performance Isolation on ChipMultiprocessors via an Operating System Scheduler[C]. In: Proceedings of the16thInternational Conference on Parallel Architecture and Compilation Techniques,2007,25-38
[69] Jung C, LimD, Lee J, Han S Y. Adaptive Execution Techniques for SMT MultiprocessorArchitectures[C]. In: Proceeding of the10th ACM SIGP LAN Symposium on Principlesand Practice of Parallel Programming, NewYork:ACM,2005,236-246
[70]邵立松,孔金珠,戴华东.芯片级多线程处理器的操作系统调度研究[J].计算机工程.2009,35(15):277-279.
[71] Hunt G C, Larus J R, Tarditi D, Wobber T. Broad New OS Research: Challenges andOpportunities[C]. In: Proceeding of the10th Workshop on Hot Topics in OperatingSystems, USENIX Press,2005.
[72] Kihm J, Settle A, Janiszewski A, Connors D. Understanding the impact of interthreadcache interference on ILP in modern SMT processors [J]. Journal of Instruction LevelParallelism,2005,7(6):1-28
[73] Tam D, Azimi R, Stumm M. Thread clustering: sharing-aware scheduling onSMP-CMP-SMT multiprocessors [C]. In: Proceedings of the2nd ACMSIGOPS/EuroSys European Conference on Computer Systems2007,2007,47-58
[74] Chen S, Gibbons P B, Kozuch M, et al. Scheduling threads for constructive cachesharing on CMPs[C]. In: Proceedings of the nineteenth annual ACM symposium onParallel algorithms and architectures, NewYork:ACM,2007,105-115
[75] Jiang Y, Shen X, Chen J, Tripathi R. Analysis and approximation of optimalco-scheduling on chip multiprocessors[C]. In: Proceedings of the17th internationalconference on Parallel architectures and compilation techniques,2008,220-229
[76] Tian K, Jiang Y, Shen X. Astudy on optimally co-scheduling jobs of different lengths onchip multiprocessors[C]. In: Proceedings of the6th ACM conference on Computingfrontiers,2009,41-50
[77] Fedorova A. Operating System Scheduling for Chip Multithreaded Processors [D].Massachusetts: Harvard University,2006
[78] Bolla R, Bruschi R. PC-based software routers: high performance and applicationservice support [C]. In: PRESTO’08: Workshop on Programmable Routers forExtensible Service of Tomorrow, NewYork:ACM,2008,27-32
[79] Salehi J D, Kurose J F, Towsley D. The effectiveness of affinity-based scheduling inmultiprocessor network protocol processing [J]. IEEE/ACM Transactions onNetworking,1996,4(4):516-530
[80] Chonka A, Zhou W, Knapp K, and Xiang Y. Protecting information systems from DDoSattack using multi-core methodology[C]. In: Proceedings of the IEEE8th InternationalConference on Computer and Information Technology, Sydney: IEEE,2008,270–275
[81] Yang L, Tang J, Zhao J, Li X. A case study for monitoring-oriented programming inmulti-core architecture[C]. In: IWMSE08: Proceedings of the1st internationalworkshop on Multicore software engineering, Leipzig:ACM,2008,47-52
[82] IslamR, Zhou W, Xiang Y, Mahmood AN. Spamfiltering for network traffic security ona multi-core environment[J]. Concurrency Computat.: Pract. Exper,2009,21:1307-1320
[83] Chonka A, Chong S K, Zhou W, Xiang Y. Multi-core defense system (MSDS) forprotecting computer infrastructure against DDoS attacks [J]. In: Proceedings of the2008Ninth International Conference on Parallel and Distributed Computing, Dunedin: IEEE,2008,503-508.
[84] Chonka A, Zhou W, Ngo L, Xiang Y. Ubiquitous multicore(UM) methodology formultimedia [J]. International Journal of Multimedia and Ubiquitous Engineering,2009,4:145-156
[85] Feng H, Li E, Chen Y, Zhang Y. Parallelization and characterization of SIFT onmulti-core systems [C]. In: IISWC2008, IEEE International Symposium on WorkloadCharacterization, Seattle: IEEE,2008,14-23
[86] Terboven C, Dieter A Mey, Schmidl D, Jin H, Reichstein T. Data and thread affinity inopenMP programs [C]. In: MAW’08: Proceeding of the2008workshop on Memoryaccess on future processor, NewYork:ACM,2008,377-384
[87]雷迎春,张松. Web集群服务器的分离式调度策略[J].计算机研究与发展,2002,(9):1093-1098
[88] Brodie D, Gupta A, Shi W S. Accelerating dynamic web content delivery usingkeyword-based fragment detection [J]. Journal of Web Engineering,2005,4(1):79-100
[89] Challenger J, Iyengar A, Dantzig P. A scalable system for consistently caching dynamicweb data [A]. In: Proceeding of IEEE Conference on Computer Communications[C].NewYork,1999,294-303
[90] Challenger J, Iyengar A, Witting K, Ferstat C, Reed P. A publishing system forefficiently creating dynamic web content [A]. Proc of IEEE Conference on ComputerCommunications[C]. Tel Aviv, Israel,2000,844-853
[91]尤朝,周明辉,林泊,曹东刚,梅宏.一种在线的动态网页分块缓存方法[J].电子学报,2009,37(5):1087-1091
[92] Van Der Weij W, Bhulai S, Van Der Mei R. Dynamic thread assignment in web serverperformance optimization [J]. Performance Evaluation,2009,66:301-310.
[93] Gorder P F. Multicore processors for science and engineering [J]. Computing in Science&Engineering,2007,(3):3-7
[94] Calandrino J M, Anderson J H, Baumberger D P. Ahybrid real-time scheduling approachfor large-scale multicore platforms [A]. In: ECRTS'07:19th Euromicro Conference onReal-Time Systems [C]. Pisa: IEEE,2007,247-258
[95] Zhang Q, Riska A, Sun W, Smirni E, Ciardo G. Workload-aware load balancing forclustered web servers [J]. IEEE Transactionson Parallel and Distributed Systems,2005,16:219–233
[96]张铃丽,石磊.动态网页分发加速技术研究[J].计算机技术与发展.200818(8):130-147.
[97] Nossenson R, Attiya H. The N-Burst/G/1model with heavy-tailed service-timesdistribution [J]. Modeling, Analysis and Simulation of Computer andTelecommunications systems,2004,131-138
[98] Schwefel H, Lipsky L. Impact of aggregated, self-similar on/off traffic on delay instationary queueing models [J]. Performance Evaluation2001,43:203-221
[99]林闯.计算机网络和计算机系统性能评价[M].北京:清华大学出版社,2001:74-106
[100] Fujita Y, Murata M, Miyahara H. Analysis of Web server performance towards modelingand evaluation of web systems [A]. In: the6th IEEE International conference onnetwork’98, Singapor,1998,109-111
[101] Bai Ying Wen, Cheng Chenyung. The performance estimation by queueing networkmodels for a web-based medical information system [A]. In: Proceedings of17th IEEESymposium on compuer-based medical systems [C]. Maryland: IEEE Press,2004:191-196
[102] Siddha S B. Multi-core and Linux Kernel [EB/OL], http://oss.intel.com/pdf/mclinux.pdf
[103] Cherkasova L. Scheduling strategy to improve response time for web applications [A].In: Proceedings on High Performance Computing and Networking, Amsterdam: LNCS,1998,1401:305–314
[104] Schroeder B, Harachol-Balter M. Web servers under overload: How scheduling can help[J]. ACM Transactions on Internet Technology,2006,6:20-52
[105] Elnikety S, Nahum E, Tracey J, Zwaenepoel W. A method for transparent admissioncontrol and request scheduling in e-commerce web sites [A]. In: Proceedings of the13thinternational World Wide Web conference [C]. NewYork: ACM,2004,276-286
[106] Apache. TheApache Software Foundation [EB/OL]. http://www.apache.org
[107] Bossche R V, Vanmechelen K, Broeckhove J. An evaluation of the benefits offine-grained value-based scheduling on general purpose clusters [J]. Future GenerationComputer Systems,2011,27:1-9
[108]杨嘉,王移芝. Linux内核调度器算法研究与性能分析[J].计算机技术与发展,2006,16(3):95-100
[109] Ai L, Tang M, Fidge C. Partitioning composite web service for decentralized executionusing a genetic algorithm [J]. Future Generation Computer Systems,2011,27:157-172
[110] Sharifian S, Motamedi S A, Akbari M K. Acontent-based load balancing algorithm withadmission control for cluster web servers [J]. Future Generation Computer Systems,2008,24:775-787
[111] Siddharth R Barman. Win32Thread Pool [EB/OL]. http://www.codeproject.com/Articles/11976/Win32-Thread-Pool
[112] Borst S C, Boxma O J, Nunez Queija R. Heavy tails: the effect of the service discipline[J]. Computer Performance Evaluation-Modelling Techniques and Tools,2002,2324:1–30
[113] Borst S C, Boxma O J, Nunez Queija R, Zwart A P. The impact of the service disciplineon delay asymptotics [J]. Performance Evaluation,2003,54(2):175-206
[114] Crovella M, Bestavros A. Self-similarity in world wide web traffic: evidence andpossible causes [J]. IEEE–ACM Transactionson Networking,1997,5(6):835-846
[115] El Abdouni Khayari R, Sadre R, Haverkort B. The pseudo-self-similar traffic model:application and validation [J]. Performance Evaluation,2004,56(1-4):3-22
[116] Willinger W, Taqqu M, Erramilli A. A bibliographical guide to self-similar traffic andperformance modeling for modern high-speed networks [J]. Stochastic Networks:Theory and Applications,1996,339-366
[117] Hernández-Orallo E, Vila-Carbó J. Web server performance analysis using histogramworkload models [J]. Computer Networks,2009,53:2727-2739
[118] Bonald T. The Erlang model with non-poisson calls arrivals [J]. ACM SIGMETRICSPerformance Evaluation Review,2006,34(1):276-286
[119]张宾,杨家海,吴建平. Internet流量模型分析与评述[J].软件学报,2011,22(1):115-130
[120]石江涛,王永纲,戴雪龙,颜天信.自相似网络业务流量的研究与实现[J].通信学报,2005,26(6):112-117
[121] Popescu A. Traffic self-similarity [A]. In: The IEEE International conference ontelecommunications, ICT2001[C]. Bucharest, Romania,2001
[122] Greiner M, Jobmann M, Lipsky L. The importance of power-tail distributions formodeling queuing systems [J]. Operations Research,1999,47(2):313-326
[123] Gui M, Jiang Y, Zhang Z. Comparison of two queuing models with multiple servers [J].Computer Engineering andApplication,2008,44(13):44-46
[124] Xie Z, Li X. Study of network congestion rate based on queuing theory model [J].Computer Engineering and Design,2007,28(17):4172-4174
[125] Sarvotham S, Riedi R, Baraniuk R. Network and user driven alpha-beta on-off sourcemodel for network traffic [J]. Computer Networks,2005,48:335-350
[126] Leland W E, Taqqu M S, Willinger W, Wilson D V. On the self-similar nature of ethernettraffic [J]. ACM/SIGCOMM Computer Communications Review,1993,23:183-193
[127] Erranmillj A, Narayan O, Willinger W. Experimental queuing analysis with long-rangedependent packet traffic [J]. IEEE/ACM Transactions on Networking,1996,4(2):209-223
[128] Sahinoglu Z, Tekinay S. On multimedia networks: self-similar traffic and networkperformance [J]. IEEE Communications Magazine,1999,37(1):48-52
[129] Park K, Kim G, Crovella M. On the effect of traffic self-similarity on networkperformance [A]. In: Proceedings of1997SPIE International Conference onPerformance and Control of Network Systems [C], Bellingham, USA,1997,296-310
[130] Gospodinova P, Todorov G. Comparative analysis of the self-similar queuing processand the classical queuing process in telecommunication networks [J]. In: IBIC2007: the2nd International Business Informatics Challenge and Conference [C], Dublin, Ireland,2007,296-302
[2]马龙昌.基于Web的远程监控系统的研究与应用[D].西安:长安大学,2009
[3]林海.浏览器/服务器应用开发[M].北京：科学出版社,2001
[4] Young C, Juang W L, Michael J D. Real-time intranet-controlled virtual instrumentmultiple-circuit power monitoring [J]. IEEE Transcations on Instrumentation andMeasurement,2000,49(3):579-584
[5] JimHenry. Engineering on the web [EB/OL]. http://chem.engr.utc.edu
[6] Bradford Robotic Telescope [EB/OL]. http://www.telescope.org/
[7] Shuanghua Yang, Chengwei Dai, Roger PK. Remote maintenance of control systemperformance over the Internet [J]. Control Engineering Practice,2007,15(5):533-544
[8] Brady K, Tarn T J. Internet-based remote teleoperation [C]. In: IEEE Internationalconference on robotics&automation. Leuven,1998,65-70
[9] Backes PG, Tso K S, Tharp G.K. Mars pathfinder mission Internet-based operationsusing WITS [C]. In: IEEE International conference on Robotics&Automation. SanFrancisco,2000,2025-2032
[10] Eric P, John C. Delivering real reality to the world wide web via telerobotics [C]. In:IEEE International conference on Robotics&automation. Minneapolis,1996.1694-1699
[11] Taylor K, Dalton B, Trevelyan J. Web-based tele-robotics [J]. Robotica,1999,17(1):49-57
[12]聂雪媛,时忠民,黄映城,丁桦,耿丽.基于B/S的海洋平台远程监控系统设计[J].微计算机信息,2007,05X:1-3
[13]祁享年,蒋梁中.基于Web的广域污染源水质自动监控系统研究[J].仪器仪表学报,2008,29(1):120-123
[14]李云,陈刚,魏泽峰.基于Web铁路信号电源的远程监控系统的设计与实现[J].铁路计算机应用,2007,16(8):49-52
[15]陆璐,刘发贵.基于Web的远程监控系统[M].北京:清华大学出版社,2008.61-63
[16]姚念民,郑名扬,鞠九滨.基于流水线的高性能Web服务器[J].软件学报,2003,14(6):1127-1133
[17]王彬蔚.网络中的服务质量(Qos)的研究[D].成都:电子科技大学,2002
[18] Kirubanand V B, Palaniammal S. Distributed Data Transaction of an Apache Web ServerUsing bulk service rule [J]. International Journal of Computer Application,2011,24(8):1-4
[19]罗红兵,张宝印,曹立强.利用作业可塑性改进结合回填FCFS策略的性能[J]，计算机工程与应用,2007,43(24):41-46
[20] Abdouni Khayari R E, Musovic A, Lehmann A, Fellinger P. A workload based adaptivescheduling algorithm for web server [C]. In: Proceedings of the2009Spring SimulationMulticonference. San Diego: SCSI,2009
[21] Abdouni Khayari R E. Class-based weighted fair queueing: Validation and comparisonby trace-driven simulation [J]. International Journal of Communication Systems,2005,18:975-994
[22] Fiorini P, Oboe R. Internet-based teleroboties: Problems and approaches [C]. In:International Conference ofAdvanced Robotics (Icar’97), Monterey:1997
[23] Talyor K, Dalton B. Issues in Internet Telerobotics [C]. In: Int.Conf on Field and ServiceRobtics. Canberra:Australian Robot Association,1997,151-157
[24] Multi-Core from Intel-Products and Platforms [EB/OL]. http://www.intel.com/multi-core/products.htm
[25] AMD Multi-Core Products [EB/OL]. http://multicore.amd.com/en/Products
[26] Kongetira P, Aingaran K., Olukotun K. Niagara: a32-way multithreaded sparc processor[J]. IEEE Micro,2005,25:21-29
[27] World Wide Web Consortium [EB/OL]. http://www.w3c.org
[28] RFC1738. Uniform Resource Locators (URL)[S].1994
[29]李军,徐玖平.运筹学--非线性系统优化[M].北京:科学出版社,2003.35-62.
[30]刘嘉馄.应用随机过程[M].北京:科学出版社,2006
[31]孙荣恒,李建平.排队论基础[M].北京:北京科技出版社,2002
[32]陆传赉.排队论[M].北京:北京邮电学院出版社,1994
[33]唐应辉.排队论-基础与分析技术[M].北京:北京科学出版社,2006
[34]孙荣恒.随机过程及其应用[M].北京:清华大学出版社,2004
[35][美]华兴.排队论与随机服务系统[M].上海:上海翻译出版公司,1987
[36]高世泽.概率统计引论[M].重庆:重庆大学出版社,2000
[37] Slothouber L P. A model of web server performance [C]. In: Proceedings of the FifthInternational World Wide Web Conference,1996.
[38] Nunez-Queija R. Processor-Sharing models for integrated-services networks [D].Eindhoven: Eindhoven university of technology,2000
[39] Rolia J A, Sevcik K C. The method of Layers [J]. IEEE Transactions on SoftwareEngineering,1995,21(8):689-700
[40] Ramesh S, Perros H G. A multilayer client-server queueing network model withsynchronous and asynchronous messages [J]. IEEE Transactions on SoftwareEngineering,2000,26(11):1086-1100
[41] Dilley J, Friedrich R, Jin T. Web server performance measurement and modelingtechniques [J]. Perform. Eval,1998,33(1):5-26
[42] Heidemann J, Obraczka K, Touch J. Modeling the performance of HTTP over severaltransport protocols [J]. IEEE/ACM Trans,1997,5(5):616-630
[43] Kamra A, Misra V, Nahum E M. Yaksha: a self-tuning controller for managing theperformance of3-tiered web sites [C]. In: Twlefth IEEE International workshop onquality of service,2004:47-56
[44] Wells L, Christensen S, Kristensen L M. Simulation based performance analysis of Webservers [C]. In:9thInternational workshop on Petri Nets and performance models,2001:59-68
[45] Liu X, Heo J, Sha L. Modeling3-tiered Web applications [C]. In:13th IEEEInternational Symposium on Modeling, Analysis, and Simulation of Computer andTelecommunication System,2005:307-310
[46] Van Der Mei R D, Hariharan R, Reeser P K. Web Server performance modeling [J].Telecommunication Systems,2001,16(3):361-378
[47] Cao J, Andersson M, Nyberg C. Web server performance modeling using anM/G/1/K*PS queue [C]. In:10th International Conference on Telecommunications,2003,2:1501-1506.
[48] Intel corporation terascale computing [EB/OL]. http://www.intel.com/research/platform/terascale/index.htm
[49] Multi-core processor-the next evolution in computing [EB/OL]. http://www.amd.com
[50]鲁建壮,王志英,张春元.面向SCMP的多线程前瞻控制分析与设计[J].计算机工程与科学,2006,28(10):128-130
[51]宋风龙,刘志勇,范东睿,张军超,余磊.一种片上众核结构共享Cache动态隐式隔离机制研究[J].计算机学报,2009,32(10):1896-1904
[52] El-Moursy A, Garg R, Albonesi D H, Dwarkadas S. Compatible Phase Co-Schedulingon a CMP of Multi-Threaded Processors [C]. In: Proceeding20th IEEE InternationalParallel&Distributed Processing Symposium,2006,1-10
[53] Suh T, Blough D M, Lee H H S. Supporting Cache Coherence in HeterogeneousMultiprocessor System [C]. In: Proceeding of Design, Automation and Test in EuropeConference and Exhibition,2004,1150-1155
[54] Sorin D J, Plakal M, Codon A E, Hill M D, Martin M M K, Wood D A. Specifying andverifying a broadcast and a multicast snooping cache coherence protocol [J]. Parallel andDistributed Systems,2002,13(6):556-578
[55] Hennessy J L, Patterson D A. Computer Architecture: A Quantitative Approach [M].LosAltos: Morgan Kaufmann Publishers,2002
[56]赵钊,蒋烈辉,赵秋霞,刘辉,刘振国.基于排队论的多核处理器总线急用延时分析[J].计算机工程,2008,34(21):232-235
[57]曹非,刘志勇.环连接CMP的缓存一致性协议[J].计算机研究与发展,2009,46(z2):209-215
[58]刘峰，焦容.一种改进的监视Cache协议算法[J].小型微型计算机系统,1999,20(3):222-224
[59]肖立权,周兴铭.多处理机Cache一致性的软件实现算法，计算机工程与科学，1994,16(2):64-70
[60] Jingren Zhou, John Cieslewicz, Kenneth A. Ross, Mihir Shah. Improving DatabasePerformance on Simultaneous Multithreading Processors[C]. In: Proceeding of the31stInternational Conference on Very Large Databases,VLDB Endowment,2005,49-60
[61] Bingsheng He, Yinan Li, Qiong Luo, Dongqing Yang. EaseDB: A Cache-ObliviousIn-Memory Query Processor[C]. In: Proceedings of the2007ACM SIGMODinternational conference on Management of data, New York: ACM Press,2007,1064-1066
[62] John Cieslewicz, Kenneth A.Ross. Adaptive aggregation on chip multiprocessors[C]. In:Proceeding of the33rd International Conference on Very Large Databases, New York:ACM Press,2007:339-350
[63] John Cieslewicz, Kenneth A.Ross, Ioannis Giannakakis. Parallel buffer for chipmultiprocessors[C]. In:3th International Workshop on Data Management on NewHardware, NewYork:ACM Press,2007, Article No.2.
[64] Suh G E, Rudolph L, Devadas S. Dynamic Partitioning of Shared Cache Memory [J].Journal of Supercomputer,2004,28(1):7-26
[65] Planas M M, Cazorla F, Ramirez A, Valero M. Explaining Dynamic Cache PartitioningSpeed Ups [J]. IEEE Computer Architecture Letter,2007,6(1):1-4
[66] Denning P.J. Thrashing: its causes and prevention[C]. In: Proceedings of the December9-11,1968, fall joint computer conference, part I,1968,915-922
[67] Fedorova A, Seltzer M, Small C, Nussbaum D. Performance of multithreaded chipmultiprocessors and implications for operation system design [C]. In: Proceeding of2005USENIX Technical Conference,2006,395-398
[68] Fedorova A, Seltzer M, Smith M D. Improving Performance Isolation on ChipMultiprocessors via an Operating System Scheduler[C]. In: Proceedings of the16thInternational Conference on Parallel Architecture and Compilation Techniques,2007,25-38
[69] Jung C, LimD, Lee J, Han S Y. Adaptive Execution Techniques for SMT MultiprocessorArchitectures[C]. In: Proceeding of the10th ACM SIGP LAN Symposium on Principlesand Practice of Parallel Programming, NewYork:ACM,2005,236-246
[70]邵立松,孔金珠,戴华东.芯片级多线程处理器的操作系统调度研究[J].计算机工程.2009,35(15):277-279.
[71] Hunt G C, Larus J R, Tarditi D, Wobber T. Broad New OS Research: Challenges andOpportunities[C]. In: Proceeding of the10th Workshop on Hot Topics in OperatingSystems, USENIX Press,2005.
[72] Kihm J, Settle A, Janiszewski A, Connors D. Understanding the impact of interthreadcache interference on ILP in modern SMT processors [J]. Journal of Instruction LevelParallelism,2005,7(6):1-28
[73] Tam D, Azimi R, Stumm M. Thread clustering: sharing-aware scheduling onSMP-CMP-SMT multiprocessors [C]. In: Proceedings of the2nd ACMSIGOPS/EuroSys European Conference on Computer Systems2007,2007,47-58
[74] Chen S, Gibbons P B, Kozuch M, et al. Scheduling threads for constructive cachesharing on CMPs[C]. In: Proceedings of the nineteenth annual ACM symposium onParallel algorithms and architectures, NewYork:ACM,2007,105-115
[75] Jiang Y, Shen X, Chen J, Tripathi R. Analysis and approximation of optimalco-scheduling on chip multiprocessors[C]. In: Proceedings of the17th internationalconference on Parallel architectures and compilation techniques,2008,220-229
[76] Tian K, Jiang Y, Shen X. Astudy on optimally co-scheduling jobs of different lengths onchip multiprocessors[C]. In: Proceedings of the6th ACM conference on Computingfrontiers,2009,41-50
[77] Fedorova A. Operating System Scheduling for Chip Multithreaded Processors [D].Massachusetts: Harvard University,2006
[78] Bolla R, Bruschi R. PC-based software routers: high performance and applicationservice support [C]. In: PRESTO’08: Workshop on Programmable Routers forExtensible Service of Tomorrow, NewYork:ACM,2008,27-32
[79] Salehi J D, Kurose J F, Towsley D. The effectiveness of affinity-based scheduling inmultiprocessor network protocol processing [J]. IEEE/ACM Transactions onNetworking,1996,4(4):516-530
[80] Chonka A, Zhou W, Knapp K, and Xiang Y. Protecting information systems from DDoSattack using multi-core methodology[C]. In: Proceedings of the IEEE8th InternationalConference on Computer and Information Technology, Sydney: IEEE,2008,270–275
[81] Yang L, Tang J, Zhao J, Li X. A case study for monitoring-oriented programming inmulti-core architecture[C]. In: IWMSE08: Proceedings of the1st internationalworkshop on Multicore software engineering, Leipzig:ACM,2008,47-52
[82] IslamR, Zhou W, Xiang Y, Mahmood AN. Spamfiltering for network traffic security ona multi-core environment[J]. Concurrency Computat.: Pract. Exper,2009,21:1307-1320
[83] Chonka A, Chong S K, Zhou W, Xiang Y. Multi-core defense system (MSDS) forprotecting computer infrastructure against DDoS attacks [J]. In: Proceedings of the2008Ninth International Conference on Parallel and Distributed Computing, Dunedin: IEEE,2008,503-508.
[84] Chonka A, Zhou W, Ngo L, Xiang Y. Ubiquitous multicore(UM) methodology formultimedia [J]. International Journal of Multimedia and Ubiquitous Engineering,2009,4:145-156
[85] Feng H, Li E, Chen Y, Zhang Y. Parallelization and characterization of SIFT onmulti-core systems [C]. In: IISWC2008, IEEE International Symposium on WorkloadCharacterization, Seattle: IEEE,2008,14-23
[86] Terboven C, Dieter A Mey, Schmidl D, Jin H, Reichstein T. Data and thread affinity inopenMP programs [C]. In: MAW’08: Proceeding of the2008workshop on Memoryaccess on future processor, NewYork:ACM,2008,377-384
[87]雷迎春,张松. Web集群服务器的分离式调度策略[J].计算机研究与发展,2002,(9):1093-1098
[88] Brodie D, Gupta A, Shi W S. Accelerating dynamic web content delivery usingkeyword-based fragment detection [J]. Journal of Web Engineering,2005,4(1):79-100
[89] Challenger J, Iyengar A, Dantzig P. A scalable system for consistently caching dynamicweb data [A]. In: Proceeding of IEEE Conference on Computer Communications[C].NewYork,1999,294-303
[90] Challenger J, Iyengar A, Witting K, Ferstat C, Reed P. A publishing system forefficiently creating dynamic web content [A]. Proc of IEEE Conference on ComputerCommunications[C]. Tel Aviv, Israel,2000,844-853
[91]尤朝,周明辉,林泊,曹东刚,梅宏.一种在线的动态网页分块缓存方法[J].电子学报,2009,37(5):1087-1091
[92] Van Der Weij W, Bhulai S, Van Der Mei R. Dynamic thread assignment in web serverperformance optimization [J]. Performance Evaluation,2009,66:301-310.
[93] Gorder P F. Multicore processors for science and engineering [J]. Computing in Science&Engineering,2007,(3):3-7
[94] Calandrino J M, Anderson J H, Baumberger D P. Ahybrid real-time scheduling approachfor large-scale multicore platforms [A]. In: ECRTS'07:19th Euromicro Conference onReal-Time Systems [C]. Pisa: IEEE,2007,247-258
[95] Zhang Q, Riska A, Sun W, Smirni E, Ciardo G. Workload-aware load balancing forclustered web servers [J]. IEEE Transactionson Parallel and Distributed Systems,2005,16:219–233
[96]张铃丽,石磊.动态网页分发加速技术研究[J].计算机技术与发展.200818(8):130-147.
[97] Nossenson R, Attiya H. The N-Burst/G/1model with heavy-tailed service-timesdistribution [J]. Modeling, Analysis and Simulation of Computer andTelecommunications systems,2004,131-138
[98] Schwefel H, Lipsky L. Impact of aggregated, self-similar on/off traffic on delay instationary queueing models [J]. Performance Evaluation2001,43:203-221
[99]林闯.计算机网络和计算机系统性能评价[M].北京:清华大学出版社,2001:74-106
[100] Fujita Y, Murata M, Miyahara H. Analysis of Web server performance towards modelingand evaluation of web systems [A]. In: the6th IEEE International conference onnetwork’98, Singapor,1998,109-111
[101] Bai Ying Wen, Cheng Chenyung. The performance estimation by queueing networkmodels for a web-based medical information system [A]. In: Proceedings of17th IEEESymposium on compuer-based medical systems [C]. Maryland: IEEE Press,2004:191-196
[102] Siddha S B. Multi-core and Linux Kernel [EB/OL], http://oss.intel.com/pdf/mclinux.pdf
[103] Cherkasova L. Scheduling strategy to improve response time for web applications [A].In: Proceedings on High Performance Computing and Networking, Amsterdam: LNCS,1998,1401:305–314
[104] Schroeder B, Harachol-Balter M. Web servers under overload: How scheduling can help[J]. ACM Transactions on Internet Technology,2006,6:20-52
[105] Elnikety S, Nahum E, Tracey J, Zwaenepoel W. A method for transparent admissioncontrol and request scheduling in e-commerce web sites [A]. In: Proceedings of the13thinternational World Wide Web conference [C]. NewYork: ACM,2004,276-286
[106] Apache. TheApache Software Foundation [EB/OL]. http://www.apache.org
[107] Bossche R V, Vanmechelen K, Broeckhove J. An evaluation of the benefits offine-grained value-based scheduling on general purpose clusters [J]. Future GenerationComputer Systems,2011,27:1-9
[108]杨嘉,王移芝. Linux内核调度器算法研究与性能分析[J].计算机技术与发展,2006,16(3):95-100
[109] Ai L, Tang M, Fidge C. Partitioning composite web service for decentralized executionusing a genetic algorithm [J]. Future Generation Computer Systems,2011,27:157-172
[110] Sharifian S, Motamedi S A, Akbari M K. Acontent-based load balancing algorithm withadmission control for cluster web servers [J]. Future Generation Computer Systems,2008,24:775-787
[111] Siddharth R Barman. Win32Thread Pool [EB/OL]. http://www.codeproject.com/Articles/11976/Win32-Thread-Pool
[112] Borst S C, Boxma O J, Nunez Queija R. Heavy tails: the effect of the service discipline[J]. Computer Performance Evaluation-Modelling Techniques and Tools,2002,2324:1–30
[113] Borst S C, Boxma O J, Nunez Queija R, Zwart A P. The impact of the service disciplineon delay asymptotics [J]. Performance Evaluation,2003,54(2):175-206
[114] Crovella M, Bestavros A. Self-similarity in world wide web traffic: evidence andpossible causes [J]. IEEE–ACM Transactionson Networking,1997,5(6):835-846
[115] El Abdouni Khayari R, Sadre R, Haverkort B. The pseudo-self-similar traffic model:application and validation [J]. Performance Evaluation,2004,56(1-4):3-22
[116] Willinger W, Taqqu M, Erramilli A. A bibliographical guide to self-similar traffic andperformance modeling for modern high-speed networks [J]. Stochastic Networks:Theory and Applications,1996,339-366
[117] Hernández-Orallo E, Vila-Carbó J. Web server performance analysis using histogramworkload models [J]. Computer Networks,2009,53:2727-2739
[118] Bonald T. The Erlang model with non-poisson calls arrivals [J]. ACM SIGMETRICSPerformance Evaluation Review,2006,34(1):276-286
[119]张宾,杨家海,吴建平. Internet流量模型分析与评述[J].软件学报,2011,22(1):115-130
[120]石江涛,王永纲,戴雪龙,颜天信.自相似网络业务流量的研究与实现[J].通信学报,2005,26(6):112-117
[121] Popescu A. Traffic self-similarity [A]. In: The IEEE International conference ontelecommunications, ICT2001[C]. Bucharest, Romania,2001
[122] Greiner M, Jobmann M, Lipsky L. The importance of power-tail distributions formodeling queuing systems [J]. Operations Research,1999,47(2):313-326
[123] Gui M, Jiang Y, Zhang Z. Comparison of two queuing models with multiple servers [J].Computer Engineering andApplication,2008,44(13):44-46
[124] Xie Z, Li X. Study of network congestion rate based on queuing theory model [J].Computer Engineering and Design,2007,28(17):4172-4174
[125] Sarvotham S, Riedi R, Baraniuk R. Network and user driven alpha-beta on-off sourcemodel for network traffic [J]. Computer Networks,2005,48:335-350
[126] Leland W E, Taqqu M S, Willinger W, Wilson D V. On the self-similar nature of ethernettraffic [J]. ACM/SIGCOMM Computer Communications Review,1993,23:183-193
[127] Erranmillj A, Narayan O, Willinger W. Experimental queuing analysis with long-rangedependent packet traffic [J]. IEEE/ACM Transactions on Networking,1996,4(2):209-223
[128] Sahinoglu Z, Tekinay S. On multimedia networks: self-similar traffic and networkperformance [J]. IEEE Communications Magazine,1999,37(1):48-52
[129] Park K, Kim G, Crovella M. On the effect of traffic self-similarity on networkperformance [A]. In: Proceedings of1997SPIE International Conference onPerformance and Control of Network Systems [C], Bellingham, USA,1997,296-310
[130] Gospodinova P, Todorov G. Comparative analysis of the self-similar queuing processand the classical queuing process in telecommunication networks [J]. In: IBIC2007: the2nd International Business Informatics Challenge and Conference [C], Dublin, Ireland,2007,296-302