Pub Date : 2001-08-15DOI: 10.1109/MASCOT.2001.948847
M. Squillante
Summary form only given. The control, management and optimization of performance-based measures in high-volume Web sites require a fundamental understanding of the user request patterns and the performance implications of such traffic patterns. We first present an analysis of the request patterns found at various Web server complexes, including high-volume commercial and sporting event Web sites. Our analysis demonstrates complex traffic patterns that include both short-range and long-range dependence structures and both light-tailed and heavy-tailed behavior. We then investigate the impact of these complex user request patterns on the response-time distribution of different Web server environments. Our analysis illustrates some of the key difficulties in the management and control of system resources to satisfy certain types of service-level agreements. We then describe aspects of the system architecture and techniques employed at various commercial and sporting event Web sites that reduce the overhead of serving dynamic content and that improve the Web server response-time distribution. We also present research on controlling the performance of different classes of user requests, including some new forms of service-level agreements. Various applications of our analysis and results are discussed.
{"title":"High-volume Web servers: traffic patterns, performance implications, and resource management","authors":"M. Squillante","doi":"10.1109/MASCOT.2001.948847","DOIUrl":"https://doi.org/10.1109/MASCOT.2001.948847","url":null,"abstract":"Summary form only given. The control, management and optimization of performance-based measures in high-volume Web sites require a fundamental understanding of the user request patterns and the performance implications of such traffic patterns. We first present an analysis of the request patterns found at various Web server complexes, including high-volume commercial and sporting event Web sites. Our analysis demonstrates complex traffic patterns that include both short-range and long-range dependence structures and both light-tailed and heavy-tailed behavior. We then investigate the impact of these complex user request patterns on the response-time distribution of different Web server environments. Our analysis illustrates some of the key difficulties in the management and control of system resources to satisfy certain types of service-level agreements. We then describe aspects of the system architecture and techniques employed at various commercial and sporting event Web sites that reduce the overhead of serving dynamic content and that improve the Web server response-time distribution. We also present research on controlling the performance of different classes of user requests, including some new forms of service-level agreements. Various applications of our analysis and results are discussed.","PeriodicalId":375127,"journal":{"name":"MASCOTS 2001, Proceedings Ninth International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115600764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2001-08-15DOI: 10.1109/MASCOT.2001.948870
Qian Wu, C. Williamson
For the World Wide Web, the transmission control protocol (TCP) and the hypertext transfer protocol (HTTP) are two important protocols. However, interactions between these two protocols, combined with the bandwidth asymmetry of network access technologies such as ADSL, can lead to inefficient HTTP/TCP performance. This paper investigates the effects of bandwidth asymmetry on ensemble-TCP, a protocol designed to coordinate multiple HTTP/TCP connections to improve Web document transfer performance. The evaluation is conducted using the ns-2 network simulator. The paper also proposes and evaluates two new schemes, ACC-ensemble and AF-ensemble, to improve ensemble-TCP performance on asymmetric networks. The simulation results show that AF-ensemble and ACC-ensemble perform better (often 10-50% faster) than Reno TCP and ensemble-TCP for typical user-level Web browsing activity on asymmetric networks.
{"title":"Improving ensemble-TCP performance on asymmetric networks","authors":"Qian Wu, C. Williamson","doi":"10.1109/MASCOT.2001.948870","DOIUrl":"https://doi.org/10.1109/MASCOT.2001.948870","url":null,"abstract":"For the World Wide Web, the transmission control protocol (TCP) and the hypertext transfer protocol (HTTP) are two important protocols. However, interactions between these two protocols, combined with the bandwidth asymmetry of network access technologies such as ADSL, can lead to inefficient HTTP/TCP performance. This paper investigates the effects of bandwidth asymmetry on ensemble-TCP, a protocol designed to coordinate multiple HTTP/TCP connections to improve Web document transfer performance. The evaluation is conducted using the ns-2 network simulator. The paper also proposes and evaluates two new schemes, ACC-ensemble and AF-ensemble, to improve ensemble-TCP performance on asymmetric networks. The simulation results show that AF-ensemble and ACC-ensemble perform better (often 10-50% faster) than Reno TCP and ensemble-TCP for typical user-level Web browsing activity on asymmetric networks.","PeriodicalId":375127,"journal":{"name":"MASCOTS 2001, Proceedings Ninth International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127346727","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2001-08-15DOI: 10.1109/MASCOT.2001.948852
Y. M. Teo, B. Onggo, S. Tay
A new formal approach based on partial order set (poset) theory is proposed to analyze the space requirement of discrete-event parallel simulation. We divide the memory required by a simulation problem into memory to model the states of the real-world system, memory to maintain a list of future event occurrences, and memory required to implement the event synchronization protocol. We establish the relationship between poset theory and event orderings in simulation. Based on our framework, we analyze the space requirement using an open and a closed system as examples. Our analysis shows that apart from problem size and traffic intensity that affects the memory requirement, event ordering is an important factor that can be analyzed before implementation. In an open system, a weaker event ordered simulation requires more memory than strong ordering. However, the memory requirement is constant and independent of event ordering in closed systems.
{"title":"Effect of event orderings on memory requirement in parallel simulation","authors":"Y. M. Teo, B. Onggo, S. Tay","doi":"10.1109/MASCOT.2001.948852","DOIUrl":"https://doi.org/10.1109/MASCOT.2001.948852","url":null,"abstract":"A new formal approach based on partial order set (poset) theory is proposed to analyze the space requirement of discrete-event parallel simulation. We divide the memory required by a simulation problem into memory to model the states of the real-world system, memory to maintain a list of future event occurrences, and memory required to implement the event synchronization protocol. We establish the relationship between poset theory and event orderings in simulation. Based on our framework, we analyze the space requirement using an open and a closed system as examples. Our analysis shows that apart from problem size and traffic intensity that affects the memory requirement, event ordering is an important factor that can be analyzed before implementation. In an open system, a weaker event ordered simulation requires more memory than strong ordering. However, the memory requirement is constant and independent of event ordering in closed systems.","PeriodicalId":375127,"journal":{"name":"MASCOTS 2001, Proceedings Ninth International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129956595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2001-08-15DOI: 10.1109/MASCOT.2001.948878
A. Khonsari, H. Sarbazi-Azad, M. Ould-Khaoua
Although many adaptive routing algorithms have been proposed for wormhole-routed networks, it is necessary to have a clear understanding of the factors that affect their potential performance before they can be widely adopted in commercial multicomputers. This paper proposes a new analytical model of an adaptive routing algorithm proposed by Duato (see Future Generation Computer Systems vol.10, no.10, p.45-58, 1994). The main feature of this routing algorithm is the use of a timeout mechanism to select a particular class of virtual channels at a given router. This has the advantage of reducing virtual channels multiplexing, leading to improvement in network performance. Simulation experiments reveal that the proposed analytical model predicts message latency with a good degree of accuracy.
尽管针对虫洞路由网络提出了许多自适应路由算法,但在将其广泛应用于商用多计算机之前,有必要对影响其潜在性能的因素有一个清晰的认识。本文提出了一种新的自适应路由算法的分析模型,该算法由Duato提出(参见Future Generation Computer Systems vol.10, no. 10)。10,第45-58页,1994年)。这种路由算法的主要特点是使用超时机制在给定路由器上选择特定类别的虚拟通道。这样做的好处是减少了虚拟信道的多路复用,从而提高了网络性能。仿真实验表明,所提出的分析模型能够较准确地预测消息延迟。
{"title":"Analysis of timeout-based adaptive wormhole routing","authors":"A. Khonsari, H. Sarbazi-Azad, M. Ould-Khaoua","doi":"10.1109/MASCOT.2001.948878","DOIUrl":"https://doi.org/10.1109/MASCOT.2001.948878","url":null,"abstract":"Although many adaptive routing algorithms have been proposed for wormhole-routed networks, it is necessary to have a clear understanding of the factors that affect their potential performance before they can be widely adopted in commercial multicomputers. This paper proposes a new analytical model of an adaptive routing algorithm proposed by Duato (see Future Generation Computer Systems vol.10, no.10, p.45-58, 1994). The main feature of this routing algorithm is the use of a timeout mechanism to select a particular class of virtual channels at a given router. This has the advantage of reducing virtual channels multiplexing, leading to improvement in network performance. Simulation experiments reveal that the proposed analytical model predicts message latency with a good degree of accuracy.","PeriodicalId":375127,"journal":{"name":"MASCOTS 2001, Proceedings Ninth International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115395575","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2001-08-15DOI: 10.1109/MASCOT.2001.948873
W. Kampichler, K. M. Göschka
It is well known that company Intranets are growing into ubiquitous communications media for everything. As a consequence, network traffic is notoriously dynamic, and unpredictable. Unfortunately, local area networks were designed for scalability and robustness, not for sophisticated traffic monitoring. This paper introduces a performance measurement method based on widely used IP protocol elements, which allows measurement of network performance criteria to predict the voice transmission feasibility of a given local area network. The measurement does neither depend on special VoIP equipment, nor does it need network monitoring hardware. Rather it uses special payload samples to detect unloaded network conditions to receive reference values. These samples are followed by typical VoIP application payload to obtain real-world measurement conditions. The validation of our method was done within a local area network and showed convincing results.
{"title":"Plain end-to-end measurement for local area network voice transmission feasibility","authors":"W. Kampichler, K. M. Göschka","doi":"10.1109/MASCOT.2001.948873","DOIUrl":"https://doi.org/10.1109/MASCOT.2001.948873","url":null,"abstract":"It is well known that company Intranets are growing into ubiquitous communications media for everything. As a consequence, network traffic is notoriously dynamic, and unpredictable. Unfortunately, local area networks were designed for scalability and robustness, not for sophisticated traffic monitoring. This paper introduces a performance measurement method based on widely used IP protocol elements, which allows measurement of network performance criteria to predict the voice transmission feasibility of a given local area network. The measurement does neither depend on special VoIP equipment, nor does it need network monitoring hardware. Rather it uses special payload samples to detect unloaded network conditions to receive reference values. These samples are followed by typical VoIP application payload to obtain real-world measurement conditions. The validation of our method was done within a local area network and showed convincing results.","PeriodicalId":375127,"journal":{"name":"MASCOTS 2001, Proceedings Ninth International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122076953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2001-08-15DOI: 10.1109/MASCOT.2001.948864
R. Bradford, R. Simmonds, B. Unger
A network emulator, such as the Internet Protocol Traffic and Network Emulator (IP-TNE), enables real applications running on external hosts to interact via a virtual network modelled within the emulator. It combines a real-time network simulation engine with methods to capture specific packets from a network and write packets back to the network with customised headers. This paper explains the reading and writing of packets. It describes which components can be implemented in a portable manner and which need to be implemented in different ways on different operating systems. Both kernel level and user level packet filtering are examined and performance results using gigabit Ethernet and various readers are presented.
网络仿真器,例如Internet Protocol Traffic and network emulator (IP-TNE),使运行在外部主机上的实际应用程序能够通过仿真器中建模的虚拟网络进行交互。它将实时网络模拟引擎与从网络捕获特定数据包的方法相结合,并将数据包写回带有自定义头的网络。本文解释了数据包的读写。它描述了哪些组件可以以可移植的方式实现,哪些组件需要在不同的操作系统上以不同的方式实现。研究了内核级和用户级包过滤,并给出了使用千兆以太网和各种阅读器的性能结果。
{"title":"Packet reading for network emulation","authors":"R. Bradford, R. Simmonds, B. Unger","doi":"10.1109/MASCOT.2001.948864","DOIUrl":"https://doi.org/10.1109/MASCOT.2001.948864","url":null,"abstract":"A network emulator, such as the Internet Protocol Traffic and Network Emulator (IP-TNE), enables real applications running on external hosts to interact via a virtual network modelled within the emulator. It combines a real-time network simulation engine with methods to capture specific packets from a network and write packets back to the network with customised headers. This paper explains the reading and writing of packets. It describes which components can be implemented in a portable manner and which need to be implemented in different ways on different operating systems. Both kernel level and user level packet filtering are examined and performance results using gigabit Ethernet and various readers are presented.","PeriodicalId":375127,"journal":{"name":"MASCOTS 2001, Proceedings Ninth International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127843638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2001-07-01DOI: 10.1109/MASCOT.2001.948848
C. D. Farias, L. F. Pires, W. L. Souza, C. E. Morón
This paper presents and discusses the LOTOS specification of a real-time parallel kernel. The purpose of this specification exercise has been to evaluate LOTOS with respect to its capabilities to model real-time features with a realistic industrial product. LOTOS was used to produce the formal specification of TRANS-RTXC, which is a real-time parallel kernel developed by Intelligent Systems International. This paper shows that although timing constraints cannot be explicitly represented in LOTOS, the language is suitable for the specification of co-ordination of real-time tasks, which is the main functionality of the real-time kernel. This paper also discusses the validation process of the kernel specification and the role of tools in this validation process. We believe that our experience (use of structuring techniques, use of validation methods and tools, etc.) is valuable for designers who want to apply formal models in their design or analysis tasks.
提出并讨论了一种实时并行内核的LOTOS规范。本规范练习的目的是评估LOTOS对实际工业产品的实时特性建模的能力。TRANS-RTXC是由Intelligent Systems International开发的实时并行内核,使用LOTOS生成了TRANS-RTXC的形式规范。本文表明,虽然时间约束不能在LOTOS中显式表示,但该语言适合于实时任务协调的规范,而实时任务协调是实时内核的主要功能。本文还讨论了内核规范的验证过程以及工具在验证过程中的作用。我们相信我们的经验(使用结构化技术,使用验证方法和工具等)对于想要在设计或分析任务中应用正式模型的设计人员是有价值的。
{"title":"Specification and validation of a real-time parallel kernel using LOTOS","authors":"C. D. Farias, L. F. Pires, W. L. Souza, C. E. Morón","doi":"10.1109/MASCOT.2001.948848","DOIUrl":"https://doi.org/10.1109/MASCOT.2001.948848","url":null,"abstract":"This paper presents and discusses the LOTOS specification of a real-time parallel kernel. The purpose of this specification exercise has been to evaluate LOTOS with respect to its capabilities to model real-time features with a realistic industrial product. LOTOS was used to produce the formal specification of TRANS-RTXC, which is a real-time parallel kernel developed by Intelligent Systems International. This paper shows that although timing constraints cannot be explicitly represented in LOTOS, the language is suitable for the specification of co-ordination of real-time tasks, which is the main functionality of the real-time kernel. This paper also discusses the validation process of the kernel specification and the role of tools in this validation process. We believe that our experience (use of structuring techniques, use of validation methods and tools, etc.) is valuable for designers who want to apply formal models in their design or analysis tasks.","PeriodicalId":375127,"journal":{"name":"MASCOTS 2001, Proceedings Ninth International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125966747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2001-06-01DOI: 10.1109/MASCOT.2001.948888
A. Downey
We propose a user model that explains the shape of the distribution of file sizes in local file systems and in the World Wide Web. We examine evidence from 562 file systems, 38 Web clients and 6 Web servers, and find that this model is an accurate description of these systems. We compare this model to an alternative that has been proposed, the Pareto model. Our results cast doubt on the widespread view that the distribution of file sizes is long-tailed; we discuss the implications of this conclusion for proposed explanations of self-similarity in the Internet.
{"title":"The structural cause of file size distributions","authors":"A. Downey","doi":"10.1109/MASCOT.2001.948888","DOIUrl":"https://doi.org/10.1109/MASCOT.2001.948888","url":null,"abstract":"We propose a user model that explains the shape of the distribution of file sizes in local file systems and in the World Wide Web. We examine evidence from 562 file systems, 38 Web clients and 6 Web servers, and find that this model is an accurate description of these systems. We compare this model to an alternative that has been proposed, the Pareto model. Our results cast doubt on the widespread view that the distribution of file sizes is long-tailed; we discuss the implications of this conclusion for proposed explanations of self-similarity in the Internet.","PeriodicalId":375127,"journal":{"name":"MASCOTS 2001, Proceedings Ninth International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems","volume":"1078 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116294217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}