This paper addresses the unfairness problems of a DQDB network through an structured access remedial scheme, viz., the dynamic 3-tier protocol. At low load domains, the original DQDB protocol performance is retained. At heavy loads, a dynamic bandwidth control mechanism, named Alpha Tuning Mechanism, is activated. With the right choice of the /spl alpha/-parameter, it is possible to match the service pattern (in terms of channel bandwidth) offered by the access protocol with the actual demand (or traffic) pattern in the network. At low load domains an anticipatory demand function (/spl Delta/) addresses latency related unfairness. The results demonstrate the effectiveness of this approach.<>
{"title":"The dynamic 3-tier protocol: an access remedial scheme to control unfairness in DQDB MANs","authors":"L. N. Kumar, C. Douligeris","doi":"10.1109/LCN.1994.386611","DOIUrl":"https://doi.org/10.1109/LCN.1994.386611","url":null,"abstract":"This paper addresses the unfairness problems of a DQDB network through an structured access remedial scheme, viz., the dynamic 3-tier protocol. At low load domains, the original DQDB protocol performance is retained. At heavy loads, a dynamic bandwidth control mechanism, named Alpha Tuning Mechanism, is activated. With the right choice of the /spl alpha/-parameter, it is possible to match the service pattern (in terms of channel bandwidth) offered by the access protocol with the actual demand (or traffic) pattern in the network. At low load domains an anticipatory demand function (/spl Delta/) addresses latency related unfairness. The results demonstrate the effectiveness of this approach.<<ETX>>","PeriodicalId":270137,"journal":{"name":"Proceedings of 19th Conference on Local Computer Networks","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121772979","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}
Since the emergence of cyclic reservation multiple access (CRMA) metropolitan area network (MAN) protocol, there has been only limited analysis results. This control method grants channel access to stations through channel reservations, and operates under service cycles and reserve cycles. The service commands and reserve commands signal the beginning of service cycles and reserve cycles, respectively. An improved CRMA is described, and a queueing model is developed to study the mean cycle waiting time characteristics in response to the input traffic intensity, the number of stations, and the inter-arrival time of reserve commands. The probability of no waiting; which indicates the chance that a reservation's service starts as soon as it enters the global queue, is also calculated.<>
{"title":"Analysis of cyclic reservation multiple access protocol","authors":"E. Huang","doi":"10.1109/LCN.1994.386610","DOIUrl":"https://doi.org/10.1109/LCN.1994.386610","url":null,"abstract":"Since the emergence of cyclic reservation multiple access (CRMA) metropolitan area network (MAN) protocol, there has been only limited analysis results. This control method grants channel access to stations through channel reservations, and operates under service cycles and reserve cycles. The service commands and reserve commands signal the beginning of service cycles and reserve cycles, respectively. An improved CRMA is described, and a queueing model is developed to study the mean cycle waiting time characteristics in response to the input traffic intensity, the number of stations, and the inter-arrival time of reserve commands. The probability of no waiting; which indicates the chance that a reservation's service starts as soon as it enters the global queue, is also calculated.<<ETX>>","PeriodicalId":270137,"journal":{"name":"Proceedings of 19th Conference on Local Computer Networks","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126030822","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}
We study the impact of the selection of flow control functions in high-speed transport protocols on the performance for both nonbursty client-server traffic and bulk-data communication such as file transfer in a local high-speed environment. Therefore, we consider a workstation cluster based on a FDDI network. Although there are some differences in the behaviour all flow control and retransmission schemes studied (Go back N, Selective Repeat, Selective Retransmission) are able to provide the same performance in the local environment. Here an additionally used rate control scheme is able to reduce a high buffer utilization of a receiving station for a bulk-data transfer without any impact on the transfer delay and throughput. In the conclusion we discuss both functionality and implementational aspects of transport protocols.<>
我们研究了高速传输协议中流量控制功能的选择对本地高速环境中非突发客户端-服务器流量和大数据通信(如文件传输)性能的影响。因此，我们考虑一个基于FDDI网络的工作站集群。尽管在行为上存在一些差异，但所研究的所有流量控制和重传方案(Go back N, Selective Repeat, Selective retransmission)都能够在本地环境中提供相同的性能。在这里，另外使用的速率控制方案能够在不影响传输延迟和吞吐量的情况下降低接收站对大容量数据传输的高缓冲区利用率。在结论中，我们讨论了传输协议的功能和实现方面。
{"title":"Flow control functions for high-speed transport protocols in local workstation environments","authors":"M. Frank, R. Wittenberg","doi":"10.1109/LCN.1994.386620","DOIUrl":"https://doi.org/10.1109/LCN.1994.386620","url":null,"abstract":"We study the impact of the selection of flow control functions in high-speed transport protocols on the performance for both nonbursty client-server traffic and bulk-data communication such as file transfer in a local high-speed environment. Therefore, we consider a workstation cluster based on a FDDI network. Although there are some differences in the behaviour all flow control and retransmission schemes studied (Go back N, Selective Repeat, Selective Retransmission) are able to provide the same performance in the local environment. Here an additionally used rate control scheme is able to reduce a high buffer utilization of a receiving station for a bulk-data transfer without any impact on the transfer delay and throughput. In the conclusion we discuss both functionality and implementational aspects of transport protocols.<<ETX>>","PeriodicalId":270137,"journal":{"name":"Proceedings of 19th Conference on Local Computer Networks","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132260851","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}
Local area networks (LANs) have emerged as the technology of choice for inter-computer communication. As computers get faster, so must the LAN environment that supports them. Today there are several successful competing LANs in the 100 Mbps arena, and we are now starting to look forward to the next generation of network to take over when the current generation cannot provide the necessary bandwidth and connectivity. The paper discusses some of the architectural trade-offs available to designers of the next generation LAN, and proposes an architecture which provides for convenient interconnection of multiple FDDI networks (and network segments). The underlying network architecture is based on FDDI protocols, an attractive feature for those who have invested into FDDI. Scaleability appears to be a required feature for any future network design and is addressed in detail. The ultimate goal of this research is to present an alternative next generation networking solution that could be adopted by ANSI as the FDDI follow on standard.<>
{"title":"Interconnection of FDDI LANs","authors":"B. Albert, A. Jayasumana","doi":"10.1109/LCN.1994.386614","DOIUrl":"https://doi.org/10.1109/LCN.1994.386614","url":null,"abstract":"Local area networks (LANs) have emerged as the technology of choice for inter-computer communication. As computers get faster, so must the LAN environment that supports them. Today there are several successful competing LANs in the 100 Mbps arena, and we are now starting to look forward to the next generation of network to take over when the current generation cannot provide the necessary bandwidth and connectivity. The paper discusses some of the architectural trade-offs available to designers of the next generation LAN, and proposes an architecture which provides for convenient interconnection of multiple FDDI networks (and network segments). The underlying network architecture is based on FDDI protocols, an attractive feature for those who have invested into FDDI. Scaleability appears to be a required feature for any future network design and is addressed in detail. The ultimate goal of this research is to present an alternative next generation networking solution that could be adopted by ANSI as the FDDI follow on standard.<<ETX>>","PeriodicalId":270137,"journal":{"name":"Proceedings of 19th Conference on Local Computer Networks","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134316974","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}
Support for digital audio and video streams (continuous media) in desktop computers is increasingly widespread and hence the demand for high-quality network distribution of continuous media streams is growing. While current local area and campus-wide networks have high-bandwidth links and powerful routers, the delay sensitivities of continuous media streams pose a challenge. Our paper provides an empirical investigation of the feasibility of transmitting real-time packet streams across a large extant campus network, the University of Virginia campus network. This network is representative of contemporary large enterprise networks consisting of Ethernet segments connected by high-performance routers to high-speed back-bones, e.g., FDDI rings. We focus on interactive packet voice. Delay and loss measurements are obtained for packet voice streams transmitted over three paths through the network. These measurements are used to examine the voice protocol parameters for this environment, including a novel retransmission-based error control proposed by Dempsey (1994).<>
{"title":"An empirical study of packet voice distribution over a campus-wide network","authors":"B. J. Dempsey, M. T. Lucas, A. Weaver","doi":"10.1109/LCN.1994.386573","DOIUrl":"https://doi.org/10.1109/LCN.1994.386573","url":null,"abstract":"Support for digital audio and video streams (continuous media) in desktop computers is increasingly widespread and hence the demand for high-quality network distribution of continuous media streams is growing. While current local area and campus-wide networks have high-bandwidth links and powerful routers, the delay sensitivities of continuous media streams pose a challenge. Our paper provides an empirical investigation of the feasibility of transmitting real-time packet streams across a large extant campus network, the University of Virginia campus network. This network is representative of contemporary large enterprise networks consisting of Ethernet segments connected by high-performance routers to high-speed back-bones, e.g., FDDI rings. We focus on interactive packet voice. Delay and loss measurements are obtained for packet voice streams transmitted over three paths through the network. These measurements are used to examine the voice protocol parameters for this environment, including a novel retransmission-based error control proposed by Dempsey (1994).<<ETX>>","PeriodicalId":270137,"journal":{"name":"Proceedings of 19th Conference on Local Computer Networks","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121069272","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}
The transport control protocol (TCP) was introduced in the early 1970's to enhance the service of the Internet protocol (IP) and to provide reliable data transfer across heterogeneous packet switching networks. Since then it has probably become the most widely used transport protocol. Recently, several mechanisms, such as slow start and congestion avoidance, have been added to most TCP implementations to improve its performance and to help in controlling and avoiding congestion in high speed and long delay networks. This paper investigates the performance of TCP within wide area networks and quantifies the impact that the TCP built-in congestion control mechanisms, have on overall network performance. The results show that these mechanisms have improved overall network performance, minimized network vulnerability to congestion and made it possible for TCP to operate effectively in wide area networking environments. The results also show that although disabling the congestion control mechanisms may improve the application's end-to-end performance, it introduces a higher proportion of busty traffic onto the underlying networks. This, however, makes the network more vulnerable to congestion and presents a challenge for network planning and engineering.<>
{"title":"Performance considerations for TCP/IP in wide area networks","authors":"K. Khalil, Y. Sun","doi":"10.1109/LCN.1994.386603","DOIUrl":"https://doi.org/10.1109/LCN.1994.386603","url":null,"abstract":"The transport control protocol (TCP) was introduced in the early 1970's to enhance the service of the Internet protocol (IP) and to provide reliable data transfer across heterogeneous packet switching networks. Since then it has probably become the most widely used transport protocol. Recently, several mechanisms, such as slow start and congestion avoidance, have been added to most TCP implementations to improve its performance and to help in controlling and avoiding congestion in high speed and long delay networks. This paper investigates the performance of TCP within wide area networks and quantifies the impact that the TCP built-in congestion control mechanisms, have on overall network performance. The results show that these mechanisms have improved overall network performance, minimized network vulnerability to congestion and made it possible for TCP to operate effectively in wide area networking environments. The results also show that although disabling the congestion control mechanisms may improve the application's end-to-end performance, it introduces a higher proportion of busty traffic onto the underlying networks. This, however, makes the network more vulnerable to congestion and presents a challenge for network planning and engineering.<<ETX>>","PeriodicalId":270137,"journal":{"name":"Proceedings of 19th Conference on Local Computer Networks","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115739922","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}
A new collision resolution algorithm called the space division multiple access protocol (SDMA) is presented. SDMA gains a performance advantage over similar protocols by using information about the positions of stations on the network. The protocol can operate asynchronously on a broadcast bus, allowing variable sized packet traffic. Through simulation the protocol is demonstrated to have better performance than Ethernet and the Capetanakis Tree protocol, a similar collision resolution protocol, under some traffic conditions. In particular, under heavy loads, SDMA displays better average throughput and lower variance of delay than Ethernet. The protocol demonstrates a performance bias based on the location of stations, but in most cases this bias is less severe than that experienced by Ethernet.<>
{"title":"A topology-aware collision resolution algorithm","authors":"Lewis Barnett","doi":"10.1109/LCN.1994.386600","DOIUrl":"https://doi.org/10.1109/LCN.1994.386600","url":null,"abstract":"A new collision resolution algorithm called the space division multiple access protocol (SDMA) is presented. SDMA gains a performance advantage over similar protocols by using information about the positions of stations on the network. The protocol can operate asynchronously on a broadcast bus, allowing variable sized packet traffic. Through simulation the protocol is demonstrated to have better performance than Ethernet and the Capetanakis Tree protocol, a similar collision resolution protocol, under some traffic conditions. In particular, under heavy loads, SDMA displays better average throughput and lower variance of delay than Ethernet. The protocol demonstrates a performance bias based on the location of stations, but in most cases this bias is less severe than that experienced by Ethernet.<<ETX>>","PeriodicalId":270137,"journal":{"name":"Proceedings of 19th Conference on Local Computer Networks","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123234334","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}
Describes an enterprise architecture for LAN-based office applications developed for the IBM Corporation. The LAN-based office applications include Lotus Notes, E-Mail gateways to the host, a host to LAN calendar system, word processors, graphics applications, and spreadsheet applications. The focus of the article is on the architecture of this LAN-based office system over IBM's wide area networks. The connection of the LAN office over the enterprise has brought up requirements for the distribution of databases, connections to LAN office systems outside of IBM, naming standards, a company-wide LAN address book, address book synchronization, remote monitoring, and remote management.<>
{"title":"LAN-based office for the enterprise, a case study","authors":"J. Lamb, Tony Cusato","doi":"10.1109/LCN.1994.386575","DOIUrl":"https://doi.org/10.1109/LCN.1994.386575","url":null,"abstract":"Describes an enterprise architecture for LAN-based office applications developed for the IBM Corporation. The LAN-based office applications include Lotus Notes, E-Mail gateways to the host, a host to LAN calendar system, word processors, graphics applications, and spreadsheet applications. The focus of the article is on the architecture of this LAN-based office system over IBM's wide area networks. The connection of the LAN office over the enterprise has brought up requirements for the distribution of databases, connections to LAN office systems outside of IBM, naming standards, a company-wide LAN address book, address book synchronization, remote monitoring, and remote management.<<ETX>>","PeriodicalId":270137,"journal":{"name":"Proceedings of 19th Conference on Local Computer Networks","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133230657","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}
Network management, when conducted in-band, adds traffic load to the managed network. Sometimes it is hard to tell how much traffic will result from network management. SNMP-based management stations can behave in surprising ways. Direct measurement of this traffic is needed, but needs to be done carefully. In the case studied, network management creates a significant, but tolerable amount of traffic.<>
{"title":"Network management's impact on managed networks","authors":"Christopher Amley","doi":"10.1109/LCN.1994.386580","DOIUrl":"https://doi.org/10.1109/LCN.1994.386580","url":null,"abstract":"Network management, when conducted in-band, adds traffic load to the managed network. Sometimes it is hard to tell how much traffic will result from network management. SNMP-based management stations can behave in surprising ways. Direct measurement of this traffic is needed, but needs to be done carefully. In the case studied, network management creates a significant, but tolerable amount of traffic.<<ETX>>","PeriodicalId":270137,"journal":{"name":"Proceedings of 19th Conference on Local Computer Networks","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132327799","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}
A reliable group communication protocol requires that members of the group acknowledge the reception of messages. The uncontrolled transmission of acknowledgements from the members of a group can lead to implosion; a condition that occurs when the responses flood the network or overwhelm the resources of the client's host. Scaling, the increase in the membership of a group, is a typical cause of implosion and the subsequent failure of a group communication. The problem of implosion is reviewed in this paper and a number of solutions considered; from this examination, two reliable group communication protocols are developed. Although these protocols are designed to minimize the likelihood of implosion, they also exhibit shorter data transfer times and generate less network traffic as compared to other group communication methods.<>
{"title":"Implosion-avoidance protocols for reliable group communications","authors":"L. Hughes, M. Thomson","doi":"10.1109/LCN.1994.386598","DOIUrl":"https://doi.org/10.1109/LCN.1994.386598","url":null,"abstract":"A reliable group communication protocol requires that members of the group acknowledge the reception of messages. The uncontrolled transmission of acknowledgements from the members of a group can lead to implosion; a condition that occurs when the responses flood the network or overwhelm the resources of the client's host. Scaling, the increase in the membership of a group, is a typical cause of implosion and the subsequent failure of a group communication. The problem of implosion is reviewed in this paper and a number of solutions considered; from this examination, two reliable group communication protocols are developed. Although these protocols are designed to minimize the likelihood of implosion, they also exhibit shorter data transfer times and generate less network traffic as compared to other group communication methods.<<ETX>>","PeriodicalId":270137,"journal":{"name":"Proceedings of 19th Conference on Local Computer Networks","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134125837","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：