The Internet TCP/IP protocol suite is the first higher-level protocol stack to be used on ATM based networks. High-speed networks reinstate the end-system as the communication path bottleneck. We show how the host architecture and host network interface are crucial for memory-to-memory TCP throughput. In addition, configurable parameters like the TCP maximum window size and the user data size in the send and receive system calls influence the segment flow and throughput performance. We present measurements done on Sparc2 and Sparc10 based machines for both generations of ATM-cards from FORE Systems. The first generation cards are based on programmed I/O. The second generation cards on DMA. To explain the variations in the throughput characteristics, we put small optimized probes in the network driver to log the segment flow on the TCP connections.<>
Internet TCP/IP协议套件是第一个用于基于ATM的网络的高级协议栈。高速网络恢复了终端系统作为通信路径瓶颈的地位。我们将展示主机架构和主机网络接口对于内存到内存的TCP吞吐量是如何至关重要的。此外，发送和接收系统调用中的TCP最大窗口大小和用户数据大小等可配置参数会影响段流和吞吐量性能。我们介绍了在基于Sparc2和Sparc10的机器上对FORE Systems的两代atm卡进行的测量。第一代卡片是基于可编程I/O的。第二代卡在DMA上。为了解释吞吐量特征的变化，我们在网络驱动程序中放置了小型优化探针，以记录TCP连接上的段流。
{"title":"TCP/IP behavior in a high-speed local ATM network environment","authors":"K. Moldeklev, Espen Klovning, Ø. Kure","doi":"10.1109/LCN.1994.386602","DOIUrl":"https://doi.org/10.1109/LCN.1994.386602","url":null,"abstract":"The Internet TCP/IP protocol suite is the first higher-level protocol stack to be used on ATM based networks. High-speed networks reinstate the end-system as the communication path bottleneck. We show how the host architecture and host network interface are crucial for memory-to-memory TCP throughput. In addition, configurable parameters like the TCP maximum window size and the user data size in the send and receive system calls influence the segment flow and throughput performance. We present measurements done on Sparc2 and Sparc10 based machines for both generations of ATM-cards from FORE Systems. The first generation cards are based on programmed I/O. The second generation cards on DMA. To explain the variations in the throughput characteristics, we put small optimized probes in the network driver to log the segment flow on the TCP connections.<<ETX>>","PeriodicalId":270137,"journal":{"name":"Proceedings of 19th Conference on Local Computer Networks","volume":"86 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":"126931754","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}
Broadband applications require high-performance networking facilities and the guarantee of quality of service (QOS). Existing transport protocols are incapable of providing QOS. Should a transport entity result in insufficient processing bandwidth, the layer becomes a performance bottleneck and can no longer guarantee QOS. In addition, the problem of how transfer rates can be determined in the implementation of non-window-based flow control mechanisms has been left unexplored. This paper presents a transport system prototype, called the Broadband Application Transport System (BATS), conducted over the user datagram protocol platform. It supports four classes of applications with different time sensitivity, bit rates, and connection types. In an effort to guarantee QOS, BATS employs a resource management scheme and a rate-based flow control protocol. The resource manager may cause longer delays for time-insensitive applications and the blocking of connections for time-sensitive applications. Moreover, for rate-based flow control, the transfer rate for each application class can be accurately determined. Consequently, compared with TB, BATS achieves superior performance in terms of end-to-end transfer delay and delay jitter for all application classes under various system loads.<>
{"title":"BATS: a high-performance transport system for broadband applications","authors":"M. Yuang, Jen-Chu Liu, C. Shay","doi":"10.1109/LCN.1994.386574","DOIUrl":"https://doi.org/10.1109/LCN.1994.386574","url":null,"abstract":"Broadband applications require high-performance networking facilities and the guarantee of quality of service (QOS). Existing transport protocols are incapable of providing QOS. Should a transport entity result in insufficient processing bandwidth, the layer becomes a performance bottleneck and can no longer guarantee QOS. In addition, the problem of how transfer rates can be determined in the implementation of non-window-based flow control mechanisms has been left unexplored. This paper presents a transport system prototype, called the Broadband Application Transport System (BATS), conducted over the user datagram protocol platform. It supports four classes of applications with different time sensitivity, bit rates, and connection types. In an effort to guarantee QOS, BATS employs a resource management scheme and a rate-based flow control protocol. The resource manager may cause longer delays for time-insensitive applications and the blocking of connections for time-sensitive applications. Moreover, for rate-based flow control, the transfer rate for each application class can be accurately determined. Consequently, compared with TB, BATS achieves superior performance in terms of end-to-end transfer delay and delay jitter for all application classes under various system loads.<<ETX>>","PeriodicalId":270137,"journal":{"name":"Proceedings of 19th Conference on Local Computer Networks","volume":"1 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":"130026732","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}
Switched LANs are become more widely used because they can provide a higher bandwidth than LANs based on shared media. Examples of packet switched LANs include HIPPI, and switched FDDI and Ethernet. A number of studies have evaluated the performance of HIPPI networks, making simplifying assumptions about both the network and the traffic load. In this paper we present the results of a simulation study of circuit-switched LANs such as HIPPI using more realistic models for the system and the traffic. We observe changes in throughput as high as a factor of ten when we change the system and traffic parameters. We also show how packet scheduling can be used to improve performance in some cases.<>
{"title":"Performance of circuit switched LANs under different traffic conditions","authors":"Qingming Ma, P. Steenkiste","doi":"10.1109/LCN.1994.386593","DOIUrl":"https://doi.org/10.1109/LCN.1994.386593","url":null,"abstract":"Switched LANs are become more widely used because they can provide a higher bandwidth than LANs based on shared media. Examples of packet switched LANs include HIPPI, and switched FDDI and Ethernet. A number of studies have evaluated the performance of HIPPI networks, making simplifying assumptions about both the network and the traffic load. In this paper we present the results of a simulation study of circuit-switched LANs such as HIPPI using more realistic models for the system and the traffic. We observe changes in throughput as high as a factor of ten when we change the system and traffic parameters. We also show how packet scheduling can be used to improve performance in some cases.<<ETX>>","PeriodicalId":270137,"journal":{"name":"Proceedings of 19th Conference on Local Computer Networks","volume":"28 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":"133460736","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}
Ethernet, token-ring, and FDDI are well established protocols for regulating the access to a common transmission medium among a large number of stations. All of the attached stations share this common medium and its bandwidth. Sharing of a common medium reduces the bandwidth that is available to an individual station. To increase bandwidth to the end user, emerging LAN topologies are departing from shared-media, shared-bandwidth methods in favor of dedicated-media and dedicated-bandwidth methods. Dedicated-bandwidth switched LANs can take advantage of full-duplex operation of attached stations. This is in contrast to the normal half-duplex operation of LAN stations on a shared-bandwidth LAN. This paper describes the evolution of shared-media, shared-bandwidth LANs into dedicated-media, dedicated-bandwidth switched LANs with full-duplex operation of the attached stations.<>
{"title":"Emerging trends-Full-duplex and the switched LAN","authors":"Kenneth J. Christensen, F. Noel, Norman C. Strole","doi":"10.1109/LCN.1994.386596","DOIUrl":"https://doi.org/10.1109/LCN.1994.386596","url":null,"abstract":"Ethernet, token-ring, and FDDI are well established protocols for regulating the access to a common transmission medium among a large number of stations. All of the attached stations share this common medium and its bandwidth. Sharing of a common medium reduces the bandwidth that is available to an individual station. To increase bandwidth to the end user, emerging LAN topologies are departing from shared-media, shared-bandwidth methods in favor of dedicated-media and dedicated-bandwidth methods. Dedicated-bandwidth switched LANs can take advantage of full-duplex operation of attached stations. This is in contrast to the normal half-duplex operation of LAN stations on a shared-bandwidth LAN. This paper describes the evolution of shared-media, shared-bandwidth LANs into dedicated-media, dedicated-bandwidth switched LANs with full-duplex operation of the attached stations.<<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":"115861399","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}
C. Hong, T. Yoneda, Kenichiro Tanaka, S. Honda, Y. Matsushita
This paper describes and discusses the modeling of multimedia communication networking architecture suitable to high speed networks such as LAN, B-ISDN, etc. for the flexible management and rapid introduction of services. In this model, the applications are deployed in units of software building blocks called group call server, service control server, resource management server and client agent. Each building block provides a layered view for the effective management of the multimedia network resources and services. In this paper, we propose a service scenario scheme and multimedia logical devices model for the flexible generation and effective management of services, and abstracting the network resources, respectively. Finally, this paper presents an architecture evolution model toward interoperability in a distributed processing environment (DPE). This can be applied for interoperability between multimedia network resources provided by different vendors.<>
{"title":"Multimedia communication networking architecture model for high speed network","authors":"C. Hong, T. Yoneda, Kenichiro Tanaka, S. Honda, Y. Matsushita","doi":"10.1109/LCN.1994.386594","DOIUrl":"https://doi.org/10.1109/LCN.1994.386594","url":null,"abstract":"This paper describes and discusses the modeling of multimedia communication networking architecture suitable to high speed networks such as LAN, B-ISDN, etc. for the flexible management and rapid introduction of services. In this model, the applications are deployed in units of software building blocks called group call server, service control server, resource management server and client agent. Each building block provides a layered view for the effective management of the multimedia network resources and services. In this paper, we propose a service scenario scheme and multimedia logical devices model for the flexible generation and effective management of services, and abstracting the network resources, respectively. Finally, this paper presents an architecture evolution model toward interoperability in a distributed processing environment (DPE). This can be applied for interoperability between multimedia network resources provided by different vendors.<<ETX>>","PeriodicalId":270137,"journal":{"name":"Proceedings of 19th Conference on Local Computer Networks","volume":"18 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":"129914054","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}
Traffic shaping at a (traffic) source station as a prominent congestion control solution in ATM networks. The "leaky bucket" scheme in conjunction with a cell spacer is an extensively studied and used mechanism for such a traffic shaping. By dimensioning the leaky bucket and spacer parameters, a source station attempts to regulate the behavior of its own traffic in order to conform to a "good behavior" contract with the network. In this paper, we study the effect of the a single source's traffic characteristics and its leaky bucket parameters on the maximum burst size and the burst size distribution as seen by the network. The theoretical upper bound for the burst size is derived and simulation is used to study the effect of leaky bucket parameters on probability distribution of burst sizes. It is shown that while traffic shaping is done to abide to negotiated traffic characteristics, traffic shaping can lead to large queues of cells and result in large cell delay and delay jitter in the source station.<>
{"title":"Performance characteristics of end-stations in an ATM network as viewed for applications and network","authors":"B. Patel, C. Bisdikian","doi":"10.1109/LCN.1994.386588","DOIUrl":"https://doi.org/10.1109/LCN.1994.386588","url":null,"abstract":"Traffic shaping at a (traffic) source station as a prominent congestion control solution in ATM networks. The \"leaky bucket\" scheme in conjunction with a cell spacer is an extensively studied and used mechanism for such a traffic shaping. By dimensioning the leaky bucket and spacer parameters, a source station attempts to regulate the behavior of its own traffic in order to conform to a \"good behavior\" contract with the network. In this paper, we study the effect of the a single source's traffic characteristics and its leaky bucket parameters on the maximum burst size and the burst size distribution as seen by the network. The theoretical upper bound for the burst size is derived and simulation is used to study the effect of leaky bucket parameters on probability distribution of burst sizes. It is shown that while traffic shaping is done to abide to negotiated traffic characteristics, traffic shaping can lead to large queues of cells and result in large cell delay and delay jitter in the source station.<<ETX>>","PeriodicalId":270137,"journal":{"name":"Proceedings of 19th Conference on Local Computer Networks","volume":"41 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":"127204063","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}
Transporting multimedia traffic is becoming an essential requirement for communications networks. Unlike data traffic, multimedia traffic has strict demands on latency, throughput, jitter, and bandwidth. This paper demonstrates the capabilities of the currently available 16-Mbps token ring to simultaneously carry data and multimedia traffic. Experimental data and simulation results that show the effects of data on multimedia traffic and vice versa are presented. The use of the token ring priority mechanism for traffic regulation is demonstrated. The use of multiple levels of priorities for multimedia traffic is shown to be needed to meet the performance requirements of various types of multimedia traffic. Furthermore, the results show that these requirements can be met in the presence of bursty data traffic.<>
{"title":"Performance analysis of multiple priorities on token ring LANs to support multimedia","authors":"K. Amer","doi":"10.1109/LCN.1994.386581","DOIUrl":"https://doi.org/10.1109/LCN.1994.386581","url":null,"abstract":"Transporting multimedia traffic is becoming an essential requirement for communications networks. Unlike data traffic, multimedia traffic has strict demands on latency, throughput, jitter, and bandwidth. This paper demonstrates the capabilities of the currently available 16-Mbps token ring to simultaneously carry data and multimedia traffic. Experimental data and simulation results that show the effects of data on multimedia traffic and vice versa are presented. The use of the token ring priority mechanism for traffic regulation is demonstrated. The use of multiple levels of priorities for multimedia traffic is shown to be needed to meet the performance requirements of various types of multimedia traffic. Furthermore, the results show that these requirements can be met in the presence of bursty data traffic.<<ETX>>","PeriodicalId":270137,"journal":{"name":"Proceedings of 19th Conference on Local Computer Networks","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124636463","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 analyze the behavior of the Ethernet in networks with a small number of active stations, and describe what is known as the Ethernet capture effect. Where a station transmits consecutive packets exclusively for a prolonged period despite other stations contending for access. The capture effect causes transient unfairness, which results in substantial performance degradation. We report measurements using TCP/IP that show the performance degradation. A solution is proposed that effectively overcomes the capture effect. The proposed algorithm, which we call the capture avoidance binary exponential backoff (CABEB), uses the standard binary exponential backoff (BEB) with enhancements for collision resolution in the special case when a station attempts to capture the channel subsequent to an uninterrupted consecutive transmit. Using a detailed simulation, we show the efficacy of the CABEB algorithm over the standard BEB in overcoming the unfairness resulting from stations capturing the channel. The CABEB improves throughput for protocols like TCP/IP, reduces variability in the channel access latency and eliminates packet discards due to excessive collisions in a 2-node network. The algorithm is a modification that is compliant with the Ethernet/802.3 standards. For networks with a large number of active stations, the CABEB performs as well as the standard BEB algorithm. Our study placer emphasis on the workload and network configuration that is the worst case relative to the Ethernet capture effect to show that the proposed algorithm is a substantial improvement over the existing backoff algorithm.<>
{"title":"The Ethernet capture effect: analysis and solution","authors":"K. Ramakrishnan, Henry S. Yang","doi":"10.1109/LCN.1994.386597","DOIUrl":"https://doi.org/10.1109/LCN.1994.386597","url":null,"abstract":"We analyze the behavior of the Ethernet in networks with a small number of active stations, and describe what is known as the Ethernet capture effect. Where a station transmits consecutive packets exclusively for a prolonged period despite other stations contending for access. The capture effect causes transient unfairness, which results in substantial performance degradation. We report measurements using TCP/IP that show the performance degradation. A solution is proposed that effectively overcomes the capture effect. The proposed algorithm, which we call the capture avoidance binary exponential backoff (CABEB), uses the standard binary exponential backoff (BEB) with enhancements for collision resolution in the special case when a station attempts to capture the channel subsequent to an uninterrupted consecutive transmit. Using a detailed simulation, we show the efficacy of the CABEB algorithm over the standard BEB in overcoming the unfairness resulting from stations capturing the channel. The CABEB improves throughput for protocols like TCP/IP, reduces variability in the channel access latency and eliminates packet discards due to excessive collisions in a 2-node network. The algorithm is a modification that is compliant with the Ethernet/802.3 standards. For networks with a large number of active stations, the CABEB performs as well as the standard BEB algorithm. Our study placer emphasis on the workload and network configuration that is the worst case relative to the Ethernet capture effect to show that the proposed algorithm is a substantial improvement over the existing backoff algorithm.<<ETX>>","PeriodicalId":270137,"journal":{"name":"Proceedings of 19th Conference on Local Computer Networks","volume":"123 11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122956423","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：