This paper describes our experiences, from a software perspective, with the OSIRIS network adaptor. It first identifies the problems we encountered while programming OSIRIS and optimizing network performance, and outlines how we either addressed them in the software, or had to modify the hardware. It then describes the opportunities provided by OSIRIS that we were able to exploit in the host operating system (OS); opportunities that suggested techniques for making the OS more effective in delivering network data to application programs. The most novel of these techniques, called application device channels, gives application programs running in user space direct access to the adaptor. The paper concludes with the lessons drawn from this work, which we believe will benefit the designers of future network adaptors.
{"title":"Experiences with a high-speed network adaptor: a software perspective","authors":"P. Druschel, L. Peterson, Bruce S. Davie","doi":"10.1145/190314.190315","DOIUrl":"https://doi.org/10.1145/190314.190315","url":null,"abstract":"This paper describes our experiences, from a software perspective, with the OSIRIS network adaptor. It first identifies the problems we encountered while programming OSIRIS and optimizing network performance, and outlines how we either addressed them in the software, or had to modify the hardware. It then describes the opportunities provided by OSIRIS that we were able to exploit in the host operating system (OS); opportunities that suggested techniques for making the OS more effective in delivering network data to application programs. The most novel of these techniques, called application device channels, gives application programs running in user space direct access to the adaptor. The paper concludes with the lessons drawn from this work, which we believe will benefit the designers of future network adaptors.","PeriodicalId":142337,"journal":{"name":"Proceedings of the conference on Communications architectures, protocols and applications","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132005911","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}
{"title":"Proceedings of the conference on Communications architectures, protocols and applications","authors":"J. Crowcroft","doi":"10.1145/190314","DOIUrl":"https://doi.org/10.1145/190314","url":null,"abstract":"","PeriodicalId":142337,"journal":{"name":"Proceedings of the conference on Communications architectures, protocols and applications","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115600698","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}
Due to a limited address space and poor scaling of backbone routing information, the Internet Protocol (IP) is rapidly reaching the end of its useful lifetime. The Simple Internet Protocol Plus (SIPP), a proposed next generation Internet Protocol, solves these problems with larger internet layer addresses. In addition, SIPP provides a number of advanced routing and addressing capabilities including mobility, extended (variable-length) addressing, provider selection, and certain forms of multicast. These capabilities are all achieved through a single mechanism, a generalization of the IP loose source route. We argue that, for reasons of simplicity and evolvability, a single powerful mechanism to achieve a wide range of routing and addressing functions is preferable to having multiple specific mechanisms, one for each function.
{"title":"Flexible routing and addressing for a next generation IP","authors":"P. Francis, R. Govindan","doi":"10.1145/190314.190325","DOIUrl":"https://doi.org/10.1145/190314.190325","url":null,"abstract":"Due to a limited address space and poor scaling of backbone routing information, the Internet Protocol (IP) is rapidly reaching the end of its useful lifetime. The Simple Internet Protocol Plus (SIPP), a proposed next generation Internet Protocol, solves these problems with larger internet layer addresses. In addition, SIPP provides a number of advanced routing and addressing capabilities including mobility, extended (variable-length) addressing, provider selection, and certain forms of multicast. These capabilities are all achieved through a single mechanism, a generalization of the IP loose source route. We argue that, for reasons of simplicity and evolvability, a single powerful mechanism to achieve a wide range of routing and addressing functions is preferable to having multiple specific mechanisms, one for each function.","PeriodicalId":142337,"journal":{"name":"Proceedings of the conference on Communications architectures, protocols and applications","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130359272","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 arrivals are often modeled as Poisson processes for analytic simplicity, even though a number of traffic studies have shown that packet interarrivals are not exponentially distributed. We evaluate 21 wide-area traces, investigating a number of wide-area TCP arrival processes (session and connection arrivals, FTPDATA connection arrivals within FTP sessions, and TELNET packet arrivals) to determine the error introduced by modeling them using Poisson processes. We find that user-initiated TCP session arrivals, such as remote-login and file-transfer, are well-modeled as Poisson processes with fixed hourly rates, but that other connection arrivals deviate considerably from Poisson; that modeling TELNET packet interarrivals as exponential grievously underestimates the burstiness of TELNET traffic, but using the empirical Tcplib[DJCME92] interarrivals preserves burstiness over many time scales; and that FTPDATA connection arrivals within FTP sessions come bunched into “connection burst”, the largest of which are so large that they completely dominate FTPDATA traffic. Finally, we offer some preliminary results regarding how our findings relate to the possible self-similarity of wide-area traffic.
{"title":"Wide-area traffic: the failure of Poisson modeling","authors":"V. Paxson, S. Floyd","doi":"10.1145/190314.190338","DOIUrl":"https://doi.org/10.1145/190314.190338","url":null,"abstract":"Network arrivals are often modeled as Poisson processes for analytic simplicity, even though a number of traffic studies have shown that packet interarrivals are not exponentially distributed. We evaluate 21 wide-area traces, investigating a number of wide-area TCP arrival processes (session and connection arrivals, FTPDATA connection arrivals within FTP sessions, and TELNET packet arrivals) to determine the error introduced by modeling them using Poisson processes. We find that user-initiated TCP session arrivals, such as remote-login and file-transfer, are well-modeled as Poisson processes with fixed hourly rates, but that other connection arrivals deviate considerably from Poisson; that modeling TELNET packet interarrivals as exponential grievously underestimates the burstiness of TELNET traffic, but using the empirical Tcplib[DJCME92] interarrivals preserves burstiness over many time scales; and that FTPDATA connection arrivals within FTP sessions come bunched into “connection burst”, the largest of which are so large that they completely dominate FTPDATA traffic. Finally, we offer some preliminary results regarding how our findings relate to the possible self-similarity of wide-area traffic.","PeriodicalId":142337,"journal":{"name":"Proceedings of the conference on Communications architectures, protocols and applications","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115048655","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}
In this paper, we consider the problem of providing statistical guarantees (for example, on the tail distribution of delay) under the Generalized Processor Sharing (GPS) scheduling discipline. This work is motivated by, and is an extension of, Parekh and Gallager's deterministic study of GPS scheduling discipline with leaky-bucket token controlled sessions [PG93a,b, Parekh92]. Using the exponentially bounded burstiness (E.B.B.) process model introduced in [YaSi93a] as a source traffic characterization, we establish results that extend the deterministic study of GPS: for a single GPS server in isolation, we present statistical bounds on the tail distributions of backlog and delay for each session. In the network setting, we show that networks belonging to a broad class of GPS assignments, the so-called Consistent Relative Session Treatment (CRST) GPS assignments, are stable in a stochastic sense. In particular, we establish simple bounds on the tail distribution of backlog and delay for each session in a Rate Proportional Processor Sharing (RPPS) GPS network with arbitrary topology.
{"title":"Statistical analysis of generalized processor sharing scheduling discipline","authors":"Zhi-Li Zhang, D. Towsley, J. Kurose","doi":"10.1145/190314.190321","DOIUrl":"https://doi.org/10.1145/190314.190321","url":null,"abstract":"In this paper, we consider the problem of providing statistical guarantees (for example, on the tail distribution of delay) under the Generalized Processor Sharing (GPS) scheduling discipline. This work is motivated by, and is an extension of, Parekh and Gallager's deterministic study of GPS scheduling discipline with leaky-bucket token controlled sessions [PG93a,b, Parekh92]. Using the exponentially bounded burstiness (E.B.B.) process model introduced in [YaSi93a] as a source traffic characterization, we establish results that extend the deterministic study of GPS: for a single GPS server in isolation, we present statistical bounds on the tail distributions of backlog and delay for each session. In the network setting, we show that networks belonging to a broad class of GPS assignments, the so-called Consistent Relative Session Treatment (CRST) GPS assignments, are stable in a stochastic sense. In particular, we establish simple bounds on the tail distribution of backlog and delay for each session in a Rate Proportional Processor Sharing (RPPS) GPS network with arbitrary topology.","PeriodicalId":142337,"journal":{"name":"Proceedings of the conference on Communications architectures, protocols and applications","volume":"216 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134257558","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 present a detailed statistical analysis of a 2-hour long empirical sample of VBR video. The sample was obtained by applying a simple intraframe video compression code to an action movie. The main findings of our analysis are (1) the tail behavior of the marginal bandwidth distribution can be accurately described using “heavy-tailed” distributions (e.g., Pareto); (2) the autocorrelation of the VBR video sequence decays hyperbolically (equivalent to long-range dependence) and can be modeled using self-similar processes. We combine our findings in a new (non-Markovian) source model for VBR video and present an algorithm for generating synthetic traffic. Trace-driven simulations show that statistical multiplexing results in significant bandwidth efficiency even when long-range dependence is present. Simulations of our source model show long-range dependence and heavy-tailed marginals to be important components which are not accounted for in currently used VBR video traffic models.
{"title":"Analysis, modeling and generation of self-similar VBR video traffic","authors":"M. Garrett, W. Willinger","doi":"10.1145/190314.190339","DOIUrl":"https://doi.org/10.1145/190314.190339","url":null,"abstract":"We present a detailed statistical analysis of a 2-hour long empirical sample of VBR video. The sample was obtained by applying a simple intraframe video compression code to an action movie. The main findings of our analysis are (1) the tail behavior of the marginal bandwidth distribution can be accurately described using “heavy-tailed” distributions (e.g., Pareto); (2) the autocorrelation of the VBR video sequence decays hyperbolically (equivalent to long-range dependence) and can be modeled using self-similar processes. We combine our findings in a new (non-Markovian) source model for VBR video and present an algorithm for generating synthetic traffic. Trace-driven simulations show that statistical multiplexing results in significant bandwidth efficiency even when long-range dependence is present. Simulations of our source model show long-range dependence and heavy-tailed marginals to be important components which are not accounted for in currently used VBR video traffic models.","PeriodicalId":142337,"journal":{"name":"Proceedings of the conference on Communications architectures, protocols and applications","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123407325","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}
This paper discusses congestion control from a game-theoretic perspective. There are two basic premises: (1) users are assumed to be independent and selfish, and (2) central administrative control is exercised only at the network switches. The operating points resulting from selfish user behavior depend crucially on the service disciplines implemented in network switches. This effect is investigated in a simple model consisting of a single exponential server shared by many Poisson sources. We discuss the extent to which one can guarantee, through the choice of switch service disciplines, that these selfish operating points will be efficient and fair. We also discuss to what extent the choice of switch service disciplines can ensure that these selfish operating points are unique and are easily and rapidly accessible by simple self-optimization techniques. We show that no service discipline can guarantee optimal efficiency. As for the other properties, we show that the traditional FIFO service discipline guarantees none of these properties, but that a service discipline called Fair Share guarantees all of them. While the treatment utilizes game-theoretic concepts, no previous knowledge of game theory is assumed.
{"title":"Making greed work in networks: a game-theoretic analysis of switch service disciplines","authors":"S. Shenker","doi":"10.1145/190314.190319","DOIUrl":"https://doi.org/10.1145/190314.190319","url":null,"abstract":"This paper discusses congestion control from a game-theoretic perspective. There are two basic premises: (1) users are assumed to be independent and selfish, and (2) central administrative control is exercised only at the network switches. The operating points resulting from selfish user behavior depend crucially on the service disciplines implemented in network switches. This effect is investigated in a simple model consisting of a single exponential server shared by many Poisson sources. We discuss the extent to which one can guarantee, through the choice of switch service disciplines, that these selfish operating points will be efficient and fair. We also discuss to what extent the choice of switch service disciplines can ensure that these selfish operating points are unique and are easily and rapidly accessible by simple self-optimization techniques. We show that no service discipline can guarantee optimal efficiency. As for the other properties, we show that the traditional FIFO service discipline guarantees none of these properties, but that a service discipline called Fair Share guarantees all of them. While the treatment utilizes game-theoretic concepts, no previous knowledge of game theory is assumed.","PeriodicalId":142337,"journal":{"name":"Proceedings of the conference on Communications architectures, protocols and applications","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114711887","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}
This paper describes the design of an implementation of the Transmission Control Protocol using an extension of the Standard ML (SML) language. SML supports higher-order functions, modularity, and type-safe module composition. We find that by using SML we can achieve good structure and good performance simultaneously. Good structure includes a modular decomposition of the protocol stack and of the TCP implementation, a control structure that imposes a total ordering on all events and processes them synchronously, and a test structure that allows component testing to catch problems before system integration. Strategies that help achieve good performance include using fast algorithms, using language constructs that make it easy to stage function evaluation, and language implementation features such as compacting garbage collection.
{"title":"A structured TCP in standard ML.","authors":"E. Biagioni","doi":"10.1145/190314.190318","DOIUrl":"https://doi.org/10.1145/190314.190318","url":null,"abstract":"This paper describes the design of an implementation of the Transmission Control Protocol using an extension of the Standard ML (SML) language. SML supports higher-order functions, modularity, and type-safe module composition. We find that by using SML we can achieve good structure and good performance simultaneously. Good structure includes a modular decomposition of the protocol stack and of the TCP implementation, a control structure that imposes a total ordering on all events and processes them synchronously, and a test structure that allows component testing to catch problems before system integration. Strategies that help achieve good performance include using fast algorithms, using language constructs that make it easy to stage function evaluation, and language implementation features such as compacting garbage collection.","PeriodicalId":142337,"journal":{"name":"Proceedings of the conference on Communications architectures, protocols and applications","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125592882","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}
Hop-by-hop flow control can be used to fairly share the bandwidth of a network among competing flows. No data is lost even in overload conditions; yet each flow gets access to the maximum throughput when the network is lightly loaded. However, some schemes for hop-by-hop flow control require too much memory; some of them are not resilient to errors. We propose a scheme for making hop-by-hop flow control resilient and show that it has advantages over schemes proposed by Kung. We also describe a novel method for sharing the available buffers among the flows on a link; our scheme allows us to potentially reduce the memory requirement (or increase the number of flows that can be supported) by an order of magnitude. Most of the work is described in the context of an ATM network that uses credit based flow control. However our ideas extend to networks in which flows can be distinguished, and to rate based flow control schemes.
{"title":"Reliable and efficient hop-by-hop flow control","authors":"C. Özveren, R. Simcoe, G. Varghese","doi":"10.1145/190314.190323","DOIUrl":"https://doi.org/10.1145/190314.190323","url":null,"abstract":"Hop-by-hop flow control can be used to fairly share the bandwidth of a network among competing flows. No data is lost even in overload conditions; yet each flow gets access to the maximum throughput when the network is lightly loaded. However, some schemes for hop-by-hop flow control require too much memory; some of them are not resilient to errors. We propose a scheme for making hop-by-hop flow control resilient and show that it has advantages over schemes proposed by Kung. We also describe a novel method for sharing the available buffers among the flows on a link; our scheme allows us to potentially reduce the memory requirement (or increase the number of flows that can be supported) by an order of magnitude. Most of the work is described in the context of an ATM network that uses credit based flow control. However our ideas extend to networks in which flows can be distinguished, and to rate based flow control schemes.","PeriodicalId":142337,"journal":{"name":"Proceedings of the conference on Communications architectures, protocols and applications","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125162651","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}
In recent years, a wide variety of mobile computing devices has emerged, including portables, palmtops, and personal digital assistants. Providing adequate network connectivity for these devices will require a new generation of wireless LAN technology. In this paper we study media access protocols for a single channel wireless LAN being developed at Xerox Corporation's Palo Alto Research Center. We start with the MACA media access protocol first proposed by Karn [9] and later refined by Biba [3] which uses an RTS-CTS-DATA packet exchange and binary exponential back-off. Using packet-level simulations, we examine various performance and design issues in such protocols. Our analysis leads to a new protocol, MACAW, which uses an RTS-CTS-DS-DATA-ACK message exchange and includes a significantly different backoff algorithm.
{"title":"MACAW: a media access protocol for wireless LAN's","authors":"V. Bharghavan, A. Demers, S. Shenker, Lixia Zhang","doi":"10.1145/190314.190334","DOIUrl":"https://doi.org/10.1145/190314.190334","url":null,"abstract":"In recent years, a wide variety of mobile computing devices has emerged, including portables, palmtops, and personal digital assistants. Providing adequate network connectivity for these devices will require a new generation of wireless LAN technology. In this paper we study media access protocols for a single channel wireless LAN being developed at Xerox Corporation's Palo Alto Research Center. We start with the MACA media access protocol first proposed by Karn [9] and later refined by Biba [3] which uses an RTS-CTS-DATA packet exchange and binary exponential back-off. Using packet-level simulations, we examine various performance and design issues in such protocols. Our analysis leads to a new protocol, MACAW, which uses an RTS-CTS-DS-DATA-ACK message exchange and includes a significantly different backoff algorithm.","PeriodicalId":142337,"journal":{"name":"Proceedings of the conference on Communications architectures, protocols and applications","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122266124","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：