Pub Date : 1999-05-31DOI: 10.1109/IWQOS.1999.766480
Andrew T. Campbell, J. Vicente, Daniel A. M. Villela
The creation, deployment and management of network architecture is manual, time consuming and costly. To the network architect the creation process is ad-hoc in nature, based on hand crafting small-scale network prototypes that evolve toward wide scale deployment. We envision a different paradigm where 'spawning networks' are capable of profiling, spawning, architecting and managing distinct virtual network architecture on-the-fly. This paper provides an overview of a virtual network kernel and its life cycle of spawning virtual networks, and focuses particularly on the role of resource management of virtual networks. We describe virtuosity, a virtual network resource management system that minimizes the complexity of handling multiple spawned virtual networks that operate over multiple timescales. Virtuosity is driven by per-virtual network policy exerting control and management over multiple spawned virtual networks (characterized by a set of resources) and their spawned architecture (defined as a set of interacting controllers objects) by dynamically influencing the behavior of resource controllers over slow timescales. Virtuosity provides a foundation for the management of virtual networks and forms an integral part of the virtual network kernel being developed within the Genesis project at Columbia University.
{"title":"Virtuosity: performing virtual network resource management","authors":"Andrew T. Campbell, J. Vicente, Daniel A. M. Villela","doi":"10.1109/IWQOS.1999.766480","DOIUrl":"https://doi.org/10.1109/IWQOS.1999.766480","url":null,"abstract":"The creation, deployment and management of network architecture is manual, time consuming and costly. To the network architect the creation process is ad-hoc in nature, based on hand crafting small-scale network prototypes that evolve toward wide scale deployment. We envision a different paradigm where 'spawning networks' are capable of profiling, spawning, architecting and managing distinct virtual network architecture on-the-fly. This paper provides an overview of a virtual network kernel and its life cycle of spawning virtual networks, and focuses particularly on the role of resource management of virtual networks. We describe virtuosity, a virtual network resource management system that minimizes the complexity of handling multiple spawned virtual networks that operate over multiple timescales. Virtuosity is driven by per-virtual network policy exerting control and management over multiple spawned virtual networks (characterized by a set of resources) and their spawned architecture (defined as a set of interacting controllers objects) by dynamically influencing the behavior of resource controllers over slow timescales. Virtuosity provides a foundation for the management of virtual networks and forms an integral part of the virtual network kernel being developed within the Genesis project at Columbia University.","PeriodicalId":435117,"journal":{"name":"1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129434539","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 : 1999-05-31DOI: 10.1109/IWQOS.1999.766490
Ikjun Yeom, A. Reddy
The differentiated services (DiffServ) framework is receiving wide attention as an architecture for implementing service guarantees in the Internet. This paper looks at the impact of marking strategies employed by aggregated sources (customers) on the provided service in a DiffServ network. The paper proposes two new marking algorithms that improve the fairness among the individual flows within an aggregation.
{"title":"Impact of marking strategy on aggregated flows in a differentiated services network","authors":"Ikjun Yeom, A. Reddy","doi":"10.1109/IWQOS.1999.766490","DOIUrl":"https://doi.org/10.1109/IWQOS.1999.766490","url":null,"abstract":"The differentiated services (DiffServ) framework is receiving wide attention as an architecture for implementing service guarantees in the Internet. This paper looks at the impact of marking strategies employed by aggregated sources (customers) on the provided service in a DiffServ network. The paper proposes two new marking algorithms that improve the fairness among the individual flows within an aggregation.","PeriodicalId":435117,"journal":{"name":"1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354)","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132680474","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 : 1999-05-31DOI: 10.1109/IWQOS.1999.766472
J. Crowcroft
IP is often referred to as the waist of the hourglass, because of the simple model the Internet provides packet level communication compared to other approaches (e.g., FR, X.25 or B-ISDN), but runs over a complex plethora of links and switched networks, and is used by a firmament of application and transport protocols. The ever increasing demand for capacity is pushing us past the 40 Gbit/s barrier, and towards the terabit link. Dense mode WDM offers 128 wavelengths at tens of gigabytes per wavelength. However re-tuning takes geological epochs compared to IP packet switching, or flow switching, or even QoS routing time frames. The problem resembles that of IP over ATM or other virtual circuits, but this may be misleading: what is needed is a novel approach to a network architecture, that avoids the same design flaws and pitfalls we have been forced into in IP over ATM (including MPLS). This paper briefly describes why these approaches are misled, and attempts to outline an approach based on network edge packet sorting and scheduling, which may allow us to use pure optical core networks without sacrificing the flexibility of what we might call legacy electron-datagram services.
IP通常被称为沙漏的腰,因为互联网的简单的模型提供了包级别沟通与其他方式相比,x . 25(例如,FR,或者B-ISDN),但运行在一个复杂的大量链接和交换网络,并使用应用程序和传输协议的苍穹。对容量不断增长的需求正在推动我们超越40 Gbit/s的障碍，并走向太比特链路。密集模式WDM提供128个波长，每个波长数十千兆字节。然而，与IP分组交换、流交换、甚至QoS路由的时间框架相比，重新调优需要一个地质时代。这个问题类似于IP over ATM或其他虚拟电路，但这可能会产生误导:我们需要的是一种新颖的网络架构方法，以避免我们在IP over ATM(包括MPLS)中被迫遇到的同样的设计缺陷和陷阱。本文简要描述了这些方法被误导的原因，并试图概述一种基于网络边缘分组排序和调度的方法，这种方法可能允许我们使用纯光核心网络，而不会牺牲我们可能称之为传统电子数据报服务的灵活性。
{"title":"IP over photons: how not to waste the waist of the hourglass","authors":"J. Crowcroft","doi":"10.1109/IWQOS.1999.766472","DOIUrl":"https://doi.org/10.1109/IWQOS.1999.766472","url":null,"abstract":"IP is often referred to as the waist of the hourglass, because of the simple model the Internet provides packet level communication compared to other approaches (e.g., FR, X.25 or B-ISDN), but runs over a complex plethora of links and switched networks, and is used by a firmament of application and transport protocols. The ever increasing demand for capacity is pushing us past the 40 Gbit/s barrier, and towards the terabit link. Dense mode WDM offers 128 wavelengths at tens of gigabytes per wavelength. However re-tuning takes geological epochs compared to IP packet switching, or flow switching, or even QoS routing time frames. The problem resembles that of IP over ATM or other virtual circuits, but this may be misleading: what is needed is a novel approach to a network architecture, that avoids the same design flaws and pitfalls we have been forced into in IP over ATM (including MPLS). This paper briefly describes why these approaches are misled, and attempts to outline an approach based on network edge packet sorting and scheduling, which may allow us to use pure optical core networks without sacrificing the flexibility of what we might call legacy electron-datagram services.","PeriodicalId":435117,"journal":{"name":"1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354)","volume":"166 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127567814","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 : 1999-05-31DOI: 10.1109/IWQOS.1999.766487
P. Hurley, J. Le Boudec
We propose asymmetric best-effort, a novel service to provide a "throughput versus delay jitter" differentiated service for IP packets. With this service, every best effort packet is marked as either green or blue. Green packets, typically sent by real-time applications such as interactive audio, receive more losses during bouts of congestion than blue ones. In return, they receive less delay jitter. Both green and blue services are best-effort. The incentive to choose one or other is based on the nature of one's traffic and on traffic conditions. If applications are TCP-friendly, those sending blue packets will receive more throughput but also more delay jitter, than they would if they sent green packets for a given network state and path.
{"title":"A proposal for an asymmetric best-effort service","authors":"P. Hurley, J. Le Boudec","doi":"10.1109/IWQOS.1999.766487","DOIUrl":"https://doi.org/10.1109/IWQOS.1999.766487","url":null,"abstract":"We propose asymmetric best-effort, a novel service to provide a \"throughput versus delay jitter\" differentiated service for IP packets. With this service, every best effort packet is marked as either green or blue. Green packets, typically sent by real-time applications such as interactive audio, receive more losses during bouts of congestion than blue ones. In return, they receive less delay jitter. Both green and blue services are best-effort. The incentive to choose one or other is based on the nature of one's traffic and on traffic conditions. If applications are TCP-friendly, those sending blue packets will receive more throughput but also more delay jitter, than they would if they sent green packets for a given network state and path.","PeriodicalId":435117,"journal":{"name":"1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354)","volume":"147 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127257406","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 : 1999-05-31DOI: 10.1109/IWQOS.1999.766499
J. Wechta, Martin Fricker, Fred Halsall
This paper describes a novel approach to providing high levels of quality of service (QoS) for real-time UDP-based flows transmitted within switched IEEE 802.3 LANs. There are some obvious similarities between controlling congestion and providing high levels of QoS. Hence, some methods invented in order to control congestion may also be applied to support QoS in QoS-aware LANs. Since real-time and elastic traffic have different expectations in relation to the level of service received, the presented scheme grants them different priority levels and also different treatment on a hop-by-hop basis. The modified 802.3x hop-by-hop flow control is advocated as a better congestion control solution than packet dropping. Due to lack of data packet losses, TCP traffic sources need to be provided with the necessary feedback. In the presented scheme this is done by means of an early congestion notification (ECN) mechanism. Simulation results are also presented.
{"title":"Hop-by-hop flow control as a method to improve QoS in 802.3 LANs","authors":"J. Wechta, Martin Fricker, Fred Halsall","doi":"10.1109/IWQOS.1999.766499","DOIUrl":"https://doi.org/10.1109/IWQOS.1999.766499","url":null,"abstract":"This paper describes a novel approach to providing high levels of quality of service (QoS) for real-time UDP-based flows transmitted within switched IEEE 802.3 LANs. There are some obvious similarities between controlling congestion and providing high levels of QoS. Hence, some methods invented in order to control congestion may also be applied to support QoS in QoS-aware LANs. Since real-time and elastic traffic have different expectations in relation to the level of service received, the presented scheme grants them different priority levels and also different treatment on a hop-by-hop basis. The modified 802.3x hop-by-hop flow control is advocated as a better congestion control solution than packet dropping. Due to lack of data packet losses, TCP traffic sources need to be provided with the necessary feedback. In the presented scheme this is done by means of an early congestion notification (ECN) mechanism. Simulation results are also presented.","PeriodicalId":435117,"journal":{"name":"1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130804806","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 : 1999-05-31DOI: 10.1109/IWQOS.1999.766494
N. Semret, R. Liao, A. Campbell, A. Lazar
This paper presents a decentralized auction-based approach to pricing of edge-allocated bandwidth in a differentiated services model for the Internet. The players in this architecture are users, one raw-capacity seller per network and one broker per service per network. With the progressive second price auction mechanism as the basic building block, we conduct a game theoretic analysis, deriving optimal strategies for buyers and brokers, and show the existence of network-wide equilibria. We investigate the system dynamics by simulating a scenario with three interconnected networks, and two types of services built on the proposed standard expedited forwarding (EF) and assured forwarding (AF) per-hop-behaviors.
{"title":"Market pricing of differentiated Internet services","authors":"N. Semret, R. Liao, A. Campbell, A. Lazar","doi":"10.1109/IWQOS.1999.766494","DOIUrl":"https://doi.org/10.1109/IWQOS.1999.766494","url":null,"abstract":"This paper presents a decentralized auction-based approach to pricing of edge-allocated bandwidth in a differentiated services model for the Internet. The players in this architecture are users, one raw-capacity seller per network and one broker per service per network. With the progressive second price auction mechanism as the basic building block, we conduct a game theoretic analysis, deriving optimal strategies for buyers and brokers, and show the existence of network-wide equilibria. We investigate the system dynamics by simulating a scenario with three interconnected networks, and two types of services built on the proposed standard expedited forwarding (EF) and assured forwarding (AF) per-hop-behaviors.","PeriodicalId":435117,"journal":{"name":"1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123104357","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 : 1999-05-31DOI: 10.1109/IWQOS.1999.766498
L. Cherkasova, P. Phaal
We introduce a new, session-based workload for measuring Web server performance. We define a session as a sequence of client individual requests. We then measure server throughput as a number of successfully completed sessions. Using a simulation model we show that an overloaded Web server can experience a severe loss of throughput measured as a number of completed sessions compared with the server throughput measured in requests per second. Moreover statistical analysis of completed sessions reveals that the overloaded Web server discriminates against longer sessions. We introduce a session-based admission control (SBAC) to prevent a Web server from becoming overloaded and to ensure that longer sessions can be completed. We show that a Web server augmented with the admission control mechanism is able to provide a fair guarantee of completion, for any accepted session, independent of session length. This provides a predictable and controllable platform for Web applications, and is a critical requirement for any E-business.
{"title":"Session-based admission control: a mechanism for improving performance of commercial Web sites","authors":"L. Cherkasova, P. Phaal","doi":"10.1109/IWQOS.1999.766498","DOIUrl":"https://doi.org/10.1109/IWQOS.1999.766498","url":null,"abstract":"We introduce a new, session-based workload for measuring Web server performance. We define a session as a sequence of client individual requests. We then measure server throughput as a number of successfully completed sessions. Using a simulation model we show that an overloaded Web server can experience a severe loss of throughput measured as a number of completed sessions compared with the server throughput measured in requests per second. Moreover statistical analysis of completed sessions reveals that the overloaded Web server discriminates against longer sessions. We introduce a session-based admission control (SBAC) to prevent a Web server from becoming overloaded and to ensure that longer sessions can be completed. We show that a Web server augmented with the admission control mechanism is able to provide a fair guarantee of completion, for any accepted session, independent of session length. This provides a predictable and controllable platform for Web applications, and is a critical requirement for any E-business.","PeriodicalId":435117,"journal":{"name":"1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127910515","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 : 1999-02-01DOI: 10.1109/IWQOS.1999.766500
org Liebeherr, Erhan Yilmaz
Many packet schedulers for QoS networks are equipped with a rate control mechanism. The function of a rate control mechanism (rate controller) is to buffer packets from flows which exceed their negotiated traffic profile. It has been established that rate controllers lead to reduced buffer requirements at packet switches, and do not increase the worst-case delays in a deterministic service. On the other hand, rate controllers make a scheduler non-workconserving, and, thus, may yield higher average end-to-end delays. In this study, we show that by properly modifying a rate controller, one can design a scheduler which balances buffer requirements against average delays. We present a scheduler, called earliness-based earliest deadline first (EEDF), which achieves such a balancing using a tunable rate control mechanism. In simulation experiments, we compare EEDP with a rate-controlled EDF scheduler and a workconserving version of EDF.
{"title":"Workconserving vs. non-workconserving packet scheduling: an issue revisited","authors":"org Liebeherr, Erhan Yilmaz","doi":"10.1109/IWQOS.1999.766500","DOIUrl":"https://doi.org/10.1109/IWQOS.1999.766500","url":null,"abstract":"Many packet schedulers for QoS networks are equipped with a rate control mechanism. The function of a rate control mechanism (rate controller) is to buffer packets from flows which exceed their negotiated traffic profile. It has been established that rate controllers lead to reduced buffer requirements at packet switches, and do not increase the worst-case delays in a deterministic service. On the other hand, rate controllers make a scheduler non-workconserving, and, thus, may yield higher average end-to-end delays. In this study, we show that by properly modifying a rate controller, one can design a scheduler which balances buffer requirements against average delays. We present a scheduler, called earliness-based earliest deadline first (EEDF), which achieves such a balancing using a tunable rate control mechanism. In simulation experiments, we compare EEDP with a rate-controlled EDF scheduler and a workconserving version of EDF.","PeriodicalId":435117,"journal":{"name":"1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123959803","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 : 1900-01-01DOI: 10.1109/IWQOS.1999.766491
A. Odlyzko
Differentiated services for the Internet are undergoing intensive development. It is widely accepted that they will require usage-sensitive pricing. The Paris Metro pricing (PMP) proposal is to rely on pricing alone to provide differentiated services. PMP is the simplest differentiated services system in terms of complexity.
{"title":"Paris Metro pricing: the minimalist differentiated services solution","authors":"A. Odlyzko","doi":"10.1109/IWQOS.1999.766491","DOIUrl":"https://doi.org/10.1109/IWQOS.1999.766491","url":null,"abstract":"Differentiated services for the Internet are undergoing intensive development. It is widely accepted that they will require usage-sensitive pricing. The Paris Metro pricing (PMP) proposal is to rely on pricing alone to provide differentiated services. PMP is the simplest differentiated services system in terms of complexity.","PeriodicalId":435117,"journal":{"name":"1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354)","volume":"4 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":"115090241","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 : 1900-01-01DOI: 10.1109/IWQOS.1999.766486
Srihari Nelakuditi, R. Tsang, Zhi-Li Zhang
We propose a novel localized QoS routing approach, under which no global QoS state information exchange among network nodes is needed. This approach has many advantages over the conventional global QoS routing approach based on information exchange among routers. We develop two localized QoS routing schemes and demonstrate through simulations that the proposed localized QoS routing approach is indeed a viable alternative to the global QoS routing approach.
{"title":"Quality of service routing without global information exchange","authors":"Srihari Nelakuditi, R. Tsang, Zhi-Li Zhang","doi":"10.1109/IWQOS.1999.766486","DOIUrl":"https://doi.org/10.1109/IWQOS.1999.766486","url":null,"abstract":"We propose a novel localized QoS routing approach, under which no global QoS state information exchange among network nodes is needed. This approach has many advantages over the conventional global QoS routing approach based on information exchange among routers. We develop two localized QoS routing schemes and demonstrate through simulations that the proposed localized QoS routing approach is indeed a viable alternative to the global QoS routing approach.","PeriodicalId":435117,"journal":{"name":"1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354)","volume":"92 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":"126208346","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：