Pub Date : 2000-10-01DOI: 10.1109/IWQOS.1999.766488
T. Korkmaz, M. Krunz
We investigate the problem of topology aggregation (TA) for scalable, QoS-based routing in ATM networks. TA is the process of summarizing the topological information of a subset of network elements. This summary is flooded throughout the network, and is used by various nodes to determine appropriate routes for connection requests. A key issue in the design of a TA scheme is the appropriate balance between compaction and the corresponding routing performance. The contributions of this paper are twofold. First, we introduce a source-oriented approach to TA, which provides better performance than existing approaches. The intuition behind this approach is that the advertised topology-state information is used by source nodes to determine tentative routes for connection requests. Accordingly, only relevant information to source nodes needs to be advertised. We integrate the source-oriented approach into three new TA schemes that provide different tradeoffs between compaction and accuracy. Second, we extend our source-oriented approach to multi-QoS-based TA. A key issue here is the determination of appropriate values for the multiple QoS parameters that are associated with a logical link. Two new approaches to computing these values are introduced. Extensive simulations are used to evaluate the performance of our proposed schemes.
{"title":"Source-oriented topology aggregation with multiple QoS parameters in hierarchical ATM networks","authors":"T. Korkmaz, M. Krunz","doi":"10.1109/IWQOS.1999.766488","DOIUrl":"https://doi.org/10.1109/IWQOS.1999.766488","url":null,"abstract":"We investigate the problem of topology aggregation (TA) for scalable, QoS-based routing in ATM networks. TA is the process of summarizing the topological information of a subset of network elements. This summary is flooded throughout the network, and is used by various nodes to determine appropriate routes for connection requests. A key issue in the design of a TA scheme is the appropriate balance between compaction and the corresponding routing performance. The contributions of this paper are twofold. First, we introduce a source-oriented approach to TA, which provides better performance than existing approaches. The intuition behind this approach is that the advertised topology-state information is used by source nodes to determine tentative routes for connection requests. Accordingly, only relevant information to source nodes needs to be advertised. We integrate the source-oriented approach into three new TA schemes that provide different tradeoffs between compaction and accuracy. Second, we extend our source-oriented approach to multi-QoS-based TA. A key issue here is the determination of appropriate values for the multiple QoS parameters that are associated with a logical link. Two new approaches to computing these values are introduced. Extensive simulations are used to evaluate the performance of our proposed schemes.","PeriodicalId":435117,"journal":{"name":"1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131608757","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 : 1999-12-01DOI: 10.1109/IWQOS.1999.766497
T. Abdelzaher, N. Bhatti
The Internet is undergoing substantial changes from a communication and browsing infrastructure to a medium for conducting business and selling a myriad of emerging services. The World-Wide Web provides a uniform and widely-accepted application interface used by these services to reach multitudes of clients. These changes place the Web server at the center of a gradually emerging E-service infrastructure with increasing requirements for service quality, reliability, and security guarantees in an unpredictable and highly dynamic environment. Towards that end, we introduce a Web server QoS provisioning architecture for performance differentiation among classes of clients, performance isolation among independent services, and capacity planning to provide QoS guarantees on request rate and delivered bandwidth. We present a new approach to Web server resource management based on Web content adaptation. This approach subsumes traditional admission control-based techniques and enhances server performance by selectively adapting content in accordance with both load conditions and QoS requirements. Our QoS management solutions can be implemented either in middleware transparent to the server or by direct modification of the server software. We present experimental data to illustrate the practicality of our approach.
互联网正经历着巨大的变化，从通信和浏览基础设施转变为开展业务和销售无数新兴服务的媒介。wide - world Web提供了一个统一的、被广泛接受的应用程序接口，这些服务使用它来访问大量的客户机。这些变化将Web服务器置于逐渐出现的电子服务基础设施的中心，在不可预测和高度动态的环境中，对服务质量、可靠性和安全性保证的要求越来越高。为此，我们引入了一个Web服务器QoS配置体系结构，用于区分客户端类别之间的性能差异、独立服务之间的性能隔离以及容量规划，以在请求速率和交付带宽上提供QoS保证。提出了一种基于Web内容自适应的Web服务器资源管理方法。这种方法包含了传统的基于接纳控制的技术，并通过根据负载条件和QoS要求选择性地调整内容来增强服务器性能。我们的QoS管理解决方案既可以在对服务器透明的中间件中实现，也可以通过直接修改服务器软件实现。我们提供实验数据来说明我们方法的实用性。
{"title":"Web server QoS management by adaptive content delivery","authors":"T. Abdelzaher, N. Bhatti","doi":"10.1109/IWQOS.1999.766497","DOIUrl":"https://doi.org/10.1109/IWQOS.1999.766497","url":null,"abstract":"The Internet is undergoing substantial changes from a communication and browsing infrastructure to a medium for conducting business and selling a myriad of emerging services. The World-Wide Web provides a uniform and widely-accepted application interface used by these services to reach multitudes of clients. These changes place the Web server at the center of a gradually emerging E-service infrastructure with increasing requirements for service quality, reliability, and security guarantees in an unpredictable and highly dynamic environment. Towards that end, we introduce a Web server QoS provisioning architecture for performance differentiation among classes of clients, performance isolation among independent services, and capacity planning to provide QoS guarantees on request rate and delivered bandwidth. We present a new approach to Web server resource management based on Web content adaptation. This approach subsumes traditional admission control-based techniques and enhances server performance by selectively adapting content in accordance with both load conditions and QoS requirements. Our QoS management solutions can be implemented either in middleware transparent to the server or by direct modification of the server software. We present experimental data to illustrate the practicality of our approach.","PeriodicalId":435117,"journal":{"name":"1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134099247","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.1999.766475
Ian T Foster, C. Kesselman, Craig A. Lee, Bob Lindell, K. Nahrstedt, Alain Roy
The realization of end-to-end quality of service (QoS) guarantees in emerging network-based applications requires mechanisms that support first dynamic discovery and then advance or immediate reservation of resources that will often be heterogeneous in type and implementation and independently controlled and administered. We propose the Globus Architecture for Reservation and Allocation (GARA) to address these four issues. GARA treats both reservations and computational elements such as processes, network flows, and memory blocks as first-class entities, allowing them to be created, monitored, and managed independently and uniformly. It simplifies management of heterogeneous resource types by defining uniform mechanisms for computers, networks, disk, memory, and other resources. Layering on these standard mechanisms, GARA enables the construction of application-level co-reservation and co-allocation libraries that applications can use to dynamically assemble collections of resources, guided by both application QoS requirements and the local administration policy of individual resources. We describe a prototype GARA implementation that supports three different resource type-parallel computers, individual CPU under control of the dynamic soft real-time scheduler, and integrated services networks, and provide performance results that quantify the costs of our techniques.
{"title":"A distributed resource management architecture that supports advance reservations and co-allocation","authors":"Ian T Foster, C. Kesselman, Craig A. Lee, Bob Lindell, K. Nahrstedt, Alain Roy","doi":"10.1109/IWQOS.1999.766475","DOIUrl":"https://doi.org/10.1109/IWQOS.1999.766475","url":null,"abstract":"The realization of end-to-end quality of service (QoS) guarantees in emerging network-based applications requires mechanisms that support first dynamic discovery and then advance or immediate reservation of resources that will often be heterogeneous in type and implementation and independently controlled and administered. We propose the Globus Architecture for Reservation and Allocation (GARA) to address these four issues. GARA treats both reservations and computational elements such as processes, network flows, and memory blocks as first-class entities, allowing them to be created, monitored, and managed independently and uniformly. It simplifies management of heterogeneous resource types by defining uniform mechanisms for computers, networks, disk, memory, and other resources. Layering on these standard mechanisms, GARA enables the construction of application-level co-reservation and co-allocation libraries that applications can use to dynamically assemble collections of resources, guided by both application QoS requirements and the local administration policy of individual resources. We describe a prototype GARA implementation that supports three different resource type-parallel computers, individual CPU under control of the dynamic soft real-time scheduler, and integrated services networks, and provide performance results that quantify the costs of our techniques.","PeriodicalId":435117,"journal":{"name":"1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354)","volume":"30 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":"133475380","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.1999.766476
Baochun Li, Dongyan Xu, Klara Nahrstedt
In heterogeneous network environments with performance variations present, complex distributed applications, such as distributed visual tracking applications, are desired to adapt themselves and to adjust their resource demands dynamically, in response to fluctuations in either end system or network resources. By such adaptations, they are able to preserve the user-perceptible critical QoS parameters, and trade off non-critical ones. However, correct decisions on adaptation timing and scale, such as determining data rate transmitted from the server to clients in an application, depend on accurate observations of system states, such as quantities of data in transit or arrived at the destination. Significant end-to-end delay may obstruct the desired accurate observation. We present an optimal state prediction approach to estimate current states based on available state observations. Once accurate predictions are made, the applications can be adjusted dynamically based on a control-theoretical model. Finally, we show the effectiveness of our approach with experimental results in a client-server based visual tracking application, where application control and state estimations are accomplished by middleware components.
{"title":"Optimal state prediction for feedback-based QoS adaptations","authors":"Baochun Li, Dongyan Xu, Klara Nahrstedt","doi":"10.1109/IWQOS.1999.766476","DOIUrl":"https://doi.org/10.1109/IWQOS.1999.766476","url":null,"abstract":"In heterogeneous network environments with performance variations present, complex distributed applications, such as distributed visual tracking applications, are desired to adapt themselves and to adjust their resource demands dynamically, in response to fluctuations in either end system or network resources. By such adaptations, they are able to preserve the user-perceptible critical QoS parameters, and trade off non-critical ones. However, correct decisions on adaptation timing and scale, such as determining data rate transmitted from the server to clients in an application, depend on accurate observations of system states, such as quantities of data in transit or arrived at the destination. Significant end-to-end delay may obstruct the desired accurate observation. We present an optimal state prediction approach to estimate current states based on available state observations. Once accurate predictions are made, the applications can be adjusted dynamically based on a control-theoretical model. Finally, we show the effectiveness of our approach with experimental results in a client-server based visual tracking application, where application control and state estimations are accomplished by middleware components.","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":"129329975","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.1999.766473
Hendrik Knoche, Hermann G. De Meer
In the Coqos project task performance measures and a corresponding framework are suggested and pursued as a novel and more suitable means for determining utility curves. TPM are intended to avoid limits inherent in traditional measures like mean opinion scores. MOS rely merely on subjective ratings rather than on more objective performance in relation to a particular task or application of interest. Informational relevance and its impact on subjects can be measured more effectively by TPM. Inhibiting psychological and cognitive effects like consciousness or nonconsciousness of degradations or individual focusing and perspectives of subjects can be more appropriately evaluated and dealt with by means of TPM. The increasing importance of adaptation, in particular with the advance of MPEG4, as a means for QoS provisioning, both in wireless and wired environments, requires sensible techniques to effectively determine utility curves.
{"title":"Utility curves: mean opinion scores considered biased","authors":"Hendrik Knoche, Hermann G. De Meer","doi":"10.1109/IWQOS.1999.766473","DOIUrl":"https://doi.org/10.1109/IWQOS.1999.766473","url":null,"abstract":"In the Coqos project task performance measures and a corresponding framework are suggested and pursued as a novel and more suitable means for determining utility curves. TPM are intended to avoid limits inherent in traditional measures like mean opinion scores. MOS rely merely on subjective ratings rather than on more objective performance in relation to a particular task or application of interest. Informational relevance and its impact on subjects can be measured more effectively by TPM. Inhibiting psychological and cognitive effects like consciousness or nonconsciousness of degradations or individual focusing and perspectives of subjects can be more appropriately evaluated and dealt with by means of TPM. The increasing importance of adaptation, in particular with the advance of MPEG4, as a means for QoS provisioning, both in wireless and wired environments, requires sensible techniques to effectively determine utility curves.","PeriodicalId":435117,"journal":{"name":"1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354)","volume":"43 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":"124980310","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.1999.766474
O. Schelén, Andreas Nilsson, Joakim Norrgard, Stephen Pink
We have designed an agent-based architecture for quantitative service provisioning in differentiated services capable networks. For each link-state routing domain in the network there is a topology-aware QoS agent (also known as a bandwidth broker) responsible for admission control. The architecture provides resource reservations for aggregated virtual leased lines between network domains. In this paper, we present performance measurements for resource provisioning in a prototype QoS agent. This includes an evaluation of two data structures for advance reservations and accompanying algorithms. We also compare the cost for on-demand route computations with pre-computation of routes. The objective in this paper is to evaluate the performance of end-to-end admission control within a single link-state routing domain. In a domain with 15 routers, 28 transition networks and 64 stub networks, our prototype performs approximately 25000 end-to-end admission decisions per second. The results show that an ordinary PC can be used for running a QoS agent that performs path-sensitive admission control and maintains per link resource reservations in a link-state routing domain.
{"title":"Performance of QoS agents for provisioning network resources","authors":"O. Schelén, Andreas Nilsson, Joakim Norrgard, Stephen Pink","doi":"10.1109/IWQOS.1999.766474","DOIUrl":"https://doi.org/10.1109/IWQOS.1999.766474","url":null,"abstract":"We have designed an agent-based architecture for quantitative service provisioning in differentiated services capable networks. For each link-state routing domain in the network there is a topology-aware QoS agent (also known as a bandwidth broker) responsible for admission control. The architecture provides resource reservations for aggregated virtual leased lines between network domains. In this paper, we present performance measurements for resource provisioning in a prototype QoS agent. This includes an evaluation of two data structures for advance reservations and accompanying algorithms. We also compare the cost for on-demand route computations with pre-computation of routes. The objective in this paper is to evaluate the performance of end-to-end admission control within a single link-state routing domain. In a domain with 15 routers, 28 transition networks and 64 stub networks, our prototype performs approximately 25000 end-to-end admission decisions per second. The results show that an ordinary PC can be used for running a QoS agent that performs path-sensitive admission control and maintains per link resource reservations in a link-state routing domain.","PeriodicalId":435117,"journal":{"name":"1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354)","volume":"88 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":"121441279","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.1999.766479
Tsung-Li Wu, S.F. Wu, Z. Fu, He Huang, F. Gong
In this paper, we study one type of DoQoNS (denial of quality of network service) attacks: attacks directly on the resource reservation and setup protocol. Particularly, we have studied and analyzed the RSVP protocol. Two contributions are: first, we performed a security analysis on RSVP which demonstrates the key vulnerabilities of its distributed resource reservation and setup process. Second, we proposed a new secure RSVP protocol, SDS/CD (selective digital signature with conflict detection), which combines the strength of attack prevention and intrusion detection. SDS/CD resolves a fundamental issue in network security: how to protect the integrity, in an end-to-end fashion, of a target object that is mutable along the route path. As a result, we will show that SDS/CD can deal with many insider attacks that can not be handled by the current IETF/RSVP security solution: hop-by-hop authentication.
{"title":"Securing QoS threats to RSVP messages and their countermeasures","authors":"Tsung-Li Wu, S.F. Wu, Z. Fu, He Huang, F. Gong","doi":"10.1109/IWQOS.1999.766479","DOIUrl":"https://doi.org/10.1109/IWQOS.1999.766479","url":null,"abstract":"In this paper, we study one type of DoQoNS (denial of quality of network service) attacks: attacks directly on the resource reservation and setup protocol. Particularly, we have studied and analyzed the RSVP protocol. Two contributions are: first, we performed a security analysis on RSVP which demonstrates the key vulnerabilities of its distributed resource reservation and setup process. Second, we proposed a new secure RSVP protocol, SDS/CD (selective digital signature with conflict detection), which combines the strength of attack prevention and intrusion detection. SDS/CD resolves a fundamental issue in network security: how to protect the integrity, in an end-to-end fashion, of a target object that is mutable along the route path. As a result, we will show that SDS/CD can deal with many insider attacks that can not be handled by the current IETF/RSVP security solution: hop-by-hop authentication.","PeriodicalId":435117,"journal":{"name":"1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354)","volume":"2 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":"128486375","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.1999.766495
M. Chatzaki, S. Sartzetakis, N. Papadakis, C. Courcoubetis
This work deals with the problems of routing flows with QoS requirements across MPLS-capable networks. We identify the functional capabilities that should be supported in order to optimize network resource utilization, and satisfy business or service or network level QoS requirements. We focus on the design of an appropriate architecture to combine MPLS with QoS-policy-based routing-capable components. Existing label switching technologies assume that routing is accomplished by just using traditional network layer routing protocols. Consequently network administrators have no control on the way traffic navigates the network. This can easily lead to unpleasant situations where some parts of the network are congested and some others are underutilized. The future Internet imposes the demand for advanced network control and management mechanisms. Combining label switching technologies with routing mechanisms that take into account network performance metrics and at the same time give network administrators the ability to influence routing decisions according to their preferences appears to be a very clear solution to cost-effectively and efficiently engineer the future Internet. In order to accomplish that, we endorse some of the already proposed extensions to MPLS, and introduce a routing selection mechanism based on implied costs. Such implied costs reflect the network congestion as well as the interdependencies among flows in the network, and can provide the management signals for expanding or reducing the amount of resources allocated to different service classes and routes as well as performing the route selection.
{"title":"Resource allocation in multiservice MPLS","authors":"M. Chatzaki, S. Sartzetakis, N. Papadakis, C. Courcoubetis","doi":"10.1109/IWQOS.1999.766495","DOIUrl":"https://doi.org/10.1109/IWQOS.1999.766495","url":null,"abstract":"This work deals with the problems of routing flows with QoS requirements across MPLS-capable networks. We identify the functional capabilities that should be supported in order to optimize network resource utilization, and satisfy business or service or network level QoS requirements. We focus on the design of an appropriate architecture to combine MPLS with QoS-policy-based routing-capable components. Existing label switching technologies assume that routing is accomplished by just using traditional network layer routing protocols. Consequently network administrators have no control on the way traffic navigates the network. This can easily lead to unpleasant situations where some parts of the network are congested and some others are underutilized. The future Internet imposes the demand for advanced network control and management mechanisms. Combining label switching technologies with routing mechanisms that take into account network performance metrics and at the same time give network administrators the ability to influence routing decisions according to their preferences appears to be a very clear solution to cost-effectively and efficiently engineer the future Internet. In order to accomplish that, we endorse some of the already proposed extensions to MPLS, and introduce a routing selection mechanism based on implied costs. Such implied costs reflect the network congestion as well as the interdependencies among flows in the network, and can provide the management signals for expanding or reducing the amount of resources allocated to different service classes and routes as well as performing the route selection.","PeriodicalId":435117,"journal":{"name":"1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354)","volume":"31 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":"115999520","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.1999.766484
N. Borg, E. Svanberg, O. Schelén
Mechanisms for service differentiation in datagram networks, such as the Internet, rely on packet classification in routers to provide appropriate service. Classification involves matching multiple packet header fields against a possibly large set of filters identifying the different service classes. In this paper, we describe a packet classifier based on tries and binomial trees and we investigate its scaling properties in three QoS scenarios that are likely to occur in the Internet. One scenario is based on integrated services and RSVP and the other two are based on differentiated services. By performing a series of tests, we characterize the processing and memory requirements for a software implementation of our classifier. Evaluation is done using real data sets taken from two existing high-speed networks. Results from the IntServ/RSVP tests on a Pentium 200 MHz show that it takes about 10.5 /spl mu/s per packet and requires 2000 KBytes of memory to classify among 11000 entries. Classification for a virtual leased line service based on DiffServ with the same number of entries takes about 9 /spl mu/s per packet and uses less than 250 KBytes of memory. With an average packet size of 2000 bits, our classifier can manage data rates of about 200 Mbit/s on a 200 MHz Pentium. We conclude that multi-field classification is feasible in software and that high-performance classifiers can run on low-cost hardware.
{"title":"Efficient multi-field packet classification for QoS purposes","authors":"N. Borg, E. Svanberg, O. Schelén","doi":"10.1109/IWQOS.1999.766484","DOIUrl":"https://doi.org/10.1109/IWQOS.1999.766484","url":null,"abstract":"Mechanisms for service differentiation in datagram networks, such as the Internet, rely on packet classification in routers to provide appropriate service. Classification involves matching multiple packet header fields against a possibly large set of filters identifying the different service classes. In this paper, we describe a packet classifier based on tries and binomial trees and we investigate its scaling properties in three QoS scenarios that are likely to occur in the Internet. One scenario is based on integrated services and RSVP and the other two are based on differentiated services. By performing a series of tests, we characterize the processing and memory requirements for a software implementation of our classifier. Evaluation is done using real data sets taken from two existing high-speed networks. Results from the IntServ/RSVP tests on a Pentium 200 MHz show that it takes about 10.5 /spl mu/s per packet and requires 2000 KBytes of memory to classify among 11000 entries. Classification for a virtual leased line service based on DiffServ with the same number of entries takes about 9 /spl mu/s per packet and uses less than 250 KBytes of memory. With an average packet size of 2000 bits, our classifier can manage data rates of about 200 Mbit/s on a 200 MHz Pentium. We conclude that multi-field classification is feasible in software and that high-performance classifiers can run on low-cost hardware.","PeriodicalId":435117,"journal":{"name":"1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354)","volume":"101 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":"127935686","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.1999.766482
Deying Tong, Deying Tong, Xuanming Tong
Considerable work has been done in devising mechanisms for providing service guarantees within a network. These schemes can be broadly classified into two categories, schemes that require maintaining state for each flow and schemes that do not require maintaining state for each flow within the network. Both the approaches have their advantages and proponents. This paper looks at a scheme that falls in between these two extremes, where a network switch may be able to maintain state for a fixed number of flows (possibly less than the number of flows it serves). This paper looks at the services that can be provided by a limited amount of state. As a first step, it presents SACRED, a method that employs sampling and caching in addition to RED at a router to enhance the QoS. The proposed mechanism uses caching to deal with the limited amount of state, and uses sampling to select flows. It is shown that this approach can be effective in containing non-responsive flows. It is also shown that SACRED is scalable in the sense of providing increased function with increased amount of state.
{"title":"QoS enhancement with partial state","authors":"Deying Tong, Deying Tong, Xuanming Tong","doi":"10.1109/IWQOS.1999.766482","DOIUrl":"https://doi.org/10.1109/IWQOS.1999.766482","url":null,"abstract":"Considerable work has been done in devising mechanisms for providing service guarantees within a network. These schemes can be broadly classified into two categories, schemes that require maintaining state for each flow and schemes that do not require maintaining state for each flow within the network. Both the approaches have their advantages and proponents. This paper looks at a scheme that falls in between these two extremes, where a network switch may be able to maintain state for a fixed number of flows (possibly less than the number of flows it serves). This paper looks at the services that can be provided by a limited amount of state. As a first step, it presents SACRED, a method that employs sampling and caching in addition to RED at a router to enhance the QoS. The proposed mechanism uses caching to deal with the limited amount of state, and uses sampling to select flows. It is shown that this approach can be effective in containing non-responsive flows. It is also shown that SACRED is scalable in the sense of providing increased function with increased amount of state.","PeriodicalId":435117,"journal":{"name":"1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354)","volume":"47 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":"128167003","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：