Smart box architecture
Abstract
Fundamentally the IP-based networking is designed for delivering data traffic with best-effort service, thus it is not capable of providing end-to-end QoS. Several architectures have been proposed for providing QoS in the Internet: The integrated services (Intserv) model is based on reservations and can provide QoS, however; it is not scalable. The differentiated services (Diffserv) approach is scalable but falls short of ensuring deterministic guarantees --in particular for the services that belong to the same class. Finally, the multi protocol label switching (MPLS) architecture provides mechanisms for QoS-based routing but does not have the necessary resource management and scheduling support to ensure it.
This work proposes a hybrid solution which combines the best of these technologies. First, at the network boundary Diffserv like Service Level Agreements (SLA) are provided to users by intelligent edge routers called the SBoX servers. An SBoX server uses Class Based Queuing (CBQ) with a hierarchy of flow aggregation. At the top a commodity-flow is defined for the aggregate flow between a pair of egress points. The packets of the same commodity-flow are marked by an MPLS label, which is globally unique within an Autonomous System (AS). Each commodity flow is partitioned to a set of macro-flows which are offered to users as SLAs. An SBoX server manages macro-flows and commodity flows only, and leaves the management of each macro-flow (at the micro-flow level based on some policies) to the enterprise/users which signed the SLA. Second, the commodity-flows are managed and supported inside the network by an add-on Label Switching Router (LSR) called the SBoX router which performs MPLS of commodity-flows with CBQ. The main reason for an add on solution is the lack of end-to-end deployment of LSRs, and the vertically integrated architecture of the legacy routers. This paper explains the SBoX architecture and reports experimental results obtained on a prototype network.
References
[1]
{ACL94} G. R. Ash, K. K. Chen, and J-F. Labourdette. Analysis and design of fully shared networks. Proc. of 14'th International Teletraffc Congress, pages 1311-1320, 1994.]]
[2]
{Ash95} G. R. Ash. Dynamic network evolution, with examples from at&t's evolving dynamic network. IEEE Communications Magazine, 33(7):26-39, 1995.]]
[3]
{BW99} A. Basu and Z. Wang. Fair bandwidth allocation for differentiated services. in Protocols for High Speed Networks VI, J. Touch and J. Sterbenz ed. Kluwer Academic Publishers , 1999.]]
[4]
{CFZ94} I. Chlamtac, A. Farago, and T. Zhang. Optimizing the system of virtual paths. IEEE Trans. on Networking, 2(6):581-587, Dec. 1994.]]
[5]
{Cla97} D. Clark. Internet cost allocation and pricing. Internet Economics, L. W. McKnight and J. P. Bailey (eds), pages 215-252, 1997.]]
[6]
{CW97} D. Clark and J. Wroclawski. An approach to service allocation in the internet. Internet Draft, draft-clark-diff-svc-alloc-00.txt, July 1997.]]
[7]
{Dov91a} R. D. Doverspike. Algorithms for multiplex bundling in a telecommunications network. Operations Research, 39:925-944, 1991.]]
[8]
{Dov91b} R. D. Doverspike. A multi-layered model for survivavility in intra-lata transport networks. Proc. IEEE GLOBCOM'91, pages 2025-2031, 1991.]]
[9]
{ea98} S. Blake et al. A framework for differentiated services. draft-ietf-diffserv-framework-0.1.txt, October 1998.]]
[10]
{ea99a} B. Jamoussi et al. Constraint-based lsp using ldp. Draft-ietf-mpls-cr-ldp-03.txt, September 1999.]]
[11]
{ea99b} I. Stoica et. al. Per hop behaviours based on dynamic packet states. internet draft. http://www.cs.cmu.edu/isto-ica/DPS/draft.txt, February 1999.]]
[12]
{For96} ATM Forum. P-nni specification, version 1.0. March 1996.]]
[13]
{IN98} J. Ibanez and K. Nichols. internet draft : draft-ibanez-diffserv-assured-eval-00.txt, August 1998.]]
[14]
{Kum74} K. Kummerle. Multiplexer performance for integrated line and packet switched traffic. Int. Conf. Comput. Commun. Record, pages 507-515, August 1974.]]
[15]
{Lee95} W. C. Lee. Topology aggregation for hierarchical routing in atm networks. Comput. Commun. Rev. (USA), 25(2):82-92, 1995.]]
[16]
{ML97} H. Michiel and K. Laevens. Teletraffic engineering in a broad-band era. Proc. of IEEE, 85(12):2007-2033, December 1997.]]
[17]
{MMR96} D. Mitra, J. A. Morrison, and K. G. Ramakrishnan. Atm network design and optimization: A multirate loss network framework. Proc. IEEE INFOCOM'96, pages 994-1003, 1996.]]
[18]
{NBS95} A. Nguyen, N. Bambos, and M. H. Sherif. Adaptive (t1, t2)-multiplexing transmission schemes for voice/data integrated networks. IEEE Syp. Comp. and Communications, pages 430-435, 1995.]]
[19]
{NJZ97} K. Nichols, V. Jacobson, and L. Zhang. A two bit differentiated services architecture for the internet. Internet Draft, draft-nicolas-diff-svc-arch-00.txt, November 1997.]]
[20]
{OY94} Y. Ofek and M. Yung. The integrated MetaNet architecture: A switch-based multimedia LAN for parallel computing and real-time traffic. IEEE INFOCOM'94, 1994.]]
[21]
{RVC98} E. C. Rosen, A. Viswanathan, and R. Callon. Multi protocol label switching. draft-ietf-mpls-arch-02.txt, July 1998.]]
[22]
{SPG97} S. Shenker, C. Partridge, and R. Guerin. Specification of guaranteed quality of service. rfc2211, September 1997.]]
[23]
{SSZ98} I. Stoica, S. Shenker, and H. Zhang. Core-stateless fair queueing: A scalable architecture to approximate fair bandwidth allocations in high-speed networks. Proc. of ACM SIGCOMM'98, August 1998.]]
[24]
{SW97} S. Shenker and J. Wroclawski. General characterization parameters for integrated services network elements. rfc2215, September 1997.]]
[25]
{SZ98} I. Stoica and H. Zhang. Lira: An approach for service differentiation in the internet. Proc. of NOSSDAV'98, Cambridge, England, 1998.]]
[26]
{Wro97} J. Wroclawski. Specification of the controlled-load network element service. rfc2211, September 1997.]]
[27]
{Zaf74} P. Zafiropolo. Flexible multiplexing for networks supporting line switched and packet switched data traffic. Int. Conf. Comput. Commun. Record, pages 517-523, August 1974.]]
Recommendations
QoS guarantee for multimedia traffic in smart homes
With the advent of home networking and widespread deployment of broadband connectivity to homes, a wealth of new services with real-time Quality of Service (QoS) requirements have emerged, e.g., Video on Demand (VoD), IP Telephony, which have to co-...
Novel SDN architecture for smart MPLS Traffic Engineering-DiffServ Aware management
AbstractLarge scale networks are still a major challenge for management, guarantee a good level of Quality of Service (QoS) and especially optimization (rational use of network resources). Multi-Protocol Label Switching (MPLS), mainly used in ...
Highlights- A novel SDN architecture for smart MPLS DS-TE Management is proposed.
- The ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
March 2000
39 pages
Sponsors
- USENIX Assoc: USENIX Assoc
Publisher
USENIX Association
United States
Publication History
Published: 20 March 2000
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 20Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 04 Jan 2025