Core-stateless labeling fairness

An integrated architecture to approximate fair bandwidth allocations in high speed networks

Jung-Shian Li, Cheng Pong Lo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Core-stateless mechanisms achieve better scalability by reducing the complexity of fair queuing, which usually needs to maintain states, manage buffers, and perform flow scheduling on a per flow basis. However, they require per-packet relabeling in the core routers. We propose a core-stateless fair bandwidth allocation scheme without maintaining per flow state in core routers. Furthermore, it does not need relabeling, which is commonly used in existing core-stateless schemes. Packets are labeled only once in the entrance of the network according to the characteristics of the flow to which the packets belong. No matter TCP or UDP flows can get their fair share rate by the proposed scheme. Moreover, the scheme employs an estimation of number of active flows in the core routers. The estimation can be used to provide fair share rate without maintaining per flow states. The packets belonging to the flows whose rates exceed the estimated fair share rate are dropped. The novel scheme is called core-stateless labeling fairness (CSLF). We present and discuss simulations on the performance under different traffic scenarios.

Original languageEnglish
Title of host publicationProceedings - LCN 2002
Subtitle of host publication27th Annual IEEE Conference on Local Computer Networks
PublisherIEEE Computer Society
Pages495-501
Number of pages7
ISBN (Electronic)0769515916
DOIs
Publication statusPublished - 2002 Jan 1
Event27th Annual IEEE Conference on Local Computer Networks, LCN 2002 - Tampa, United States
Duration: 2002 Nov 62002 Nov 8

Publication series

NameProceedings - Conference on Local Computer Networks, LCN
Volume2002-January

Other

Other27th Annual IEEE Conference on Local Computer Networks, LCN 2002
CountryUnited States
CityTampa
Period02-11-0602-11-08

Fingerprint

HIgh speed networks
Frequency allocation
Routers
Labeling
Scalability
Scheduling
Flow rate

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Hardware and Architecture

Cite this

Li, J-S., & Lo, C. P. (2002). Core-stateless labeling fairness: An integrated architecture to approximate fair bandwidth allocations in high speed networks. In Proceedings - LCN 2002: 27th Annual IEEE Conference on Local Computer Networks (pp. 495-501). [1181822] (Proceedings - Conference on Local Computer Networks, LCN; Vol. 2002-January). IEEE Computer Society. https://doi.org/10.1109/LCN.2002.1181822
Li, Jung-Shian ; Lo, Cheng Pong. / Core-stateless labeling fairness : An integrated architecture to approximate fair bandwidth allocations in high speed networks. Proceedings - LCN 2002: 27th Annual IEEE Conference on Local Computer Networks. IEEE Computer Society, 2002. pp. 495-501 (Proceedings - Conference on Local Computer Networks, LCN).
@inproceedings{633887f9d65b4b62827d99c0d2de50ff,
title = "Core-stateless labeling fairness: An integrated architecture to approximate fair bandwidth allocations in high speed networks",
abstract = "Core-stateless mechanisms achieve better scalability by reducing the complexity of fair queuing, which usually needs to maintain states, manage buffers, and perform flow scheduling on a per flow basis. However, they require per-packet relabeling in the core routers. We propose a core-stateless fair bandwidth allocation scheme without maintaining per flow state in core routers. Furthermore, it does not need relabeling, which is commonly used in existing core-stateless schemes. Packets are labeled only once in the entrance of the network according to the characteristics of the flow to which the packets belong. No matter TCP or UDP flows can get their fair share rate by the proposed scheme. Moreover, the scheme employs an estimation of number of active flows in the core routers. The estimation can be used to provide fair share rate without maintaining per flow states. The packets belonging to the flows whose rates exceed the estimated fair share rate are dropped. The novel scheme is called core-stateless labeling fairness (CSLF). We present and discuss simulations on the performance under different traffic scenarios.",
author = "Jung-Shian Li and Lo, {Cheng Pong}",
year = "2002",
month = "1",
day = "1",
doi = "10.1109/LCN.2002.1181822",
language = "English",
series = "Proceedings - Conference on Local Computer Networks, LCN",
publisher = "IEEE Computer Society",
pages = "495--501",
booktitle = "Proceedings - LCN 2002",
address = "United States",

}

Li, J-S & Lo, CP 2002, Core-stateless labeling fairness: An integrated architecture to approximate fair bandwidth allocations in high speed networks. in Proceedings - LCN 2002: 27th Annual IEEE Conference on Local Computer Networks., 1181822, Proceedings - Conference on Local Computer Networks, LCN, vol. 2002-January, IEEE Computer Society, pp. 495-501, 27th Annual IEEE Conference on Local Computer Networks, LCN 2002, Tampa, United States, 02-11-06. https://doi.org/10.1109/LCN.2002.1181822

Core-stateless labeling fairness : An integrated architecture to approximate fair bandwidth allocations in high speed networks. / Li, Jung-Shian; Lo, Cheng Pong.

Proceedings - LCN 2002: 27th Annual IEEE Conference on Local Computer Networks. IEEE Computer Society, 2002. p. 495-501 1181822 (Proceedings - Conference on Local Computer Networks, LCN; Vol. 2002-January).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Core-stateless labeling fairness

T2 - An integrated architecture to approximate fair bandwidth allocations in high speed networks

AU - Li, Jung-Shian

AU - Lo, Cheng Pong

PY - 2002/1/1

Y1 - 2002/1/1

N2 - Core-stateless mechanisms achieve better scalability by reducing the complexity of fair queuing, which usually needs to maintain states, manage buffers, and perform flow scheduling on a per flow basis. However, they require per-packet relabeling in the core routers. We propose a core-stateless fair bandwidth allocation scheme without maintaining per flow state in core routers. Furthermore, it does not need relabeling, which is commonly used in existing core-stateless schemes. Packets are labeled only once in the entrance of the network according to the characteristics of the flow to which the packets belong. No matter TCP or UDP flows can get their fair share rate by the proposed scheme. Moreover, the scheme employs an estimation of number of active flows in the core routers. The estimation can be used to provide fair share rate without maintaining per flow states. The packets belonging to the flows whose rates exceed the estimated fair share rate are dropped. The novel scheme is called core-stateless labeling fairness (CSLF). We present and discuss simulations on the performance under different traffic scenarios.

AB - Core-stateless mechanisms achieve better scalability by reducing the complexity of fair queuing, which usually needs to maintain states, manage buffers, and perform flow scheduling on a per flow basis. However, they require per-packet relabeling in the core routers. We propose a core-stateless fair bandwidth allocation scheme without maintaining per flow state in core routers. Furthermore, it does not need relabeling, which is commonly used in existing core-stateless schemes. Packets are labeled only once in the entrance of the network according to the characteristics of the flow to which the packets belong. No matter TCP or UDP flows can get their fair share rate by the proposed scheme. Moreover, the scheme employs an estimation of number of active flows in the core routers. The estimation can be used to provide fair share rate without maintaining per flow states. The packets belonging to the flows whose rates exceed the estimated fair share rate are dropped. The novel scheme is called core-stateless labeling fairness (CSLF). We present and discuss simulations on the performance under different traffic scenarios.

UR - http://www.scopus.com/inward/record.url?scp=84948956654&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84948956654&partnerID=8YFLogxK

U2 - 10.1109/LCN.2002.1181822

DO - 10.1109/LCN.2002.1181822

M3 - Conference contribution

T3 - Proceedings - Conference on Local Computer Networks, LCN

SP - 495

EP - 501

BT - Proceedings - LCN 2002

PB - IEEE Computer Society

ER -

Li J-S, Lo CP. Core-stateless labeling fairness: An integrated architecture to approximate fair bandwidth allocations in high speed networks. In Proceedings - LCN 2002: 27th Annual IEEE Conference on Local Computer Networks. IEEE Computer Society. 2002. p. 495-501. 1181822. (Proceedings - Conference on Local Computer Networks, LCN). https://doi.org/10.1109/LCN.2002.1181822