An Extended Model for TCP Loss Recovery Latency with Random Packet Losses

Beomjoon KIM; Yong-Hoon CHOI; Jaiyong LEE

doi:10.1093/ietcom/e89-b.1.28

An Extended Model for TCP Loss Recovery Latency with Random Packet Losses

Beomjoon KIM, Yong-Hoon CHOI, Jaiyong LEE

Full Text Views

0

Share
Cite this

Summary :

It has been a very important issue to evaluate the performance of transmission control protocol (TCP), and the importance is still growing up because TCP will be deployed more widely in future wireless as well as wireline networks. It is also the reason why there have been a lot of efforts to analyze TCP performance more accurately. Most of these works are focusing on overall TCP end-to-end throughput that is defined as the number of bytes transmitted for a given time period. Even though each TCP's fast recovery strategy should be considered in computation of the exact time period, it has not been considered sufficiently in the existing models. That is, for more detailed performance analysis of a TCP implementation, the fast recovery latency during which lost packets are retransmitted should be considered with its relevant strategy. In this paper, we extend the existing models in order to capture TCP's loss recovery behaviors in detail. On the basis of the model, the loss recovery latency of three TCP implementations can be derived with considering the number of retransmitted packets. In particular, the proposed model differentiates the loss recovery performance of TCP using selective acknowledgement (SACK) option from TCP NewReno. We also verify that the proposed model reflects the precise latency of each TCP's loss recovery by simulations.

Publication: IEICE TRANSACTIONS on Communications Vol.E89-B No.1 pp.28-37

Publication Date: 2006/01/01

Publicized

Online ISSN: 1745-1345

DOI: 10.1093/ietcom/e89-b.1.28

Type of Manuscript: PAPER

Category: Network

Cite this

Copy

Beomjoon KIM, Yong-Hoon CHOI, Jaiyong LEE, "An Extended Model for TCP Loss Recovery Latency with Random Packet Losses" in IEICE TRANSACTIONS on Communications, vol. E89-B, no. 1, pp. 28-37, January 2006, doi: 10.1093/ietcom/e89-b.1.28.
Abstract: It has been a very important issue to evaluate the performance of transmission control protocol (TCP), and the importance is still growing up because TCP will be deployed more widely in future wireless as well as wireline networks. It is also the reason why there have been a lot of efforts to analyze TCP performance more accurately. Most of these works are focusing on overall TCP end-to-end throughput that is defined as the number of bytes transmitted for a given time period. Even though each TCP's fast recovery strategy should be considered in computation of the exact time period, it has not been considered sufficiently in the existing models. That is, for more detailed performance analysis of a TCP implementation, the fast recovery latency during which lost packets are retransmitted should be considered with its relevant strategy. In this paper, we extend the existing models in order to capture TCP's loss recovery behaviors in detail. On the basis of the model, the loss recovery latency of three TCP implementations can be derived with considering the number of retransmitted packets. In particular, the proposed model differentiates the loss recovery performance of TCP using selective acknowledgement (SACK) option from TCP NewReno. We also verify that the proposed model reflects the precise latency of each TCP's loss recovery by simulations.
URL: https://globals.ieice.org/en_transactions/communications/10.1093/ietcom/e89-b.1.28/_p

Copy

@ARTICLE{e89-b_1_28,
author={Beomjoon KIM, Yong-Hoon CHOI, Jaiyong LEE, },
journal={IEICE TRANSACTIONS on Communications},
title={An Extended Model for TCP Loss Recovery Latency with Random Packet Losses},
year={2006},
volume={E89-B},
number={1},
pages={28-37},
abstract={It has been a very important issue to evaluate the performance of transmission control protocol (TCP), and the importance is still growing up because TCP will be deployed more widely in future wireless as well as wireline networks. It is also the reason why there have been a lot of efforts to analyze TCP performance more accurately. Most of these works are focusing on overall TCP end-to-end throughput that is defined as the number of bytes transmitted for a given time period. Even though each TCP's fast recovery strategy should be considered in computation of the exact time period, it has not been considered sufficiently in the existing models. That is, for more detailed performance analysis of a TCP implementation, the fast recovery latency during which lost packets are retransmitted should be considered with its relevant strategy. In this paper, we extend the existing models in order to capture TCP's loss recovery behaviors in detail. On the basis of the model, the loss recovery latency of three TCP implementations can be derived with considering the number of retransmitted packets. In particular, the proposed model differentiates the loss recovery performance of TCP using selective acknowledgement (SACK) option from TCP NewReno. We also verify that the proposed model reflects the precise latency of each TCP's loss recovery by simulations.},
keywords={},
doi={10.1093/ietcom/e89-b.1.28},
ISSN={1745-1345},
month={January},}

Copy

TY - JOUR
TI - An Extended Model for TCP Loss Recovery Latency with Random Packet Losses
T2 - IEICE TRANSACTIONS on Communications
SP - 28
EP - 37
AU - Beomjoon KIM
AU - Yong-Hoon CHOI
AU - Jaiyong LEE
PY - 2006
DO - 10.1093/ietcom/e89-b.1.28
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E89-B
IS - 1
JA - IEICE TRANSACTIONS on Communications
Y1 - January 2006
AB - It has been a very important issue to evaluate the performance of transmission control protocol (TCP), and the importance is still growing up because TCP will be deployed more widely in future wireless as well as wireline networks. It is also the reason why there have been a lot of efforts to analyze TCP performance more accurately. Most of these works are focusing on overall TCP end-to-end throughput that is defined as the number of bytes transmitted for a given time period. Even though each TCP's fast recovery strategy should be considered in computation of the exact time period, it has not been considered sufficiently in the existing models. That is, for more detailed performance analysis of a TCP implementation, the fast recovery latency during which lost packets are retransmitted should be considered with its relevant strategy. In this paper, we extend the existing models in order to capture TCP's loss recovery behaviors in detail. On the basis of the model, the loss recovery latency of three TCP implementations can be derived with considering the number of retransmitted packets. In particular, the proposed model differentiates the loss recovery performance of TCP using selective acknowledgement (SACK) option from TCP NewReno. We also verify that the proposed model reflects the precise latency of each TCP's loss recovery by simulations.
ER -