Multicast Congestion Control with Quantized Congestion Notification in Data Center Networks

Yuki TANISAWA; Miki YAMAMOTO

doi:10.1587/transcom.E97.B.1121

Multicast Congestion Control with Quantized Congestion Notification in Data Center Networks

Yuki TANISAWA, Miki YAMAMOTO

Full Text Views

0

Share
Cite this

Summary :

In data center networks, group communication is currently playing an important role and multicast communications is an effective way to support group communication for large numbers of virtual machines. Layer-2 congestion control named QCN (Quantized Congestion Notification) has been proposed to realize the high reliability required by LAN/SAN integration in data center networking. Our preliminary evaluation in this paper shows that a multicast flow suffers lower throughput than unicast flows when conventional QCN is applied in a naive manner. This is because a sending device receives congestion feedback from multiple locations on a multicast tree and decreases transmission rate accordingly. To counter this throughput degradation of multicast flows, we propose a new Layer 2 congestion control algorithm in multicast environment, Quantized Congestion Notification with Bottleneck Selection (QCN/BS). In QCN/BS, the switch in the worst congestion level is selected and the transmission rate of the sending device is calculated exclusively according to feedback from the selected switch. Simulation results show that when conventional QCN is used, a multicast flow experiences lower and more severely unfair throughput than a unicast flow. The proposed QCN/BS resolves this problem.

Publication: IEICE TRANSACTIONS on Communications Vol.E97-B No.6 pp.1121-1129

Publication Date: 2014/06/01

Publicized

Online ISSN: 1745-1345

DOI: 10.1587/transcom.E97.B.1121

Type of Manuscript: PAPER

Category: Network Management/Operation

Authors

Yuki TANISAWA
Kansai University
Miki YAMAMOTO
Kansai University

Keyword

data center, congestion control, QCN

Cite this

Copy

Yuki TANISAWA, Miki YAMAMOTO, "Multicast Congestion Control with Quantized Congestion Notification in Data Center Networks" in IEICE TRANSACTIONS on Communications, vol. E97-B, no. 6, pp. 1121-1129, June 2014, doi: 10.1587/transcom.E97.B.1121.
Abstract: In data center networks, group communication is currently playing an important role and multicast communications is an effective way to support group communication for large numbers of virtual machines. Layer-2 congestion control named QCN (Quantized Congestion Notification) has been proposed to realize the high reliability required by LAN/SAN integration in data center networking. Our preliminary evaluation in this paper shows that a multicast flow suffers lower throughput than unicast flows when conventional QCN is applied in a naive manner. This is because a sending device receives congestion feedback from multiple locations on a multicast tree and decreases transmission rate accordingly. To counter this throughput degradation of multicast flows, we propose a new Layer 2 congestion control algorithm in multicast environment, Quantized Congestion Notification with Bottleneck Selection (QCN/BS). In QCN/BS, the switch in the worst congestion level is selected and the transmission rate of the sending device is calculated exclusively according to feedback from the selected switch. Simulation results show that when conventional QCN is used, a multicast flow experiences lower and more severely unfair throughput than a unicast flow. The proposed QCN/BS resolves this problem.
URL: https://globals.ieice.org/en_transactions/communications/10.1587/transcom.E97.B.1121/_p

Copy

@ARTICLE{e97-b_6_1121,
author={Yuki TANISAWA, Miki YAMAMOTO, },
journal={IEICE TRANSACTIONS on Communications},
title={Multicast Congestion Control with Quantized Congestion Notification in Data Center Networks},
year={2014},
volume={E97-B},
number={6},
pages={1121-1129},
abstract={In data center networks, group communication is currently playing an important role and multicast communications is an effective way to support group communication for large numbers of virtual machines. Layer-2 congestion control named QCN (Quantized Congestion Notification) has been proposed to realize the high reliability required by LAN/SAN integration in data center networking. Our preliminary evaluation in this paper shows that a multicast flow suffers lower throughput than unicast flows when conventional QCN is applied in a naive manner. This is because a sending device receives congestion feedback from multiple locations on a multicast tree and decreases transmission rate accordingly. To counter this throughput degradation of multicast flows, we propose a new Layer 2 congestion control algorithm in multicast environment, Quantized Congestion Notification with Bottleneck Selection (QCN/BS). In QCN/BS, the switch in the worst congestion level is selected and the transmission rate of the sending device is calculated exclusively according to feedback from the selected switch. Simulation results show that when conventional QCN is used, a multicast flow experiences lower and more severely unfair throughput than a unicast flow. The proposed QCN/BS resolves this problem.},
keywords={},
doi={10.1587/transcom.E97.B.1121},
ISSN={1745-1345},
month={June},}

Copy

TY - JOUR
TI - Multicast Congestion Control with Quantized Congestion Notification in Data Center Networks
T2 - IEICE TRANSACTIONS on Communications
SP - 1121
EP - 1129
AU - Yuki TANISAWA
AU - Miki YAMAMOTO
PY - 2014
DO - 10.1587/transcom.E97.B.1121
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E97-B
IS - 6
JA - IEICE TRANSACTIONS on Communications
Y1 - June 2014
AB - In data center networks, group communication is currently playing an important role and multicast communications is an effective way to support group communication for large numbers of virtual machines. Layer-2 congestion control named QCN (Quantized Congestion Notification) has been proposed to realize the high reliability required by LAN/SAN integration in data center networking. Our preliminary evaluation in this paper shows that a multicast flow suffers lower throughput than unicast flows when conventional QCN is applied in a naive manner. This is because a sending device receives congestion feedback from multiple locations on a multicast tree and decreases transmission rate accordingly. To counter this throughput degradation of multicast flows, we propose a new Layer 2 congestion control algorithm in multicast environment, Quantized Congestion Notification with Bottleneck Selection (QCN/BS). In QCN/BS, the switch in the worst congestion level is selected and the transmission rate of the sending device is calculated exclusively according to feedback from the selected switch. Simulation results show that when conventional QCN is used, a multicast flow experiences lower and more severely unfair throughput than a unicast flow. The proposed QCN/BS resolves this problem.
ER -