Adaptive marking threshold method for delay-sensitive TCP in data center network

Adaptive marking threshold method for delay-sensitive TCP in data center network
复制标题

数据中心网络中时延敏感TCP的自适应标记阈值方法

DOI:
10.1016/j.jnca.2015.10.012
复制
发表时间:
2016-02
影响因子:
8.7
通讯作者:
Yi Pan
Yi Pan
中科院分区:
计算机科学2区
文献类型:
--
作者:
Tao Zhang;Jianxin Wang;Jiawei Huang;Jianer Chen;Yi Pan

文献摘要

参考文献

被引文献

相似文献

由于高度动态的流量负载,提供延迟敏感的服务是数据中心面临的挑战。许多新的传输协议,如DCTCP,D2TCP和L2DCT,使用显式拥塞通知(ECN)来控制交换机队列长度,以实现低延迟传输。然而,原有的ECN标记阈值未能在瓶颈链路利用率和排队延迟之间进行实时权衡,从而增加了流完成时间。在本文中,我们提出了自适应标记阈值(AMT),主动调整标记阈值,以消除不必要的延迟,并保持高的链路利用率在同一时间。NS2仿真和物理实验台的实验结果表明,AMT在数据中心交换机变化不大的情况下,显著降低了典型应用在不同网络场景下的流完成时间。
Due to the highly dynamic traffic load, providing delay-sensitive services is a challenge in data centers. Many recent transport protocols, such as DCTCP, D 2 TCP, and L 2 DCT, use Explicit Congestion Notification (ECN) to control the switch queue length for achieving low-latency transmission. However, the original ECN marking threshold fails to make real-time tradeoff between bottleneck link utilization and queueing delay, thereby increasing the flow completion time. In this paper, we propose Adaptive Marking Threshold (AMT), which proactively tunes the marking threshold to eliminate the unnecessary queueing delay, and maintains high link utilization at the same time. The experimental results of NS2 simulation and physical testbed show that AMT significantly reduces the flow completion time of typical applications across different network scenarios with negligible change in the data center switch.
自适应加速数据中心 TCP
DOI: 10.1109/tc.2014.2345393
发表时间: 2015-06
期刊: Transaction on Computer
影响因子: --
作者:
Tao Zhang;Jianxin Wang;Jiawei Huang;Yi Huang;Jianer Chen;Yi Pan
通讯作者: Yi Pan
DOI: 10.4018/978-1-4666-5888-2.ch615
发表时间: 2015
期刊: --
影响因子: --
作者:
M. H. Rehmani;Y. Saleem
通讯作者: M. H. Rehmani;Y. Saleem
DOI: 10.1126/science.310.5746.195
发表时间: 2005-10
期刊: Science
影响因子: 56.9
作者:
D. Kennedy
通讯作者: D. Kennedy
DOI: 10.1145/1644893.1644918
发表时间: 2009-11
期刊: --
影响因子: --
作者:
Srikanth Kandula;S. Sengupta;A. Greenberg;Parveen Patel;R. Chaiken
通讯作者: Srikanth Kandula;S. Sengupta;A. Greenberg;Parveen Patel;R. Chaiken
DOI: 10.1109/tc.2013.157
发表时间: 2014-11
影响因子: 3.7
作者:
Wanchun Jiang;Fengyuan Ren;Yongwei Wu;Chuang Lin;I. Stojmenovic
通讯作者: Wanchun Jiang;Fengyuan Ren;Yongwei Wu;Chuang Lin;I. Stojmenovic