%0 Conference Proceedings
%T Regional Congestion Mitigation in Lossless Datacenter Networks
%+ Chinese Academy of Sciences [Beijing] (CAS)
%+ University of Chinese Academy of Sciences [Beijing] (UCAS)
%+ Chinese Academy of Sciences [Changchun Branch] (CAS)
%A Liu, Xiaoli
%A Yang, Fan
%A Jin, Yanan
%A Wang, Zhan
%A Cao, Zheng
%A Sun, Ninghui
%< avec comité de lecture
%( Lecture Notes in Computer Science
%B 14th IFIP International Conference on Network and Parallel Computing (NPC)
%C Hefei, China
%Y Xuanhua Shi
%Y Hong An
%Y Chao Wang
%Y Mahmut Kandemir
%Y Hai Jin
%I Springer International Publishing
%3 Network and Parallel Computing
%V LNCS-10578
%P 62-74
%8 2017-10-20
%D 2017
%R 10.1007/978-3-319-68210-5_6
%K Lossless datacenter network
%K Congestion control
%K Adaptive routing
%Z Computer Science [cs]Conference papers
%X To stop harmful congestion spreading, lossless network needs much faster congestion detection and reaction than the end-to-end approach. In this paper, we propose a switch-level regional congestion mitigation mechanism (RCM) that performs traffic management just at the congestion region edge. RCM moves the end-to-end congestion control to hop-by-hop switch level to lower the congested region’s load as fast as possible. Meanwhile, to handle longer congestion, RCM detours the non-congestion flows to a light-loaded available path based on regional congestion degree to avoid the congestion region. Evaluation shows that the proposed RCM mechanism can perform timely congestion control over microburst flows, and achieve >10% improvement on mice flow’s FCT and throughput than DCQCN, with rarely performance reduction on elephant flows.
%G English
%Z TC 10
%Z WG 10.3
%2 https://inria.hal.science/hal-01705435/document
%2 https://inria.hal.science/hal-01705435/file/457609_1_En_6_Chapter.pdf
%L hal-01705435
%U https://inria.hal.science/hal-01705435
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-TC
%~ IFIP-TC10
%~ IFIP-NPC
%~ IFIP-WG10-3
%~ IFIP-LNCS-10578