SSRC：时延敏感流的数据源端速率控制算法

doi:10.11959/j.issn.1000-436x.2019070

通信学报 ›› 2019, Vol. 40 ›› Issue (7): 14-26.doi: 10.11959/j.issn.1000-436x.2019070

SSRC：时延敏感流的数据源端速率控制算法

杨洋¹,曹敏¹,杨家海^2,³,车嵘¹,刘伟¹

¹ 国防科技大学信息通信学院，陕西西安 710106
² 清华大学网络科学与网络空间研究院，北京 100084
³ 清华信息科学与技术国家实验室（筹），北京 100084

修回日期:2019-02-13 出版日期:2019-07-25 发布日期:2019-07-30
作者简介:杨洋（1980- ），男，江苏无锡人，博士，国防科技大学讲师，主要研究方向为计算机网络、路由协议、流量工程等。|曹敏（1985- ），女，陕西咸阳人，国防科技大学讲师，主要研究方向为通信与信息系统、信号处理等。|杨家海（1966- ），男，浙江云和人，清华大学教授、博士生导师，主要研究方向为计算机网络、网络管理与测量、网络安全、云计算与大数据等。|车嵘（1979- ），女，甘肃兰州人，国防科技大学副教授，主要研究方向为信号与信息处理、图像通信技术等。|刘伟（1982- ），女，安徽安庆人，博士，国防科技大学副教授，主要研究方向为信号与信息处理、无线通信技术等。
基金资助:
国家重点研发计划基金资助项目(2016YFB0801302);国防科技大学计划科研基金资助项目(ZK18-03-59)

SSRC:source rate control algorithm for delay-sensitive flow in data center network

Yang YANG¹,Min CAO¹,Jiahai YANG^2,³,Rong CHE¹,Wei LIU¹

¹ School of Information and Communication,National University of Defence Technology,Xi’an 710106,China
² Institute for the Network Sciences and Cyberspace,Tsinghua University,Beijing 100084,China
³ Tsinghua National Laboratory for Information Science and Technology (TNList),Beijing 100084,China

Revised:2019-02-13 Online:2019-07-25 Published:2019-07-30
Supported by:
The National Key Research and Development Program of China(2016YFB0801302);The Research Program of National University of Defence Technology(ZK18-03-59)

摘要/Abstract

摘要：

当前的研究工作针对如何保证时延敏感流的传输时间进行了大量研究，但普遍存在时效性不够强的问题。基于 SDN/OpenFlow架构，提出了数据源端控制算法 SSRC。该算法依据网络的全局视图，快速定位拥塞可能发生的节点，并及时对目标流的源端速率进行调节，可以缩短算法的响应时间。实验结果表明，与DCTCP 等算法相比，所提算法的流完成时间平均缩短了 75%，且能够保证时延敏感流的传输时间，很好地解决Incast问题。

关键词: 时延敏感, 长流, 软件定义网络, 缓存溢出

Abstract:

Previous work had studied how to ensure the transmission time of delay-sensitive flows,but falled short in its effectiveness for a given period.Motivated by that and based on SDN/OpenFlow framework,a SDN-based source rate control (SSRC) algorithm was proposed.With a global view of network,SSRC can quickly locate the potential congestion node,adjust the transmission rate of source and reduce the response time of SSRC.The experiment results show that compared with DCTCP and other algorithms,SSRC can shorten the completion time of flows by 75% in average,which can ensure the transmission time of delay-sensitive and solve the problem of Incast well.

Key words: delay-sensitive, long flow, software-defined network, buffer overflow

中图分类号:

TP393

杨洋,曹敏,杨家海,车嵘,刘伟. SSRC：时延敏感流的数据源端速率控制算法[J]. 通信学报, 2019, 40(7): 14-26.

Yang YANG,Min CAO,Jiahai YANG,Rong CHE,Wei LIU. SSRC:source rate control algorithm for delay-sensitive flow in data center network[J]. Journal on Communications, 2019, 40(7): 14-26.

图/表 10

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

参考文献 23

[1]	ALIZADEH M , GREENBERG A , MALTZ D A ,et al. Data center tcp (dctcp)[C]// The ACM Conference on SIGCOMM. ACM, 2010: 63-74.
[2]	DEAN J , GHEMAWAT S . MapReduce:simplified data processing on large clusters[J]. Communications of the ACM, 2008,51(1): 107-113.
[3]	XU L , XU K , JIANG Y ,et al. Enhancing TCP incast congestion control over large-scale datacenter networks[C]// The IEEE International Symposium on Quality of Service. IEEE, 2016: 225-230.
[4]	SHAH Z . Mitigating TCP incast issue in cloud data centres using software-defined networking (SDN):a survey[J]. KSII Transactions on Internet and Information Systems, 2018,12(11): 5179-5202.
[5]	ABDELMONIEM A M , BRAHIM B , ABU A J . Mitigating incast-TCP congestion in data centers with SDN[J]. Annales des Telecommunications/Annals of Telecommunications, 2018,73(3): 263-277.
[6]	杨洋, 杨家海, 温皓森 . 基于时隙传输的数据中心路由算法设计[J]. 软件学报, 2018,29(8): 2485-2501.
	YANG Y , YANG J H , WEN H S . Another routing algorithm design based on timeslot of transmission in data center networks[J]. Journal of Software, 2018,29(8): 2485-2501.
[7]	ZHANG J , REN F Y , LIN C ,et al. Modeling and solving TCP incast problem in data center networks[J]. IEEE Transactions on Parallel and Distributed Systems, 2015,26(2): 478-491.
[8]	VAMANAN B , HASAN J , VIJAYKUMAR T . Deadline-aware datacenter TCP (D2TCP)[C]// The ACM Conference on SIGCOMM. ACM, 2012: 115-126.
[9]	WU H , FENG Z , GUO C ,et al. ICTCP:incast congestion control for TCP in data center networks[J]. IEEE/ACM Transactions Networking, 2013,21(2): 345-358.
[10]	MORTEZA K , WAKEMAN I , GEORGE P . MMPTCP:a multipath transport protocol for data centers[C]// The IEEE International Conference on Computer Communications. IEEE, 2016.
[11]	FORD C,RAICIUM , HANDLEY S , et al . RFC6824:TCP extension for multipath operation with multiple addresses[R]. IEEE,(2013-01-01)[2018-12-20].
[12]	RAMAKRISHNAN K , FLOYD S , BLACK D . RFC 3168:The addition of explicit congestion notification (ECN) to IP[R]. IETF,(2001-09-01)[2013-03-02].
[13]	WILSON C , BALLANI H , KARAGIANNIS T ,et al. Better never than late:meeting deadlines in datacenter networks[C]// The ACM Conference on SIGCOMM. ACM, 2011: 50-61.
[14]	AMAR P , ELIE K , VIJAY V ,et al. Measurement and analysis of TCP throughput collapse in cluster-based storage systems[C]// The USENIX Conference on File and Storage Technologies. USENIX Association, 2008.
[15]	PAN R , PRABHAKAR B , LAXMIKANTHA A . QCN:quantized congestion notification an overview[R]. IEEE,(2009-05-29)[2019-01-28].
[16]	ZHANG J , REN F Y , TANG L ,et al. Taming TCP incast throughput collapse in data center networks[C]// The IEEE International Conference on Network Protocols. IEEE, 2013.
[17]	WASSERMA M , HARTMAN S . OpenFlow switch specification[R]. Huawei,(2012-08-01)[2013-04-02].
[18]	UHLIG S . Non-stationarity and high-order scaling in TCP flow arrivals:a methodological analysis[J]. ACM SIGCOMM Computer Communications Review, 2004,43(2): 9-24.
[19]	ROUGHAN M , VEITCH D . Measuring long-range dependence under changing traffic conditions[C]// The Annual Joint Conference of the IEEE Computer and Communications Societies. IEEE, 1999: 1513-1521.
[20]	BONALD T , COMTE C . The multi-source model for dimensioning data networks[J]. Computer Networks, 2016,109(2): 225-233.
[21]	CAO J , XIA R , YANG P ,et al. Per-packet load-balanced,low-latency routing for clos-based data center networks[C]// The Seventh Conference on Emerging Networking Experiments and Technologies. ACM, 2013: 49-60.
[22]	陆传赉 . 排队论[M]. 北京: 北京邮电大学出版社, 2009.
	LU C J . Queuing theory[M]. Beijing: Beijing University of Posts and Telecommunications PressPress, 2009.
[23]	SIEGFRIED S , JIANMING S . Fractional programming:the sum-ofratios case[J]. Optimization Methods and Software, 2003,18(2): 219-229.

SSRC：时延敏感流的数据源端速率控制算法

SSRC:source rate control algorithm for delay-sensitive flow in data center network

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 23

相关文章 15

Metrics

推荐阅读 0

[1]	王东滨, 吴东哲, 智慧, 郭昆, 张勖, 时金桥, 张宇, 陆月明. 软件定义网络抗拒绝服务攻击的流表溢出防护[J]. 通信学报, 2023, 44(2): 1-11.
[2]	沙宗轩, 霍如, 孙闯, 汪硕, 黄韬. 基于深度强化学习的转发效能感知流量调度算法[J]. 通信学报, 2022, 43(8): 30-40.
[3]	燕昺昊, 刘勤让, 沈剑良, 汤先拓, 梁栋. 软件定义网络中一种快速无循环路径迁移策略[J]. 通信学报, 2022, 43(5): 24-35.
[4]	吴平, 常朝稳, 左志斌, 马莹莹. 基于地址重载的SDN分组转发验证[J]. 通信学报, 2022, 43(3): 88-100.
[5]	李传煌, 陈泱婷, 唐晶晶, 楼佳丽, 谢仁华, 方春涛, 王伟明, 陈超. QL-STCT：一种SDN链路故障智能路由收敛方法[J]. 通信学报, 2022, 43(2): 131-142.
[6]	吴平, 常朝稳, 马莹莹. 基于端址重载的SDN包转发验证[J]. 通信学报, 2021, 42(7): 70-83.
[7]	李劲夫, 冯文江, 王文收, 蒋卫恒, 杨崇海. 下行MIMO广播信道中基于偏袒干扰消除的回溯干扰对齐方案[J]. 通信学报, 2021, 42(6): 94-106.
[8]	常朝稳, 金建树, 韩培胜, 祝现威. 基于属性签名标识的SDN数据包转发验证方案[J]. 通信学报, 2021, 42(6): 131-144.
[9]	周启钊, 于俊清, 李冬. SDN控制层泛洪防御机制研究：检测与缓解[J]. 通信学报, 2021, 42(11): 41-53.
[10]	李硕朋, 方娟, 陈肯. 基于SRv6的确定性网络服务共享保护方案[J]. 通信学报, 2021, 42(10): 32-42.
[11]	姚蓝,兰巨龙. 基于联盟博弈的自适应SDN交换机迁移机制[J]. 通信学报, 2020, 41(8): 1-10.
[12]	王耀民,王霞,董易,张松海,施心陵. 基于斐波那契树优化算法的数据中心流量调度策略[J]. 通信学报, 2020, 41(6): 112-127.
[13]	韩珍珍,赵国锋,徐川,周文涛,周洋洋. 基于时延的LEO卫星网络SDN控制器动态放置方法[J]. 通信学报, 2020, 41(3): 126-135.
[14]	赖英旭,蒲叶玮,刘静. 基于最小代价路径的交换机迁移方法研究[J]. 通信学报, 2020, 41(2): 131-142.
[15]	柯文龙,王勇,叶苗,陈俊奇. Ceph云存储网络中一种业务优先级区分的多播流调度方法[J]. 通信学报, 2020, 41(11): 40-51.