MDCent:一种高可扩展、高吞吐量的模块间互连结构  被引量:4

MDCent:A Modular Data Center Interconnection with High Scalability and High Performance

在线阅读下载全文

作  者:陆菲菲[1,2] 朱桂明 陶志荣 谢向辉 郭得科[3] 

机构地区:[1]数学工程与先进计算国家重点实验室,江苏无锡214125 [2]解放军信息工程大学国家数字交换系统工程技术研究中心,郑州450002 [3]国防科学技术大学信息系统工程重点实验室,长沙410073

出  处:《计算机研究与发展》2015年第5期1127-1136,共10页Journal of Computer Research and Development

基  金:国家"八六三"高技术研究发展计划基金项目(2013AA01A213);国家自然科学基金项目(91430214)

摘  要:近年来,提出的以服务器为中心的新型数据中心网络互连结构部分程度地解决了传统树型结构面临的性能瓶颈和可扩展性难题,同时出现了以集装箱为基本模块构建超大规模的数据中心.然而,如何设计模块之间的互连结构,确保数据中心网络具有高可扩展性、模块之间具有高带宽是一个非常具有挑战性的问题.以BCube为代表的新型数据中心网络,能够将数千台服务器互连在一个集装箱内,且对各种典型流量模式提供较高的带宽.提出了一种常量度数的模块之间的互连结构MDCent.MDCent基于BCube结构进行模块内服务器互连,利用模块内大量未被使用的上行端口,在各个模块保持常量度数的情况下,能够保证模块之间具有高可扩展性,同时模块之间具有较高的带宽.A fundamental goal of data-center networking is to efficiently interconnect a large number of servers with low equipment cost while keeping high network bandwidth. Some server-centric data center networking structures are proposed to tackle the performance bottleneck and the extensibility problems that the traditional tree-based networking schemes are born with. Shipping-container-based data centers are introduced as building blocks for constructing mega-data centers. However, it is a challenge how to interconnect those containers to make sure that the network among the containers has both high scalability and high performance. As a new server-centric network architecture, BCube is able to interconnect thousands of servers into a container and provide high bandwidth for typical traffic patterns. This paper presents a networking architecture among containers called MDCent, which is based on BCube to interconnect servers inside a container. MDCent makes the network among containers have both high scalability and performance on condition that each container makes use of a lot of unused up-link ports and has a fixed degree.

关 键 词:数据中心网络 模块 互连结构 高可扩展 高吞吐量 集装箱 

分 类 号:TP393[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象