BCN: Bidimensional Compound Networks for Data Centers

نویسندگان

  • Deke Guo
  • Tao Chen
  • Dan Li
چکیده

A fundamental challenge in data centers is how to design distinguished networking topology for efficiently interconnecting a large number of servers. This paper studies the design of Data Center Networking (DCN) from the aspect of the degree/diameter problem, which determines desirable DCNs that support the largest number of servers given maximum server degree and given diameter. More specifically, we propose the bidimensional compound network (BCN) to interconnect servers with dual ports and low-cost commodity switches. BCN is a level-i irregular compound graph recursively defined in the first dimension for 0≤i, and a level one regular compound graph in the second dimension. In each dimension, a high-level BCN employs a one low level BCN as a unit cluster and connects many such clusters by means of a complete graph. A BCN of level one in each dimension is the largest known DCN with server degree 2 and diameter 7, and is large enough for a single data center. In addition, BCN has many attractive features, such as low diameter, constant server degree, high bisection width, supporting of incremental expansion, and good fault-tolerance ability. Mathematic analysis and comprehensive simulations show that BCN possesses excellent topology properties and is a viable interconnection structure for data centers. To the best of our knowledge, this is the first work studying the degree/diameter problem in data centers.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Improved routing algorithms in the dual-port datacenter networks HCN and BCN

We present significantly improved one-to-one routing algorithms in the datacenter networks HCN and BCN in that our routing algorithms result in much shorter paths when compared with existing routing algorithms. We also present a much tighter analysis of HCN and BCN by observing that there is a very close relationship between the datacenter networks HCN and the interconnection networks known as ...

متن کامل

Identification of ternary boron–carbon–nitrogen hexagonal phases by x-ray absorption spectroscopy

Boron carbon nitride ~BCN! films have been grown by B4C evaporation with concurrent N2 1 ion assistance, and have been characterized by x-ray absorption near edge ~XANES! spectroscopy. Upon the nitrogen insertion, the film structure evolves from BxC-like to h-BN-like. The hexagonal structure corresponds to a true ternary BCN compound that can be understood as h-BN with carbon incorporated in su...

متن کامل

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING CONGESTION MANAGEMENT FOR LOSSLESS ETHERNET OPERATION by Jinjing

CONGESTION MANAGEMENT FOR LOSSLESS ETHERNET OPERATION by Jinjing Jiang ADVISOR: Professor Raj Jain May 2008 Saint Louis, Missouri IEEE 802.1 standards committee is working on a new specification for congestion notification in Ethernet networks. The goal of this work is to enable applications of Ethernet in backend data center networks. Such applications typically use Fiber Channel and Infiniban...

متن کامل

Antimycobacterial activity of bacteriocins and their complexes with liposomes.

OBJECTIVES Bacteriocins (Bcn) are natural peptides that are secreted by several taxonomically distant bacteria and exert bactericidal activity against other bacterial species. Their capacity to inhibit growth of virulent Mycobacterium tuberculosis H37Rv was evaluated in this study. METHODS Five different Bcn were isolated and purified from bacterial culture supernatants, their amino acid sequ...

متن کامل

Estimation of Discharge over the Submerged Compound Sharp-Crested Weir using Artificial Neural Networks and Genetic Programming

Truncated sharp crested weirs are used to measure flow rate and control upstream water surface in irrigation canals and laboratory flumes. The main advantages of such weirs are ease of construction and capability of measuring a wide range of flows with sufficient accuracy. Artificial neural networks (ANNs) and genetic programming (GP) have recently been used for estimation of hydraulic data. In...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2009