Software-Defined Cluster

详细信息    查看全文

• 作者：Hua Nie (1)
  Xiao-Jun Yang (2)
  Tao-Ying Liu (3)
  
  1. School of Computer and Communication Engineering ; University of Science and Technology Beijing ; Beijing ; 100083 ; China
  2. Dawning Information Industry Co. ; Ltd ; Beijing ; 100193 ; China
  3. Institute of Computing Technology ; Chinese Academy of Sciences ; Beijing ; 100190 ; China
  
• 关键词：software ; defined cluster ; global I/O space ; hardware ; supported native access
• 刊名：Journal of Computer Science and Technology
• 出版年：2015
• 出版时间：March 2015
• 年：2015
• 卷：30
• 期：2
• 页码：252-258
• 全文大小：1,085 KB
• 参考文献：1. Rahul K. Microservers target workloads and architecture trends. Technical Report, Intel, April 2013.
  2. Bell, G, Gray, J, Szalay, A (2006) Petascale computational systems. Computer 39: pp. 110-112 CrossRef
  3. Hemsoth N. The new era of computing: An interview with 鈥淒r. Data鈥? Jan. 2012. of_computing_an_interview_with_dr_data.html" class="a-plus-plus">http://www.datanami.com/datanami/2012/01/23/the_new_era_of_computing_an_interview_with_dr_data.html, Jan. 2015.
  4. Bergman K, Borkar S, Campbell D / et al. ExaScale computing study: Technology challenges in achieving ExaScale systems. Technique Report, Sept. 2008. http://www.cse.nd.edu/Reports/2008/TR-2008-13.pdf, Jan, 2015.
  5. Kreutz, D, Ramos, FMV, Esteves Verissimo, P, Esteves Rothenberg, C, Azodolmolky, S, Uhlig, S (2015) Software-defined networking: A comprehensive survey. Proceedings of the IEEE 103: pp. 14-76 CrossRef
  
• 刊物类别：Computer Science
• 刊物主题：Computer Science, general
  Software Engineering
  Theory of Computation
  Data Structures, Cryptology and Information Theory
  Artificial Intelligence and Robotics
  Information Systems Applications and The Internet
  Chinese Library of Science
  
• 出版者：Springer Boston
• ISSN：1860-4749

文摘

The cluster architecture has played an important role in high-end computing for the past 20 years. With the advent of Internet services, big data, and cloud computing, traditional clusters face three challenges: 1) providing flexible system balance among computing, memory, and I/O capabilities; 2) reducing resource pooling overheads; and 3) addressing low performance-power efficiency. This position paper proposes a software-defined cluster (SDC) architecture to deal with these challenges. The SDC architecture inherits two features of traditional cluster: its architecture is multicomputer and it has loosely-coupled interconnect. SDC provides two new mechanisms: global I/O space (GIO) and hardware-supported native access (HNA) to remote devices. Application software can define a virtual cluster best suited to its needs from resources pools provided by a physical cluster, and traditional cluster ecosystems need no modification. We also discuss a prototype design and implementation of a 32-processor cloud server utilizing the SDC architecture.