The design methodology of Phoenix cluster system software stack

  • Authors:

  • Jianfeng Zhan;Lei Wang;Bibo Tu;Hui Wang;Zhihong Zhang;Yi Jin;Yu Wen;Yuansheng Chen;Peng Wang;Bizhu Qiu;Dan Meng;Ninghui Sun

  • Affiliations:

  • Chinese Academy of Sciences, Beijing, China;Chinese Academy of Sciences, Beijing, China;Chinese Academy of Sciences, Beijing, China;Chinese Academy of Sciences, Beijing, China;Chinese Academy of Sciences, Beijing, China;Chinese Academy of Sciences, Beijing, China;Chinese Academy of Sciences, Beijing, China;Chinese Academy of Sciences, Beijing, China;Chinese Academy of Sciences, Beijing, China;Chinese Academy of Sciences, Beijing, China;Chinese Academy of Sciences, Beijing, China;Chinese Academy of Sciences, Beijing, China

  • Venue:
  • CHINA HPC '07 Proceedings of the 2007 Asian technology information program's (ATIP's) 3rd workshop on High performance computing in China: solution approaches to impediments for high performance computing
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

Though many research groups have explored the design methodology of cluster system software stack, few works discuss what constitutes a good one. In this paper, we choose four criteria throughout the lifecycle of cluster system software stack to evaluate its design methodology, including code reusability, evolveability, adaptability and manageability. According to the four criteria, we have proposed a management service-based layered design methodology and built a complete cluster system software stack for both scientific and business computing. Our practices and evaluations show our design methodology has advantages over others in terms of the proposed criteria.