Advertisement

Reliability Analysis of Data Center Network

  • Abhilasha Sharma
  • R. G. Sangeetha
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 468)

Abstract

High computational systems consisting of multiple processors need interconnection networks to provide communication between them. Torus and Benes networks are highly scalable data center network and found to be the suitable candidates to work in this environment. Fault tolerance and reliability are the crucial issues for any scalable network. This paper analyzes the network reliability of torus and Benes networks of size 8 × 8 and 16 × 16. In this study, we have evaluated the network reliability for both the networks using an accurate analytical method. This analysis is performed for the network of size 8 × 8 and 16 × 16 two-dimensional torus and Benes networks. For this analysis, the confidence levels from 0.99 (high switch reliability) to 0.90 (low switch reliability) have been considered. The overall system reliability has been evaluated considering both node and link failures. The results are validated and compared with existing Benes network using MATLAB. The analysis shows that the reliability of torus network is better than Benes network. This is observed because torus network has more number of alternative paths than Benes network.

References

  1. 1.
    Wang T et al (2016) Towards cost-effective and low latency data center network architecture. Comput Commun 82:1–12 CrossRefGoogle Scholar
  2. 2.
    Abu-Libdeh H et al (2010) Symbiotic routing in future data centers ACM SIGCOMM. Comput Commun Rev 40(4):51–62CrossRefGoogle Scholar
  3. 3.
    Wang T et al (2015) Designing efficient high performance server-centric data center network architecture. Comput Netw 79:283–296CrossRefGoogle Scholar
  4. 4.
    Wang T et al (2014) Sprintnet: a high performance server-centric network architecture for data centers. In: Communications (ICC), 2014 IEEE International Conference on, IEEE, New YorkGoogle Scholar
  5. 5.
    Guo C et al (2009) BCube: a high performance, server-centric network architecture for modular data centers. ACM SIGCOMM Comput Commun Rev 39(4):63–74CrossRefGoogle Scholar
  6. 6.
    Guo C et al (2008) Dcell: a scalable and fault-tolerant network structure for data centers. ACM SIGCOMM Comput Commun Rev 38(4):75–86CrossRefGoogle Scholar
  7. 7.
    Calabretta N et al (2013) On the performance of a large-scale optical packet switch under realistic data center traffic. J Opt Commun Netw 5(6):565–573CrossRefGoogle Scholar
  8. 8.
    Al-Fares M, Loukissas A, Vahdat A (2008) A scalable, commodity data center network architecture. ACM SIGCOMM Comput Commun Rev. 38(4):63–74CrossRefGoogle Scholar
  9. 9.
    Farrington N et al (2010) Helios: a hybrid electrical/optical switch architecture for modular data centers. ACM SIGCOMM Comput Commun Rev 40(4):339–350CrossRefGoogle Scholar
  10. 10.
    Wang G et al (2010) c-Through: part-time optics in data centers. ACM SIGCOMM Comput Commun Rev 40(4):327–338CrossRefGoogle Scholar
  11. 11.
    Chen D et al (2012) The IBM blue gene/Q interconnection fabric. IEEE Micro 32(1):32–43CrossRefGoogle Scholar
  12. 12.
    Brightwell R, Pedretti K, Underwood KD (2005) Initial performance evaluation of the Cray SeaStar interconnect. In: Proceedings of the 13th symposium on High performance interconnects, 2005, IEEE, New YorkGoogle Scholar
  13. 13.
    Adiga NR et al (2005) Blue Gene/L torus interconnection network. IBM J Res Dev 49.2.3:265–276CrossRefGoogle Scholar
  14. 14.
    Alverson R, Roweth D, Kaplan L (2010) The gemini system interconnect. IEEE 18th annual symposium on high performance interconnects (HOTI), IEEE, New YorkGoogle Scholar
  15. 15.
    Jahanshahi M, Bistouni F (2015) Improving the reliability of the Benes network for use in large-scale systems. Microelectron Reliab 55(3):679–695CrossRefGoogle Scholar
  16. 16.
    Jahanshahi M, Bistouni F (2014) A new approach to improve reliability of the multistage interconnection networks. Comput Electr Eng 40(8):348–374CrossRefGoogle Scholar
  17. 17.
    Birolini Alessandro (2007) Reliability engineering, vol 5. Springer, HeidelbergMATHGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.SENSE, VIT UniversityChennaiIndia

Personalised recommendations