Routing-Contained Virtualization Based on Up*/Down* Forwarding

  • Åshild Grønstad Solheim
  • Olav Lysne
  • Thomas Sødring
  • Tor Skeie
  • Jakob Aleksander Libak
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4873)

Abstract

Virtualization of computing resources is becoming increasingly important both for high-end servers and multi-core CPUs. In a virtualized system, the set of resources that constitute a virtual compute entity should be spatially separated from each other. Dividing the cores on a chip, or the CPUs in a high end server into disjoint sets for each task is a trivial problem. Ensuring that they use disjoint parts of the interconnection network is, however, complex, and in existing methods the requirement of routing-containment of each virtual partition severely degrades the utilization of the system. In this paper, we present an allocation strategy that is based on Up*/Down* routing. Through simulations, we demonstrate increases (in some cases above 30%) in system utilization relative to state-of-the-art in a Dimension Order routed mesh - a topology that is assumed to be widely deployed in Networks on Chip.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bulhões, P.T., et al.: N1 grid engine 6 features and capabilities. Sun Microsystems White Paper (2004)Google Scholar
  2. 2.
    HP. Adaptive enterprise: Business and IT synchronized to capitalize on change. HP White Paper (2005)Google Scholar
  3. 3.
    IBM. Unleash the power of e-business on demand. IBM White Paper (2003)Google Scholar
  4. 4.
    Sun Microsystems. Sun grid compute utility - reference guide. Part No. 819-5131-10 (2006)Google Scholar
  5. 5.
    Amazon Elastic Compute Cloud, amazon.com/gp/browse.html?node=,201590011
  6. 6.
    Duato, J., Yalamanchili, S., Ni, L.: Interconnection Networks: An Engineering Approach. Morgan Kaufmann, San Francisco (2003)Google Scholar
  7. 7.
    Lysne, O., et al.: The interconnection network - architectural challenges for Utility Computing Data Centres. Computer (December 2006) (submitted)Google Scholar
  8. 8.
    Subramani, V., et al.: Selective buddy allocation for scheduling parallel jobs on clusters. In: 4th IEEE Int’l. Conf. Cluster Comp., pp. 107–116 (2002)Google Scholar
  9. 9.
    Chen, H.-L., Hu, S.-H.: Submesh determination in faulty tori and meshes. IEEE Trans. Par. and Dist. Syst. 12(3), 272–282 (2001)CrossRefGoogle Scholar
  10. 10.
    Ding, J., Bhuyan, L.N.: An adaptive submesh allocation strategy for two dimensional mesh connected systems. In: Int’l. Conf. Par. Proc., p. 193 (1993)Google Scholar
  11. 11.
    Gupta, V., Jayendran, A.: A flexible processor allocation strategy for mesh connected parallel systems. In: Int’l. Conf. Par. Proc., p. 166 (1996)Google Scholar
  12. 12.
    Kang, M., et al.: Isomorphic strategy for processor allocation in k-ary n-cube systems. IEEE Trans. Comp. 52(5), 645–657 (2003)CrossRefGoogle Scholar
  13. 13.
    Kim, G., Yoon, H.: On submesh allocation for mesh multicomputers: A best-fit allocation and a virtual submesh allocation for faulty meshes. IEEE Trans. Par. and Dist. Syst. 9(2), 175–185 (1998)CrossRefGoogle Scholar
  14. 14.
    Wu, F., Hsu, C.-C., Chou, L.-P.: Processor allocation in the mesh multiprocessors using the Leapfrog method. IEEE Trans. Par. and Dist. Syst. 14(3), 276–289 (2003)CrossRefGoogle Scholar
  15. 15.
    Zhu, Y.: Efficient processor allocation strategies for mesh-connected parallel computers. Jrnl. Par. and Dist. Comp. 16(4), 328–337 (1992)MATHCrossRefGoogle Scholar
  16. 16.
    Qiao, W., Ni, L.M.: Efficient processor allocation for 3D tori. In: 9th Int’l. Par. Proc. Symp., pp. 466–471 (1995)Google Scholar
  17. 17.
    Chuang, P.-J., Wu, C.-M.: An efficient recognition-complete processor allocation strategy for k-ary n-cube multiprocessors. IEEE Trans. Par. and Dist. Syst. 11(5), 485–490 (2000)CrossRefGoogle Scholar
  18. 18.
    Mao, W., Chen, J., Watson III, W.: Efficient subtorus processor allocation in a multi-dimensional torus. In: 8th Int’l. Conf. High-Perf. Comp. Asia-Pacific Reg., p. 53 (2005)Google Scholar
  19. 19.
    Choo, H., Yoo, S.-M., Youn, H.Y.: Processor scheduling and allocation for 3D torus multicomputer systems. IEEE Trans. Par. and Dist. Syst. 11(5), 475–484 (2000)CrossRefGoogle Scholar
  20. 20.
    Chiu, G.-M., Chen, S.-K.: An efficient submesh allocation scheme for two-dimensional meshes with little overhead. IEEE Trans. Par. and Dist. Syst. 10(5), 471 (1999)CrossRefGoogle Scholar
  21. 21.
    Bunde, D.P., Leung, V.J., Mache, J.: Communication patterns and allocation strategies. In: 18th Int’l. Par. and Dist. Proc. Symp., p. 248 (2004)Google Scholar
  22. 22.
    Leung, V., et al.: Processor allocation on Cplant: Achieving general processor locality using one-dimensional allocation strategies. In: 4th IEEE Int’l. Conf. Cluster Comp., pp. 296–304 (2002)Google Scholar
  23. 23.
    Lo, V., et al.: Non-contiguous processor allocation algorithms for mesh-connected multicomputers. IEEE Trans. Par. and Dist. Syst. 8(7), 712–726 (1997)CrossRefGoogle Scholar
  24. 24.
    Mache, J., Lo, V., Windisch, K.: Minimizing message passing contention in fragmentation free processor allocation. In: 10th Int’l. Conf. Par. and Dist. Comp. Syst., pp. 120–124 (1997)Google Scholar
  25. 25.
    Li, K., Cheng, K.: A two-dimensional buddy system for dynamic resource allocation in a partitionable mesh connected system. Jrnl. Par. and Dist. Comp. 12, 79–83 (1991)CrossRefGoogle Scholar
  26. 26.
    Lysne, O., et al.: Layered routing in irregular networks. IEEE Trans. Par. and Dist. Syst. 17(1), 51–65 (2006)CrossRefGoogle Scholar
  27. 27.
    Sancho, J.C., et al.: Effective methodology for deadlock-free minimal routing in InfiniBand networks. In: Int’l. Conf. Par. Proc., pp. 409–418 (2002)Google Scholar
  28. 28.
    Skeie, T., et al.: LASH-TOR: A generic transition-oriented routing algorithm. In: 11th Int’l. Conf. Par. and Dist. Syst. (2004)Google Scholar
  29. 29.
    Schroeder, M.D., et al.: Autonet: a high-speed, self-configuring local area network using point-to-point links. SRC Res. Rep. 59, Digital Equipment Corp. (1990)Google Scholar
  30. 30.
    Windisch, K., Lo, V., Bose, B.: Contiguous and non-contiguous processor allocation algorithms for k-ary n-cubes. In: Int’l. Conf. Par. Proc., p. 164 (1995)Google Scholar
  31. 31.
    Chuang, P.-J., Tzeng, N.-F.: An efficient submesh allocation strategy for mesh computer systems. In: 11th Int’l. Conf. Dist. Comp. Syst., p. 256 (1991)Google Scholar
  32. 32.
  33. 33.
  34. 34.
    Kermani, P., Kleinrock, L.: Virtual cut-through: A new computer communication switching technique. Computer Networks 3, 267–286 (1979)MATHMathSciNetGoogle Scholar
  35. 35.
    Sancho, J.C., Robles, A., Duato, J.: An effective methodology to improve the performance of the Up*/Down* routing algorithm. IEEE Trans. Par. and Dist. Syst. 15(8), 740–754 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Åshild Grønstad Solheim
    • 1
    • 2
  • Olav Lysne
    • 1
    • 2
  • Thomas Sødring
    • 1
  • Tor Skeie
    • 1
    • 2
  • Jakob Aleksander Libak
    • 1
  1. 1.Networks and Distributed Systems Group, Simula Research Laboratory, LysakerNorway
  2. 2.Department of Informatics, University of Oslo, OsloNorway

Personalised recommendations