Usage Patterns in Multi-tenant Data Centers: a Large-Case Field Study

Chapter

Abstract

Data centers are nowadays ubiquitous and have become a commonplace computing platform for corporations as well as individuals, providing a diverse array of services. Data centers may be universal and prevalent, but so are their administrative challenges that include how to best use them, as well as how to optimize their power and cooling costs. The sheer diversity of customer demands (e.g., one may expect very different needs and performance expectations between individual users of cloud-based data centers versus corporate customers) make data center administration challenging and without clear solutions. Studying the workload that typical data centers experience can provide many useful insights for the better usage of data centers, for the design of autonomic management policies for various resources, even for more efficient power and/or cooling management policies.

References

  1. 1.
    M. Al-Fares, A. Loukissas, and A. Vahdat. A scalable, commodity data center network architecture. In SIGCOMM, pages 63–74, 2008.Google Scholar
  2. 2.
    T. Benson, A. Akella, and D. A. Maltz. Network traffic characteristics of data centers in the wild. In IMC, pages 267–280, 2010.Google Scholar
  3. 3.
    R. Birke, L. Y. Chen, and E. Smirni. Data centers in the cloud: A large scale performance study. In IEEE CLOUD, pages 336–343, 2012.Google Scholar
  4. 4.
    G. Chen, W. He, J. Liu, S. Nath, L. Rigas, L. Xiao, and F. Zhao. Energy-aware server provisioning and load dispatching for connection-intensive internet services. In NSDI, pages 337–350, 2008.Google Scholar
  5. 5.
    Y. Chen, A. Das, W. Qin, A. Sivasubramaniam, Q. Wang, and N. Gautam. Managing server energy and operational costs in hosting centers. In SIGMETRICS, pages 303–314, 2005.Google Scholar
  6. 6.
    N. El-Sayed, I. A. Stefanovici, G. Amvrosiadis, A. A. Hwang, and B. Schroeder. Temperature management in data centers: why some (might) like it hot. In SIGMETRICS, pages 163–174, 2012.Google Scholar
  7. 7.
    S. Govindan, J. Choi, B. Urgaonkar, A. Sivasubramaniam, and A. Baldini. Statistical profiling-based techniques for effective power provisioning in data centers. In EuroSys, pages 317–330, 2009.Google Scholar
  8. 8.
    C. Guo, H. Wu, K. Tan, L. Shi, Y. Zhang, and S. Lu. Dcell: a scalable and fault-tolerant network structure for data centers. In SIGCOMM, pages 75–86, 2008.Google Scholar
  9. 9.
    D. Halperin, S. Kandula, J. Padhye, P. Bahl, and D. Wetherall. Augmenting data center networks with multi-gigabit wireless links. In SIGCOMM, pages 38–49, 2011.Google Scholar
  10. 10.
    B. Heller, S. Seetharaman, P. Mahadevan, Y. Yiakoumis, P. Sharma, S. Banerjee, and N. McKeown. Elastictree: Saving energy in data center networks. In NSDI, pages 249–264, 2010.Google Scholar
  11. 11.
    M. Kutare, G. Eisenhauer, C. Wang, K. Schwan, V. Talwar, and M. W. Matthew. Monalytics: online monitoring and analytics for managing large scale data centers. In ICAC, pages 141–150, 2010.Google Scholar
  12. 12.
    R. Singh, U. Sharma, E. Cecchet, and P. Shenoy. Autonomic mix-aware provisioning for non-stationary data center workloads. In ICAC, pages 21–30, 2010.Google Scholar
  13. 13.
    X. Zhu, D. Young, B. J. Watson, Z. Wang, J. Rolia, S. Singhal, B. McKee, C. Hyser, D. Gmach, R. Gardner, T. Christian, and L. Cherkasova. 1000 islands: an integrated approach to resource management for virtualized data centers. Cluster Computing, 12(1):45–57, 2009.Google Scholar

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  1. 1.IBM Research Zurich LabRüschlikonSwitzerland
  2. 2.College of William and MaryWilliamsburgUSA

Personalised recommendations