AppFlow: Autonomic performance-per-watt management of large-scale data centers

Bithika Khargharia, Haoting Luo, Youssif Al-Nashif, Salim A Hariri

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

The characteristic of dramatic fluctuation in the resource provisioning for real-time applications calls for an elastic delivery of computing services. Current datacenter deployment schemes, which feature a strong tie between servers and applications, are increasingly challenged to ensure power efficiency in terms of multiple peak loads provisioning, optimal average resources utilization, variable runtime workloads profiling, datacenter manageability and overhead control on the datacenter Total Cost of Ownership (TCO). Researchers have exploited paradigms such as virtualization and migration for large-scale computing systems; however, there is still a long way before we can optimally address the power-performance trade-off. This paper provides an autonomic power management scheme for the resource provisioning process for large-scale data centers while meeting the Service-Level Agreement (SLA) and power requirements. The system status is continuously monitored using a cross-layered hierarchy to optimally scale up and down the virtual machine resources such that power and performance can be optimized. We have applied our technique to autonomically manage high performance platforms with multi-core processors and multi rank memory subsystems. Our experimental results show around 56.25% platform energy savings for memory-intensive workload, 63.75% platform energy savings for processor-intensive workload and 47.5% platform energy savings for mixed workload while maintaining.

Original languageEnglish (US)
Title of host publicationProceedings - 2010 IEEE/ACM International Conference on Green Computing and Communications, GreenCom 2010, 2010 IEEE/ACM International Conference on Cyber, Physical and Social Computing, CPSCom 2010
Pages103-111
Number of pages9
DOIs
Publication statusPublished - 2010
Event2010 IEEE/ACM International Conference on Green Computing and Communications, GreenCom 2010, 2010 IEEE/ACM International Conference on Cyber, Physical and Social Computing, CPSCom 2010 - Hangzhou, China
Duration: Dec 18 2010Dec 20 2010

Other

Other2010 IEEE/ACM International Conference on Green Computing and Communications, GreenCom 2010, 2010 IEEE/ACM International Conference on Cyber, Physical and Social Computing, CPSCom 2010
CountryChina
CityHangzhou
Period12/18/1012/20/10

    Fingerprint

Keywords

  • Autonomic computing
  • Data center
  • Power management

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Theoretical Computer Science

Cite this

Khargharia, B., Luo, H., Al-Nashif, Y., & Hariri, S. A. (2010). AppFlow: Autonomic performance-per-watt management of large-scale data centers. In Proceedings - 2010 IEEE/ACM International Conference on Green Computing and Communications, GreenCom 2010, 2010 IEEE/ACM International Conference on Cyber, Physical and Social Computing, CPSCom 2010 (pp. 103-111). [5724818] https://doi.org/10.1109/GreenCom-CPSCom.2010.103