ABSTRACT
Power delivery, electricity consumption, and heat management are becoming key challenges in data center environments. Several past solutions have individually evaluated different techniques to address separate aspects of this problem, in hardware and software, and at local and global levels. Unfortunately, there has been no corresponding work on coordinating all these solutions. In the absence of such coordination, these solutions are likely to interfere with one another, in unpredictable (and potentially dangerous) ways. This paper seeks to address this problem. We make two key contributions. First, we propose and validate a power management solution that coordinates different individual approaches. Using simulations based on 180 server traces from nine different real-world enterprises, we demonstrate the correctness, stability, and efficiency advantages of our solution. Second, using our unified architecture as the base, we perform a detailed quantitative sensitivity analysis and draw conclusions about the impact of different architectures, implementations, workloads, and system design choices.
Supplemental Material
Available for Download
Slides from the presentation
Supplemental material for No "power" struggles: coordinated multi-level power management for the data center
- L. Barroso. The price of performance. ACM Queue, 3(7), Sept. 2005. Google ScholarDigital Library
- P. Bohrer et al. The case for power management in web servers. In Power Aware Computing (PACS), 2002. Google ScholarDigital Library
- D. Brooks and M. Martonosi. Dynamic thermal management for high-performance microprocessors. In 7th International Symposium on High-Performance Computer Architecture, 2001. Google ScholarDigital Library
- E.V. Carrera, E. Pinheiro, and R. Bianchini. Conserving disk energy in network servers. In 17th International Conference on Supercomputing, 2003. Google ScholarDigital Library
- J. Chase et al. Managing energy and server resources in hosting centers. In 18th Symposium on Operating Systems Principles (SOSP), 2001. Google ScholarDigital Library
- J. Chase and R. Doyle. Balance of power: Energy management for server clusters. In 8th Workshop on Hot Topics in Operating Systems, May 2001. Google ScholarDigital Library
- Y. Chen et al. Managing server energy and operational costs in hosting centers. In ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems, June 2005. Google ScholarDigital Library
- CIM Specification, DMTF industry group, www.dmtf,orgGoogle Scholar
- B. Diniz et al. Limiting the power consumption of main memory. In 34th International Symposium on Computer Architecture (ISCA), June 2007. Google ScholarDigital Library
- J. Donald and M. Martonosi. Techniques for multicore thermal management: Classification and new exploration. In Proc. of the 33rd International Symposium on Computer Architecture, 2006. Google ScholarDigital Library
- M. Elnozahy, M. Kistler, and R. Rajamony. Energy-efficient server clusters. In Power Aware Computing Systems (PACS), February 2002. Google ScholarDigital Library
- X. Fan et al. Power provisioning for a warehouse-sized computer, In 34th ACM International Symposium on Computer Architecture, CA, June 2007. Google ScholarDigital Library
- W. Felter et al., A performance-conserving approach for reducing peak power consumption in server systems. In 19th International Conference on Supercomputing, 2005. Google ScholarDigital Library
- M. Femal and V. Freeh. Safe over-provisioning: Using power limits to increase aggregate throughput. In Power-Aware Computing Systems (PACS), December 2004. Google ScholarDigital Library
- P. Gelsinger. Intel Developer Forum, Keynote, April 2006.Google Scholar
- The Green Grid", http://www.thegreengrid.org/homeGoogle Scholar
- T. Heath et al. Self-configuring heterogeneous server clusters. In Workshop on Compilers and Operating Systems for Low Power (COLP), 2003.Google Scholar
- Hewlett Packard. HP Power Regulator for Proliant. Online. http://h18004.www1.hp.com/products/servers/management/ilo/powerregulator.html.Google Scholar
- Intel Corporation, Motorola Corporation, and Toshiba Corporation. Advanced configuration and power interface specification, December 1996. http://www.teleport.com/acpi.Google Scholar
- P. Juang et al. Formal coordinated, distributed energy management of chip multiprocessors, International Symposium on Low Power Electronics and Design (ISLPED-05), August, 2005 Google ScholarDigital Library
- C. Lefurgy et al. Energy management for commercial servers. In IEEE Computer, pp. 39--48, December 2003. Google ScholarDigital Library
- R. Nathuji and K. Schwan. VirtualPower: Coordinated power management in virtualized enterprise systems. In Proc. of the 21st Symposium on Operating Systems Principles (SOSP), October 2007. Google ScholarDigital Library
- C. Patel and P. Ranganathan. Enterprise power and cooling. ASPLOS Tutorial, October 2006.Google Scholar
- C. Patel et al. Energy flow in the information technology stack: Introducing the coefficient of the ensemble at its impact on total cost of ownership. In HP Labs Technical Report HPL-2006-55, 2006.Google Scholar
- E. Pinheiro et al. Load balancing and unbalancing for power and performance in cluster-based systems. In Proc. of the Workshop on Compilers and Operating Systems for Low Power (COLP), 2001.Google Scholar
- R. Raghavendra et al. "No power struggles: Coordinated multi-level power management for the data center," Hewlett Packard Technical Report, HPL-TR-2007-194, December 2007.Google Scholar
- P. Ranganathan and P. Leech. Simulating complex enterprise workloads using utilization traces. In 10th Workshop on Computer Architecture Evaluation using Commercial Workloads (CAECW), February 2007.Google Scholar
- P. Ranganathan et al. Ensemble-level power management for dense blade servers. In Proc. of the 33rd International Symposium on Computer Architecture (ISCA), 2006. Google ScholarDigital Library
- J. Rolia et al. Statistical service assurances for applications in utility grid environments. In 10th International Workshop on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS), October 2002 Google ScholarDigital Library
- D.G. Sachs et al. Grace: A cross-layer adaptation framework for saving energy. In IEEE Computer, special issue on Power-Aware Computing, December 2003.Google Scholar
- V. Sharma et al. Power-aware QoS management in web servers. In Proc. of the Real-Time Systems Symposium, December 2003. Google ScholarDigital Library
- United States Environmental Protection Agency (EPA). Enterprise server and data center efficiency initiatives. http://www.energystar.gov/index.cfm?c=prod_development.server_efficiency.Google Scholar
- A. Vahdat et al. Every joule is precious: The case for revisiting operating system design for power efficiency. In 9th ACM SIGOPS European Workshop, 2000. Google ScholarDigital Library
- VMware. Vmotion: Virtual machine migration. http://www.vmware.com/products/vi/vc/vmotion.html.Google Scholar
- Z. Wang, X. Zhu, and S. Singhal. Utilization and SLO-based control for dynamic sizing of resource partitions. In 16th IFIP/IEEE Distributed Systems: Operations and Management, Oct. 2005. Google ScholarDigital Library
- Q. Wu et al. Formal control techniques for power-performance management, IEEE Micro, Vol. 25, No. 5, September, 2005, pp. 52--63. Google ScholarDigital Library
- H. Zeng et al. Ecosystem: managing energy as a first class operating system resource. In Proc. of the ASPLOS-X, pp. 123--132. ACM Press, 2002. Google ScholarDigital Library
- H. Zeng et al. Currentcy: A unifying abstraction for expressing energy. In Proc. of the Usenix Annual Technical Conference, June 2003. Google ScholarDigital Library
Index Terms
- No "power" struggles: coordinated multi-level power management for the data center
Recommendations
VirtualPower: coordinated power management in virtualized enterprise systems
SOSP '07Power management has become increasingly necessary in large-scale datacenters to address costs and limitations in cooling or power delivery. This paper explores how to integrate power management mechanisms and policies with the virtualization ...
No "power" struggles: coordinated multi-level power management for the data center
ASPLOS '08Power delivery, electricity consumption, and heat management are becoming key challenges in data center environments. Several past solutions have individually evaluated different techniques to address separate aspects of this problem, in hardware and ...
No "power" struggles: coordinated multi-level power management for the data center
ASPLOS '08Power delivery, electricity consumption, and heat management are becoming key challenges in data center environments. Several past solutions have individually evaluated different techniques to address separate aspects of this problem, in hardware and ...
Comments