Abstract
This paper highlights the growing importance of storage energy consumption in a typical data center, and asserts that storage energy research should drive towards a vision of energy proportionality for achieving significant energy savings. Our analysis of real-world enterprise workloads shows a potential energy reduction of 40-75% using an ideally proportional system. We then present a preliminary analysis of appropriate techniques to achieve proportionality, chosen to match both application requirements and workload characteristics. Based on the techniques we have identified, we believe that energy proportionality is achievable in storage systems at a time scale that will make sense in real world environments.
- Intel Pentium 4 Processor on 90 nm Process, 2005. http://download.intel.com/design/Pentium4/datashts/3056103.pdf.Google Scholar
- Intel Xeon Processor 5500 Series, 2009. http://www.intel.com/Assets/PDF/Prodbrief/xeon-5500.pdf.Google Scholar
- Is storage top energy hog in data centers? http://searchstorage.techtarget.com/news/article/0,289142,sid5_gci1285060,00.html.Google Scholar
- M. Allalouf, Y. Arbitman, M. Factor, R. Kat, K. Meth, and D. Naor. Storage Modeling for Power Estimation. In ACM SYSTOR, 2009. Google ScholarDigital Library
- L.A. Barroso and U. Hlzle. The Case for Energy-Proportional Computing. IEEE Computer, 40(12), 2007. Google ScholarDigital Library
- T. Burd, T. Pering, A. Stratakos, and R. Brodersen. A Dynamic Voltage-Scaled Microprocessor System. In IEEE ISSCC, 2000.Google ScholarCross Ref
- D. Colarelli and D. Grunwald. Massive Arrays of Idle Disks for Storage Archives. In SC, 2002. Google ScholarDigital Library
- S. Gurumurthiy, A. Sivasubramaniamy, M. Kandemiry, and H. Frankez. DRPM: dynamic speed control for power management in server class disks. In 13th ISCA, 2003. Google ScholarDigital Library
- D. Narayanan, A. Donnelly, and A. Rowstron. Write Off-Loading: Practical Power Management for Enterprise Storage. In 6th FAST, 2008. Google ScholarDigital Library
- D. Narayanan, A. Donnelly, E. Thereska, S. Elnikety, and A. Rowstron. Everest: Scaling down peak loads through I/O off-loading. In 8th FAST, 2008.Google Scholar
- A.E. Papathanasiou and M.L. Scott. Energy Efficient Prefetching and Caching. In USENIX, 2004. Google ScholarDigital Library
- E. Pinheiro and R. Bianchini. Energy conservation techniques for disk array-based servers. In 18th ICS, 2004. Google ScholarDigital Library
- D. Reinsel. The Real Costs to Power and Cool All the World's External Storage. In IDC Report, Doc 212714, 2008.Google Scholar
- G. Schulz. Storage Industry Trends and IT Infrastructure Resource Management (IRM), 2007. http://www.storageio.com/DownloadItems/CMG/MSP_CMG_May03_2007.pdf.Google Scholar
- Seagate Technology. Seagate's Sound Barrier Technology (SBT). http://www.seagate.com/docs/pdf/whitepaper/sound_barrier.pdf.Google Scholar
- N. Tolia, Z. Wang, M. Marwah, C. Bash, P. Ranganathan, and X. Zhu. Delivering Energy Proportionality with Non Energy-Proportional Systems-Optimizing the Ensemble. In USENIX HotPower, 2008. Google ScholarDigital Library
- C. Weddle, M. Oldham, J. Qian, A.-I. A. Wang, P. Reiher, and G. Kuenning. PARAID: A Gear-Shifting Power-Aware RAID. In 5th FAST, 2007. Google ScholarDigital Library
- Q. Zhu, F.M. David, C.F. Devaraj, Z. Li, Y. Zhou, and P. Cao. Reducing Energy Consumption of Disk Storage Using Power-Aware Cache Management. In 10th HPCA, 2004. Google ScholarDigital Library
- Q. Zhu, Z. Chen, L. Tan, Y. Zhou, K. Keeton, and J. Wilkes. Hibernator: helping disk arrays sleep through the winter. In 20th ACM SOSP, volume 39, 2005. Google ScholarDigital Library
Index Terms
- Energy proportionality for storage: impact and feasibility
Recommendations
Energy proportionality for disk storage using replication
EDBT/ICDT '11: Proceedings of the 14th International Conference on Extending Database TechnologySaving energy for storage is of major importance as storage devices (and cooling them off) may contribute over 25 percent of the total energy consumed in a datacenter. Recent work introduced the concept of energy proportionality and argued that it is a ...
Revisiting Server Energy Proportionality
ICPP '13: Proceedings of the 2013 42nd International Conference on Parallel ProcessingServer energy proportionality refers to a proposed ideal that a server consumes energy proportional to its utilization level. Since its introduction in 2007, the ideal has been adopted by the server industry as a design goal to further optimize the ...
Scaling the Energy Proportionality Wall with KnightShift
Measuring energy proportionality accurately and understanding the reasons for disproportionality are critical first steps in designing future energy-efficient servers. This article presents two metrics—linear deviation and proportionality gap—that let ...
Comments