DOI QR코드

DOI QR Code

A Study on Energy Efficiency in Servers Adopting AFA(All-Flash Array)

AFA(All-Flash Array) 탑재 서버의 에너지 효율성에 대한 연구

  • 김영만 (국민대학교 소프트웨어학부) ;
  • 한재일 (국민대학교 소프트웨어학부)
  • Received : 2018.11.09
  • Accepted : 2019.02.15
  • Published : 2019.03.31

Abstract

Maximizing energy efficiency minimizes the energy consumption of computation, storage and communications required for IT services, resulting in economic and environmental benefits. Recent advancement of flash and next generation non-volatile memory technology and price decrease of those memories have led to the rise of so-called AFA (All-Flash Array) storage devices made of flash or next generation non-volatile memory. Currently, the AFA devices are rapidly replacing traditional storages in the high-performance servers due to their fast input/output characteristics. However, it is not well known how effective the energy efficiency of the AFA devices in the real world. This paper shows input/output performance and power consumption of the AFA devices measured on the Linux XFS file system via experiments and discusses energy efficiency of the AFA devices in the real world.

Keywords

OTSBB9_2019_v18n1_79_f0001.png 이미지

Inside of a Server Computer

OTSBB9_2019_v18n1_79_f0002.png 이미지

CentOS 7 Linux Operating System

OTSBB9_2019_v18n1_79_f0003.png 이미지

Write Time(File Size)

OTSBB9_2019_v18n1_79_f0004.png 이미지

Power Consumption(File Size)

OTSBB9_2019_v18n1_79_f0005.png 이미지

Write Time(CPU Speed)

OTSBB9_2019_v18n1_79_f0006.png 이미지

Power Consumption(CPU Speed)

OTSBB9_2019_v18n1_79_f0007.png 이미지

Write Time(Fsync Call Count)

OTSBB9_2019_v18n1_79_f0008.png 이미지

Power Consumption(Fsync Call Count)

OTSBB9_2019_v18n1_79_f0009.png 이미지

Write Time(Write Buffer Size)

OTSBB9_2019_v18n1_79_f0010.png 이미지

Read Time(File Size)

OTSBB9_2019_v18n1_79_f0011.png 이미지

Power Consumption(File Size)

OTSBB9_2019_v18n1_79_f0012.png 이미지

Read Time(CPU Speed)

OTSBB9_2019_v18n1_79_f0013.png 이미지

Power Consumption(CPU Speed)

OTSBB9_2019_v18n1_79_f0014.png 이미지

Read Time(Read Buffer Size)

OTSBB9_2019_v18n1_79_f0015.png 이미지

Power Consumption(Read Buffer Size)

OTSBB9_2019_v18n1_79_f0016.png 이미지

Read Time(Data Type)

OTSBB9_2019_v18n1_79_f0017.png 이미지

Power Consumption(Data Type)

Average Power Consumption

OTSBB9_2019_v18n1_79_t0001.png 이미지

References

  1. Acun, B. et al., "Power, Reliability, and Performance : One System to Rule Them All", Computer, Vol.49, No.10, 2016, 30-31. https://doi.org/10.1109/MC.2016.310
  2. Agrawal, D., S. Das, and A. El Abbadi, "Big data and cloud computing : current state and future opportunities", Proceedings of the 14th International Conference on Extending Database Technology, Uppsala, ACM, 2011, 530-533.
  3. Agrawal, N. et al., "Design tradeoffs for SSD performance", USENIX 2008 Annual Technical Conference, Boston, Massachusetts, June 2008, 57-70.
  4. Armbrust, M. et al., "A view of cloud computing", Communications of the ACM, Vol. 53, No.4, 2010, 50-58. https://doi.org/10.1145/1721654.1721672
  5. Caulfield, A.M. et al., "Providing safe, user space access to fast, solid state disks", Proceedings of the seventeenth international conference on Architectural Support for Programming Languages and Operating Systems, London, ACM, 2012, 387-400.
  6. Choi, G.S., B. On, K. Choi, and S. Yi, "PTL : PRAM Translation Layer", Microprocessors and Microsystems, Vol.37, 2013, 24-32. https://doi.org/10.1016/j.micpro.2012.07.002
  7. Condit, J. et al., "Better I/O through byte-addressable, persistent memory", in Proceedings of the ACM SIGOPS 22nd symposium on Operating systems principles, Big Sky, ACM, 2009, 133-146.
  8. Han, J. and Y. Kim, "A Study on the Performance and Energy Efficiency in the AFAbased Computing Server Environment", KITS 2017 Fall Conference, Seoul, Korea, 2017, 419-422.
  9. Intel16, https://ark.intel.com/ko/products/83349/Intel-Xeon-Processor-E5-2603-v3-15MCache-1_60-GHz?q=xeon%20e5-2603%20v3.
  10. Intel24, https://ark.intel.com/ko/products/83352/Intel-Xeon-Processor-E5-2620-v3-15MCache-2_40-GHz.
  11. Intelssd, http://www.intel.com/content/dam/www/public/us/en/documents/product-specifications/ssd-750-spec.pdf.
  12. Jedec, https://www.jedec.org/.
  13. Netlist1, Netlist NVvault DDR4 NVDIMM with pmem Driver V0.3.pdf.
  14. Netlist2, http://www.netlist.com/products/vaultmemory-storage/nvvault-ddr4-nvdimm/default.aspx.
  15. Netlist3, Netlist DDR4 NVvault Operational Guide V1.0p.pdf.
  16. Park, Y. et al., "PFFS : a scalable flash memory file system for the hybrid architecture of phase-change RAM and NAND flash", Proceedings of the 2008 ACM symposium on Applied computing, Fortaleza, ACM, 2008, 1498-1503.
  17. Samsung, http://www.samsung.com/semiconductor/minisite/ssd/downloads/document/Samsung_SSD_750_EVO_Data_Sheet_Rev_2_1.pdf.
  18. Set, R. and D.A. Wood, "Energy-Proportional Computing: A New Definition", Computer, Vol.50, No.8, 2017, 26-32. https://doi.org/10.1109/MC.2017.3001248
  19. Suei, P., M. Yeh, and T. Kuo, "Endurance-Aware Flash-Cache Management for Storage Servers", IEEE Transactions on Computers, Vol.63, No.10, 2014, 2416-2430. https://doi.org/10.1109/TC.2013.119
  20. Tech1, http://searchsolidstatestorage.techtarget.com/definition/Flash-array.
  21. Tech2, https://www.techrepublic.com/article/allflash-arrays-the-smart-persons-guide/.
  22. Wdc, https://www.wdc.com/content/dam/wdc/website/downloadable_assets/eng/spec_data_sheet/2879-771436.pdf.
  23. Wu, X. et al., "Using Performance-Power Modeling to Improve Energy Efficiency of HPC Applications", Computer, Vol.49, No.10, 2016, 20-21. https://doi.org/10.1109/MC.2016.311
  24. Zhang, Y. and S. Swanson, "A study of application performance with non-volatile main memory", 31st Symposium on Mass Storage Systems and Technologies(MSST), Santa Clara, CA, USA, 2015, 1-10.
(34141) Korea Institute of Science and Technology Information, 245, Daehak-ro, Yuseong-gu, Daejeon
Copyright (C) KISTI. All Rights Reserved.