Can Storage Devices be Power Adaptive?
Authors: 
Dedong Xie, Theano Stavrinos, Kan Zhu, Simon Peter, Baris Kasikci, Thomas AndersonAuthors Info & Claims
Dedong Xie, Theano Stavrinos, Kan Zhu, Simon Peter, Baris Kasikci, Thomas AndersonAuthors Info & ClaimsPages 47 - 54
Abstract
Power is becoming a scarce resource for data centers, raising the need for power adaptive system design---the ability to dynamically change power consumption---to match available power. Storage makes up an increasing fraction of total data center power consumption. As such, it holds great potential to contribute to data center power adaptivity.
To this end, we conduct a measurement study of power control mechanisms on a variety of modern data center storage devices. By changing device power states and shaping IO, we achieve a power dynamic range of up to 59.4% of the device's maximum operating power. We also study power control trade-offs, including throughput and latency. Based on our observations, we construct storage device power-throughput models and discuss the implications on power adaptive storage system design.
References
[1]
Bilge Acun, Benjamin Lee, Fiodar Kazhamiaka, Kiwan Maeng, Udit Gupta, Manoj Chakkaravarthy, David Brooks, and Carole-Jean Wu. 2023. Carbon Explorer: A Holistic Framework for Designing Carbon Aware Datacenters. In Proceedings of the 28th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS'23). Association for Computing Machinery (ACM), New York, NY, USA.
[2]
U.S. Energy Information Administration. 2024. U.S. Energy Information Administration (EIA). https://www.eia.gov/opendata/index.php
[3]
Hrishikesh Amur, James Cipar, Varun Gupta, Gregory R Ganger, Michael A Kozuch, and Karsten Schwan. 2010. Robust and flexible power-proportional storage. In Proceedings of the 1st ACM Symposium on Cloud Computing 2010 (SoCC'10). Association for Computing Machinery (ACM), New York, NY, USA.
[4]
Jens Axboe. 2017. fio - Flexible I/O tester rev. 3.36. https://fio.readthedocs.io/en/latest/fio_doc.html
[5]
Matias Bjørling, Philippe Bonnet, Luc Bouganim, and Björn Pór Jónsson. 2010. uFLIP: Understanding the energy consumption of flash devices. Bulletin of the Technical Committee on Data Engineering 33, 4 (2010), 48--54.
[6]
Hung-Ching Chang, Erik Kruus, Thomas J Barnes, Abhishek R Agrawal, and Kirk W Cameron. 2012. Storage Power Optimizations for Client Devices and Data Centers. Intel Technology Journal 16, 3 (2012).
[7]
Seokhei Cho, Changhyun Park, Youjip Won, Sooyong Kang, Jaehyuk Cha, Sungroh Yoon, and Jongmoo Choi. 2015. Design tradeoffs of SSDs: From energy consumption's perspective. ACM Transactions on Storage (TOS) 11, 2 (2015), 1--24.
[8]
Intel Corporation. 2011. Designing Energy Efficient SATA Devices: Overview and Implementation Recommendations. https://www.intel.com/content/dam/doc/reference-guide/sata-devices-implementation-recommendations.pdf
[9]
Jeff Dean and Amin Vahdat. 2023. Exciting Directions for ML Models and the Implications for Computing Hardware. https://www.youtube.com/watch?v=EFe7-WZMMhc
[10]
Laura M Grupp, Adrian M Caulfield, Joel Coburn, Steven Swanson, Eitan Yaakobi, Paul H Siegel, and Jack K Wolf. 2009. Characterizing flash memory: Anomalies, observations, and applications. In Proceedings of the 42nd Annual IEEE/ACM International Symposium on Microarchitecture (MICRO'09). Association for Computing Machinery (ACM), New York, NY, USA.
[11]
Jonmichael Hands, Dennis Worley, and Lakhveer Kaur. 2022. Technology power features - NVM express. https://nvmexpressorg/resource/technology-power-features/
[12]
Bryan Harris and Nihat Altiparmak. 2020. Ultra-Low Latency SSDs' Impact on Overall Energy Efficiency. In Proceedings of the 12th USENIX Workshop on Hot Topics in Storage and File Systems (HotStorage'20). USENIX Association, Berkeley, CA, USA.
[13]
Bryan Harris and Nihat Altiparmak. 2022. When poll is more energy efficient than interrupt. In Proceedings of the 14th ACM Workshop on Hot Topics in Storage and File Systems (HotStorage '22). Association for Computing Machinery (ACM), New York, NY, USA.
[14]
Tianhang Huang, Tianyi Zhai, Xin Zhang, and Xiaomeng Di. 2021. Electric Power-grid Friendly Characteristic Data Center Energy Consumption Optimization Method. In Journal of Physics: Conference Series, Vol. 2095. IOP Publishing, 012026.
[15]
Anthony Hylick, Andrew Rice, Brian Jones, and Ripduman Sohan. 2007. Hard drive power consumption uncovered. SIGMETRICS Perform. Evaluation Rev. 35, 3 (2007), 54--55.
[16]
Anthony Hylick, Ripduman Sohan, Andrew Rice, and Brian Jones. 2008. An Analysis of Hard Drive Energy Consumption. In 2008 IEEE International Symposium on Modeling, Analysis and Simulation of Computers and Telecommunication Systems. IEEE Computer Society, Washington, DC, USA.
[17]
Intel. 2024. AHCI specification. https://www.intel.com/content/www/us/en/io/serial-ata/ahci.html
[18]
Shaohong Li, Xi Wang, Faria Kalim, Xiao Zhang, Sangeetha Abdu Jyothi, Karan Grover, Vasileios Kontorinis, Nina Narodytska, Owolabi Legunsen, Sreekumar Kodakara, et al. 2020. Thunderbolt: Throughput-Optimized, Quality-of-Service-Aware Power Capping at Scale. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI'20). USENIX Association, Berkeley, CA, USA.
[19]
Sulav Malla, Qingyuan Deng, Zoh Ebrahimzadeh, Joe Gasperetti, Sajal Jain, Parimala Kondety, Thiara Ortiz, and Debra Vieira. 2020. Coordinated priority-aware charging of distributed batteries in oversubscribed data centers. In Proceedings of the 53rd Annual IEEE/ACM International Symposium on Microarchitecture (MICRO'20). Association for Computing Machinery (ACM), New York, NY, USA.
[20]
Varun Mehra and Raiden Hasegawa. 2023. Supporting power grids with demand response at Google data centers. https://cloud.google.com/blog/products/infrastructure/using-demand-response-to-reduce-data-center-power-consumption
[21]
Vidyabhushan Mohan, Sudhanva Gurumurthi, and Mircea R Stan. 2010. FlashPower: A detailed power model for NAND flash memory. In 2010 Design, Automation & Test in Europe Conference & Exhibition (DATE'10). IEEE Computer Society, Washington, DC, USA.
[22]
Satadru Pan, Theano Stavrinos, Yunqiao Zhang, Atul Sikaria, Pavel Zakharov, Abhinav Sharma, Shiva Shankar, Mike Shuey, Richard Wareing, Monika Gangapuram, Guanglei Cao, Christian Preseau, Pratap Singh, Kestutis Patiejunas, JR Tipton, Ethan Katz-Bassett, and Wyatt Lloyd. 2021. Facebook's Tectonic Filesystem: Efficiency from Exascale. In Proceedings of the 19th USENIX Conference on File and Storage Technologies (FAST'21). USENIX Association, Berkeley, CA, USA.
[23]
Jinha Park, Sungjoo Yoo, Sunggu Lee, and Chanik Park. 2009. Power modeling of solid state disk for dynamic power management policy design in embedded systems. In Software Technologies for Embedded and Ubiquitous Systems: 7th IFIP WG 10.2 International Workshop. Springer, 24--35.
[24]
Samsung. 2012. Samsung SM843 Pro. https://www.compuram.biz/documents/datasheet/SM843_Datasheet.pdf
[25]
Samsung. 2017. Samsung SSD 960 EVO M.2. https://download.semiconductor.samsung.com/resources/data-sheet/Samsung_SSD_960_EVO_Data_Sheet_Rev_1_2.pdf
[26]
Samsung. 2017. Samsung V-NAND SSD 860 EVO. https://download.semiconductor.samsung.com/resources/data-sheet/Samsung_SSD_860_EVO_Data_Sheet_Rev1.pdf
[27]
Samsung. 2024. Samsung PM1743. https://semiconductor.samsung.com/us/ssd/enterprise-ssd/pm1743/
[28]
Euiseong Seo, Seon-Yeong Park, and Bhuvan Urgaonkar. 2008. Empirical Analysis on Energy Efficiency of Flash-based SSDs. In Proceedings of the 2008 USENIX Workshop on Power-Aware Computing and Systems (HotPower'08). USENIX Association, Berkeley, CA, USA.
[29]
Arman Shehabi, Sarah Smith, Dale Sartor, Richard Brown, Magnus Herrlin, Jonathan Koomey, Eric Masanet, Nathaniel Horner, Inês Azevedo, and William Lintner. 2016. United states data center energy usage report. (2016).
[30]
Seungyong Shin and Dongkun Shin. 2010. Power Consumption Characterization of Flash Memory SSD. In ICEIC: International Conference on Electronics, Informations and Communications. 14--18.
[31]
Sidharth Sundar, William Simpson, Jacob Higdon, Caeden Whitaker, Bryan Harris, and Nihat Altiparmak. 2023. Energy Implications of IO Interface Design Choices. In Proceedings of the 15th ACM Workshop on Hot Topics in Storage and File Systems (HotStorage '23). Association for Computing Machinery (ACM), New York, NY, USA.
[32]
Supermicro. 2024. Supermicro X13 for Storage. https://www.supermicro.com/en/products/x13
[33]
Billy Tallis. 2020. The Samsung 980 PRO PCIe 4.0 SSD Review: A Spirit of Hope. https://www.anandtech.com/show/16087/the-samsung-980-pro-pcie-4-ssd-review/8
[34]
Eno Thereska, Austin Donnelly, and Dushyanth Narayanan. 2011. Sierra: practical power-proportionality for data center storage. In Proceedings of the 6th European Conference on Computer Systems (EuroSys '11). Association for Computing Machinery (ACM), New York, NY, USA.
[35]
Luis Useche, Jorge Guerra, Medha Bhadkamkar, Mauricio Alarcon, and Raju Rangaswami. 2008. EXCES: External caching in energy saving storage systems. In Proceedings of the 2008 IEEE 14th International Symposium on High Performance Computer Architecture (HPCA'08). IEEE Computer Society, Washington, DC, USA.
[36]
Akshat Verma, Ricardo Koller, Luis Useche, and Raju Rangaswami. 2010. SRCMap: Energy Proportional Storage Using Dynamic Consolidation. In Proceedings of the 8th USENIX Conference on File and Storage Technologies (FAST'10). USENIX Association, Berkeley, CA, USA.
[37]
Charles Weddle, Mathew Oldham, Jin Qian, An-I Andy Wang, Peter Reiher, and Geoff Kuenning. 2007. PARAID: A gear-shifting power-aware RAID. ACM Transactions on Storage (TOS) 3, 3 (2007), 13-es.
[38]
Caeden Whitaker, Sidharth Sundar, Bryan Harris, and Nihat Altiparmak. 2023. Do we still need IO schedulers for low-latency disks?. In Proceedings of the 15th ACM Workshop on Hot Topics in Storage and File Systems (HotStorage '23). Association for Computing Machinery (ACM), New York, NY, USA.
[39]
Qiang Wu, Qingyuan Deng, Lakshmi Ganesh, Chang-Hong Hsu, Yun Jin, Sanjeev Kumar, Bin Li, Justin Meza, and Yee Jiun Song. 2016. Dynamo: Facebook's data center-wide power management system. ACM SIGARCH Computer Architecture News 44, 3 (2016), 469--480.
[40]
Jiali Xing, Bilge Acun, Aditya Sundarrajan, David Brooks, Manoj Chakkaravarthy, Nikky Avila, Carole-Jean Wu, and Benjamin C Lee. 2023. Carbon Responder: Coordinating Demand Response for the Datacenter Fleet. arXiv preprint arXiv:2311.08589 (2023).
[41]
Balgeun Yoo, Youjip Won, Seokhei Cho, Sooyong Kang, Jongmoo Choi, and Sungroh Yoon. 2011. SSD Characterization: From Energy Consumption's Perspective. In Proceedings of the 3rd USENIX Workshop on Hot Topics in Storage and File Systems (HotStorage'11). USENIX Association, Berkeley, CA, USA.
[42]
Jie Zhang, Mustafa Shihab, and Myoungsoo Jung. 2014. Power, Energy, and Thermal Considerations in SSD-Based I/O Acceleration. In Proceedings of the 6th USENIX Workshop on Hot Topics in Storage and File Systems (HotStorage'14) USENIX Association, Berkeley, CA, USA.
[43]
Mark Zhao, Niket Agarwal, Aarti Basant, Buğra Gedik, Satadru Pan, Mustafa Ozdal, Rakesh Komuravelli, Jerry Pan, Tianshu Bao, Haowei Lu, et al. 2022. Understanding data storage and ingestion for large-scale deep recommendation model training: Industrial product. In Proceedings of the 49th Annual International Symposium on Computer Architecture (ISCA'22). Association for Computing Machinery (ACM), New York, NY, USA.
[44]
Mark Zhao, Satadru Pan, Niket Agarwal, Zhaoduo Wen, David Xu, Anand Natarajan, Pavan Kumar, Ritesh Tijoriwala, Karan Asher, Hao Wu, et al. 2023. Tectonic-Shift: A Composite Storage Fabric for Large-Scale ML Training. In 2023 USENIX Annual Technical Conference (USENIX ATC'23). USENIX Association, Berkeley, CA, USA.
Index Terms
- Can Storage Devices be Power Adaptive?
Recommendations
Joint optimization of idle and cooling power in data centers while maintaining response time
ASPLOS '10Server power and cooling power amount to a significant fraction of modern data centers' recurring costs. While data centers provision enough servers to guarantee response times under the maximum loading, data centers operate under much less loading most ...
Joint optimization of idle and cooling power in data centers while maintaining response time
ASPLOS '10Server power and cooling power amount to a significant fraction of modern data centers' recurring costs. While data centers provision enough servers to guarantee response times under the maximum loading, data centers operate under much less loading most ...
Joint optimization of idle and cooling power in data centers while maintaining response time
ASPLOS XV: Proceedings of the fifteenth International Conference on Architectural support for programming languages and operating systemsServer power and cooling power amount to a significant fraction of modern data centers' recurring costs. While data centers provision enough servers to guarantee response times under the maximum loading, data centers operate under much less loading most ...
Comments
Information & Contributors
Information
Published In
July 2024
141 pages
ISBN:9798400706301
DOI:10.1145/3655038
Copyright © 2024 Owner/Author.
This work is licensed under a Creative Commons Attribution International 4.0 License.
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 08 July 2024
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Funding Sources
- NSF
Conference
HOTSTORAGE '24
Sponsor:
HOTSTORAGE '24: 16th ACM Workshop on Hot Topics in Storage and File Systems
July 8 - 9, 2024
CA, Santa Clara, USA
Acceptance Rates
Overall Acceptance Rate 34 of 87 submissions, 39%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 234Total Downloads
- Downloads (Last 12 months)234
- Downloads (Last 6 weeks)103
Reflects downloads up to 15 Sep 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in