Chapter Four - State of the Art on Technology and Practices for Improving the Energy Efficiency of Data Storage
Introduction
Information is at the core of any business, but storing and making available all the information required to run today’s businesses have become real challenges. With the storage needs of organizations expected to grow by a factor of 44 between 2010 and 2020 [1], efficiency has never been so popular. The constant fall in the price per GB of storage led to a scenario where it is simpler and less costly to add extra capacity than to look for alternatives to avoid data duplicates and minimize other inefficiencies.
As the cost of powering and cooling storage resources becomes an issue, inefficiencies are no longer accepted. Studies show that large enterprises are currently faced with the difficult task of providing sufficient power and cooling capacity, while midsize companies are challenged with finding enough floor space for their storage systems. As data storage accounts for a large part of the energy consumed by data centers, it is crucial to make storage systems more energy efficient and to choose the appropriate solutions when deploying storage infrastructure.
This chapter discusses technologies that improve the energy efficiency of data storage solutions. Moreover, it describes best practices that—in addition to the use of the discussed technologies—can improve the energy efficiency of storage infrastructure in enterprises and data centers.
Section snippets
Taxonomy of Data Storage Solutions
With the goal of providing reproducible and standardized assessment of the energy efficiency of storage solutions, the SNIA has created the SNIA Emerald Power Efficiency Measurement specification [2]. As part of the specification, SNIA has proposed a taxonomy for storage products to ease the evaluation of energy efficiency of different storage equipments and allow comparisons among devices produced by different manufacturers. This taxonomy, which has been adapted by the ENERGY STAR program [3],
Device-level Solutions
This section describes energy-efficient solutions that operate at the device level. We also describe tape-based systems as a device-level approach, though they are often solution aggregates as tapes appear as an alternative to technology that relies either on hard disk drives of solid-state drives.
Solutions for Storage Elements
As discussed earlier, we adopt SNIA’s terminology to discuss and assess storage solutions. In earlier sections, we analyzed the existing solutions for improving the energy efficiency of individual storage components (i.e., storage devices) such as hard disk drives and solid-state drives. The next sections assess how these device-level techniques are used and combined to improve the energy efficiency of composite storage solutions such as disk arrays, direct attached storage, and networked
Recommendations for Best Practices
This section provides an overview of best practices adopted to reduce the power consumption and improve the energy efficiency of storage resources in enterprises and data centers. The SNIA and NetApp, for example, have released recommendations that describe best practices for data storage in data centers [42], [32], [36]. The best practices for improving energy efficiency frequently revolve around some principles that are described in this section. There are other techniques, however, which
Community Efforts and Benchmarks
Manufacturers of storage equipment generally use the power consumption under idle state to indicate that a specific power-efficient solution saves energy when compared to a non-efficient counterpart. Actual energy savings are, however, highly dependent on the application workloads and the data-management policies in place. Some metrics take into account performance factors such as data throughput and the energy footprint of centers that use the equipments. Some metrics often found in the
Conclusions
This chapter discussed the state of the art on techniques and best practices for improving the energy efficiency of data storage solutions. Current techniques for improving energy efficiency of storage solutions act mainly at two levels, namely the level of individual devices and at the level of storage elements such as disk arrays and storage area network equipment.
The efficiency of most solutions available for storage elements is highly dependent on the application workloads under which they
Acknowledgement
The work presented in this chapter has been supported by the PrimeEnergyIT project (an European project financially supported by the Intelligent Energy in Europe program).
Marcos Dias de Assunção is a researcher at IBM Research Brazil, in Sao Paulo. He obtained a Ph.D. in Computer Science and Software Engineering (2009) from the University of Melbourne, Australia, and a M.Sc. (2004) from the Federal University of Santa Catarina in Florianopolis, Brazil. Prior to joining IBM Research, he was a postdoctoral researcher at INRIA Lyon, in France, working on energy efficiency for large-scale distributed systems such as Grids and Clouds. His current topics of interest
References (44)
- J. Gantz, D. Reinsel, The digital universe decade—are you ready?, IDC iVIEW, May...
- SNIA Emerald power efficiency measurement specification, SNIA Green Storage Initiative, August...
- ENERGY, STAR program requirements for data center storage, draft 1, ENERGY STAR, PROGRAM,...
- Consolidate storage infrastructure and create a greener datacenter, White paper, Oracle, April...
- Power and Cost Efficient Data Storage, Hie Electronics, Inc. (2012)...
- User guide for the SNIA Emerald power efficiency measurement spec, SNIA Green Storage Initiative, October...
- D. Reine, M. Kahn, Disk and tape square off again—tape remains king of the hill with lto-4, Clipper...
- Consolidate storage infrastructure and create a greener datacenter, Oracle White Paper, April...
- E. Otoo, D. Rotem, S. Tsao, Analysis of trade-off between power saving and response time in disk storage systems, in:...
- Seagate PowerChoice technology provides unprecedented hard drive power savings and flexibility, Technology Paper,...
eRAID: Conserving energy in conventional disk-based RAID system
IEEE Transactions on Computers
Cited by (1)
Marcos Dias de Assunção is a researcher at IBM Research Brazil, in Sao Paulo. He obtained a Ph.D. in Computer Science and Software Engineering (2009) from the University of Melbourne, Australia, and a M.Sc. (2004) from the Federal University of Santa Catarina in Florianopolis, Brazil. Prior to joining IBM Research, he was a postdoctoral researcher at INRIA Lyon, in France, working on energy efficiency for large-scale distributed systems such as Grids and Clouds. His current topics of interest include Cloud computing, workload migration to Clouds and analytics services.
Dr Laurent Leèvre obtained his Ph.D. in Computer Science in January 1997 at LIP Laboratory (Laboratoire Informatique du Parallélisme) in ENS-Lyon (Ecole Normale Supérieure), France. From 1997 to 2001, he was assistant professor in computer science in Lyon 1 University. Since 2001, he is a permanent researcher in computer science at INRIA (the French Institute for Research in Computer Science and Control). He is a member of the RESO team (High Performance Networks, Protocols and Services) from the LIP laboratory in Lyon, France. He has organized several conferences in high performance networking and computing and he is a member of several program committees. He has co-authored more than 100 papers published in refereed journals and conference proceedings. He is a member of IEEE and takes part in several research projects. His research interests include: distributed computing and networking, Green and Energy Efficient Computing and Networking, autonomic networking, high performance networks protocols and services.