skip to main content
10.1145/2168836.2168845acmconferencesArticle/Chapter ViewAbstractPublication PageseurosysConference Proceedingsconference-collections
research-article

Frugal storage for cloud file systems

Published:10 April 2012Publication History

ABSTRACT

Enterprises are moving their IT infrastructure to cloud service providers with the goal of saving costs and simplifying management overhead. One of the critical services for any enterprise is its file system, where users require real-time access to files. Cloud service providers provide several building blocks such as Amazon EBS, or Azure Cache, each with very different pricing structures that differ on the basis of storage, access and bandwidth costs. Moving an entire file system to the cloud using such services is not cost-optimal if we rely on only one of these services. In this paper, we propose FCFS, a storage solution that drastically reduces the cost of operating a file system in the cloud. Our solution integrates multiple storage services and dynamically adapts the storage volume sizes of each service to provide a cost-efficient solution with provable performance bounds. Using real-world large scale data sets spanning a variety of work loads from an enterprise data center, we show that FCFS can reduce file storage and access costs in current cloud services by a factor of two or more, while allowing users to utilize the benefits of the various cloud storage services.

References

  1. Amazon. EBS to S3 Snapshot Block Size. https://forums.aws.amazon.com/message.jspa?messageID =142082.Google ScholarGoogle Scholar
  2. Amazon. Elastic block store. http://aws.amazon.com/ebs/.Google ScholarGoogle Scholar
  3. Amazon. Elasticache. http://aws.amazon.com/elasticache/.Google ScholarGoogle Scholar
  4. Amazon. Simple storage service faqs. http://aws.amazon.com/s3/faqs/.Google ScholarGoogle Scholar
  5. Azure. Caching service. http://msdn.microsoft.com/en-us/library/windowsazure/gg278356.aspx.Google ScholarGoogle Scholar
  6. S.-H. Gary Chan and F. A. Tobagi. Modeling and dimensioning hierarchical storage systems for low-delay video services. IEEE Transactions on Computers, 52, July 2003. Google ScholarGoogle ScholarDigital LibraryDigital Library
  7. D. Isaac. Hierarchical storage management for relational databases. In Symposium on Mass Storage Systems, 1993.Google ScholarGoogle ScholarCross RefCross Ref
  8. A. Karlin, M. Manasse, L. McGeoch, and S. Owicki. Competitive randomized algorithms for non-uniform problems. In Proc. of ACM-SIAM Symposium on Discrete Algorithms (SODA), 1990. Google ScholarGoogle ScholarDigital LibraryDigital Library
  9. A. W. Leung, S. Pasupathy, G. Goodson, and E. L. Miller. Measurement and analysis of large-scale network file system workloads. In Proc. of the USENIX (ATC) Annual Technical Conference, 2008. Google ScholarGoogle ScholarDigital LibraryDigital Library
  10. N. Megiddo and D. Modha. Arc: A self-tuning,. low overhead replacement cache. In Proceedings of the USENIX Conference on (FAST) File and Storage Technologies, 2003. Google ScholarGoogle ScholarDigital LibraryDigital Library
  11. D. Narayanan, A. Donnelly, and A. Rowstron. MSR Cambridge Traces. http://iotta.snia.org/traces/388.Google ScholarGoogle Scholar
  12. D. Narayanan, A. Donnelly, and A. Rowstron. Write off-loading: practical power management for enterprise storage. In Proceedings of the USENIX Conference on (FAST) File and Storage Technologies, 2008. Google ScholarGoogle ScholarDigital LibraryDigital Library
  13. S3-EBS. Amazon's Elastic Block Store explained. http://blog.rightscale.com/2008/08/20/amazon-ebs-explained/.Google ScholarGoogle Scholar
  14. S3Backer. FUSE-based single file backing store via Amazon S3. http://code.google.com/p/s3backer/wiki/ChoosingBlockSize.Google ScholarGoogle Scholar
  15. Wikipedia. Hierarchical storage management. http://en.wikipedia.org/wiki/Hierarchical_storage_management.Google ScholarGoogle Scholar
  16. J. Wilkes, R. Golding, C. Staelin, and T. Sullivan. The hp autoraid hierarchical storage system. ACM Transactions on Computer Systems, 14, Feb 1996. Google ScholarGoogle ScholarDigital LibraryDigital Library

Index Terms

  1. Frugal storage for cloud file systems

    Recommendations

    Reviews

    David Bruce Henderson

    Typical modern physical storage systems have a hierarchy of several tiers of storage, with data moving automatically between the various tiers depending on the frequency of access to the data. Fast but expensive storage is used for data that needs to be accessed quickly and frequently, while slower but less expensive storage is used for data that doesn't experience frequent access. The authors of this paper have developed a framework for applying this hierarchical storage strategy to cloud storage services. The authors present a short introduction to hierarchical storage, summarize related works, and then make their proposition. Basically, they contend that significant cost advantages can be achieved through a hierarchical structuring of multiple cloud storage offerings with different cost/performance characteristics. They present their frugal cloud file system (FCFS) as a solution and demonstrate its effectiveness using the pricing of Amazon's cloud service offerings. Cloud-based storage has a significant advantage over physical storage alternatives in that the size of the various tiers of storage can be dynamic rather than fixed. The proposed solution integrates multiple storage services and dynamically adapts the storage volume sizes of each service to improve cost effectiveness. The paper explains the solution at a high level, illustrated with graphs and figures. The authors then lay out their dynamic storage framework and two schemes for determining when and how to dynamically move data between the different storage tiers. The authors provide the results of simulations using real-life disk traces from a medium-sized data center to support their claims of cost effectiveness. The paper is supported by figures and associated cost examples that will be useful to those actively considering cloud storage as a strategic solution. A tiered hierarchical strategy for cloud storage seems intuitively to be a winner, just as hierarchical tiered physical storage was before it. All that is needed now is for someone to offer FCFS as a cloud service. Online Computing Reviews Service

    Michael G. Murphy

    As more and more enterprises look to cloud storage to meet their data storage needs at a lower cost of operation, this issue is of important practical significance. In this paper, Puttaswamy et al. address cost-effective cloud storage. They propose a frugal cloud file system (FCFS), a storage management application designed to reduce operating costs in the cloud. Specific comparisons are made to Amazon's Elastic Block Store (EBS), Simple Storage Service (S3), and ElastiCache, which represent of a variety of cloud storage options. The major tradeoff is between storage and access costs. Dynamically managing this tradeoff with products that emphasize one factor or the other offers significant overall cost savings. The first section provides a conceptual introduction, a summary of related work, and the authors' view of what this paper contributes to the field. Subsequent sections provide a motivating framework for dynamic storage; a careful description of FCFS; cost optimization algorithms, including cost analysis; experimental design and the nature of the real-life traces used; an evaluation of the results; and concluding thoughts. Twelve figures, three tables, and pseudocode for block reads in FCFS effectively complement the text. The paper is interesting and insightful within the constraints noted by the authors. It will be interesting to see whether significant contributions based on actual implementations are made to the literature on cloud storage, since such a report tends to become a postmortem after the technology moves forward and the older technology has lost its proprietary advantage. Online Computing Reviews Service

    Access critical reviews of Computing literature here

    Become a reviewer for Computing Reviews.

    Comments

    Login options

    Check if you have access through your login credentials or your institution to get full access on this article.

    Sign in
    • Published in

      cover image ACM Conferences
      EuroSys '12: Proceedings of the 7th ACM european conference on Computer Systems
      April 2012
      394 pages
      ISBN:9781450312233
      DOI:10.1145/2168836

      Copyright © 2012 ACM

      Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      • Published: 10 April 2012

      Permissions

      Request permissions about this article.

      Request Permissions

      Check for updates

      Qualifiers

      • research-article

      Acceptance Rates

      Overall Acceptance Rate241of1,308submissions,18%

      Upcoming Conference

      EuroSys '24
      Nineteenth European Conference on Computer Systems
      April 22 - 25, 2024
      Athens , Greece

    PDF Format

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader