%%% -*-BibTeX-*-
%%% ====================================================================
%%% BibTeX-file{
%%%     author          = "Nelson H. F. Beebe",
%%%     version         = "1.22",
%%%     date            = "01 April 2014",
%%%     time            = "06:00:38 MDT",
%%%     filename        = "tos.bib",
%%%     address         = "University of Utah
%%%                        Department of Mathematics, 110 LCB
%%%                        155 S 1400 E RM 233
%%%                        Salt Lake City, UT 84112-0090
%%%                        USA",
%%%     telephone       = "+1 801 581 5254",
%%%     FAX             = "+1 801 581 4148",
%%%     URL             = "http://www.math.utah.edu/~beebe",
%%%     checksum        = "53158 6170 32361 309431",
%%%     email           = "beebe at math.utah.edu, beebe at acm.org,
%%%                        beebe at computer.org (Internet)",
%%%     codetable       = "ISO/ASCII",
%%%     keywords        = "bibliography; BibTeX; ACM Transactions on
%%%                        Storage; TOS",
%%%     license         = "public domain",
%%%     supported       = "yes",
%%%     docstring       = "This is a COMPLETE BibTeX bibliography for
%%%                        ACM Transactions on Storage (CODEN ????, ISSN
%%%                        1553-3077 (print), 1553-3093 (electronic)),
%%%                        completely covering all issues from volume 1,
%%%                        number 1, February 2005 to date.
%%%
%%%                        The ACM maintains World Wide Web pages with
%%%                        journal tables of contents for 2005--date at
%%%
%%%                            http://www.acm.org/tos/
%%%                            http://www.acm.org/pubs/contents/journals/tos/
%%%                            http://portal.acm.org/browse_dl.cfm?idx=J960
%%%
%%%                        That data has been automatically converted to
%%%                        BibTeX form, corrected for spelling and page
%%%                        number errors, and merged into this file.
%%%
%%%                        At version 1.22, the COMPLETE year coverage
%%%                        looks like this:
%%%
%%%                             2005 (  17)    2009 (  21)    2013 (  14)
%%%                             2006 (  18)    2010 (  14)    2014 (   8)
%%%                             2007 (  13)    2011 (  14)
%%%                             2008 (  15)    2012 (  18)
%%%
%%%                             Article:        152
%%%
%%%                             Total entries:  152
%%%
%%%                        Spelling has been verified with the UNIX
%%%                        spell and GNU ispell programs using the
%%%                        exception dictionary stored in the companion
%%%                        file with extension .sok.
%%%
%%%                        ACM copyrights explicitly permit abstracting
%%%                        with credit, so article abstracts, keywords,
%%%                        and subject classifications have been
%%%                        included in this bibliography wherever
%%%                        available.  Article reviews have been
%%%                        omitted, until their copyright status has
%%%                        been clarified.
%%%
%%%                        bibsource keys in the bibliography entries
%%%                        below indicate the entry originally came
%%%                        from the computer science bibliography
%%%                        archive, even though it has likely since
%%%                        been corrected and updated.
%%%
%%%                        URL keys in the bibliography point to
%%%                        World Wide Web locations of additional
%%%                        information about the entry.
%%%
%%%                        BibTeX citation tags are uniformly chosen
%%%                        as name:year:abbrev, where name is the
%%%                        family name of the first author or editor,
%%%                        year is a 4-digit number, and abbrev is a
%%%                        3-letter condensation of important title
%%%                        words. Citation tags were automatically
%%%                        generated by software developed by the
%%%                        author for the BibNet Project.
%%%
%%%                        In this bibliography, entries are sorted
%%%                        by journal, and then by publication order,
%%%                        with the help of ``bibsort -byvolume''.  The
%%%                        bibsort utility is available from
%%%                        ftp://ftp.math.utah.edu/pub/tex/bib.
%%%
%%%                        The author will be grateful for reports of
%%%                        errors of any kind in this bibliography.
%%%
%%%                        The checksum field above contains a CRC-16
%%%                        checksum as the first value, followed by the
%%%                        equivalent of the standard UNIX wc (word
%%%                        count) utility output of lines, words, and
%%%                        characters.  This is produced by Robert
%%%                        Solovay's checksum utility."
%%%     }
%%% ====================================================================

@Preamble{"\input bibnames.sty" #
   "\hyphenation{
   }" #
   "\ifx \undefined \circled \def \circled #1{(#1)}\fi" #
   "\ifx \undefined \reg \def \reg {\circled{R}}\fi"
}

%%% ====================================================================
%%% Acknowledgement abbreviations:

@String{ack-nhfb = "Nelson H. F. Beebe,
                    University of Utah,
                    Department of Mathematics, 110 LCB,
                    155 S 1400 E RM 233,
                    Salt Lake City, UT 84112-0090, USA,
                    Tel: +1 801 581 5254,
                    FAX: +1 801 581 4148,
                    e-mail: \path|beebe@math.utah.edu|,
                            \path|beebe@acm.org|,
                            \path|beebe@computer.org| (Internet),
                    URL: \path|http://www.math.utah.edu/~beebe/|"}

%%% ====================================================================
%%% Journal abbreviations:

@String{j-TOS                   = "ACM Transactions on Storage"}

%%% ====================================================================
%%% Bibliography entries sorted in publication order:

@Article{Rajan:2005:E,
  author =       "Sreeranga P. Rajan",
  title =        "Editorial",
  journal =      j-TOS,
  volume =       "1",
  number =       "1",
  pages =        "1--2",
  month =        feb,
  year =         "2005",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Thu Apr 14 12:33:44 MDT 2005",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Yu:2005:CAR,
  author =       "Haifeng Yu and Amin Vahdat",
  title =        "Consistent and automatic replica regeneration",
  journal =      j-TOS,
  volume =       "1",
  number =       "1",
  pages =        "3--37",
  month =        feb,
  year =         "2005",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Thu Apr 14 12:33:44 MDT 2005",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Huang:2005:CRK,
  author =       "Andrew C. Huang and Armando Fox",
  title =        "Cheap recovery: a key to self-managing state",
  journal =      j-TOS,
  volume =       "1",
  number =       "1",
  pages =        "38--70",
  month =        feb,
  year =         "2005",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Thu Apr 14 12:33:44 MDT 2005",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Ellard:2005:DPE,
  author =       "Daniel Ellard and James Megquier",
  title =        "{DISP}: {Practical}, efficient, secure and
                 fault-tolerant distributed data storage",
  journal =      j-TOS,
  volume =       "1",
  number =       "1",
  pages =        "71--94",
  month =        feb,
  year =         "2005",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Thu Apr 14 12:33:44 MDT 2005",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Hughes:2005:RSR,
  author =       "Gordon F. Hughes and Joseph F. Murray",
  title =        "Reliability and security of {RAID} storage systems and
                 {D2D} archives using {SATA} disk drives",
  journal =      j-TOS,
  volume =       "1",
  number =       "1",
  pages =        "95--107",
  month =        feb,
  year =         "2005",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Thu Apr 14 12:33:44 MDT 2005",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Wu:2005:TRL,
  author =       "Changxun Wu and Randal Burns",
  title =        "Tunable randomization for load management in
                 shared-disk clusters",
  journal =      j-TOS,
  volume =       "1",
  number =       "1",
  pages =        "108--131",
  month =        feb,
  year =         "2005",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Thu Apr 14 12:33:44 MDT 2005",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Sivathanu:2005:ISS,
  author =       "Muthian Sivathanu and Vijayan Prabhakaran and Andrea
                 C. Arpaci-Dusseau and Remzi H. Arpaci-Dusseau",
  title =        "Improving storage system availability with {D-GRAID}",
  journal =      j-TOS,
  volume =       "1",
  number =       "2",
  pages =        "133--170",
  month =        may,
  year =         "2005",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1063786.1063787",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Thu Jul 7 13:56:40 MDT 2005",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Jiang:2005:NFS,
  author =       "Anxiao (Andrew) Jiang and Jehoshua Bruck",
  title =        "Network file storage with graceful performance
                 degradation",
  journal =      j-TOS,
  volume =       "1",
  number =       "2",
  pages =        "171--189",
  month =        may,
  year =         "2005",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1063786.1063788",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Thu Jul 7 13:56:40 MDT 2005",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Peterson:2005:ETS,
  author =       "Zachary Peterson and Randal Burns",
  title =        "{Ext3cow}: a time-shifting file system for regulatory
                 compliance",
  journal =      j-TOS,
  volume =       "1",
  number =       "2",
  pages =        "190--212",
  month =        may,
  year =         "2005",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1063786.1063789",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Thu Jul 7 13:56:40 MDT 2005",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  URL =          "http://hssl.cs.jhu.edu/~zachary/papers/peterson-tos05.pdf",
  abstract =     "The ext3cow file system, built on the popular ext3
                 file system, provides an open-source file versioning
                 and snapshot platform for compliance with the
                 versioning and auditability requirements of recent
                 electronic record retention legislation. Ext3cow
                 provides a time-shifting interface that permits a
                 real-time and continuous view of data in the past.
                 Time-shifting does not pollute the file system
                 namespace nor require snapshots to be mounted as a
                 separate file system. Further, ext3cow is implemented
                 entirely in the file system space and, therefore, does
                 not modify kernel interfaces or change the operation of
                 other file systems. Ext3cow takes advantage of the
                 fine-grained control of on-disk and in-memory data
                 available only to a file system, resulting in minimal
                 degradation of performance and functionality.
                 Experimental results confirm this hypothesis; ext3cow
                 performs comparably to ext3 on many benchmarks and on
                 trace-driven experiments.",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Li:2005:MBC,
  author =       "Zhenmin Li and Zhifeng Chen and Yuanyuan Zhou",
  title =        "Mining block correlations to improve storage
                 performance",
  journal =      j-TOS,
  volume =       "1",
  number =       "2",
  pages =        "213--245",
  month =        may,
  year =         "2005",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1063786.1063790",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Thu Jul 7 13:56:40 MDT 2005",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Garg:2005:BDD,
  author =       "Nitin Garg and Sumeet Sobti and Junwen Lai and
                 Fengzhou Zheng and Kai Li and Randolph Y. Wang and
                 Arvind Krishnamurthy",
  title =        "Bridging the digital divide: storage media $+$ postal
                 network $=$ generic high-bandwidth communication",
  journal =      j-TOS,
  volume =       "1",
  number =       "2",
  pages =        "246--275",
  month =        may,
  year =         "2005",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1063786.1063791",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Thu Jul 7 13:56:40 MDT 2005",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Making high-bandwidth Internet access pervasively
                 available to a large worldwide audience is a difficult
                 challenge, especially in many developing regions. As we
                 wait for the uncertain takeoff of technologies that
                 promise to improve the situation, we propose to explore
                 an approach that is potentially more easily realizable:
                 the use of digital storage media transported by the
                 postal system as a general digital communication
                 mechanism. We shall call such a system a Postmanet.
                 Compared to more conventional wide-area connectivity
                 options, the Postmanet has several important
                 advantages, including wide global reach, great
                 bandwidth potential, low cost, and ease of incremental
                 adoption. While the idea of sending digital content via
                 the postal system is not a new one, none of the
                 existing attempts have turned the postal system into a
                 generic and transparent communication channel that not
                 only can cater to a wide array of applications, but
                 also effectively manage the many idiosyncrasies
                 associated with using the postal system. In the
                 proposed Postmanet, we see two recurring themes at many
                 different levels of the system. One is the simultaneous
                 exploitation of the Internet and the postal system so
                 we can combine their latency and bandwidth advantages.
                 The other is the exploitation of the abundant capacity
                 and bandwidth of the Postmanet to improve its latency,
                 cost, and reliability.",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Ganesan:2005:MSS,
  author =       "Deepak Ganesan and Ben Greenstein and Deborah Estrin
                 and John Heidemann and Ramesh Govindan",
  title =        "Multiresolution storage and search in sensor
                 networks",
  journal =      j-TOS,
  volume =       "1",
  number =       "3",
  pages =        "277--315",
  month =        aug,
  year =         "2005",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Sep 17 15:49:46 MDT 2005",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Seo:2005:EDR,
  author =       "Beomjoo Seo and Roger Zimmermann",
  title =        "Efficient disk replacement and data migration
                 algorithms for large disk subsystems",
  journal =      j-TOS,
  volume =       "1",
  number =       "3",
  pages =        "316--345",
  month =        aug,
  year =         "2005",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Sep 17 15:49:46 MDT 2005",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Li:2005:PDE,
  author =       "Xiaodong Li and Zhenmin Li and Yuanyuan Zhou and
                 Sarita Adve",
  title =        "Performance directed energy management for main memory
                 and disks",
  journal =      j-TOS,
  volume =       "1",
  number =       "3",
  pages =        "346--380",
  month =        aug,
  year =         "2005",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Sep 17 15:49:46 MDT 2005",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Chang:2005:EML,
  author =       "Li-Pin Chang and Tei-Wei Kuo",
  title =        "Efficient management for large-scale flash-memory
                 storage systems with resource conservation",
  journal =      j-TOS,
  volume =       "1",
  number =       "4",
  pages =        "381--418",
  month =        nov,
  year =         "2005",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Fri May 26 08:38:08 MDT 2006",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Anastasiadis:2005:SFT,
  author =       "Stergios V. Anastasiadis and Kenneth C. Sevcik and
                 Michael Stumm",
  title =        "Scalable and fault-tolerant support for variable
                 bit-rate data in the {Exedra} streaming server",
  journal =      j-TOS,
  volume =       "1",
  number =       "4",
  pages =        "419--456",
  month =        nov,
  year =         "2005",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Fri May 26 08:38:08 MDT 2006",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Karlsson:2005:TPD,
  author =       "Magnus Karlsson and Christos Karamanolis and Xiaoyun
                 Zhu",
  title =        "{Triage}: Performance differentiation for storage
                 systems using adaptive control",
  journal =      j-TOS,
  volume =       "1",
  number =       "4",
  pages =        "457--480",
  month =        nov,
  year =         "2005",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Fri May 26 08:38:08 MDT 2006",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Hong:2006:UMBa,
  author =       "Bo Hong and Feng Wang and Scott A. Brandt and Darrell
                 D. E. Long and Thomas J. E. Schwarz and S. J.",
  title =        "Using {MEMS}-based storage in computer
                 systems---{MEMS} storage architectures",
  journal =      j-TOS,
  volume =       "2",
  number =       "1",
  pages =        "1--21",
  month =        feb,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Wed Aug 23 05:41:22 MDT 2006",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Hsieh:2006:EIH,
  author =       "Jen-Wei Hsieh and Tei-Wei Kuo and Li-Pin Chang",
  title =        "Efficient identification of hot data for flash memory
                 storage systems",
  journal =      j-TOS,
  volume =       "2",
  number =       "1",
  pages =        "22--40",
  month =        feb,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Wed Aug 23 05:41:22 MDT 2006",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Gurumurthi:2006:TID,
  author =       "Sudhanva Gurumurthi and Anand Sivasubramaniam",
  title =        "Thermal issues in disk drive design: Challenges and
                 possible solutions",
  journal =      j-TOS,
  volume =       "2",
  number =       "1",
  pages =        "41--73",
  month =        feb,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Wed Aug 23 05:41:22 MDT 2006",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Wright:2006:VUS,
  author =       "Charles P. Wright and Jay Dave and Puja Gupta and
                 Harikesavan Krishnan and David P. Quigley and Erez
                 Zadok and Mohammad Nayyer Zubair",
  title =        "Versatility and {Unix} semantics in namespace
                 unification",
  journal =      j-TOS,
  volume =       "2",
  number =       "1",
  pages =        "74--105",
  month =        feb,
  year =         "2006",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1138041.1138045",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Wed Aug 23 05:41:22 MDT 2006",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Administrators often prefer to keep related sets of
                 files in different locations or media, as it is easier
                 to maintain them separately. Users, however, prefer to
                 see all files in one location for convenience. One
                 solution that accommodates both needs is virtual
                 namespace unification---providing a merged view of
                 several directories without physically merging them.
                 For example, namespace unification can merge the
                 contents of several CD-ROM images without unpacking
                 them, merge binary directories from different packages,
                 merge views from several file servers, and more.
                 Namespace unification can also enable snapshotting by
                 marking some data sources read-only and then utilizing
                 copy-on-write for the read-only sources. For example,
                 an OS image may be contained on a read-only CD-ROM
                 image---and the user's configuration, data, and
                 programs could be stored in a separate read-write
                 directory. With copy-on-write unification, the user
                 need not be concerned about the two disparate file
                 systems. It is difficult to maintain Unix semantics
                 while offering a versatile namespace unification
                 system. Past efforts to provide such unification often
                 compromised on the set of features provided or Unix
                 compatibility---resulting in an incomplete solution
                 that users could not use. We designed and implemented a
                 versatile namespace unification system called Unionfs.
                 Unionfs maintains Unix semantics while offering
                 advanced namespace unification features: dynamic
                 insertion and removal of namespaces at any point in the
                 merged view, mixing read-only and read-write
                 components, efficient in-kernel duplicate elimination,
                 NFS interoperability, and more. Since releasing our
                 Linux implementation, it has been used by thousands of
                 users and over a dozen Linux distributions, which
                 helped us discover and solve many practical problems.",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Mykletun:2006:AIO,
  author =       "Einar Mykletun and Maithili Narasimha and Gene
                 Tsudik",
  title =        "Authentication and integrity in outsourced databases",
  journal =      j-TOS,
  volume =       "2",
  number =       "2",
  pages =        "107--138",
  month =        may,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Wed Aug 23 05:41:22 MDT 2006",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Hong:2006:UMBb,
  author =       "Bo Hong and Scott A. Brandt and Darrell D. E. Long and
                 Ethan L. Miller and Ying Lin",
  title =        "Using {MEMS}-based storage in computer
                 systems---device modeling and management",
  journal =      j-TOS,
  volume =       "2",
  number =       "2",
  pages =        "139--160",
  month =        may,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Wed Aug 23 05:41:22 MDT 2006",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Zadok:2006:IFS,
  author =       "Erez Zadok and Rakesh Iyer and Nikolai Joukov and
                 Gopalan Sivathanu and Charles P. Wright",
  title =        "On incremental file system development",
  journal =      j-TOS,
  volume =       "2",
  number =       "2",
  pages =        "161--196",
  month =        may,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Wed Aug 23 05:41:22 MDT 2006",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Sugahara:2006:SMB,
  author =       "Satoshi Sugahara and Masaaki Tanaka",
  title =        "Spin {MOSFETs} as a basis for spintronics",
  journal =      j-TOS,
  volume =       "2",
  number =       "2",
  pages =        "197--219",
  month =        may,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Wed Aug 23 05:41:22 MDT 2006",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Vazhkudai:2006:CCD,
  author =       "Sudharshan S. Vazhkudai and Xiaosong Ma and Vincent W.
                 Freeh and Jonathan W. Strickland and Nandan Tammineedi
                 and Tyler Simon and Stephen L. Scott",
  title =        "Constructing collaborative desktop storage caches for
                 large scientific datasets",
  journal =      j-TOS,
  volume =       "2",
  number =       "3",
  pages =        "221--254",
  month =        aug,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Apr 14 11:04:31 MDT 2007",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Won:2006:ISC,
  author =       "Youjip Won and Hyungkyu Chang and Jaemin Ryu and
                 Yongdai Kim and Junseok Shim",
  title =        "Intelligent storage: Cross-layer optimization for soft
                 real-time workload",
  journal =      j-TOS,
  volume =       "2",
  number =       "3",
  pages =        "255--282",
  month =        aug,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Apr 14 11:04:31 MDT 2007",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Zhang:2006:SPV,
  author =       "Jianyong Zhang and Anand Sivasubramaniam and Qian Wang
                 and Alma Riska and Erik Riedel",
  title =        "Storage performance virtualization via throughput and
                 latency control",
  journal =      j-TOS,
  volume =       "2",
  number =       "3",
  pages =        "283--308",
  month =        aug,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Apr 14 11:04:31 MDT 2007",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Wang:2006:CFS,
  author =       "An-I Andy Wang and Geoff Kuenning and Peter Reiher and
                 Gerald Popek",
  title =        "The {\em Conquest\/} file system: Better performance
                 through a disk\slash persistent-{RAM} hybrid design",
  journal =      j-TOS,
  volume =       "2",
  number =       "3",
  pages =        "309--348",
  month =        aug,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Apr 14 11:04:31 MDT 2007",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Memik:2006:MTE,
  author =       "Gokhan Memik and Mahmut T. Kandemir and Wei-Keng Liao
                 and Alok Choudhary",
  title =        "Multicollective {I/O}: {A} technique for exploiting
                 inter-file access patterns",
  journal =      j-TOS,
  volume =       "2",
  number =       "3",
  pages =        "349--369",
  month =        aug,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Apr 14 11:04:31 MDT 2007",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Kang:2006:AVA,
  author =       "Sukwoo Kang and A. L. Narasimha Reddy",
  title =        "An approach to virtual allocation in storage systems",
  journal =      j-TOS,
  volume =       "2",
  number =       "4",
  pages =        "371--399",
  month =        nov,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Apr 14 11:04:31 MDT 2007",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Nijim:2006:MIS,
  author =       "Mais Nijim and Xiao Qin and Tao Xie",
  title =        "Modeling and improving security of a local disk system
                 for write-intensive workloads",
  journal =      j-TOS,
  volume =       "2",
  number =       "4",
  pages =        "400--423",
  month =        nov,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Apr 14 11:04:31 MDT 2007",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Bobbarjung:2006:IDE,
  author =       "Deepak R. Bobbarjung and Suresh Jagannathan and Cezary
                 Dubnicki",
  title =        "Improving duplicate elimination in storage systems",
  journal =      j-TOS,
  volume =       "2",
  number =       "4",
  pages =        "424--448",
  month =        nov,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Apr 14 11:04:31 MDT 2007",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Wu:2006:DEI,
  author =       "Chin-Hsien Wu and Tei-Wei Kuo and Li-Pin Chang",
  title =        "The design of efficient initialization and crash
                 recovery for log-based file systems over flash memory",
  journal =      j-TOS,
  volume =       "2",
  number =       "4",
  pages =        "449--467",
  month =        nov,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Apr 14 11:04:31 MDT 2007",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Lin:2006:EID,
  author =       "Song Lin and Demetrios Zeinalipour-Yazti and Vana
                 Kalogeraki and Dimitrios Gunopulos and Walid A. Najjar",
  title =        "Efficient indexing data structures for flash-based
                 sensor devices",
  journal =      j-TOS,
  volume =       "2",
  number =       "4",
  pages =        "468--503",
  month =        nov,
  year =         "2006",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Apr 14 11:04:31 MDT 2007",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Arnan:2007:DDR,
  author =       "Ron Arnan and Eitan Bachmat and Tao Kai Lam and Ruben
                 Michel",
  title =        "Dynamic data reallocation in disk arrays",
  journal =      j-TOS,
  volume =       "3",
  number =       "1",
  pages =        "??--??",
  month =        mar,
  year =         "2007",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Apr 14 11:04:31 MDT 2007",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "2",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Kim:2007:ZR,
  author =       "Seon Ho Kim and Hong Zhu and Roger Zimmermann",
  title =        "Zoned-{RAID}",
  journal =      j-TOS,
  volume =       "3",
  number =       "1",
  pages =        "??--??",
  month =        mar,
  year =         "2007",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1227835.1227836",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Apr 14 11:04:31 MDT 2007",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "The RAID (Redundant Array of Inexpensive Disks) system
                 has been widely used in practical storage applications
                 for better performance, cost effectiveness, and
                 reliability. This study proposes a novel variant of
                 RAID named Zoned-RAID (Z-RAID). Z-RAID improves the
                 performance of traditional RAID by utilizing the zoning
                 property of modern disks which provides multiple zones
                 with different data transfer rates within a disk.
                 Z-RAID levels 1, 5, and 6 are introduced to enhance the
                 effective data transfer rate of RAID levels 1, 5, and
                 6, respectively, by constraining the placement of data
                 blocks in multizone disks. We apply the Z-RAID to a
                 practical and popular application, streaming media
                 server, that requires a high-data transfer rate as well
                 as a high reliability. The analytical and experimental
                 results demonstrate the superiority of Z-RAID to
                 conventional RAID. Z-RAID provides a higher effective
                 data transfer rate in normal mode with no disadvantage.
                 In the presence of a disk failure, Z-RAID still
                 performs as well as RAID.",
  acknowledgement = ack-nhfb,
  articleno =    "1",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Zhang:2007:SEA,
  author =       "Guangyan Zhang and Jiwu Shu and Wei Xue and Weimin
                 Zheng",
  title =        "{SLAS}: An efficient approach to scaling round-robin
                 striped volumes",
  journal =      j-TOS,
  volume =       "3",
  number =       "1",
  pages =        "??--??",
  month =        mar,
  year =         "2007",
  CODEN =        "????",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Apr 14 11:04:31 MDT 2007",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "3",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Wright:2007:EAS,
  author =       "Charles P. Wright and Richard Spillane and Gopalan
                 Sivathanu and Erez Zadok",
  title =        "Extending {ACID} semantics to the file system",
  journal =      j-TOS,
  volume =       "3",
  number =       "2",
  pages =        "4:1--4:??",
  month =        jun,
  year =         "2007",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1242520.1242521",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Mon Jun 16 17:36:16 MDT 2008",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "An organization's data is often its most valuable
                 asset, but today's file systems provide few facilities
                 to ensure its safety. Databases, on the other hand,
                 have long provided transactions. Transactions are
                 useful because they provide atomicity, consistency,
                 isolation, and durability (ACID). Many applications
                 could make use of these semantics, but databases have a
                 wide variety of nonstandard interfaces. For example,
                 applications like mail servers currently perform
                 elaborate error handling to ensure atomicity and
                 consistency, because it is easier than using a DBMS. A
                 transaction-oriented programming model eliminates
                 complex error-handling code because failed operations
                 can simply be aborted without side effects. We have
                 designed a file system that exports ACID transactions
                 to user-level applications, while preserving the
                 ubiquitous and convenient POSIX interface. In our
                 prototype ACID file system, called Amino, updated
                 applications can protect arbitrary sequences of system
                 calls within a transaction. Unmodified applications
                 operate without any changes, but each system call is
                 transaction protected. We also built a recoverable
                 memory library with support for nested transactions to
                 allow applications to keep their in-memory data
                 structures consistent with the file system. Our
                 performance evaluation shows that ACID semantics can be
                 added to applications with acceptable overheads. When
                 Amino adds atomicity, consistency, and isolation
                 functionality to an application, it performs close to
                 Ext3. Amino achieves durability up to 46\% faster than
                 Ext3, thanks to improved locality.",
  acknowledgement = ack-nhfb,
  articleno =    "4",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "databases; file systems; file system transactions;
                 ptrace monitors; recoverable memory",
}

@Article{Ding:2007:BCM,
  author =       "Xiaoning Ding and Song Jiang and Feng Chen",
  title =        "A buffer cache management scheme exploiting both
                 temporal and spatial localities",
  journal =      j-TOS,
  volume =       "3",
  number =       "2",
  pages =        "5:1--5:??",
  month =        jun,
  year =         "2007",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1242520.1242522",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Mon Jun 16 17:36:16 MDT 2008",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "On-disk sequentiality of requested blocks, or their
                 spatial locality, is critical to real disk performance
                 where the throughput of access to sequentially-placed
                 disk blocks can be an order of magnitude higher than
                 that of access to randomly-placed blocks.
                 Unfortunately, spatial locality of cached blocks is
                 largely ignored, and only temporal locality is
                 considered in current system buffer cache managements.
                 Thus, disk performance for workloads without dominant
                 sequential accesses can be seriously degraded. To
                 address this problem, we propose a scheme called DULO
                 (DU al LO cality) which exploits both temporal and
                 spatial localities in the buffer cache management.
                 Leveraging the filtering effect of the buffer cache,
                 DULO can influence the I/O request stream by making the
                 requests passed to the disk more sequential, thus
                 significantly increasing the effectiveness of I/O
                 scheduling and prefetching for disk performance
                 improvements.\par

                 We have implemented a prototype of DULO in Linux
                 2.6.11. The implementation shows that DULO can
                 significantly increases disk I/O throughput for
                 real-world applications such as a Web server, TPC
                 benchmark, file system benchmark, and scientific
                 programs. It reduces their execution times by as much
                 as 53\%.",
  acknowledgement = ack-nhfb,
  articleno =    "5",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "caching; file systems; hard disk; spatial locality;
                 temporal locality",
}

@Article{Rangaswami:2007:BMB,
  author =       "Raju Rangaswami and Zoran Dimitrijevi{\'c} and Edward
                 Chang and Klaus Schauser",
  title =        "Building {MEMS}-based storage systems for streaming
                 media",
  journal =      j-TOS,
  volume =       "3",
  number =       "2",
  pages =        "6:1--6:??",
  month =        jun,
  year =         "2007",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1242520.1242523",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Mon Jun 16 17:36:16 MDT 2008",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "The performance of streaming media servers has been
                 limited by the dual requirements of high disk
                 throughput (to service more clients simultaneously) and
                 low memory use (to decrease system cost). To achieve
                 high disk throughput, disk drives must be accessed with
                 large IOs to amortize disk access overhead. Large IOs
                 imply an increased requirement of expensive DRAM, and,
                 consequently, greater overall system cost. MEMS-based
                 storage, an emerging storage technology, is predicted
                 to offer a price-performance point between those of
                 DRAM and disk drives. In this study, we propose storage
                 architectures that use the relatively inexpensive
                 MEMS-based storage devices as an intermediate layer
                 (between DRAM and disk drives) for temporarily staging
                 large disk IOs at a significantly lower cost. We
                 present data layout mechanisms and synchronized IO
                 scheduling algorithms for the real-time storage and
                 retrieval of streaming data within such an augmented
                 storage system. Analytical evaluation suggests that
                 MEMS-augmented storage hierarchies can reduce the cost
                 and improve the throughput of streaming servers
                 significantly.",
  acknowledgement = ack-nhfb,
  articleno =    "6",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "I/O scheduling; MEMS-based storage; multidisk storage;
                 storage architecture; streaming media",
}

@Article{Arpaci-Dusseau:2007:ISI,
  author =       "Andrea Arpaci-Dusseau and Remzi Arpaci-Dusseau",
  title =        "Introduction to special issue {USENIX} {FAST} 2007",
  journal =      j-TOS,
  volume =       "3",
  number =       "3",
  pages =        "7:1--7:??",
  month =        oct,
  year =         "2007",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1288783.1288784",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Mon Jun 16 17:36:25 MDT 2008",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "7",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Schroeder:2007:UDF,
  author =       "Bianca Schroeder and Garth A. Gibson",
  title =        "Understanding disk failure rates: What does an {MTTF}
                 of 1,000,000 hours mean to you?",
  journal =      j-TOS,
  volume =       "3",
  number =       "3",
  pages =        "8:1--8:??",
  month =        oct,
  year =         "2007",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1288783.1288785",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Mon Jun 16 17:36:25 MDT 2008",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Component failure in large-scale IT installations is
                 becoming an ever-larger problem as the number of
                 components in a single cluster approaches a
                 million.\par

                 This article is an extension of our previous study on
                 disk failures [Schroeder and Gibson 2007] and presents
                 and analyzes field-gathered disk replacement data from
                 a number of large production systems, including
                 high-performance computing sites and internet services
                 sites. More than 110,000 disks are covered by this
                 data, some for an entire lifetime of five years. The
                 data includes drives with SCSI and FC, as well as SATA
                 interfaces. The mean time-to-failure (MTTF) of those
                 drives, as specified in their datasheets, ranges from
                 1,000,000 to 1,500,000 hours, suggesting a nominal
                 annual failure rate of at most 0.88\%.\par

                 We find that in the field, annual disk replacement
                 rates typically exceed 1\%, with 2--4\% common and up
                 to 13\% observed on some systems. This suggests that
                 field replacement is a fairly different process than
                 one might predict based on datasheet MTTF.\par

                 We also find evidence, based on records of disk
                 replacements in the field, that failure rate is not
                 constant with age, and that rather than a significant
                 infant mortality effect, we see a significant early
                 onset of wear-out degradation. In other words, the
                 replacement rates in our data grew constantly with age,
                 an effect often assumed not to set in until after a
                 nominal lifetime of 5 years.\par

                 Interestingly, we observe little difference in
                 replacement rates between SCSI, FC, and SATA drives,
                 potentially an indication that disk-independent factors
                 such as operating conditions affect replacement rates
                 more than component-specific ones. On the other hand,
                 we see only one instance of a customer rejecting an
                 entire population of disks as a bad batch, in this case
                 because of media error rates, and this instance
                 involved SATA disks.\par

                 Time between replacement, a proxy for time between
                 failure, is not well modeled by an exponential
                 distribution and exhibits significant levels of
                 correlation, including autocorrelation and long-range
                 dependence.",
  acknowledgement = ack-nhfb,
  articleno =    "8",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "annual failure rates; annual replacement rates;
                 datasheet MTTF; failure correlation; hard drive
                 failure; hard drive replacements; infant mortality;
                 MTTF; storage reliability; time between failure;
                 wear-out",
}

@Article{Agrawal:2007:FYS,
  author =       "Nitin Agrawal and William J. Bolosky and John R.
                 Douceur and Jacob R. Lorch",
  title =        "A five-year study of file-system metadata",
  journal =      j-TOS,
  volume =       "3",
  number =       "3",
  pages =        "9:1--9:??",
  month =        oct,
  year =         "2007",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1288783.1288788",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Mon Jun 16 17:36:25 MDT 2008",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "For five years, we collected annual snapshots of
                 file-system metadata from over 60,000 Windows PC file
                 systems in a large corporation. In this article, we use
                 these snapshots to study temporal changes in file size,
                 file age, file-type frequency, directory size,
                 namespace structure, file-system population, storage
                 capacity and consumption, and degree of file
                 modification. We present a generative model that
                 explains the namespace structure and the distribution
                 of directory sizes. We find significant temporal trends
                 relating to the popularity of certain file types, the
                 origin of file content, the way the namespace is used,
                 and the degree of variation among file systems, as well
                 as more pedestrian changes in size and capacities. We
                 give examples of consequent lessons for designers of
                 file systems and related software.",
  acknowledgement = ack-nhfb,
  articleno =    "9",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "file systems; generative model; longitudinal study",
}

@Article{Gill:2007:OMS,
  author =       "Binny S. Gill and Luis Angel D. Bathen",
  title =        "Optimal multistream sequential prefetching in a shared
                 cache",
  journal =      j-TOS,
  volume =       "3",
  number =       "3",
  pages =        "10:1--10:??",
  month =        oct,
  year =         "2007",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1288783.1288789",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Mon Jun 16 17:36:25 MDT 2008",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Prefetching is a widely used technique in modern data
                 storage systems. We study the most widely used class of
                 prefetching algorithms known as sequential prefetching.
                 There are two problems that plague the state-of-the-art
                 sequential prefetching algorithms: (i) cache pollution,
                 which occurs when prefetched data replaces more useful
                 prefetched or demand-paged data, and (ii) prefetch
                 wastage, which happens when prefetched data is evicted
                 from the cache before it can be used.\par

                 A sequential prefetching algorithm can have a fixed or
                 adaptive degree of prefetch and can be either
                 synchronous (when it can prefetch only on a miss) or
                 asynchronous (when it can also prefetch on a hit). To
                 capture these distinctions we define four classes of
                 prefetching algorithms: fixed synchronous (FS), fixed
                 asynchronous (FA), adaptive synchronous (AS), and
                 adaptive asynchronous (AsynchA). We find that the
                 relatively unexplored class of AsynchA algorithms is in
                 fact the most promising for sequential prefetching. We
                 provide a first formal analysis of the criteria
                 necessary for optimal throughput when using an AsynchA
                 algorithm in a cache shared by multiple steady
                 sequential streams. We then provide a simple
                 implementation called AMP (adaptive multistream
                 prefetching) which adapts accordingly, leading to
                 near-optimal performance for any kind of sequential
                 workload and cache size.\par

                 Our experimental setup consisted of an IBM xSeries 345
                 dual processor server running Linux using five SCSI
                 disks. We observe that AMP convincingly outperforms all
                 the contending members of the FA, FS, and AS classes
                 for any number of streams and over all cache sizes. As
                 anecdotal evidence, in an experiment with 100
                 concurrent sequential streams and varying cache sizes,
                 AMP surpasses the FA, FS, and AS algorithms by
                 29--172\%, 12--24\%, and 21--210\%, respectively, while
                 outperforming OBL by a factor of 8. Even for complex
                 workloads like SPC1-Read, AMP is consistently the
                 best-performing algorithm. For the SPC2 video-on-demand
                 workload, AMP can sustain at least 25\% more streams
                 than the next best algorithm. Furthermore, for a
                 workload consisting of short sequences, where
                 optimality is more elusive, AMP is able to outperform
                 all the other contenders in overall
                 performance.\par

                 Finally, we implemented AMP in the state-of-the-art
                 enterprise storage system, the IBM system storage
                 DS8000 series. We demonstrated that AMP dramatically
                 improves performance for common sequential and batch
                 processing workloads and delivers up to a twofold
                 increase in the sequential read capacity.",
  acknowledgement = ack-nhfb,
  articleno =    "10",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "adaptive prefetching; asynchronous prefetching; cache
                 pollution; degree of prefetch; fixed prefetching;
                 multistream read; optimal prefetching; prefetch
                 wastage; prestaging; sequential prefetching;
                 synchronous prefetching; trigger distance",
}

@Article{Yumerefendi:2007:SAN,
  author =       "Aydan R. Yumerefendi and Jeffrey S. Chase",
  title =        "Strong accountability for network storage",
  journal =      j-TOS,
  volume =       "3",
  number =       "3",
  pages =        "11:1--11:??",
  month =        oct,
  year =         "2007",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1288783.1288786",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Mon Jun 16 17:36:25 MDT 2008",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "This article presents the design, implementation, and
                 evaluation of CATS, a network storage service with
                 strong accountability properties. CATS offers a simple
                 web services interface that allows clients to read and
                 write opaque objects of variable size. This interface
                 is similar to the one offered by existing commercial
                 Internet storage services. CATS extends the
                 functionality of commercial Internet storage services
                 by offering support for strong accountability.\par

                 A CATS server annotates read and write responses with
                 evidence of correct execution, and offers audit and
                 challenge interfaces that enable clients to verify that
                 the server is faithful. A faulty server cannot conceal
                 its misbehavior, and evidence of misbehavior is
                 independently verifiable by any participant. CATS
                 clients are also accountable for their actions on the
                 service. A client cannot deny its actions, and the
                 server can prove the impact of those actions on the
                 state views it presented to other
                 clients.\par

                 Experiments with a CATS prototype evaluate the cost of
                 accountability under a range of conditions and expose
                 the primary factors influencing the level of assurance
                 and the performance of a strongly accountable storage
                 server. The results show that strong accountability is
                 practical for network storage systems in settings with
                 strong identity and modest degrees of write-sharing. We
                 discuss how the accountability concepts and techniques
                 used in CATS generalize to other classes of network
                 services.",
  acknowledgement = ack-nhfb,
  articleno =    "11",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "accountability; accountable services; accountable
                 storage",
}

@Article{Cipar:2007:CSU,
  author =       "James Cipar and Mark D. Corner and Emery D. Berger",
  title =        "Contributing storage using the transparent file
                 system",
  journal =      j-TOS,
  volume =       "3",
  number =       "3",
  pages =        "12:1--12:??",
  month =        oct,
  year =         "2007",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1288783.1288787",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Mon Jun 16 17:36:25 MDT 2008",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Contributory applications allow users to donate unused
                 resources on their personal computers to a shared pool.
                 Applications such as SETI@home, Folding@home, and
                 Freenet are now in wide use and provide a variety of
                 services, including data processing and content
                 distribution. However, while several research projects
                 have proposed contributory applications that support
                 peer-to-peer storage systems, their adoption has been
                 comparatively limited. We believe that a key barrier to
                 the adoption of contributory storage systems is that
                 contributing a large quantity of local storage
                 interferes with the principal user of the
                 machine.\par

                 To overcome this barrier, we introduce the Transparent
                 File System (TFS). TFS provides background tasks with
                 large amounts of unreliable storage --- all of the
                 currently available space --- without impacting the
                 performance of ordinary file access operations. We show
                 that TFS allows a peer-to-peer contributory storage
                 system to provide 40\% more storage at twice the
                 performance when compared to a user-space storage
                 mechanism. We analyze the impact of TFS on replication
                 in peer-to-peer storage systems and show that TFS does
                 not appreciably increase the resources needed for file
                 replication.",
  acknowledgement = ack-nhfb,
  articleno =    "12",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "aging; contributory systems; fragmentation;
                 peer-to-peer",
}

@Article{Weddle:2007:PGS,
  author =       "Charles Weddle and Mathew Oldham and Jin Qian and An-I
                 Andy Wang and Peter Reiher and Geoff Kuenning",
  title =        "{PARAID}: {A} gear-shifting power-aware {RAID}",
  journal =      j-TOS,
  volume =       "3",
  number =       "3",
  pages =        "13:1--13:??",
  month =        oct,
  year =         "2007",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1288783.1288787",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Mon Jun 16 17:36:25 MDT 2008",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Reducing power consumption for server-class computers
                 is important, since increased energy usage causes more
                 heat dissipation, greater cooling requirements, reduced
                 computational density, and higher operating costs. For
                 a typical data center, storage accounts for 27\% of
                 energy consumption. Conventional server-class RAIDs
                 cannot easily reduce power because loads are balanced
                 to use all disks, even for light loads.\par

                 We have built the power-aware RAID (PARAID), which
                 reduces energy use of commodity server-class disks
                 without specialized hardware. PARAID uses a skewed
                 striping pattern to adapt to the system load by varying
                 the number of powered disks. By spinning disks down
                 during light loads, PARAID can reduce power
                 consumption, while still meeting performance demands,
                 by matching the number of powered disks to the system
                 load. Reliability is achieved by limiting disk power
                 cycles and using different RAID encoding schemes. Based
                 on our five-disk prototype, PARAID uses up to 34\% less
                 power than conventional RAIDs while achieving similar
                 performance and reliability.",
  acknowledgement = ack-nhfb,
  articleno =    "13",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "energy efficiency; power savings; RAID",
}

@Article{Maccormick:2008:NPR,
  author =       "John Maccormick and Chandramohan A. Thekkath and
                 Marcus Jager and Kristof Roomp and Lidong Zhou and Ryan
                 Peterson",
  title =        "Niobe: {A} practical replication protocol",
  journal =      j-TOS,
  volume =       "3",
  number =       "4",
  pages =        "1:1--1:??",
  month =        feb,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1326542.1326543",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Mon Jun 16 17:36:37 MDT 2008",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "The task of consistently and reliably replicating data
                 is fundamental in distributed systems, and numerous
                 existing protocols are able to achieve such replication
                 efficiently. When called on to build a large-scale
                 enterprise storage system with built-in replication, we
                 were therefore surprised to discover that no existing
                 protocols met our requirements. As a result, we
                 designed and deployed a new replication protocol called
                 Niobe. Niobe is in the primary-backup family of
                 protocols, and shares many similarities with other
                 protocols in this family. But we believe Niobe is
                 significantly more practical for large-scale enterprise
                 storage than previously published protocols. In
                 particular, Niobe is simple, flexible, has rigorously
                 proven yet simply stated consistency guarantees, and
                 exhibits excellent performance. Niobe has been deployed
                 as the backend for a commercial Internet service; its
                 consistency properties have been proved formally from
                 first principles, and further verified using the TLA +
                 specification language. We describe the protocol
                 itself, the system built to deploy it, and some of our
                 experiences in doing so.",
  acknowledgement = ack-nhfb,
  articleno =    "1",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "enterprise storage; replication",
}

@Article{Rodeh:2008:BTS,
  author =       "Ohad Rodeh",
  title =        "{B}-trees, shadowing, and clones",
  journal =      j-TOS,
  volume =       "3",
  number =       "4",
  pages =        "2:1--2:??",
  month =        feb,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1326542.1326544",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Mon Jun 16 17:36:37 MDT 2008",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "B-trees are used by many file systems to represent
                 files and directories. They provide guaranteed
                 logarithmic time key-search, insert, and remove. File
                 systems like WAFL and ZFS use shadowing, or
                 copy-on-write, to implement snapshots, crash recovery,
                 write-batching, and RAID. Serious difficulties arise
                 when trying to use B-trees and shadowing in a single
                 system.\par

                 This article is about a set of B-tree algorithms that
                 respects shadowing, achieves good concurrency, and
                 implements cloning (writable snapshots). Our cloning
                 algorithm is efficient and allows the creation of a
                 large number of clones.\par

                 We believe that using our B-trees would allow shadowing
                 file systems to better scale their on-disk data
                 structures.",
  acknowledgement = ack-nhfb,
  articleno =    "2",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "B-trees; concurrency; copy-on-write; shadowing;
                 snapshots",
}

@Article{Dutta:2008:WBG,
  author =       "Kaushik Dutta and Raju Rangaswami and Sajib Kundu",
  title =        "Workload-based generation of administrator hints for
                 optimizing database storage utilization",
  journal =      j-TOS,
  volume =       "3",
  number =       "4",
  pages =        "3:1--3:??",
  month =        feb,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1326542.1326545",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Mon Jun 16 17:36:37 MDT 2008",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Database storage management at data centers is a
                 manual, time-consuming, and error-prone task. Such
                 management involves regular movement of database
                 objects across storage nodes in an attempt to balance
                 the I/O bandwidth utilization across disk drives.
                 Achieving such balance is critical for avoiding I/O
                 bottlenecks and thereby maximizing the utilization of
                 the storage system. However, manual management of the
                 aforesaid task, apart from increasing administrative
                 costs, encumbers the greater risks of untimely and
                 erroneous operations. We address the preceding concerns
                 with STORM, an automated approach that combines
                 low-overhead information gathering of database access
                 and storage usage patterns with efficient analysis to
                 generate accurate and timely hints for the
                 administrator regarding data movement operations.
                 STORM's primary objective is minimizing the volume of
                 data movement required (to minimize potential down-time
                 or reduction in performance) during the reconfiguration
                 operation, with the secondary constraints of space and
                 balanced I/O-bandwidth-utilization across the storage
                 devices. We analyze and evaluate STORM theoretically,
                 using a simulation framework, as well as
                 experimentally. We show that the dynamic data layout
                 reconfiguration problem is NP-hard and we present a
                 heuristic that provides an approximate solution in $O(N
                 \log (N / M) + (N / M )^2)$ time, where M is the number
                 of storage devices and $N$ is the total number of
                 database objects residing in the storage devices. A
                 simulation study shows that the heuristic converges to
                 an acceptable solution that is successful in balancing
                 storage utilization with an accuracy that lies within
                 7\% of the ideal solution. Finally, an experimental
                 study demonstrates that the STORM approach can improve
                 the overall performance of the TPC-C benchmark by as
                 much as 22\%, by reconfiguring an initial random, but
                 evenly distributed, placement of database objects.",
  acknowledgement = ack-nhfb,
  articleno =    "3",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Verma:2008:UBU,
  author =       "Akshat Verma and Rohit Jain and Sugata Ghosal",
  title =        "A utility-based unified disk scheduling framework for
                 shared mixed-media services",
  journal =      j-TOS,
  volume =       "3",
  number =       "4",
  pages =        "4:1--4:??",
  month =        feb,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1326542.1326546",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Mon Jun 16 17:36:37 MDT 2008",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "We present a new disk scheduling framework to address
                 the needs of a shared multimedia service that provides
                 differentiated multilevel quality-of-service for
                 mixed-media workloads. In such a shared service,
                 requests from different users have different associated
                 performance objectives and utilities, in accordance
                 with the negotiated service-level agreements (SLAs).
                 Service providers typically provision resources only
                 for average workload intensity, so it becomes important
                 to handle workload surges in a way that maximizes the
                 utility of the served requests.\par

                 We capture the performance objectives and utilities
                 associated with these multiclass diverse workloads in a
                 unified framework and formulate the disk scheduling
                 problem as a reward maximization problem. We map the
                 reward maximization problem to a minimization problem
                 on graphs and, by novel use of graph-theoretic
                 techniques, design a scheduling algorithm that is
                 computationally efficient and optimal in the class of
                 seek-optimizing algorithms. Comprehensive experimental
                 studies demonstrate that the proposed algorithm
                 outperforms other disk schedulers under all loads, with
                 the performance improvement approaching 100\% under
                 certain high load conditions. In contrast to existing
                 schedulers, the proposed scheduler is extensible to new
                 performance objectives (workload type) and utilities by
                 simply altering the reward functions associated with
                 the requests.",
  acknowledgement = ack-nhfb,
  articleno =    "4",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "disk scheduling; GSP; profit maximization; shortest
                 path",
}

@Article{Hildrum:2008:SOL,
  author =       "Kirsten Hildrum and Fred Douglis and Joel L. Wolf and
                 Philip S. Yu and Lisa Fleischer and Akshay Katta",
  title =        "Storage optimization for large-scale distributed
                 stream-processing systems",
  journal =      j-TOS,
  volume =       "3",
  number =       "4",
  pages =        "5:1--5:??",
  month =        feb,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1326542.1326547",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Mon Jun 16 17:36:37 MDT 2008",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "We consider storage in an extremely large-scale
                 distributed computer system designed for stream
                 processing applications. In such systems, both incoming
                 data and intermediate results may need to be stored to
                 enable analyses at unknown future times. The quantity
                 of data of potential use would dominate even the
                 largest storage system. Thus, a mechanism is needed to
                 keep the data most likely to be used. One recently
                 introduced approach is to employ retention value
                 functions, which effectively assign each data object a
                 value that changes over time in a prespecified way
                 [Douglis et al.2004]. Storage space for data entering
                 the system is reclaimed automatically by deleting data
                 of the lowest current value. In such large systems,
                 there will naturally be multiple file systems
                 available, each with different properties. Choosing the
                 right file system for a given incoming stream of data
                 presents a challenge. In this article we provide a
                 novel and effective scheme for optimizing the placement
                 of data within a distributed storage subsystem
                 employing retention value functions. The goal is to
                 keep the data of highest overall value, while
                 simultaneously balancing the read load to the file
                 system. The key aspects of such a scheme are quite
                 different from those that arise in traditional file
                 assignment problems. We further motivate this
                 optimization problem and describe a solution, comparing
                 its performance to other reasonable schemes via
                 simulation experiments.",
  acknowledgement = ack-nhfb,
  articleno =    "5",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "file assignment problem; load balancing; optimization;
                 storage management; streaming systems; theory",
}

@Article{Dholakia:2008:NID,
  author =       "Ajay Dholakia and Evangelos Eleftheriou and Xiao-Yu Hu
                 and Ilias Iliadis and Jai Menon and K. K. Rao",
  title =        "A new intra-disk redundancy scheme for
                 high-reliability {RAID} storage systems in the presence
                 of unrecoverable errors",
  journal =      j-TOS,
  volume =       "4",
  number =       "1",
  pages =        "1:1--1:??",
  month =        may,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1353452.1353453",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Mon Jun 16 17:36:45 MDT 2008",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Today's data storage systems are increasingly adopting
                 low-cost disk drives that have higher capacity but
                 lower reliability, leading to more frequent rebuilds
                 and to a higher risk of unrecoverable media errors. We
                 propose an efficient intradisk redundancy scheme to
                 enhance the reliability of RAID systems. This scheme
                 introduces an additional level of redundancy inside
                 each disk, on top of the RAID redundancy across
                 multiple disks. The RAID parity provides protection
                 against disk failures, whereas the proposed scheme aims
                 to protect against media-related unrecoverable errors.
                 In particular, we consider an intradisk redundancy
                 architecture that is based on an interleaved
                 parity-check coding scheme, which incurs only
                 negligible I/O performance degradation. A comparison
                 between this coding scheme and schemes based on
                 traditional Reed--Solomon codes and single-parity-check
                 codes is conducted by analytical means. A new model is
                 developed to capture the effect of correlated
                 unrecoverable sector errors. The probability of an
                 unrecoverable failure associated with these schemes is
                 derived for the new correlated model, as well as for
                 the simpler independent error model. We also derive
                 closed-form expressions for the mean time to data loss
                 of RAID-5 and RAID-6 systems in the presence of
                 unrecoverable errors and disk failures. We then combine
                 these results to characterize the reliability of RAID
                 systems that incorporate the intradisk redundancy
                 scheme. Our results show that in the practical case of
                 correlated errors, the interleaved parity-check scheme
                 provides the same reliability as the optimum, albeit
                 more complex, Reed--Solomon coding scheme. Finally, the
                 I/O and throughput performances are evaluated by means
                 of analysis and event-driven simulation.",
  acknowledgement = ack-nhfb,
  articleno =    "1",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "file and I/O systems; RAID; reliability analysis;
                 stochastic modeling",
}

@Article{Essary:2008:PDG,
  author =       "David Essary and Ahmed Amer",
  title =        "Predictive data grouping: Defining the bounds of
                 energy and latency reduction through predictive data
                 grouping and replication",
  journal =      j-TOS,
  volume =       "4",
  number =       "1",
  pages =        "2:1--2:??",
  month =        may,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1353452.1353454",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Mon Jun 16 17:36:45 MDT 2008",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "We demonstrate that predictive grouping is an
                 effective mechanism for reducing disk arm movement,
                 thereby simultaneously reducing energy consumption and
                 data access latency. We further demonstrate that
                 predictive grouping has untapped dramatic potential to
                 further improve access performance and limit energy
                 consumption. Data retrieval latencies are considered a
                 major bottleneck, and with growing volumes of data and
                 increased storage needs it is only growing in
                 significance. Data storage infrastructure is therefore
                 a growing consumer of energy at data-center scales,
                 while the individual disk is already a significant
                 concern for mobile computing (accounting for almost a
                 third of a mobile system's energy demands). While
                 improving responsiveness of storage subsystems and
                 hence reducing latencies in data retrieval is often
                 considered contradictory with efforts to reduce disk
                 energy consumption, we demonstrate that predictive data
                 grouping has the potential to simultaneously work
                 towards both these goals. Predictive data grouping has
                 advantages in its applicability compared to both prior
                 approaches to reducing latencies and to reducing energy
                 usage. For latencies, grouping can be performed
                 opportunistically, thereby avoiding the serious
                 performance penalties that can be incurred with prior
                 applications of access prediction (such as predictive
                 prefetching of data). For energy, we show how
                 predictive grouping can even save energy use for an
                 individual disk that is never idle.\par

                 Predictive data grouping with effective replication
                 results in a reduction of the overall mechanical
                 movement required to retrieve data. We have built upon
                 our detailed measurements of disk power consumption,
                 and have estimated both the energy expended by a hard
                 disk for its mechanical components, and that needed to
                 move the disk arm. We have further compared, via
                 simulation, three models of predictive grouping of
                 on-disk data, including an optimal arrangement of data
                 that is guaranteed to minimize disk arm movement. These
                 experiments have allowed us to measure the limits of
                 performance improvement achievable with optimal data
                 grouping and replication strategies on a single device,
                 and have further allowed us to demonstrate the
                 potential of such schemes to reduce energy consumption
                 of mechanical components by up to 70\%.",
  acknowledgement = ack-nhfb,
  articleno =    "2",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "data grouping; latency; layout optimization; power;
                 power management; replication",
}

@Article{Tran:2008:NAD,
  author =       "Dinh Nguyen Tran and Phung Chinh Huynh and Y. C. Tay
                 and Anthony K. H. Tung",
  title =        "A new approach to dynamic self-tuning of database
                 buffers",
  journal =      j-TOS,
  volume =       "4",
  number =       "1",
  pages =        "3:1--3:??",
  month =        may,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1353452.1353455",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Mon Jun 16 17:36:45 MDT 2008",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Current businesses rely heavily on efficient access to
                 their databases. Manual tuning of these database
                 systems by performance experts is increasingly
                 infeasible: For small companies, hiring an expert may
                 be too expensive; for large enterprises, even an expert
                 may not fully understand the interaction between a
                 large system and its multiple changing workloads. This
                 trend has led major vendors to offer tools that
                 automatically and dynamically tune a database
                 system.\par

                 Many database tuning knobs concern the buffer pool for
                 caching data and disk pages. Specifically, these knobs
                 control the buffer allocation and thus the cache miss
                 probability, which has direct impact on
                 performance.\par

                 Previous methods for automatic buffer tuning are based
                 on simulation, black-box control, gradient descent, and
                 empirical equations. This article presents a new
                 approach, using calculations with an
                 analytically-derived equation that relates miss
                 probability to buffer allocation; this equation fits
                 four buffer replacement policies, as well as twelve
                 datasets from mainframes running commercial databases
                 in large corporations.\par

                 The equation identifies a buffer-size limit that is
                 useful for buffer tuning and powering down idle
                 buffers. It can also replace simulation in predicting
                 I/O costs. Experiments with PostgreSQL illustrate how
                 the equation can help optimize online buffer
                 partitioning, ensure fairness in buffer reclamation,
                 and dynamically retune the allocation when workloads
                 change. It is also used, in conjunction with DB2's
                 interface for retrieving miss data, for tuning DB2
                 buffer allocation to achieve targets for differentiated
                 service.",
  acknowledgement = ack-nhfb,
  articleno =    "3",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "autonomic computing; buffer allocation; miss
                 probability",
}

@Article{Matthews:2008:ITM,
  author =       "Jeanna Matthews and Sanjeev Trika and Debra Hensgen
                 and Rick Coulson and Knut Grimsrud",
  title =        "Intel{\reg} Turbo Memory: Nonvolatile disk caches in
                 the storage hierarchy of mainstream computer systems",
  journal =      j-TOS,
  volume =       "4",
  number =       "2",
  pages =        "4:1--4:??",
  month =        may,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1367829.1367830",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Mon Jun 16 17:36:51 MDT 2008",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Hard-disk drives are a significant bottleneck to
                 system performance and are also responsible for a
                 significant fraction of total system power consumption.
                 Intel Turbo Memory addresses these problems by adding a
                 new layer to the storage hierarchy: a platform-based
                 and nonvolatile, disk cache. In this article, we
                 describe the hardware and software elements of the
                 Intel Turbo Memory architecture. We show how it
                 supports the new ReadyBoost and ReadyDrive features in
                 Microsoft Vista and describe its key caching
                 algorithms. We present performance, power savings, and
                 wear-leveling results achieved by Intel Turbo Memory.",
  acknowledgement = ack-nhfb,
  articleno =    "4",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "disk cache; NAND; nonvolatile memory; solid-state
                 disk; write-back",
}

@Article{Traeger:2008:NYS,
  author =       "Avishay Traeger and Erez Zadok and Nikolai Joukov and
                 Charles P. Wright",
  title =        "A nine year study of file system and storage
                 benchmarking",
  journal =      j-TOS,
  volume =       "4",
  number =       "2",
  pages =        "5:1--5:??",
  month =        may,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1367829.1367831",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Mon Jun 16 17:36:51 MDT 2008",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Benchmarking is critical when evaluating performance,
                 but is especially difficult for file and storage
                 systems. Complex interactions between I/O devices,
                 caches, kernel daemons, and other OS components result
                 in behavior that is rather difficult to analyze.
                 Moreover, systems have different features and
                 optimizations, so no single benchmark is always
                 suitable. The large variety of workloads that these
                 systems experience in the real world also adds to this
                 difficulty.\par

                 In this article we survey 415 file system and storage
                 benchmarks from 106 recent papers. We found that most
                 popular benchmarks are flawed and many research papers
                 do not provide a clear indication of true performance.
                 We provide guidelines that we hope will improve future
                 performance evaluations. To show how some widely used
                 benchmarks can conceal or overemphasize overheads, we
                 conducted a set of experiments. As a specific example,
                 slowing down read operations on ext2 by a factor of 32
                 resulted in only a 2--5\% wall-clock slowdown in a
                 popular compile benchmark. Finally, we discuss future
                 work to improve file system and storage benchmarking.",
  acknowledgement = ack-nhfb,
  articleno =    "5",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "benchmarks; file systems; storage systems",
}

@Article{Baker:2008:ISI,
  author =       "Mary Baker",
  title =        "Introduction to special issue of {USENIX FAST 2008}",
  journal =      j-TOS,
  volume =       "4",
  number =       "3",
  pages =        "6:1--6:??",
  month =        nov,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1416944.1416945",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:33:07 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "6",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Jiang:2008:DDC,
  author =       "Weihang Jiang and Chongfeng Hu and Yuanyuan Zhou and
                 Arkady Kanevsky",
  title =        "Are disks the dominant contributor for storage
                 failures?: {A} comprehensive study of storage subsystem
                 failure characteristics",
  journal =      j-TOS,
  volume =       "4",
  number =       "3",
  pages =        "7:1--7:??",
  month =        nov,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1416944.1416946",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:33:07 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Building reliable storage systems becomes increasingly
                 challenging as the complexity of modern storage systems
                 continues to grow. Understanding storage failure
                 characteristics is crucially important for designing
                 and building a reliable storage system. While several
                 recent studies have been conducted on understanding
                 storage failures, almost all of them focus on the
                 failure characteristics of one component --- disks ---
                 and do not study other storage component
                 failures.\par

                 This article analyzes the failure characteristics of
                 storage subsystems. More specifically, we analyzed the
                 storage logs collected from about 39,000 storage
                 systems commercially deployed at various customer
                 sites. The dataset covers a period of 44 months and
                 includes about 1,800,000 disks hosted in about 155,000
                 storage-shelf enclosures. Our study reveals many
                 interesting findings, providing useful guidelines for
                 designing reliable storage systems. Some of our major
                 findings include: (1) In addition to disk failures that
                 contribute to 20--55\% of storage subsystem failures,
                 other components such as physical interconnects and
                 protocol stacks also account for a significant
                 percentage of storage subsystem failures. (2) Each
                 individual storage subsystem failure type, and storage
                 subsystem failure as a whole, exhibits strong
                 self-correlations. In addition, these failures exhibit
                 ``bursty'' patterns. (3) Storage subsystems configured
                 with redundant interconnects experience 30--40\% lower
                 failure rates than those with a single interconnect.
                 (4) Spanning disks of a RAID group across multiple
                 shelves provides a more resilient solution for storage
                 subsystems than within a single shelf.",
  acknowledgement = ack-nhfb,
  articleno =    "7",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "disk failures; failure characteristics; storage
                 subsystem; Storage system",
}

@Article{Bairavasundaram:2008:ADC,
  author =       "Lakshmi N. Bairavasundaram and Andrea C.
                 Arpaci-Dusseau and Remzi H. Arpaci-Dusseau and Garth
                 R. Goodson and Bianca Schroeder",
  title =        "An analysis of data corruption in the storage stack",
  journal =      j-TOS,
  volume =       "4",
  number =       "3",
  pages =        "8:1--8:??",
  month =        nov,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1416944.1416947",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:33:07 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "An important threat to reliable storage of data is
                 silent data corruption. In order to develop suitable
                 protection mechanisms against data corruption, it is
                 essential to understand its characteristics. In this
                 article, we present the first large-scale study of data
                 corruption. We analyze corruption instances recorded in
                 production storage systems containing a total of 1.53
                 million disk drives, over a period of 41 months. We
                 study three classes of corruption: checksum mismatches,
                 identity discrepancies, and parity inconsistencies. We
                 focus on checksum mismatches since they occur the
                 most.\par

                 We find more than 400,000 instances of checksum
                 mismatches over the 41-month period. We find many
                 interesting trends among these instances, including:
                 (i) nearline disks (and their adapters) develop
                 checksum mismatches an order of magnitude more often
                 than enterprise-class disk drives, (ii) checksum
                 mismatches within the same disk are not independent
                 events and they show high spatial and temporal
                 locality, and (iii) checksum mismatches across
                 different disks in the same storage system are not
                 independent. We use our observations to derive lessons
                 for corruption-proof system design.",
  acknowledgement = ack-nhfb,
  articleno =    "8",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "Data corruption; disk drive reliability",
}

@Article{Tsafrir:2008:PSF,
  author =       "Dan Tsafrir and Tomer Hertz and David Wagner and Dilma
                 {Da Silva}",
  title =        "Portably solving file races with hardness
                 amplification",
  journal =      j-TOS,
  volume =       "4",
  number =       "3",
  pages =        "9:1--9:??",
  month =        nov,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1416944.1416948",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:33:07 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "The file-system API of contemporary systems makes
                 programs vulnerable to TOCTTOU
                 (time-of-check-to-time-of-use) race conditions.
                 Existing solutions either help users to detect these
                 problems (by pinpointing their locations in the code),
                 or prevent the problem altogether (by modifying the
                 kernel or its API). But the latter alternative is not
                 prevalent, and the former is just the first step:
                 Programmers must still address TOCTTOU flaws within the
                 limits of the existing API with which several important
                 tasks cannot be accomplished in a portable
                 straightforward manner. Recently, Dean and Hu [2004]
                 addressed this problem and suggested a probabilistic
                 hardness amplification approach that alleviated the
                 matter. Alas, shortly after, Borisov et al. [2005]
                 responded with an attack termed ``filesystem maze''
                 that defeated the new approach.\par

                 We begin by noting that mazes constitute a generic way
                 to deterministically win many TOCTTOU races (gone are
                 the days when the probability was small). In the face
                 of this threat, we: (1) develop a new user-level
                 defense that can withstand mazes; and (2) show that our
                 method is undefeated even by much stronger hypothetical
                 attacks that provide the adversary program with ideal
                 conditions to win the race (enjoying complete and
                 instantaneous knowledge about the defending program's
                 actions and being able to perfectly synchronize
                 accordingly). The fact that our approach is immune to
                 these unrealistic attacks suggests it can be used as a
                 simple and portable solution to a large class of
                 TOCTTOU vulnerabilities, without requiring
                 modifications to the underlying operating system.",
  acknowledgement = ack-nhfb,
  articleno =    "9",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "Race conditions; time-of-check-to-time-of-use;
                 TOCTTOU",
}

@Article{Narayanan:2008:WLP,
  author =       "Dushyanth Narayanan and Austin Donnelly and Antony
                 Rowstron",
  title =        "Write off-loading: Practical power management for
                 enterprise storage",
  journal =      j-TOS,
  volume =       "4",
  number =       "3",
  pages =        "10:1--10:??",
  month =        nov,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1416944.1416949",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:33:07 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "In enterprise data centers power usage is a problem
                 impacting server density and the total cost of
                 ownership. Storage uses a significant fraction of the
                 power budget and there are no widely deployed
                 power-saving solutions for enterprise storage systems.
                 The traditional view is that enterprise workloads make
                 spinning disks down ineffective because idle periods
                 are too short. We analyzed block-level traces from 36
                 volumes in an enterprise data center for one week and
                 concluded that significant idle periods exist, and that
                 they can be further increased by modifying the
                 read/write patterns using {\em write off-loading}.
                 Write off-loading allows write requests on spun-down
                 disks to be temporarily redirected to persistent
                 storage elsewhere in the data center.\par

                 The key challenge is doing this transparently and
                 efficiently at the block level, without sacrificing
                 consistency or failure resilience. We describe our
                 write off-loading design and implementation that
                 achieves these goals. We evaluate it by replaying
                 portions of our traces on a rack-based testbed. Results
                 show that just spinning disks down when idle saves
                 28--36\% of energy, and write off-loading further
                 increases the savings to 45--60\%.",
  acknowledgement = ack-nhfb,
  articleno =    "10",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "DiskEnergy; disk spin-down; energy; enterprise
                 storage; power; write off-loading",
}

@Article{MacCormick:2009:KNA,
  author =       "John MacCormick and Nicholas Murphy and Venugopalan
                 Ramasubramanian and Udi Wieder and Junfeng Yang and
                 Lidong Zhou",
  title =        "Kinesis: {A} new approach to replica placement in
                 distributed storage systems",
  journal =      j-TOS,
  volume =       "4",
  number =       "4",
  pages =        "11:1--11:??",
  month =        jan,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1480439.1480440",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:33:20 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Kinesis is a novel data placement model for
                 distributed storage systems. It exemplifies three
                 design principles: {\em structure\/} (division of
                 servers into a few failure-isolated segments), {\em
                 freedom of choice\/} (freedom to allocate the best
                 servers to store and retrieve data based on current
                 resource availability), and {\em scattered
                 distribution\/} (independent, pseudo-random spread of
                 replicas in the system). These design principles enable
                 storage systems to achieve balanced utilization of
                 storage and network resources in the presence of
                 incremental system expansions, failures of single and
                 shared components, and skewed distributions of data
                 size and popularity. In turn, this ability leads to
                 significantly reduced resource provisioning costs, good
                 user-perceived response times, and fast, parallelized
                 recovery from independent and correlated
                 failures.\par

                 This article validates Kinesis through theoretical
                 analysis, simulations, and experiments on a prototype
                 implementation. Evaluations driven by real-world traces
                 show that Kinesis can significantly outperform the
                 widely used Chain replica-placement strategy in terms
                 of resource requirements, end-to-end delay, and failure
                 recovery.",
  acknowledgement = ack-nhfb,
  articleno =    "11",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "load balancing; multiple-choice paradigm; Storage
                 system",
}

@Article{Huang:2009:QSS,
  author =       "Chih-Yuan Huang and Tei-Wei Kuo and Ai-Chun Pang",
  title =        "{QoS} for storage subsystems using {IEEE-1394}",
  journal =      j-TOS,
  volume =       "4",
  number =       "4",
  pages =        "12:1--12:??",
  month =        jan,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1480439.1480441",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:33:20 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "IEEE-1394 is widely adopted in various commercial
                 products for computing, communication, and
                 entertainment. Although many services with
                 Quality-of-Service (QoS) supports are now available in
                 systems over IEEE-1394, little work is done for
                 QoS-based resource allocation. In this article, we aim
                 at the design of a bandwidth reservation mechanism and
                 its policy for isochronous requests, such as those from
                 cameras. We then address the QoS support issue for
                 asynchronous requests, such as those from disks, and an
                 analytic framework for probability-based QoS
                 guarantees. This work is concluded by the proposing of
                 a topology configuration algorithm for IEEE-1394
                 devices. The capability of the proposed methodology and
                 the analytic framework are evaluated by a series of
                 experiments over a Linux-based system prototype.",
  acknowledgement = ack-nhfb,
  articleno =    "12",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "IEEE-1394; I/O subsystem; quality-of-service; real
                 time",
}

@Article{Anastasiadis:2009:RFA,
  author =       "Stergios V. Anastasiadis and Rajiv G. Wickremesinghe
                 and Jeffrey S. Chase",
  title =        "Rethinking {FTP}: Aggressive block reordering for
                 large file transfers",
  journal =      j-TOS,
  volume =       "4",
  number =       "4",
  pages =        "13:1--13:??",
  month =        jan,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1480439.1480442",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:33:20 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Whole-file transfer is a basic primitive for Internet
                 content dissemination. Content servers are increasingly
                 limited by disk arm movement, given the rapid growth in
                 disk density, disk transfer rates, server network
                 bandwidth, and content size. Individual file transfers
                 are sequential, but the block access sequence on a
                 content server is effectively random when many slow
                 clients access large files concurrently. Although
                 larger blocks can help improve disk throughput,
                 buffering requirements increase linearly with block
                 size.\par

                 This article explores a novel block reordering
                 technique that can reduce server disk traffic
                 significantly when large content files are shared. The
                 idea is to transfer blocks to each client in any order
                 that is convenient for the server. The server sends
                 blocks to each client opportunistically in order to
                 maximize the advantage from the disk reads it issues to
                 serve other clients accessing the same file. We first
                 illustrate the motivation and potential impact of
                 aggressive block reordering using simple analytical
                 models. Then we describe a file transfer system using a
                 simple block reordering algorithm, called Circus.
                 Experimental results with the Circus prototype show
                 that it can improve server throughput by a factor of
                 two or more in workloads with strong file access
                 locality.",
  acknowledgement = ack-nhfb,
  articleno =    "13",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "Disk access; file transfer protocols; scheduling",
}

@Article{Choi:2009:JFT,
  author =       "Hyun Jin Choi and Seung-Ho Lim and Kyu Ho Park",
  title =        "{JFTL}: {A} flash translation layer based on a journal
                 remapping for flash memory",
  journal =      j-TOS,
  volume =       "4",
  number =       "4",
  pages =        "14:1--14:??",
  month =        jan,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1480439.1480443",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:33:20 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "In flash memory-based storage, a Flash Translation
                 Layer (FTL) manages the mapping between the logical
                 addresses of a file system and the physical addresses
                 of the flash memory. When a journaling file system is
                 set up on the FTL, the consistency of the file system
                 is guaranteed by duplications of the same file system
                 changes in both the journal region of the file system
                 and the home locations of the changes. However, these
                 duplications inevitably degrade the performance of the
                 file system. In this article we present an efficient
                 FTL, called {\em JFTL}, based on a journal remapping
                 technique. The FTL uses an address mapping method to
                 write all the data to a new region in a process known
                 as an out-of-place update. Because of this process, the
                 existing data in flash memory is not overwritten by
                 such an update. By using this characteristic of the
                 FTL, the JFTL remaps addresses of the logged file
                 system changes to addresses of the home locations of
                 the changes, instead of writing the changes once more
                 to flash memory. Thus, the JFTL efficiently eliminates
                 redundant data in the flash memory as well as
                 preserving the consistency of the journaling file
                 system. Our experiments confirm that, when associated
                 with a writeback or ordered mode of a conventional EXT3
                 file system, the JFTL enhances the performance of EXT3
                 by up to 20\%. Furthermore, when the JFTL operates with
                 a journaled mode of EXT3, there is almost a twofold
                 performance gain in many cases. Moreover, the recovery
                 performance of the JFTL is much better than that of the
                 FTL.",
  acknowledgement = ack-nhfb,
  articleno =    "14",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "Flash memory; flash translation layer; garbage
                 detection; journaling file system; journal remapping",
}

@Article{Li:2009:GCS,
  author =       "Mingqiang Li and Jiwu Shu and Weimin Zheng",
  title =        "{GRID} codes: Strip-based erasure codes with high
                 fault tolerance for storage systems",
  journal =      j-TOS,
  volume =       "4",
  number =       "4",
  pages =        "15:1--15:??",
  month =        jan,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1480439.1480444",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:33:20 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "As storage systems grow in size and complexity, they
                 are increasingly confronted with concurrent disk
                 failures together with multiple unrecoverable sector
                 errors. To ensure high data reliability and
                 availability, erasure codes with high fault tolerance
                 are required. In this article, we present a new family
                 of erasure codes with high fault tolerance, named GRID
                 codes. They are called such because they are a family
                 of {\em strip-based codes\/} whose strips are arranged
                 into multi-dimensional grids. In the construction of
                 GRID codes, we first introduce a concept of {\em
                 matched codes\/} and then discuss how to use matched
                 codes to construct GRID codes. In addition, we propose
                 an iterative reconstruction algorithm for GRID codes.
                 We also discuss some important features of GRID codes.
                 Finally, we compare GRID codes with several categories
                 of existing codes. Our comparisons show that for
                 large-scale storage systems, our GRID codes have
                 attractive advantages over many existing erasure codes:
                 (a) They are completely XOR-based and have very regular
                 structures, ensuring easy implementation; (b) they can
                 provide up to 15 and even higher fault tolerance; and
                 (c) their storage efficiency can reach up to 80\% and
                 even higher. All the advantages make GRID codes more
                 suitable for large-scale storage systems.",
  acknowledgement = ack-nhfb,
  articleno =    "15",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "Disk failure; erasure code; fault tolerance; storage
                 system; unrecoverable sector error",
}

@Article{Bahn:2009:PPS,
  author =       "Hyokyung Bahn and Soyoon Lee and Sam H. Noh",
  title =        "{P\slash PA-SPTF}: Parallelism-aware request
                 scheduling algorithms for {MEMS}-based storage
                 devices",
  journal =      j-TOS,
  volume =       "5",
  number =       "1",
  pages =        "1:1--1:??",
  month =        mar,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1502777.1502778",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:33:38 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "MEMS-based storage is foreseen as a promising storage
                 media that provides high-bandwidth, low-power
                 consumption, high-density, and low cost. Due to these
                 versatile features, MEMS storage is anticipated to be
                 used for a wide range of applications from storage for
                 small handheld devices to high capacity mass storage
                 servers. However, MEMS storage has vastly different
                 physical characteristics compared to a traditional
                 disk. First, MEMS storage has thousands of heads that
                 can be activated simultaneously. Second, the media of
                 MEMS storage is a square structure which is different
                 from the platter structure of disks. This article
                 presents a new request scheduling algorithm for MEMS
                 storage called P-SPTF that makes use of the
                 aforementioned characteristics. P-SPTF considers the
                 parallelism of MEMS storage as well as the seek time of
                 requests on the two dimensional square structure. We
                 then present another algorithm called PA-SPTF that
                 considers the aging factor so that starvation
                 resistance is improved. Simulation studies show that
                 PA-SPTF improves the performance of MEMS storage by up
                 to 39.2\% in terms of the average response time and
                 62.4\% in terms of starvation resistance compared to
                 the widely acknowledged SPTF algorithm. We also show
                 that there exists a spectrum of scheduling algorithms
                 that subsumes both the P-SPTF and PA-SPTF algorithms.",
  acknowledgement = ack-nhfb,
  articleno =    "1",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "MEMS-based storage; parallelism; scheduling; seek
                 time; starvation",
}

@Article{Ma:2009:NAS,
  author =       "Di Ma and Gene Tsudik",
  title =        "A new approach to secure logging",
  journal =      j-TOS,
  volume =       "5",
  number =       "1",
  pages =        "2:1--2:??",
  month =        mar,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1502777.1502779",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:33:38 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "The need for secure logging is well-understood by the
                 security professionals, including both researchers and
                 practitioners. The ability to efficiently verify all
                 (or some) log entries is important to any application
                 employing secure logging techniques. In this article,
                 we begin by examining the state of the art in secure
                 logging and identify some problems inherent to systems
                 based on trusted third-party servers. We then propose a
                 different approach to secure logging based upon
                 recently developed Forward-Secure Sequential Aggregate
                 (FssAgg) authentication techniques. Our approach offers
                 both space-efficiency and provable security. We
                 illustrate two concrete schemes --- one
                 private-verifiable and one public-verifiable --- that
                 offer practical secure logging without any reliance on
                 online trusted third parties or secure hardware. We
                 also investigate the concept of immutability in the
                 context of forward-secure sequential aggregate
                 authentication to provide finer grained verification.
                 Finally we evaluate proposed schemes and report on our
                 experience with implementing them within a secure
                 logging system.",
  acknowledgement = ack-nhfb,
  articleno =    "2",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "forward secure sequential aggregate (FssAgg)
                 authentication; forward-secure stream integrity; MACs;
                 Secure logging; signatures; truncation attack",
}

@Article{Garrison:2009:UFS,
  author =       "John A. Garrison and A. L. Narasimha Reddy",
  title =        "{Umbrella File System}: Storage management across
                 heterogeneous devices",
  journal =      j-TOS,
  volume =       "5",
  number =       "1",
  pages =        "3:1--3:??",
  month =        mar,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1502777.1502780",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:33:38 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "With the advent of and recent developments in Flash
                 storage, device characteristic diversity is becoming
                 both more prevalent and more distinct. In this article,
                 we describe the Umbrella File System (UmbrellaFS), a
                 stackable file system designed to provide flexibility
                 in matching diversity of file access characteristics to
                 diversity of device characteristics through a user or
                 system administrator specified policy. We present the
                 design and results from a prototype implementation of
                 UmbrellaFS on both Linux 2.4 and 2.6. The results show
                 that UmbrellaFS has little overhead for most file
                 system operations while providing an ability better to
                 utilize the differences in Flash and traditional hard
                 drives. With appropriate use of rules, we have shown
                 improvements of up to 44\% in certain situations.",
  acknowledgement = ack-nhfb,
  articleno =    "3",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "Device characteristics; flash drives; namespaces;
                 policy-driven storage",
}

@Article{Mi:2009:EMI,
  author =       "Ningfang Mi and Alma Riska and Qi Zhang and Evgenia
                 Smirni and Erik Riedel",
  title =        "Efficient management of idleness in storage systems",
  journal =      j-TOS,
  volume =       "5",
  number =       "2",
  pages =        "4:1--4:??",
  month =        jun,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1534912.1534913",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:33:46 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Various activities that intend to enhance performance,
                 reliability, and availability of storage systems are
                 scheduled with low priority and served during idle
                 times. Under such conditions, idleness becomes a
                 valuable ``resource'' that needs to be efficiently
                 managed. A common approach in system design is to be
                 nonwork conserving by ``idle waiting'', that is, delay
                 the scheduling of background jobs to avoid slowing down
                 upcoming foreground tasks.\par

                 In this article, we complement ``idle waiting'' with
                 the ``estimation'' of background work to be served in
                 every idle interval to effectively manage the trade-off
                 between the performance of foreground and background
                 tasks. As a result, the storage system is better
                 utilized without compromising foreground performance.
                 Our analysis shows that if idle times have low
                 variability, then idle waiting is not necessary. Only
                 if idle times are highly variable does idle waiting
                 become necessary to minimize the impact of background
                 activity on foreground performance. We further show
                 that if there is burstiness in idle intervals, then it
                 is possible to predict accurately the length of
                 incoming idle intervals and use this information to
                 serve more background jobs without affecting foreground
                 performance.",
  acknowledgement = ack-nhfb,
  articleno =    "4",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "background jobs; continuous data histogram; foreground
                 jobs; idleness; idle periods; low priority work;
                 performance guarantee; resource management; storage
                 systems",
}

@Article{Storer:2009:PSR,
  author =       "Mark W. Storer and Kevin M. Greenan and Ethan L.
                 Miller and Kaladhar Voruganti",
  title =        "{POTSHARDS} --- a secure, recoverable, long-term
                 archival storage system",
  journal =      j-TOS,
  volume =       "5",
  number =       "2",
  pages =        "5:1--5:??",
  month =        jun,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1534912.1534914",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:33:46 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Users are storing ever-increasing amounts of
                 information digitally, driven by many factors including
                 government regulations and the public's desire to
                 digitally record their personal histories.
                 Unfortunately, many of the security mechanisms that
                 modern systems rely upon, such as encryption, are
                 poorly suited for storing data for indefinitely long
                 periods of time; it is very difficult to manage keys
                 and update cryptosystems to provide secrecy through
                 encryption over periods of decades. Worse, an adversary
                 who can compromise an archive need only wait for
                 cryptanalysis techniques to catch up to the encryption
                 algorithm used at the time of the compromise in order
                 to obtain ``secure'' data. To address these concerns,
                 we have developed POTSHARDS, an archival storage system
                 that provides long-term security for data with very
                 long lifetimes without using encryption. Secrecy is
                 achieved by using unconditionally secure secret
                 splitting and spreading the resulting shares across
                 separately managed archives. Providing availability and
                 data recovery in such a system can be difficult; thus,
                 we use a new technique, approximate pointers, in
                 conjunction with secure distributed RAID techniques to
                 provide availability and reliability across independent
                 archives. To validate our design, we developed a
                 prototype POTSHARDS implementation. In addition to
                 providing us with an experimental testbed, this
                 prototype helped us to understand the design issues
                 that must be addressed in order to maximize security.",
  acknowledgement = ack-nhfb,
  articleno =    "5",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "approximate pointers; Archival storage; secret
                 splitting",
}

@Article{Bhadkamkar:2009:SSS,
  author =       "Medha Bhadkamkar and Fernando Farfan and Vagelis
                 Hristidis and Raju Rangaswami",
  title =        "Storing semi-structured data on disk drives",
  journal =      j-TOS,
  volume =       "5",
  number =       "2",
  pages =        "6:1--6:??",
  month =        jun,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1534912.1534915",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:33:46 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Applications that manage semi-structured data are
                 becoming increasingly commonplace. Current approaches
                 for storing semi-structured data use existing storage
                 machinery; they either map the data to relational
                 databases, or use a combination of flat files and
                 indexes. While employing these existing storage
                 mechanisms provides readily available solutions, there
                 is a need to more closely examine their suitability to
                 this class of data. Particularly, retrofitting existing
                 solutions for semi-structured data can result in a
                 mismatch between the tree structure of the data and the
                 access characteristics of the underlying storage device
                 (disk drive). This study explores various possibilities
                 in the design space of native storage solutions for
                 semi-structured data by exploring alternative
                 approaches that match application data access
                 characteristics to those of the underlying disk drive.
                 For evaluating the effectiveness of the proposed native
                 techniques in relation to the existing solution, we
                 experiment with XML data using the XPathMark benchmark.
                 Extensive evaluation reveals the strengths and
                 weaknesses of the proposed native data layout
                 techniques. While the existing solutions work really
                 well for {\em deep-focused\/} queries into a
                 semi-structured document (those that result in
                 retrieving entire subtrees), the proposed native
                 solutions substantially outperform for the {\em
                 non-deep-focused\/} queries, which we demonstrate are
                 at least as important as the deep-focused. We believe
                 that native data layout techniques offer a unique
                 direction for improving the performance of
                 semi-structured data stores for a variety of important
                 workloads. However, given that the proposed native
                 techniques require circumventing current storage stack
                 abstractions, further investigation is warranted before
                 they can be applied to general-purpose storage
                 systems.",
  acknowledgement = ack-nhfb,
  articleno =    "6",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "Semi-structured data; storage management; XML",
}

@Article{Thomasian:2009:HRR,
  author =       "Alexander Thomasian and Mario Blaum",
  title =        "Higher reliability redundant disk arrays:
                 Organization, operation, and coding",
  journal =      j-TOS,
  volume =       "5",
  number =       "3",
  pages =        "7:1--7:??",
  month =        nov,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1629075.1629076",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:33:57 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Parity is a popular form of data protection in {\em
                 redundant arrays of inexpensive/independent disks
                 (RAID)}. RAID5 dedicates one out of {\em N\/} disks to
                 parity to mask single disk failures, that is, the
                 contents of a block on a failed disk can be
                 reconstructed by exclusive-ORing the corresponding
                 blocks on surviving disks. RAID5 can mask a single disk
                 failure, and it is vulnerable to data loss if a second
                 disk failure occurs. The RAID5 rebuild process
                 systematically reconstructs the contents of a failed
                 disk on a spare disk, returning the system to its
                 original state, but the rebuild process may be
                 unsuccessful due to unreadable sectors. This has led to
                 {\em two disk failure tolerant arrays (2DFTs)}, such as
                 RAID6 based on Reed--Solomon (RS) codes. EVENODD, RDP
                 (Row-Diagonal-Parity), the X-code, and RM2 (Row-Matrix)
                 are 2DFTs with parity coding. RM2 incurs a higher level
                 of redundancy than two disks, while the X-code is
                 limited to a prime number of disks. RDP is optimal with
                 respect to the number of XOR operations at the
                 encoding, but not for short write operations. For small
                 symbol sizes EVENODD and RDP have the same disk access
                 pattern as RAID6, while RM2 and the X-code incur a high
                 recovery cost with two failed disks. We describe
                 variations to RAID5 and RAID6 organizations, including
                 clustered RAID, different methods to update parities,
                 rebuild processing, disk scrubbing to eliminate sector
                 errors, and the {\em intra-disk redundancy (IDR)\/}
                 method to deal with sector errors. We summarize the
                 results of recent studies of failures in hard disk
                 drives. We describe Markov chain reliability models to
                 estimate RAID {\em mean time to data loss (MTTDL)\/}
                 taking into account sector errors and the effect of
                 disk scrubbing. Numerical results show that RAID5 plus
                 IDR attains the same MTTDL level as RAID6, while
                 incurring a lower performance penalty. We conclude with
                 a survey of analytic and simulation studies of RAID
                 performance and tools and benchmarks for RAID
                 performance evaluation.",
  acknowledgement = ack-nhfb,
  articleno =    "7",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "Disk array; disk failure studies; performance
                 evaluation; RAID; reliability evaluation",
}

@Article{Tosun:2009:DCS,
  author =       "Ali {\c{S}}aman Tosun",
  title =        "Divide-and-conquer scheme for strictly optimal
                 retrieval of range queries",
  journal =      j-TOS,
  volume =       "5",
  number =       "3",
  pages =        "8:1--8:??",
  month =        nov,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1629075.1629077",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:33:57 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Declustering distributes data among parallel disks to
                 reduce retrieval cost using I/O parallelism. Many
                 schemes were proposed for single copy declustering of
                 spatial data. Recently, declustering using replication
                 gained a lot of interest and several schemes with
                 different properties were proposed. It is
                 computationally expensive to verify optimality of
                 replication schemes designed for range queries and
                 existing schemes verify optimality for up to 50 disks.
                 In this article, we propose a novel method to find
                 replicated declustering schemes that render all spatial
                 range queries optimal. The proposed scheme uses
                 threshold based declustering, divisibility of large
                 queries for optimization and optimistic approach to
                 compute maximum flow. The proposed scheme is generic
                 and works for any number of dimensions. Experimental
                 results show that using 3 copies there exist
                 allocations that render all spatial range queries
                 optimal for up to 750 disks in 2 dimensions and with
                 the exception of several values for up to 100 disks in
                 3 dimensions. The proposed scheme improves search for
                 strictly optimal replicated declustering schemes
                 significantly and will be a valuable tool to answer
                 open problems on replicated declustering.",
  acknowledgement = ack-nhfb,
  articleno =    "8",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "Declustering; number theory; parallel I/0;
                 replication; spatial range query; threshold",
}

@Article{Qin:2009:DLB,
  author =       "Xiao Qin and Hong Jiang and Adam Manzanares and
                 Xiaojun Ruan and Shu Yin",
  title =        "Dynamic load balancing for {I/O}-intensive
                 applications on clusters",
  journal =      j-TOS,
  volume =       "5",
  number =       "3",
  pages =        "9:1--9:??",
  month =        nov,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1629075.1629078",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:33:57 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Load balancing for clusters has been investigated
                 extensively, mainly focusing on the effective usage of
                 global CPU and memory resources. However, previous CPU-
                 or memory-centric load balancing schemes suffer
                 significant performance drop under I/O-intensive
                 workloads due to the imbalance of I/O load. To solve
                 this problem, we propose two simple yet effective
                 I/O-aware load-balancing schemes for two types of
                 clusters: (1) homogeneous clusters where nodes are
                 identical and (2) heterogeneous clusters, which are
                 comprised of a variety of nodes with different
                 performance characteristics in computing power, memory
                 capacity, and disk speed. In addition to assigning
                 I/O-intensive sequential and parallel jobs to nodes
                 with light I/O loads, the proposed schemes judiciously
                 take into account both CPU and memory load sharing in
                 the system. Therefore, our schemes are able to maintain
                 high performance for a wide spectrum of workloads. We
                 develop analytic models to study mean slowdowns, task
                 arrival, and transfer processes in system levels. Using
                 a set of real I/O-intensive parallel applications and
                 synthetic parallel jobs with various I/O
                 characteristics, we show that our proposed schemes
                 consistently improve the performance over existing
                 non-I/O-aware load-balancing schemes, including CPU-
                 and Memory-aware schemes and a PBS-like batch scheduler
                 for parallel and sequential jobs, for a diverse set of
                 workload conditions. Importantly, this performance
                 improvement becomes much more pronounced when the
                 applications are I/O-intensive. For example, the
                 proposed approaches deliver 23.6--88.0 \% performance
                 improvements for I/O-intensive applications such as LU
                 decomposition, Sparse Cholesky, Titan, Parallel text
                 searching, and Data Mining. When I/O load is low or
                 well balanced, the proposed schemes are capable of
                 maintaining the same level of performance as the
                 existing non-I/O-aware schemes.",
  acknowledgement = ack-nhfb,
  articleno =    "9",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "clusters; heterogeneity; I/O-intensive applications;
                 Load balancing; storage systems",
}

@Article{Xie:2009:FAS,
  author =       "Tao Xie and Yao Sun",
  title =        "A file assignment strategy independent of workload
                 characteristic assumptions",
  journal =      j-TOS,
  volume =       "5",
  number =       "3",
  pages =        "10:1--10:??",
  month =        nov,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1629075.1629079",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:33:57 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "The problem of statically assigning nonpartitioned
                 files in a parallel I/O system has been extensively
                 investigated. A basic workload characteristic
                 assumption of most existing solutions to the problem is
                 that there exists a strong inverse correlation between
                 file access frequency and file size. In other words,
                 the most popular files are typically small in size,
                 while the large files are relatively unpopular. Recent
                 studies on the characteristics of Web proxy traces
                 suggested, however, the correlation, if any, is so weak
                 that it can be ignored. Hence, the following two
                 questions arise naturally. First, can existing
                 algorithms still perform well when the workload
                 assumption does not hold? Second, if not, can one
                 develop a new file assignment strategy that is immune
                 to the workload assumption? To answer these questions,
                 we first evaluate the performance of three well-known
                 file assignment algorithms with and without the
                 workload assumption, respectively. Next, we develop a
                 novel static nonpartitioned file assignment strategy
                 for parallel I/O systems, called static round-robin
                 (SOR), which is immune to the workload assumption.
                 Comprehensive experimental results show that SOR
                 consistently improves the performance in terms of mean
                 response time over the existing schemes.",
  acknowledgement = ack-nhfb,
  articleno =    "10",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "File assignment; load balancing; parallel I/O;
                 workload characteristics; Zipfian distribution",
}

@Article{Seltzer:2009:ISI,
  author =       "Margo Seltzer and Ric Wheeler",
  title =        "Introduction to special issue {FAST 2009}",
  journal =      j-TOS,
  volume =       "5",
  number =       "4",
  pages =        "11:1--11:??",
  month =        dec,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1629080.1629081",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:34:12 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "11",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Hasan:2009:PHF,
  author =       "Ragib Hasan and Radu Sion and Marianne Winslett",
  title =        "Preventing history forgery with secure provenance",
  journal =      j-TOS,
  volume =       "5",
  number =       "4",
  pages =        "12:1--12:??",
  month =        dec,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1629080.1629082",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:34:12 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "As increasing amounts of valuable information are
                 produced and persist digitally, the ability to
                 determine the origin of data becomes important. In
                 science, medicine, commerce, and government, data
                 provenance tracking is essential for rights protection,
                 regulatory compliance, management of intelligence and
                 medical data, and authentication of information as it
                 flows through workplace tasks. While significant
                 research has been conducted in this area, the
                 associated security and privacy issues have not been
                 explored, leaving provenance information vulnerable to
                 illicit alteration as it passes through untrusted
                 environments.\par

                 In this article, we show how to provide strong
                 integrity and confidentiality assurances for data
                 provenance information at the kernel, file system, or
                 application layer. We describe Sprov, our
                 provenance-aware system prototype that implements
                 provenance tracking of data writes at the application
                 layer, which makes Sprov extremely easy to deploy. We
                 present empirical results that show that, for real-life
                 workloads, the runtime overhead of Sprov for recording
                 provenance with confidentiality and integrity
                 guarantees ranges from 1\% to 13\%, when all file
                 modifications are recorded, and from 12\% to 16\%, when
                 all file read and modifications are tracked.",
  acknowledgement = ack-nhfb,
  articleno =    "12",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "audit; confidentiality; integrity; lineage;
                 provenance; security",
}

@Article{Muniswamy-Reddy:2009:CBV,
  author =       "Kiran-Kumar Muniswamy-Reddy and David A. Holland",
  title =        "Causality-based versioning",
  journal =      j-TOS,
  volume =       "5",
  number =       "4",
  pages =        "13:1--13:??",
  month =        dec,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1629080.1629083",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:34:12 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Versioning file systems provide the ability to recover
                 from a variety of failures, including file corruption,
                 virus and worm infestations, and user mistakes.
                 However, using versions to recover from data-corrupting
                 events requires a human to determine precisely which
                 files and versions to restore. We can create more
                 meaningful versions and enhance the value of those
                 versions by capturing the causal connections among
                 files, facilitating selection and recovery of precisely
                 the right versions after data corrupting events.\par

                 We determine when to create new versions of files
                 automatically using the causal relationships among
                 files. The literature on versioning file systems
                 usually examines two extremes of possible
                 version-creation algorithms: open-to-close versioning
                 and versioning on every write. We evaluate causal
                 versions of these two algorithms and introduce two
                 additional causality-based algorithms: Cycle-Avoidance
                 and Graph-Finesse.\par

                 We show that capturing and maintaining causal
                 relationships imposes less than 7\% overhead on a
                 versioning system, providing benefit at low cost. We
                 then show that Cycle-Avoidance provides more meaningful
                 versions of files created during concurrent program
                 execution, with overhead comparable to open/close
                 versioning. Graph-Finesse provides even greater
                 control, frequently at comparable overhead, but
                 sometimes at unacceptable overhead. Versioning on every
                 write is an interesting extreme case, but is far too
                 costly to be useful in practice.",
  acknowledgement = ack-nhfb,
  articleno =    "13",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "causality; data provenance",
}

@Article{Vrable:2009:CFB,
  author =       "Michael Vrable and Stefan Savage and Geoffrey M.
                 Voelker",
  title =        "{Cumulus}: Filesystem backup to the cloud",
  journal =      j-TOS,
  volume =       "5",
  number =       "4",
  pages =        "14:1--14:??",
  month =        dec,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1629080.1629084",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:34:12 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Cumulus is a system for efficiently implementing
                 filesystem backups over the Internet, specifically
                 designed under a {\em thin cloud\/} assumption --- that
                 the remote datacenter storing the backups does not
                 provide any special backup services, but only a
                 least-common-denominator storage interface. Cumulus
                 aggregates data from small files for storage and uses
                 LFS-inspired segment cleaning to maintain storage
                 efficiency. While Cumulus can use virtually any storage
                 service, we show its efficiency is comparable to
                 integrated approaches.",
  acknowledgement = ack-nhfb,
  articleno =    "14",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "Backup; cloud storage",
}

@Article{Batsakis:2009:CNC,
  author =       "Alexandros Batsakis and Randal Burns and Arkady
                 Kanevsky and James Lentini and Thomas Talpey",
  title =        "{CA-NFS}: {A} congestion-aware network file system",
  journal =      j-TOS,
  volume =       "5",
  number =       "4",
  pages =        "15:1--15:??",
  month =        dec,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1629080.1629085",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:34:12 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "We develop a holistic framework for adaptively
                 scheduling asynchronous requests in distributed file
                 systems. The system is holistic in that it manages all
                 resources, including network bandwidth, server I/O,
                 server CPU, and client and server memory utilization.
                 It accelerates, defers, or cancels asynchronous
                 requests in order to improve application-perceived
                 performance directly. We employ congestion pricing via
                 online auctions to coordinate the use of system
                 resources by the file system clients so that they can
                 detect shortages and adapt their resource usage. We
                 implement our modifications in the Congestion-Aware
                 Network File System (CA-NFS), an extension to the
                 ubiquitous network file system (NFS). Our experimental
                 result shows that CA-NFS results in a 20\% improvement
                 in execution times when compared with NFS for a variety
                 of workloads.",
  acknowledgement = ack-nhfb,
  articleno =    "15",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "congestion; File systems; NFS; performance;
                 scalability",
}

@Article{Agrawal:2009:GRI,
  author =       "Nitin Agrawal and Andrea C. Arpaci-Dusseau and Remzi
                 H. Arpaci-Dusseau",
  title =        "Generating realistic {{\em Impressions\/}} for
                 file-system benchmarking",
  journal =      j-TOS,
  volume =       "5",
  number =       "4",
  pages =        "16:1--16:??",
  month =        dec,
  year =         "2009",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1629080.1629086",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Mar 16 15:34:12 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "The performance of file systems and related software
                 depends on characteristics of the underlying
                 file-system image (i.e., file-system metadata and file
                 contents). Unfortunately, rather than benchmarking with
                 realistic file-system images, most system designers and
                 evaluators rely on {\em ad hoc\/} assumptions and
                 (often inaccurate) rules of thumb. Furthermore, the
                 lack of standardization and reproducibility makes
                 file-system benchmarking ineffective. To remedy these
                 problems, we develop Impressions, a framework to
                 generate statistically accurate file-system images with
                 realistic metadata and content. Impressions is
                 flexible, supporting user-specified constraints on
                 various file-system parameters using a number of
                 statistical techniques to generate consistent images.
                 In this article, we present the design, implementation,
                 and evaluation of Impressions and demonstrate its
                 utility using desktop search as a case study. We
                 believe Impressions will prove to be useful to system
                 developers and users alike.",
  acknowledgement = ack-nhfb,
  articleno =    "16",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "File and storage system benchmarking",
}

@Article{Khatib:2010:OMB,
  author =       "Mohammed G. Khatib and Pieter H. Hartel",
  title =        "Optimizing {MEMS}-based storage devices for mobile
                 battery-powered systems",
  journal =      j-TOS,
  volume =       "6",
  number =       "1",
  pages =        "1:1--1:??",
  month =        mar,
  year =         "2010",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1714454.1714455",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Aug 14 17:04:28 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "An emerging storage technology, called MEMS-based
                 storage, promises nonvolatile storage devices with
                 ultrahigh density, high rigidity, a small form factor,
                 and low cost. For these reasons, MEMS-based storage
                 devices are suitable for battery-powered mobile systems
                 such as PDAs. For deployment in such systems,
                 MEMS-based storage devices must consume little energy.
                 This work mainly targets reducing the energy
                 consumption of this class of devices.\par

                 We derive the operation modes of a MEMS-based storage
                 device and systemically devise a policy in each mode
                 for energy saving. Three types of policies are
                 presented: power management, shutdown, and data-layout
                 policy. Combined, these policies reduce the total
                 energy consumed by a MEMS-based storage device. A
                 MEMS-based storage device that enforces these policies
                 comes close to Flash with respect to energy consumption
                 and response time. However, enhancement on the device
                 level is still needed; we present some suggestions to
                 resolve this issue.",
  acknowledgement = ack-nhfb,
  articleno =    "1",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "design space; energy efficiency; green storage; mobile
                 systems; Probe storage",
}

@Article{Yu:2010:NVS,
  author =       "Young Jin Yu and Dong In Shin and Hyeonsang Eom and
                 Heon Young Yeom",
  title =        "{NCQ} vs. {I/O} scheduler: Preventing unexpected
                 misbehaviors",
  journal =      j-TOS,
  volume =       "6",
  number =       "1",
  pages =        "2:1--2:??",
  month =        mar,
  year =         "2010",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1714454.1714456",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Aug 14 17:04:28 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Native Command Queueing (NCQ) is an optimization
                 technology to maximize throughput by reordering
                 requests inside a disk drive. It has been so successful
                 that NCQ has become the standard in SATA 2 protocol
                 specification, and the great majority of disk vendors
                 have adopted it for their recent disks. However, there
                 is a possibility that the technology may lead to an
                 information gap between the OS and a disk drive. A
                 NCQ-enabled disk tries to optimize throughput without
                 realizing the intention of an OS, whereas the OS does
                 its best under the assumption that the disk will do as
                 it is told without specific knowledge regarding the
                 details of the disk mechanism. Let us call this {\em
                 expectation discord}, which may cause serious problems
                 such as request starvations or performance anomaly. In
                 this article, we (1) confirm that {\em expectation
                 discord\/} actually occurs in real systems; (2) propose
                 software-level approaches to solve them; and (3)
                 evaluate our mechanism. Experimental results show that
                 our solution is simple, cheap (no special hardware
                 required), portable, and effective.",
  acknowledgement = ack-nhfb,
  articleno =    "2",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "hybrid scheduling; I/O prioritization; NCQ; SATA 2;
                 starvation detection",
}

@Article{Jung:2010:FES,
  author =       "Jaemin Jung and Youjip Won and Eunki Kim and Hyungjong
                 Shin and Byeonggil Jeon",
  title =        "{FRASH}: Exploiting storage class memory in hybrid
                 file system for hierarchical storage",
  journal =      j-TOS,
  volume =       "6",
  number =       "1",
  pages =        "3:1--3:??",
  month =        mar,
  year =         "2010",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1714454.1714457",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Aug 14 17:04:28 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "In this work, we develop a novel hybrid file system,
                 FRASH, for storage-class memory and NAND Flash. Despite
                 the promising physical characteristics of storage-class
                 memory, its scale is an order of magnitude smaller than
                 the current storage device scale. This fact makes it
                 less than desirable for use as an independent storage
                 device. We carefully analyze in-memory and on-disk file
                 system objects in a log-structured file system, and
                 exploit memory and storage aspects of the storage-class
                 memory to overcome the drawbacks of the current
                 log-structured file system. FRASH provides a hybrid
                 view storage-class memory. It harbors an in-memory data
                 structure as well as a on-disk structure. It provides
                 nonvolatility to key data structures which have been
                 maintained in-memory in a legacy log-structured file
                 system. This approach greatly improves the mount
                 latency and effectively resolves the robustness issue.
                 By maintaining on-disk structure in storage-class
                 memory, FRASH provides byte-addressability to the file
                 system object and metadata for page, and subsequently
                 greatly improves the I/O performance compared to the
                 legacy log-structured approach. While storage-class
                 memory offers byte granularity, it is still far slower
                 than its DRAM counter part. We develop a copy-on-mount
                 technique to overcome the access latency difference
                 between main memory and storage-class memory. Our file
                 system was able to reduce the mount time by 92\% and
                 file system I/O performance was increased by 16\%.",
  acknowledgement = ack-nhfb,
  articleno =    "3",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "Flash storage; log-structured file system",
}

@Article{Balakrishnan:2010:DRR,
  author =       "Mahesh Balakrishnan and Asim Kadav and Vijayan
                 Prabhakaran and Dahlia Malkhi",
  title =        "Differential {RAID}: Rethinking {RAID} for {SSD}
                 reliability",
  journal =      j-TOS,
  volume =       "6",
  number =       "2",
  pages =        "4:1--4:??",
  month =        jul,
  year =         "2010",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1807060.1807061",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Aug 14 17:04:39 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "SSDs exhibit very different failure characteristics
                 compared to hard drives. In particular, the bit error
                 rate (BER) of an SSD climbs as it receives more writes.
                 As a result, RAID arrays composed from SSDs are subject
                 to correlated failures. By balancing writes evenly
                 across the array, RAID schemes can wear out devices at
                 similar times. When a device in the array fails towards
                 the end of its lifetime, the high BER of the remaining
                 devices can result in data loss. We propose Diff-RAID,
                 a parity-based redundancy solution that creates an age
                 differential in an array of SSDs. Diff-RAID distributes
                 parity blocks unevenly across the array, leveraging
                 their higher update rate to age devices at different
                 rates. To maintain this age differential when old
                 devices are replaced by new ones, Diff-RAID reshuffles
                 the parity distribution on each drive replacement. We
                 evaluate Diff-RAID's reliability by using real BER data
                 from 12 flash chips on a simulator and show that it is
                 more reliable than RAID-5, in some cases by multiple
                 orders of magnitude. We also evaluate Diff-RAID's
                 performance using a software implementation on a
                 5-device array of 80 GB Intel X25-M SSDs and show that
                 it offers a trade-off between throughput and
                 reliability.",
  acknowledgement = ack-nhfb,
  articleno =    "4",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "flash; RAID; SSD",
}

@Article{Chang:2010:SEN,
  author =       "Yuan-Hao Chang and Jian-Hong Lin and Jen-Wei Hsieh and
                 Tei-Wei Kuo",
  title =        "A strategy to emulate {NOR} flash with {NAND} flash",
  journal =      j-TOS,
  volume =       "6",
  number =       "2",
  pages =        "5:1--5:??",
  month =        jul,
  year =         "2010",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1807060.1807062",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Aug 14 17:04:39 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "This work is motivated by a strong market demand for
                 the replacement of NOR flash memory with NAND flash
                 memory to cut down the cost of many embedded-system
                 designs, such as mobile phones. Different from
                 LRU-related caching or buffering studies, we are
                 interested in prediction-based prefetching based on
                 given execution traces of application executions. An
                 implementation strategy is proposed for the storage of
                 the prefetching information with limited SRAM and
                 run-time overheads. An efficient prediction procedure
                 is presented based on information extracted from
                 application executions to reduce the performance gap
                 between NAND flash memory and NOR flash memory in
                 reads. With the behavior of a target application
                 extracted from a set of collected traces, we show that
                 data access to NOR flash memory can respond effectively
                 over the proposed implementation.",
  acknowledgement = ack-nhfb,
  articleno =    "5",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "data prefetching; flash memory; NAND; NOR",
}

@Article{Gim:2010:EIQ,
  author =       "Jongmin Gim and Youjip Won",
  title =        "Extract and infer quickly: Obtaining sector geometry
                 of modern hard disk drives",
  journal =      j-TOS,
  volume =       "6",
  number =       "2",
  pages =        "6:1--6:??",
  month =        jul,
  year =         "2010",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1807060.1807063",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Aug 14 17:04:39 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "The modern hard disk drive is a complex and
                 complicated device. It consists of 2--4 heads,
                 thousands of sectors per track, several hundred
                 thousands of tracks, and tens of zones. The beginnings
                 of adjacent tracks are placed with a certain angular
                 offset. Sectors are placed on the tracks and accessed
                 in some order. Angular offset and sector placement
                 order vary widely subject to vendors and models. The
                 success of an efficient file and storage subsystem
                 design relies on the proper understanding of the
                 underlying storage device characteristics. The
                 characterization of hard disk drives has been a subject
                 of intense research for more than a decade. The scale
                 and complexity of state-of-the-art hard disk drive
                 technology calls for a new way of extracting and
                 analyzing the characteristics of the hard disk drive.
                 In this work, we develop a novel disk characterization
                 suite, DIG (Disk Geometry Analyzer), which allows us to
                 rapidly extract and characterize the key performance
                 metrics of the modern hard disk drive. Development of
                 this tool is accompanied by thorough examination of
                 four off-the-shelf hard disk drives. DIG consists of
                 three key ingredients: $O(1)$ a track boundary
                 detection algorithm; $O(\log n)$ a zone boundary
                 detection algorithm; and hybrid sampling based seek
                 time profiling. We particularly focus on addressing the
                 scalability aspect of disk characterization. With DIG,
                 we are able to extract key metrics of hard disk drives,
                 for example, track sizes, zone information, sector
                 geometry and so on, within 3--20 minutes. DIG allows us
                 to determine the sector layout mechanism of the
                 underlying hard disk drive, for example, hybrid
                 serpentine, cylinder serpentine, and surface
                 serpentine, and to a build complete sector map from LBN
                 to the three dimensional space of (Cylinder, Head,
                 Sector). Examining the hard disk drives with DIG, we
                 made a number of important observations. In modern hard
                 disk drives, head switch overhead is far greater than
                 track switch overhead. It seems that hard disk drive
                 vendors put greater emphasis on reducing the number of
                 head switches for data access. Most disk vendors use
                 surface serpentine, cylinder serpentine, or hybrid
                 serpentine schemes in laying sectors on the platters.
                 The legacy seek time model, which takes the form of $a
                 + b \sqrt d$ leaves much to be desired for use in
                 modern hard disk drives especially for short seeks
                 (less than 5000 tracks). We compare the performance of
                 the DIG against the existing state-of-the-art disk
                 profiling algorithm. Compared to the existing
                 state-of-the-art disk characterization algorithm, the
                 DIG algorithm significantly decreases the time to
                 extract comprehensive sector geometry information from
                 1920 minutes to 7 minutes and 1927 minutes to 180
                 minutes in best and worst case scenarios,
                 respectively.",
  acknowledgement = ack-nhfb,
  articleno =    "6",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "Hard disk; performance characterization; sector
                 geometry; seek time; track skew; zone",
}

@Article{Wang:2010:SSO,
  author =       "Yang Wang and Jiwu Shu and Guangyan Zhang and Wei Xue
                 and Weimin Zheng",
  title =        "{SOPA}: Selecting the optimal caching policy
                 adaptively",
  journal =      j-TOS,
  volume =       "6",
  number =       "2",
  pages =        "7:1--7:??",
  month =        jul,
  year =         "2010",
  CODEN =        "????",
  DOI =          "http://doi.acm.org/10.1145/1807060.1807064",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Aug 14 17:04:39 MDT 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "With the development of storage technology and
                 applications, new caching policies are continuously
                 being introduced. It becomes increasingly important for
                 storage systems to be able to select the matched
                 caching policy dynamically under varying workloads.
                 This article proposes SOPA, a cache framework to
                 adaptively select the matched policy and perform policy
                 switches in storage systems. SOPA encapsulates the
                 functions of a caching policy into a module, and
                 enables online policy switching by policy
                 reconstruction. SOPA then selects the policy matched
                 with the workload dynamically by collecting and
                 analyzing access traces. To reduce the decision-making
                 cost, SOPA proposes an asynchronous decision making
                 process. The simulation experiments show that no single
                 caching policy performed well under all of the
                 different workloads. With SOPA, a storage system could
                 select the appropriate policy for different workloads.
                 The real-system evaluation results show that SOPA
                 reduced the average response time by up to 20.3\% and
                 11.9\% compared with LRU and ARC, respectively.",
  acknowledgement = ack-nhfb,
  articleno =    "7",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
  keywords =     "Caching policies; policy adaptation; policy switch",
}

@Article{Burns:2010:GEF,
  author =       "Randal Burns and Kimberly Keeton",
  title =        "Guest editorial: {FAST'10}",
  journal =      j-TOS,
  volume =       "6",
  number =       "3",
  pages =        "8:1--8:??",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1837915.1837916",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Nov 23 10:40:15 MST 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "8",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Schroeder:2010:ULS,
  author =       "Bianca Schroeder and Sotirios Damouras and Phillipa
                 Gill",
  title =        "Understanding latent sector errors and how to protect
                 against them",
  journal =      j-TOS,
  volume =       "6",
  number =       "3",
  pages =        "9:1--9:??",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1837915.1837917",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Nov 23 10:40:15 MST 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "9",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Sehgal:2010:OEP,
  author =       "Priya Sehgal and Vasily Tarasov and Erez Zadok",
  title =        "Optimizing energy and performance for server-class
                 file system workloads",
  journal =      j-TOS,
  volume =       "6",
  number =       "3",
  pages =        "10:1--10:??",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1837915.1837918",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Nov 23 10:40:15 MST 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "10",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Sundararaman:2010:MOS,
  author =       "Swaminathan Sundararaman and Sriram Subramanian and
                 Abhishek Rajimwale and Andrea C. Arpaci-Dusseau and
                 Remzi H. Arpaci-Dusseau and Michael M. Swift",
  title =        "{Membrane}: {Operating} system support for restartable
                 file systems",
  journal =      j-TOS,
  volume =       "6",
  number =       "3",
  pages =        "11:1--11:??",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1837915.1837919",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Nov 23 10:40:15 MST 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "11",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Veeraraghavan:2010:QRF,
  author =       "Kaushik Veeraraghavan and Jason Flinn and Edmund B.
                 Nightingale and Brian Noble",
  title =        "{quFiles}: {The} right file at the right time",
  journal =      j-TOS,
  volume =       "6",
  number =       "3",
  pages =        "12:1--12:??",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1837915.1837920",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Nov 23 10:40:15 MST 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "12",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Koller:2010:DUC,
  author =       "Ricardo Koller and Raju Rangaswami",
  title =        "{I/O Deduplication}: {Utilizing} content similarity to
                 improve {I/O} performance",
  journal =      j-TOS,
  volume =       "6",
  number =       "3",
  pages =        "13:1--13:??",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1837915.1837921",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Nov 23 10:40:15 MST 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "13",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Josephson:2010:DFS,
  author =       "William K. Josephson and Lars A. Bongo and Kai Li and
                 David Flynn",
  title =        "{DFS}: {A} file system for virtualized flash storage",
  journal =      j-TOS,
  volume =       "6",
  number =       "3",
  pages =        "14:1--14:??",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1837915.1837922",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Nov 23 10:40:15 MST 2010",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "14",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Shim:2011:HFT,
  author =       "Gyudong Shim and Youngwoo Park and Kyu Ho Park",
  title =        "A hybrid flash translation layer with adaptive merge
                 for {SSDs}",
  journal =      j-TOS,
  volume =       "6",
  number =       "4",
  pages =        "15:1--15:??",
  month =        may,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1970338.1970339",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Jun 7 18:40:46 MDT 2011",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "15",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Plank:2011:MDR,
  author =       "James S. Plank and Adam L. Buchsbaum and Bradley T.
                 Vander Zanden",
  title =        "Minimum density {RAID-6} codes",
  journal =      j-TOS,
  volume =       "6",
  number =       "4",
  pages =        "16:1--16:??",
  month =        may,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1970338.1970340",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Jun 7 18:40:46 MDT 2011",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "16",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Tian:2011:OAU,
  author =       "Lei Tian and Qiang Cao and Hong Jiang and Dan Feng and
                 Changsheng Xie and Qin Xin",
  title =        "Online availability upgrades for parity-based {RAIDs}
                 through supplementary parity augmentations",
  journal =      j-TOS,
  volume =       "6",
  number =       "4",
  pages =        "17:1--17:??",
  month =        may,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1970338.1970341",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Jun 7 18:40:46 MDT 2011",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "17",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Chang:2011:DLC,
  author =       "Yuan-Hao Chang and Ping-Yi Hsu and Yung-Feng Lu and
                 Tei-Wei Kuo",
  title =        "A driver-layer caching policy for removable storage
                 devices",
  journal =      j-TOS,
  volume =       "7",
  number =       "1",
  pages =        "1:1--1:??",
  month =        jun,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1970343.1970344",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Oct 22 09:33:53 MDT 2011",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "1",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Tomazic:2011:FFE,
  author =       "Saso Tomazic and Vesna Pavlovic and Jasna Milovanovic
                 and Jaka Sodnik and Anton Kos and Sara Stancin and
                 Veljko Milutinovic",
  title =        "Fast file existence checking in archiving systems",
  journal =      j-TOS,
  volume =       "7",
  number =       "1",
  pages =        "2:1--2:??",
  month =        jun,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1970343.1970345",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Oct 22 09:33:53 MDT 2011",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "2",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Manzanares:2011:PBP,
  author =       "Adam Manzanares and Xiao Qin and Xiaojun Ruan and Shu
                 Yin",
  title =        "{PRE-BUD}: {Prefetching} for energy-efficient parallel
                 {I/O} systems with buffer disks",
  journal =      j-TOS,
  volume =       "7",
  number =       "1",
  pages =        "3:1--3:??",
  month =        jun,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1970343.1970346",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Oct 22 09:33:53 MDT 2011",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "3",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Shin:2011:RBI,
  author =       "Dong In Shin and Young Jin Yu and Hyeong S. Kim and
                 Hyeonsang Eom and Heon Young Yeom",
  title =        "Request Bridging and Interleaving: Improving the
                 Performance of Small Synchronous Updates under
                 Seek-Optimizing Disk Subsystems",
  journal =      j-TOS,
  volume =       "7",
  number =       "2",
  pages =        "4:1--4:??",
  month =        jul,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1970348.1970349",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Oct 22 09:33:54 MDT 2011",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "4",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Iliadis:2011:DSV,
  author =       "Ilias Iliadis and Robert Haas and Xiao-Yu Hu and
                 Evangelos Eleftheriou",
  title =        "Disk Scrubbing Versus Intradisk Redundancy for {RAID}
                 Storage Systems",
  journal =      j-TOS,
  volume =       "7",
  number =       "2",
  pages =        "5:1--5:??",
  month =        jul,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1970348.1970350",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Oct 22 09:33:54 MDT 2011",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "5",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{You:2011:PFE,
  author =       "Lawrence L. You and Kristal T. Pollack and Darrell D.
                 E. Long and K. Gopinath",
  title =        "{PRESIDIO}: {A} Framework for Efficient Archival Data
                 Storage",
  journal =      j-TOS,
  volume =       "7",
  number =       "2",
  pages =        "6:1--6:??",
  month =        jul,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1970348.1970351",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sat Oct 22 09:33:54 MDT 2011",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "6",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Brinkmann:2011:GE,
  author =       "Andr{\'e} Brinkmann and David Pease",
  title =        "Guest Editorial",
  journal =      j-TOS,
  volume =       "7",
  number =       "3",
  pages =        "7:1--7:??",
  month =        oct,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2027066.2027067",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sun Nov 6 06:42:42 MST 2011",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "7",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Carns:2011:UIC,
  author =       "Philip Carns and Kevin Harms and William Allcock and
                 Charles Bacon and Samuel Lang and Robert Latham and
                 Robert Ross",
  title =        "Understanding and Improving Computational Science
                 Storage Access through Continuous Characterization",
  journal =      j-TOS,
  volume =       "7",
  number =       "3",
  pages =        "8:1--8:??",
  month =        oct,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2027066.2027068",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sun Nov 6 06:42:42 MST 2011",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "8",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Zhang:2011:YCY,
  author =       "Xuechen Zhang and Yuehai Xu and Song Jiang",
  title =        "{YouChoose}: Choosing your Storage Device as a
                 Performance Interface to Consolidated {I/O} Service",
  journal =      j-TOS,
  volume =       "7",
  number =       "3",
  pages =        "9:1--9:??",
  month =        oct,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2027066.2027069",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sun Nov 6 06:42:42 MST 2011",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "9",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Huang:2011:RRT,
  author =       "Zhen Huang and Ernst Biersack and Yuxing Peng",
  title =        "Reducing Repair Traffic in {P2P} Backup Systems: Exact
                 Regenerating Codes on Hierarchical Codes",
  journal =      j-TOS,
  volume =       "7",
  number =       "3",
  pages =        "10:1--10:??",
  month =        oct,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2027066.2027070",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sun Nov 6 06:42:42 MST 2011",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "10",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Xiang:2011:HAF,
  author =       "Liping Xiang and Yinlong Xu and John C. S. Lui and
                 Qian Chang and Yubiao Pan and Runhui Li",
  title =        "A Hybrid Approach to Failed Disk Recovery Using
                 {RAID-6} Codes: Algorithms and Performance Evaluation",
  journal =      j-TOS,
  volume =       "7",
  number =       "3",
  pages =        "11:1--11:??",
  month =        oct,
  year =         "2011",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2027066.2027071",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sun Nov 6 06:42:42 MST 2011",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "11",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Agrawal:2012:EGS,
  author =       "Nitin Agrawal and Leo Arulraj and Andrea C.
                 Arpaci-Dusseau and Remzi H. Arpaci-Dusseau",
  title =        "Emulating goliath storage systems with {David}",
  journal =      j-TOS,
  volume =       "7",
  number =       "4",
  pages =        "12:1--12:??",
  month =        jan,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2078861.2078862",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Fri Mar 16 15:48:58 MDT 2012",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Benchmarking file and storage systems on large
                 file-system images is important, but difficult and
                 often infeasible. Typically, running benchmarks on such
                 large disk setups is a frequent source of frustration
                 for file-system evaluators; the scale alone acts as a
                 strong deterrent against using larger, albeit
                 realistic, benchmarks. To address this problem, we
                 develop David: a system that makes it practical to run
                 large benchmarks using modest amount of storage or
                 memory capacities readily available on most computers.
                 David creates a `compressed' version of the original
                 file-system image by omitting all file data and laying
                 out metadata more efficiently; an online storage model
                 determines the runtime of the benchmark workload on the
                 original uncompressed image. David works under any file
                 system, as demonstrated in this article with ext3 and
                 btrfs. We find that David reduces storage requirements
                 by orders of magnitude; David is able to emulate a 1-TB
                 target workload using only an 80 GB available disk,
                 while still modeling the actual runtime accurately.
                 David can also emulate newer or faster devices, for
                 example, we show how David can effectively emulate a
                 multidisk RAID using a limited amount of memory.",
  acknowledgement = ack-nhfb,
  articleno =    "12",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Sundararaman:2012:MCC,
  author =       "Swaminathan Sundararaman and Yupu Zhang and Sriram
                 Subramanian and Andrea C. Arpaci-Dusseau and Remzi
                 H. Arpaci-Dusseau",
  title =        "Making the common case the only case with anticipatory
                 memory allocation",
  journal =      j-TOS,
  volume =       "7",
  number =       "4",
  pages =        "13:1--13:??",
  month =        jan,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2078861.2078863",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Fri Mar 16 15:48:58 MDT 2012",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "We present anticipatory memory allocation (AMA), a new
                 method to build kernel code that is robust to
                 memory-allocation failures. AMA avoids the usual
                 difficulties in handling allocation failures through a
                 novel combination of static and dynamic techniques.
                 Specifically, a developer, with assistance from AMA
                 static analysis tools, determines how much memory a
                 particular call into a kernel subsystem will need, and
                 then preallocates said amount immediately upon entry to
                 the kernel; subsequent allocation requests are serviced
                 from the preallocated pool and thus guaranteed never to
                 fail. We describe the static and runtime components of
                 AMA, and then present a thorough evaluation of Linux
                 ext2-mfr, a case study in which we transform the Linux
                 ext2 file system into a memory-failure robust version
                 of itself. Experiments reveal that ext2-mfr avoids
                 memory-allocation failures successfully while incurring
                 little space or time overhead.",
  acknowledgement = ack-nhfb,
  articleno =    "13",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Meyer:2012:SPD,
  author =       "Dutch T. Meyer and William J. Bolosky",
  title =        "A study of practical deduplication",
  journal =      j-TOS,
  volume =       "7",
  number =       "4",
  pages =        "14:1--14:??",
  month =        jan,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2078861.2078864",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Fri Mar 16 15:48:58 MDT 2012",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "We collected file system content data from 857 desktop
                 computers at Microsoft over a span of 4 weeks. We
                 analyzed the data to determine the relative efficacy of
                 data deduplication, particularly considering whole-file
                 versus block-level elimination of redundancy. We found
                 that whole-file deduplication achieves about three
                 quarters of the space savings of the most aggressive
                 block-level deduplication for storage of live file
                 systems, and 87\% of the savings for backup images. We
                 also studied file fragmentation, finding that it is not
                 prevalent, and updated prior file system metadata
                 studies, finding that the distribution of file sizes
                 continues to skew toward very large unstructured
                 files.",
  acknowledgement = ack-nhfb,
  articleno =    "14",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Wu:2012:AWB,
  author =       "Guanying Wu and Xubin He and Ben Eckart",
  title =        "An adaptive write buffer management scheme for
                 flash-based {SSDs}",
  journal =      j-TOS,
  volume =       "8",
  number =       "1",
  pages =        "1:1--1:??",
  month =        feb,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2093139.2093140",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Fri Mar 16 15:48:59 MDT 2012",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Solid State Drives (SSD's) have shown promise to be a
                 candidate to replace traditional hard disk drives. The
                 benefits of SSD's over HDD's include better durability,
                 higher performance, and lower power consumption, but
                 due to certain physical characteristics of NAND flash,
                 which comprise SSD's, there are some challenging areas
                 of improvement and further research. We focus on the
                 layout and management of the small amount of RAM that
                 serves as a cache between the SSD and the system that
                 uses it. Of the techniques that have previously been
                 proposed to manage this cache, we identify several
                 sources of inefficient cache space management due to
                 the way pages are clustered in blocks and the limited
                 replacement policy. We find that in many traces hot
                 pages reside in otherwise cold blocks, and that the
                 spatial locality of most clusters can be fully
                 exploited in a limited time period, so we develop a
                 hybrid page/block architecture along with an advanced
                 replacement policy, called BPAC, or Block-Page Adaptive
                 Cache, to exploit both temporal and spatial locality.
                 Our technique involves adaptively partitioning the SSD
                 on-disk cache to separately hold pages with high
                 temporal locality in a page list and clusters of pages
                 with low temporal but high spatial locality in a block
                 list. In addition, we have developed a novel mechanism
                 for flash-based SSD's to characterize the spatial
                 locality of the disk I/O workload and an approach to
                 dynamically identify the set of low spatial locality
                 clusters. We run trace-driven simulations to verify our
                 design and find that it outperforms other popular
                 flash-aware cache schemes under different workloads.
                 For instance, compared to a popular flash aware cache
                 algorithm BPLRU, BPAC reduces the number of cache
                 evictions by up to 79.6\% and 34\% on average.",
  acknowledgement = ack-nhfb,
  articleno =    "1",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Luo:2012:ESI,
  author =       "Jianqiang Luo and Kevin D. Bowers and Alina Oprea and
                 Lihao Xu",
  title =        "Efficient software implementations of large finite
                 fields {${\rm GF}(2^n)$} for secure storage
                 applications",
  journal =      j-TOS,
  volume =       "8",
  number =       "1",
  pages =        "2:1--2:??",
  month =        feb,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2093139.2093141",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Fri Mar 16 15:48:59 MDT 2012",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Finite fields are widely used in constructing
                 error-correcting codes and cryptographic algorithms. In
                 practice, error-correcting codes use small finite
                 fields to achieve high-throughput encoding and
                 decoding. Conversely, cryptographic systems employ
                 considerably larger finite fields to achieve high
                 levels of security. We focus on developing efficient
                 software implementations of arithmetic operations in
                 reasonably large finite fields as needed by secure
                 storage applications. In this article, we study several
                 arithmetic operation implementations for finite fields
                 ranging from ${\rm GF}(2^{32})$ to ${\rm GF}(2^{128})$.
                 We implement multiplication and division in these
                 finite fields by making use of precomputed tables in
                 smaller fields, and several techniques of extending
                 smaller field arithmetic into larger field operations.
                 We show that by exploiting known techniques, as well as
                 new optimizations, we are able to efficiently support
                 operations over finite fields of interest. We perform a
                 detailed evaluation of several techniques, and show
                 that we achieve very practical performance for both
                 multiplication and division. Finally, we show how these
                 techniques find applications in the implementation of
                 HAIL, a highly available distributed cloud storage
                 layer. Using the newly implemented arithmetic
                 operations in ${\rm GF}(2^{64})$, HAIL improves its
                 performance by a factor of two, while simultaneously
                 providing a higher level of security.",
  acknowledgement = ack-nhfb,
  articleno =    "2",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Chang:2012:COM,
  author =       "Yuan-Hao Chang and Cheng-Kang Hsieh and Po-Chun Huang
                 and Pi-Cheng Hsiu",
  title =        "A caching-oriented management design for the
                 performance enhancement of solid-state drives",
  journal =      j-TOS,
  volume =       "8",
  number =       "1",
  pages =        "3:1--3:??",
  month =        feb,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2093139.2093142",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Fri Mar 16 15:48:59 MDT 2012",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "While solid-state drives are excellent alternatives to
                 hard disks in mobile devices, a number of performance
                 and reliability issues need to be addressed. In this
                 work, we design an efficient flash management scheme
                 for the performance improvement of low-cost MLC flash
                 memory devices. Specifically, we design an efficient
                 flash management scheme for multi-chipped flash memory
                 devices with cache support, and develop a two-level
                 address translation mechanism with an adaptive caching
                 policy. We evaluated the approach on real workloads.
                 The results demonstrate that it can improve the
                 performance of multi-chipped solid-state drives through
                 logical-to-physical mappings and concurrent accesses to
                 flash chips.",
  acknowledgement = ack-nhfb,
  articleno =    "3",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Mao:2012:HHP,
  author =       "Bo Mao and Hong Jiang and Suzhen Wu and Lei Tian and
                 Dan Feng and Jianxi Chen and Lingfang Zeng",
  title =        "{HPDA}: a hybrid parity-based disk array for enhanced
                 performance and reliability",
  journal =      j-TOS,
  volume =       "8",
  number =       "1",
  pages =        "4:1--4:??",
  month =        feb,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2093139.2093143",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Fri Mar 16 15:48:59 MDT 2012",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Flash-based Solid State Drive (SSD) has been
                 productively shipped and deployed in large scale
                 storage systems. However, a single flash-based SSD
                 cannot satisfy the capacity, performance and
                 reliability requirements of the modern storage systems
                 that support increasingly demanding data-intensive
                 computing applications. Applying RAID schemes to SSDs
                 to meet these requirements, while a logical and viable
                 solution, faces many challenges. In this article, we
                 propose a Hybrid Parity-based Disk Array architecture
                 (short for HPDA), which combines a group of SSDs and
                 two hard disk drives (HDDs) to improve the performance
                 and reliability of SSD-based storage systems. In HPDA,
                 the SSDs (data disks) and part of one HDD (parity disk)
                 compose a RAID4 disk array. Meanwhile, a second HDD and
                 the free space of the parity disk are mirrored to form
                 a RAID1-style write buffer that temporarily absorbs the
                 small write requests and acts as a surrogate set during
                 recovery when a disk fails. The write data is reclaimed
                 to the data disks during the lightly loaded or idle
                 periods of the system. Reliability analysis shows that
                 the reliability of HPDA, in terms of MTTDL (Mean Time
                 To Data Loss), is better than that of either pure
                 HDD-based or SSD-based disk array. Our prototype
                 implementation of HPDA and the performance evaluations
                 show that HPDA significantly outperforms either
                 HDD-based or SSD-based disk array.",
  acknowledgement = ack-nhfb,
  articleno =    "4",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Klonatos:2012:TOS,
  author =       "Yannis Klonatos and Thanos Makatos and Manolis
                 Marazakis and Michail D. Flouris and Angelos Bilas",
  title =        "Transparent Online Storage Compression at the
                 Block-Level",
  journal =      j-TOS,
  volume =       "8",
  number =       "2",
  pages =        "5:1--5:??",
  month =        may,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2180905.2180906",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Nov 6 18:17:34 MST 2012",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "In this work, we examine how transparent block-level
                 compression in the I/O path can improve both the space
                 efficiency and performance of online storage. We
                 present ZBD, a block-layer driver that transparently
                 compresses and decompresses data as they flow between
                 the file-system and storage devices. Our system
                 provides support for variable-size blocks, metadata
                 caching, and persistence, as well as block allocation
                 and cleanup. ZBD targets maintaining high performance,
                 by mitigating compression and decompression overheads
                 that can have a significant impact on performance by
                 leveraging modern multicore CPUs through explicit work
                 scheduling. We present two case-studies for
                 compression. First, we examine how our approach can be
                 used to increase the capacity of SSD-based caches, thus
                 increasing their cost-effectiveness. Then, we examine
                 how ZBD can improve the efficiency of online disk-based
                 storage systems. We evaluate our approach in the Linux
                 kernel on a commodity server with multicore CPUs, using
                 PostMark, SPECsfs2008, TPC-C, and TPC-H. Preliminary
                 results show that transparent online block-level
                 compression is a viable option for improving effective
                 storage capacity, it can improve I/O performance up to
                 80\% by reducing I/O traffic and seek distance, and has
                 a negative impact on performance, up to 34\%, only when
                 single-thread I/O latency is critical. In particular,
                 for SSD-based caching, our results indicate that, in
                 line with current technology trends, compressed caching
                 trades off CPU utilization for performance and enhances
                 SSD efficiency as a storage cache up to 99\%.",
  acknowledgement = ack-nhfb,
  articleno =    "5",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Adams:2012:AWB,
  author =       "Ian F. Adams and Mark W. Storer and Ethan L. Miller",
  title =        "Analysis of Workload Behavior in Scientific and
                 Historical Long-Term Data Repositories",
  journal =      j-TOS,
  volume =       "8",
  number =       "2",
  pages =        "6:1--6:??",
  month =        may,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2180905.2180907",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Nov 6 18:17:34 MST 2012",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "The scope of archival systems is expanding beyond
                 cheap tertiary storage: scientific and medical data is
                 increasingly digital, and the public has a growing
                 desire to digitally record their personal histories.
                 Driven by the increase in cost efficiency of hard
                 drives, and the rise of the Internet, content archives
                 have become a means of providing the public with fast,
                 cheap access to long-term data. Unfortunately,
                 designers of purpose-built archival systems are either
                 forced to rely on workload behavior obtained from a
                 narrow, anachronistic view of archives as simply cheap
                 tertiary storage, or extrapolate from marginally
                 related enterprise workload data and traditional
                 library access patterns. To close this knowledge gap
                 and provide relevant input for the design of effective
                 long-term data storage systems, we studied the workload
                 behavior of several systems within this expanded
                 archival storage space. Our study examined several
                 scientific and historical archives, covering a mixture
                 of purposes, media types, and access models---that is,
                 public versus private. Our findings show that, for more
                 traditional private scientific archival storage, files
                 have become larger, but update rates have remained
                 largely unchanged. However, in the public content
                 archives we observed, we saw behavior that diverges
                 from the traditional ``write-once, read-maybe''
                 behavior of tertiary storage. Our study shows that the
                 majority of such data is modified---sometimes
                 unnecessarily---relatively frequently, and that
                 indexing services such as Google and internal data
                 management processes may routinely access large
                 portions of an archive, accounting for most of the
                 accesses. Based on these observations, we identify
                 areas for improving the efficiency and performance of
                 archival storage systems.",
  acknowledgement = ack-nhfb,
  articleno =    "6",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Hsieh:2012:MDI,
  author =       "Jen-Wei Hsieh and Chung-Hsien Wu and Ge-Ming Chiu",
  title =        "{MFTL}: {A} Design and Implementation for {MLC} Flash
                 Memory Storage Systems",
  journal =      j-TOS,
  volume =       "8",
  number =       "2",
  pages =        "7:1--7:??",
  month =        may,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2180905.2180908",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Nov 6 18:17:34 MST 2012",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "NAND flash memory has gained its popularity in a
                 variety of applications as a storage medium due to its
                 low power consumption, nonvolatility, high performance,
                 physical stability, and portability. In particular,
                 Multi-Level Cell (MLC) flash memory, which provides a
                 lower cost and higher density solution, has occupied
                 the largest part of NAND flash-memory market share.
                 However, MLC flash memory also introduces new
                 challenges: (1) Pages in a block must be written
                 sequentially. (2) Information to indicate a page being
                 obsoleted cannot be recorded in its spare area due to
                 the limitation on the number of partial programming.
                 Since most of applications access NAND flash memory
                 under FAT file system, this article designs an MLC
                 Flash Translation Layer (MFTL) for flash-memory storage
                 systems which takes constraints of MLC flash memory and
                 access behaviors of FAT file system into consideration.
                 A series of trace-driven simulations was conducted to
                 evaluate the performance of the proposed scheme.
                 Although MFTL is designed for MLC flash memory and FAT
                 file system, it is applicable to SLC flash memory and
                 other file systems as well. Our experiment results show
                 that the proposed MFTL could achieve a good performance
                 for various access patterns even on SLC flash memory.",
  acknowledgement = ack-nhfb,
  articleno =    "7",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Tran:2012:ECB,
  author =       "Nguyen Tran and Frank Chiang and Jinyang Li",
  title =        "Efficient cooperative backup with decentralized trust
                 management",
  journal =      j-TOS,
  volume =       "8",
  number =       "3",
  pages =        "8:1--8:??",
  month =        sep,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2339118.2339119",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Nov 6 18:17:35 MST 2012",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Existing backup systems are unsatisfactory: commercial
                 backup services are reliable but expensive while
                 peer-to-peer systems are cheap but offer limited
                 assurance of data reliability. This article introduces
                 Friendstore, a system that provides inexpensive and
                 reliable backup by giving users the choice to store
                 backup data only on nodes they trust (typically those
                 owned by friends and colleagues). Because it is built
                 on trusted nodes, Friendstore is not burdened by the
                 complexity required to cope with potentially malicious
                 participants. Friendstore only needs to detect and
                 repair accidental data loss and to ensure balanced
                 storage exchange. The disadvantage of using only
                 trusted nodes is that Friendstore cannot achieve
                 perfect storage utilization. Friendstore is designed
                 for a heterogeneous environment where nodes have very
                 different access link speeds and available disk spaces.
                 To ensure long-term data reliability, a node with
                 limited upload bandwidth refrains from storing more
                 data than its calculated maintainable capacity. A high
                 bandwidth node might be limited by its available disk
                 space. We introduce a simple coding scheme, called
                 XOR(1,2), which doubles a node's ability to store
                 backup information in the same amount of disk space at
                 the cost of doubling the amount of data transferred
                 during restore. Analysis and simulations using
                 long-term node activity traces show that a node can
                 reliably back up tens of gigabytes of data even with
                 low upload bandwidth.",
  acknowledgement = ack-nhfb,
  articleno =    "8",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Abd-El-Malek:2012:FSV,
  author =       "Michael Abd-El-Malek and Matthew Wachs and James Cipar
                 and Karan Sanghi and Gregory R. Ganger and Garth
                 A. Gibson and Michael K. Reiter",
  title =        "File system virtual appliances: {Portable} file system
                 implementations",
  journal =      j-TOS,
  volume =       "8",
  number =       "3",
  pages =        "9:1--9:??",
  month =        sep,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2339118.2339120",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Nov 6 18:17:35 MST 2012",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "File system virtual appliances (FSVAs) address the
                 portability headaches that plague file system (FS)
                 developers. By packaging their FS implementation in a
                 virtual machine (VM), separate from the VM that runs
                 user applications, they can avoid the need to port the
                 file system to each operating system (OS) and OS
                 version. A small FS-agnostic proxy, maintained by the
                 core OS developers, connects the FSVA to whatever OS
                 the user chooses. This article describes an FSVA design
                 that maintains FS semantics for unmodified FS
                 implementations and provides desired OS and
                 virtualization features, such as a unified buffer cache
                 and VM migration. Evaluation of prototype FSVA
                 implementations in Linux and NetBSD, using Xen as the
                 virtual machine manager (VMM), demonstrates that the
                 FSVA architecture is efficient, FS-agnostic, and able
                 to insulate file system implementations from OS
                 differences that would otherwise require explicit
                 porting.",
  acknowledgement = ack-nhfb,
  articleno =    "9",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Luo:2012:GXC,
  author =       "Xianghong Luo and Jiwu Shu",
  title =        "Generalized {X-code}: an efficient {RAID-6} code for
                 arbitrary size of disk array",
  journal =      j-TOS,
  volume =       "8",
  number =       "3",
  pages =        "10:1--10:??",
  month =        sep,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2339118.2339121",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Nov 6 18:17:35 MST 2012",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Many RAID-6 codes have been proposed in the
                 literature, but each has its limitations. Horizontal
                 code has the ability to adapt to the arbitrary size of
                 a disk array but its high computational complexity is a
                 major shortcoming. In contrast, the computational
                 complexity of vertical code (e.g. X-code) often
                 achieves the theoretical optimality, but vertical code
                 is limited to using a prime number as the size of the
                 disk array In this article, we propose a novel
                 efficient RAID-6 code for arbitrary size of disk array:
                 generalized X-code. We move the redundant elements
                 along their calculation diagonals in X-code onto two
                 specific disks and change two data elements into
                 redundant elements in order to realize our new code.
                 The generalized X-code achieves optimal encoding and
                 updating complexity and low decoding complexity; in
                 addition, it has the ability to adapt to arbitrary size
                 of disk array. Furthermore, we also provide a method
                 for generalizing horizontal code to achieve optimal
                 encoding and updating complexity while keeping the
                 code's original ability to adapt to arbitrary size of
                 disk array.",
  acknowledgement = ack-nhfb,
  articleno =    "10",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Long:2012:EN,
  author =       "Darrell Long",
  title =        "Editorial note",
  journal =      j-TOS,
  volume =       "8",
  number =       "4",
  pages =        "11:1--11:??",
  month =        nov,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2385603.2385604",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sun May 5 09:02:36 MDT 2013",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "11",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Bolosky:2012:ISI,
  author =       "Bill Bolosky and Jason Flinn",
  title =        "Introduction to the special issue {USENIX FAST 2012}",
  journal =      j-TOS,
  volume =       "8",
  number =       "4",
  pages =        "12:1--12:??",
  month =        nov,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2385603.2385605",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sun May 5 09:02:36 MDT 2013",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  acknowledgement = ack-nhfb,
  articleno =    "12",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Shilane:2012:WOR,
  author =       "Philip Shilane and Mark Huang and Grant Wallace and
                 Windsor Hsu",
  title =        "{WAN}-optimized replication of backup datasets using
                 stream-informed delta compression",
  journal =      j-TOS,
  volume =       "8",
  number =       "4",
  pages =        "13:1--13:??",
  month =        nov,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2385603.2385606",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sun May 5 09:02:36 MDT 2013",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Replicating data off site is critical for disaster
                 recovery reasons, but the current approach of
                 transferring tapes is cumbersome and error prone.
                 Replicating across a wide area network (WAN) is a
                 promising alternative, but fast network connections are
                 expensive or impractical in many remote locations, so
                 improved compression is needed to make WAN replication
                 truly practical. We present a new technique for
                 replicating backup datasets across a WAN that not only
                 eliminates duplicate regions of files (deduplication)
                 but also compresses similar regions of files with delta
                 compression, which is available as a feature of EMC
                 Data Domain systems. Our main contribution is an
                 architecture that adds stream-informed delta
                 compression to already existing deduplication systems
                 and eliminates the need for new, persistent indexes.
                 Unlike techniques based on knowing a file's version or
                 that use a memory cache, our approach achieves delta
                 compression across all data replicated to a server at
                 any time in the past. From a detailed analysis of
                 datasets and statistics from hundreds of customers
                 using our product, we achieve an additional 2X
                 compression from delta compression beyond deduplication
                 and local compression, which enables customers to
                 replicate data that would otherwise fail to complete
                 within their backup window.",
  acknowledgement = ack-nhfb,
  articleno =    "13",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Kim:2012:RSS,
  author =       "Hyojun Kim and Nitin Agrawal and Cristian Ungureanu",
  title =        "Revisiting storage for smartphones",
  journal =      j-TOS,
  volume =       "8",
  number =       "4",
  pages =        "14:1--14:??",
  month =        nov,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2385603.2385607",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sun May 5 09:02:36 MDT 2013",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Conventional wisdom holds that storage is not a big
                 contributor to application performance on mobile
                 devices. Flash storage (the type most commonly used
                 today) draws little power, and its performance is
                 thought to exceed that of the network subsystem. In
                 this article, we present evidence that storage
                 performance does indeed affect the performance of
                 several common applications such as Web browsing, maps,
                 application install, email, and Facebook. For several
                 Android smartphones, we find that just by varying the
                 underlying flash storage, performance over WiFi can
                 typically vary between 100\% and 300\% across
                 applications; in one extreme scenario, the variation
                 jumped to over 2000\%. With a faster network (set up
                 over USB), the performance variation rose even further.
                 We identify the reasons for the strong correlation
                 between storage and application performance to be a
                 combination of poor flash device performance, random
                 I/O from application databases, and heavy-handed use of
                 synchronous writes. Based on our findings, we implement
                 and evaluate a set of pilot solutions to address the
                 storage performance deficiencies in smartphones.",
  acknowledgement = ack-nhfb,
  articleno =    "14",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Fryer:2012:RVF,
  author =       "Daniel Fryer and Kuei Sun and Rahat Mahmood and
                 Tinghao Cheng and Shaun Benjamin and Ashvin Goel and
                 Angela Demke Brown",
  title =        "{Recon}: Verifying file system consistency at
                 runtime",
  journal =      j-TOS,
  volume =       "8",
  number =       "4",
  pages =        "15:1--15:??",
  month =        nov,
  year =         "2012",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2385603.2385608",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sun May 5 09:02:36 MDT 2013",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "File system bugs that corrupt metadata on disk are
                 insidious. Existing reliability methods, such as
                 checksums, redundancy, or transactional updates, merely
                 ensure that the corruption is reliably preserved.
                 Typical workarounds, based on using backups or
                 repairing the file system, are painfully slow. Worse,
                 the recovery may result in further corruption. We
                 present Recon, a system that protects file system
                 metadata from buggy file system operations. Our
                 approach leverages file systems that provide crash
                 consistency using transactional updates. We define
                 declarative statements called consistency invariants
                 for a file system. These invariants must be satisfied
                 by each transaction being committed to disk to preserve
                 file system integrity. Recon checks these invariants at
                 commit, thereby minimizing the damage caused by buggy
                 file systems. The major challenges to this approach are
                 specifying invariants and interpreting file system
                 behavior correctly without relying on the file system
                 code. Recon provides a framework for file-system
                 specific metadata interpretation and invariant
                 checking. We show the feasibility of interpreting
                 metadata and writing consistency invariants for the
                 Linux ext3 file system using this framework. Recon can
                 detect random as well as targeted file-system
                 corruption at runtime as effectively as the offline
                 e2fsck file-system checker, with low overhead.",
  acknowledgement = ack-nhfb,
  articleno =    "15",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{You:2013:USL,
  author =       "Gae-Won You and Seung-Won Hwang and Navendu Jain",
  title =        "{Ursa}: Scalable Load and Power Management in Cloud
                 Storage Systems",
  journal =      j-TOS,
  volume =       "9",
  number =       "1",
  pages =        "1:1--1:??",
  month =        mar,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2435204.2435205",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sun May 5 09:02:36 MDT 2013",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Enterprise and cloud data centers are comprised of
                 tens of thousands of servers providing petabytes of
                 storage to a large number of users and applications. At
                 such a scale, these storage systems face two key
                 challenges: (1) hot-spots due to the dynamic popularity
                 of stored objects; and (2) high operational costs due
                 to power and cooling. Existing storage solutions,
                 however, are unsuitable to address these challenges
                 because of the large number of servers and data
                 objects. This article describes the design,
                 implementation, and evaluation of Ursa, a system that
                 scales to a large number of storage nodes and objects,
                 and aims to minimize latency and bandwidth costs during
                 system reconfiguration. Toward this goal, Ursa
                 formulates an optimization problem that selects a
                 subset of objects from hot-spot servers and performs
                 topology-aware migration to minimize reconfiguration
                 costs. As exact optimization is computationally
                 expensive, we devise scalable approximation techniques
                 for node selection and efficient divide-and-conquer
                 computation. We also show that the same dynamic
                 reconfiguration techniques can be leveraged to reduce
                 power costs by dynamically migrating data off
                 under-utilized nodes, and powering up servers
                 neighboring existing hot-spots to reduce
                 reconfiguration costs. Our evaluation shows that Ursa
                 achieves cost-effective load management, is
                 time-responsive in computing placement decisions (e.g.,
                 about two minutes for 10K nodes and 10M objects), and
                 provides power savings of 15\%--37\%.",
  acknowledgement = ack-nhfb,
  articleno =    "1",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Hatzieleftheriou:2013:IBE,
  author =       "Andromachi Hatzieleftheriou and Stergios V.
                 Anastasiadis",
  title =        "Improving Bandwidth Efficiency for Consistent
                 Multistream Storage",
  journal =      j-TOS,
  volume =       "9",
  number =       "1",
  pages =        "2:1--2:??",
  month =        mar,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2435204.2435206",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sun May 5 09:02:36 MDT 2013",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Synchronous small writes play a critical role in
                 system availability because they safely log recent
                 state modifications for fast recovery from crashes.
                 Demanding systems typically dedicate separate devices
                 to logging for adequate performance during normal
                 operation and redundancy during state reconstruction.
                 However, storage stacks enforce page-sized granularity
                 in data transfers from memory to disk. Thus, they
                 consume excessive storage bandwidth to handle small
                 writes, which hurts performance. The problem becomes
                 worse, as filesystems often handle multiple concurrent
                 streams, which effectively generate random I/O traffic.
                 In a journaled filesystem, we introduce wasteless
                 journaling as a mount mode that coalesces synchronous
                 concurrent small writes of data into full page-sized
                 journal blocks. Additionally, we propose selective
                 journaling to automatically activate wasteless
                 journaling on data writes with size below a fixed
                 threshold. We implemented a functional prototype of our
                 design over a widely-used filesystem. Our modes are
                 compared against existing methods using microbenchmarks
                 and application-level workloads on stand-alone servers
                 and a multitier networked system. We examine
                 synchronous and asynchronous writes. Coalescing small
                 data updates to the journal sequentially preserves
                 filesystem consistency while it reduces consumed
                 bandwidth up to several factors, decreases recovery
                 time up to 22\%, and lowers write latency up to orders
                 of magnitude.",
  acknowledgement = ack-nhfb,
  articleno =    "2",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Huang:2013:PCF,
  author =       "Cheng Huang and Minghua Chen and Jin Li",
  title =        "{Pyramid Codes}: Flexible Schemes to Trade Space for
                 Access Efficiency in Reliable Data Storage Systems",
  journal =      j-TOS,
  volume =       "9",
  number =       "1",
  pages =        "3:1--3:??",
  month =        mar,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2435204.2435207",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Sun May 5 09:02:36 MDT 2013",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "We design flexible schemes to explore the tradeoffs
                 between storage space and access efficiency in reliable
                 data storage systems. Aiming at this goal, two new
                 classes of erasure-resilient codes are introduced ---
                 Basic Pyramid Codes (BPC) and Generalized Pyramid Codes
                 (GPC). Both schemes require slightly more storage space
                 than conventional schemes, but significantly improve
                 the critical performance of read during failures and
                 unavailability. As a by-product, we establish a
                 necessary matching condition to characterize the limit
                 of failure recovery, that is, unless the matching
                 condition is satisfied, a failure case is impossible to
                 recover. In addition, we define a maximally recoverable
                 (MR) property. For all ERC schemes holding the MR
                 property, the matching condition becomes sufficient,
                 that is, all failure cases satisfying the matching
                 condition are indeed recoverable. We show that GPC is
                 the first class of non-MDS schemes holding the MR
                 property.",
  acknowledgement = ack-nhfb,
  articleno =    "3",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Huang:2013:ERD,
  author =       "Jianzhong Huang and Fenghao Zhang and Xiao Qin and
                 Changsheng Xie",
  title =        "Exploiting Redundancies and Deferred Writes to
                 Conserve Energy in Erasure-Coded Storage Clusters",
  journal =      j-TOS,
  volume =       "9",
  number =       "2",
  pages =        "4:1--4:??",
  month =        jul,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2491472.2491473",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Thu Dec 12 18:12:43 MST 2013",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "We present a power-efficient scheme for erasure-coded
                 storage clusters --- ECS$^2$ --- which aims to offer
                 high energy efficiency with marginal reliability
                 degradation. ECS$^2$ utilizes data redundancies and
                 deferred writes to conserve energy. In ECS$^2$ parity
                 blocks are buffered exclusively in active data nodes
                 whereas parity nodes are placed into low-power mode. $
                 (k + r, k) $ RS-coded ECS$^2$ can achieve $ \lceil (r +
                 1) / 2 \rceil $-fault tolerance for $k$ active data
                 nodes and $r$-fault tolerance for all $ k + r $ nodes.
                 ECS$^2$ employs the following three optimizing
                 approaches to improve the energy efficiency of storage
                 clusters. (1) An adaptive threshold policy takes system
                 configurations and I/O workloads into account to
                 maximize standby time periods; (2) a selective
                 activation policy minimizes the number of
                 power-transitions in storage nodes; and (3) a
                 region-based buffer policy speeds up the
                 synchronization process by migrating parity blocks in a
                 batch method. After implementing an ECS$^2$ -based
                 prototype in a Linux cluster, we evaluated its energy
                 efficiency and performance using four different types
                 of I/O workloads. The experimental results indicate
                 that compared to energy-oblivious erasure-coded
                 storage, ECS$^2$ can save the energy used by storage
                 clusters up to 29.8\% and 28.0\% in read-intensive and
                 write-dominated workloads when $ k = 6 $ and $ r = 3 $,
                 respectively. The results also show that ECS$^2$
                 accomplishes high power efficiency in both normal and
                 failed cases without noticeably affecting the I/O
                 performance of storage clusters.",
  acknowledgement = ack-nhfb,
  articleno =    "4",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Altiparmak:2013:GOR,
  author =       "Nihat Altiparmak and Ali Saman Tosun",
  title =        "Generalized Optimal Response Time Retrieval of
                 Replicated Data from Storage Arrays",
  journal =      j-TOS,
  volume =       "9",
  number =       "2",
  pages =        "5:1--5:??",
  month =        jul,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2491472.2491474",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Thu Dec 12 18:12:43 MST 2013",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Declustering techniques reduce query response times
                 through parallel I/O by distributing data among
                 parallel disks. Recently, replication-based approaches
                 were proposed to further reduce the response time.
                 Efficient retrieval of replicated data from multiple
                 disks is a challenging problem. Existing retrieval
                 techniques are designed for storage arrays with
                 identical disks, having no initial load or network
                 delay. In this article, we consider the generalized
                 retrieval problem of replicated data where the disks in
                 the system might be heterogeneous, the disks may have
                 initial load, and the storage arrays might be located
                 on different sites. We first formulate the generalized
                 retrieval problem using a Linear Programming (LP) model
                 and solve it with mixed integer programming techniques.
                 Next, the generalized retrieval problem is formulated
                 as a more efficient maximum flow problem. We prove that
                 the retrieval schedule returned by the maximum flow
                 technique yields the optimal response time and this
                 result matches the LP solution. We also propose a
                 low-complexity online algorithm for the generalized
                 retrieval problem by not guaranteeing the optimality of
                 the result. Performance of proposed and state of the
                 art retrieval strategies are investigated using various
                 replication schemes, query types, query loads, disk
                 specifications, network delays, and initial loads.",
  acknowledgement = ack-nhfb,
  articleno =    "5",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Sankar:2013:DSE,
  author =       "Sriram Sankar and Mark Shaw and Kushagra Vaid and
                 Sudhanva Gurumurthi",
  title =        "Datacenter Scale Evaluation of the Impact of
                 Temperature on Hard Disk Drive Failures",
  journal =      j-TOS,
  volume =       "9",
  number =       "2",
  pages =        "6:1--6:24",
  month =        jul,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2491472.2491475",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Thu Dec 12 18:12:43 MST 2013",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "With the advent of cloud computing and online
                 services, large enterprises rely heavily on their
                 datacenters to serve end users. A large datacenter
                 facility incurs increased maintenance costs in addition
                 to service unavailability when there are increased
                 failures. Among different server components, hard disk
                 drives are known to contribute significantly to server
                 failures; however, there is very little understanding
                 of the major determinants of disk failures in
                 datacenters. In this work, we focus on the
                 interrelationship between temperature, workload, and
                 hard disk drive failures in a large scale datacenter.
                 We present a dense storage case study from a population
                 housing thousands of servers and tens of thousands of
                 disk drives, hosting a large-scale online service at
                 Microsoft. We specifically establish correlation
                 between temperatures and failures observed at different
                 location granularities: (a) inside drive locations in a
                 server chassis, (b) across server locations in a rack,
                 and (c) across multiple racks in a datacenter. We show
                 that temperature exhibits a stronger correlation to
                 failures than the correlation of disk utilization with
                 drive failures. We establish that variations in
                 temperature are not significant in datacenters and have
                 little impact on failures. We also explore workload
                 impacts on temperature and disk failures and show that
                 the impact of workload is not significant. We then
                 experimentally evaluate knobs that control disk drive
                 temperature, including workload and chassis design
                 knobs. We corroborate our findings from the real data
                 study and show that workload knobs show minimal impact
                 on temperature. Chassis knobs like disk placement and
                 fan speeds have a larger impact on temperature.
                 Finally, we also show the proposed cost benefit of
                 temperature optimizations that increase hard disk drive
                 reliability.",
  acknowledgement = ack-nhfb,
  articleno =    "6",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Wu:2013:SFS,
  author =       "Xiaojian Wu and Sheng Qiu and A. L. Narasimha Reddy",
  title =        "{SCMFS}: a File System for Storage Class Memory and
                 its Extensions",
  journal =      j-TOS,
  volume =       "9",
  number =       "3",
  pages =        "7:1--7:??",
  month =        aug,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2501620.2501621",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Thu Dec 12 18:12:47 MST 2013",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/linux.bib;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib;
                 http://www.math.utah.edu/pub/tex/bib/unix.bib",
  abstract =     "Modern computer systems have been built around the
                 assumption that persistent storage is accessed via a
                 slow, block-based interface. However, emerging
                 nonvolatile memory technologies (sometimes referred to
                 as storage class memory (SCM)), are poised to
                 revolutionize storage systems. The SCM devices can be
                 attached directly to the memory bus and offer fast,
                 fine-grained access to persistent storage. In this
                 article, we propose a new file system --- SCMFS, which
                 is specially designed for Storage Class Memory. SCMFS
                 is implemented on the virtual address space and
                 utilizes the existing memory management module of the
                 operating system to help mange the file system space.
                 As a result, we largely simplified the file system
                 operations of SCMFS, which allowed us a better
                 exploration of performance gain from SCM. We have
                 implemented a prototype in Linux and evaluated its
                 performance through multiple benchmarks. The
                 experimental results show that SCMFS outperforms other
                 memory resident file systems, tmpfs, ramfs and ext2 on
                 ramdisk, and achieves about 70\% of memory bandwidth
                 for file read/write operations.",
  acknowledgement = ack-nhfb,
  articleno =    "7",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Natanzon:2013:DSA,
  author =       "Assaf Natanzon and Eitan Bachmat",
  title =        "Dynamic Synchronous\slash Asynchronous Replication",
  journal =      j-TOS,
  volume =       "9",
  number =       "3",
  pages =        "8:1--8:??",
  month =        aug,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2508011",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Thu Dec 12 18:12:47 MST 2013",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Online, remote, data replication is critical for
                 today's enterprise IT organization. Availability of
                 data is key to the success of the organization. A few
                 hours of downtime can cost from thousands to millions
                 of dollars With increasing frequency, companies are
                 instituting disaster recovery plans to ensure
                 appropriate data availability in the event of a
                 catastrophic failure or disaster that destroys a site
                 (e.g. flood, fire, or earthquake). Synchronous and
                 asynchronous replication technologies have been
                 available for a long period of time. Synchronous
                 replication has the advantage of no data loss, but due
                 to latency, synchronous replication is limited by
                 distance and bandwidth. Asynchronous replication on the
                 other hand has no distance limitation, but leads to
                 some data loss which is proportional to the data lag.
                 We present a novel method, implemented within EMC
                 Recover-Point, which allows the system to dynamically
                 move between these replication options without any
                 disruption to the I/O path. As latency grows, the
                 system will move from synchronous replication to
                 semi-synchronous replication and then to snapshot
                 shipping. It returns to synchronous replication as more
                 bandwidth is available and latency allows.",
  acknowledgement = ack-nhfb,
  articleno =    "8",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Rodeh:2013:BLB,
  author =       "Ohad Rodeh and Josef Bacik and Chris Mason",
  title =        "{BTRFS}: The {Linux} {B}-Tree Filesystem",
  journal =      j-TOS,
  volume =       "9",
  number =       "3",
  pages =        "9:1--9:32",
  month =        aug,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2501620.2501623",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Thu Dec 12 18:12:47 MST 2013",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/linux.bib;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib;
                 http://www.math.utah.edu/pub/tex/bib/unix.bib",
  abstract =     "BTRFS is a Linux filesystem that has been adopted as
                 the default filesystem in some popular versions of
                 Linux. It is based on copy-on-write, allowing for
                 efficient snapshots and clones. It uses B-trees as its
                 main on-disk data structure. The design goal is to work
                 well for many use cases and workloads. To this end,
                 much effort has been directed to maintaining even
                 performance as the filesystem ages, rather than trying
                 to support a particular narrow benchmark use-case.
                 Linux filesystems are installed on smartphones as well
                 as enterprise servers. This entails challenges on many
                 different fronts.\par

                 --- Scalability. The filesystem must scale in many
                 dimensions: disk space, memory, and CPUs.\par

                 --- Data integrity. Losing data is not an option, and
                 much effort is expended to safeguard the content. This
                 includes checksums, metadata duplication, and RAID
                 support built into the filesystem.\par

                 --- Disk diversity. The system should work well with
                 SSDs and hard disks. It is also expected to be able to
                 use an array of different sized disks, which poses
                 challenges to the RAID and striping
                 mechanisms.\par

                 This article describes the core ideas, data structures,
                 and algorithms of this filesystem. It sheds light on
                 the challenges posed by defragmentation in the presence
                 of snapshots, and the tradeoffs required to maintain
                 even performance in the face of a wide spectrum of
                 workloads.",
  acknowledgement = ack-nhfb,
  articleno =    "9",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Jiang:2013:PSE,
  author =       "Song Jiang and Xiaoning Ding and Yuehai Xu and Kei
                 Davis",
  title =        "A Prefetching Scheme Exploiting both Data Layout and
                 Access History on Disk",
  journal =      j-TOS,
  volume =       "9",
  number =       "3",
  pages =        "10:1--10:??",
  month =        aug,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2508010",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Thu Dec 12 18:12:47 MST 2013",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Prefetching is an important technique for improving
                 effective hard disk performance. A prefetcher seeks to
                 accurately predict which data will be requested and
                 load it ahead of the arrival of the corresponding
                 requests. Current disk prefetch policies in major
                 operating systems track access patterns at the level of
                 file abstraction. While this is useful for exploiting
                 application-level access patterns, for two reasons
                 file-level prefetching cannot realize the full
                 performance improvements achievable by prefetching.
                 First, certain prefetch opportunities can only be
                 detected by knowing the data layout on disk, such as
                 the contiguous layout of file metadata or data from
                 multiple files. Second, nonsequential access of disk
                 data (requiring disk head movement) is much slower than
                 sequential access, and the performance penalty for
                 mis-prefetching a randomly located block, relative to
                 that of a sequential block, is correspondingly greater.
                 To overcome the inherent limitations of prefetching at
                 logical file level, we propose to perform prefetching
                 directly at the level of disk layout, and in a portable
                 way. Our technique, called DiskSeen, is intended to be
                 supplementary to, and to work synergistically with, any
                 present file-level prefetch policies. DiskSeen tracks
                 the locations and access times of disk blocks and,
                 based on analysis of their temporal and spatial
                 relationships, seeks to improve the sequentiality of
                 disk accesses and overall prefetching performance. It
                 also implements a mechanism to minimize
                 mis-prefetching, on a per-application basis, to
                 mitigate the corresponding performance penalty. Our
                 implementation of the DiskSeen scheme in the Linux 2.6
                 kernel shows that it can significantly improve the
                 effectiveness of prefetching, reducing execution times
                 by 20\%--60\% for microbenchmarks and real applications
                 such as grep, CVS, and TPC-H. Even for workloads
                 specifically designed to expose its weaknesses,
                 DiskSeen incurs only minor performance loss.",
  acknowledgement = ack-nhfb,
  articleno =    "10",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Zhang:2013:DEN,
  author =       "Guangyan Zhang and Weimin Zheng and Keqin Li",
  title =        "Design and Evaluation of a New Approach to {RAID-0}
                 Scaling",
  journal =      j-TOS,
  volume =       "9",
  number =       "4",
  pages =        "11:1--11:??",
  month =        nov,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2491054",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Thu Dec 12 18:12:51 MST 2013",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Scaling up a RAID-0 volume with added disks can
                 increase its storage capacity and I/O bandwidth
                 simultaneously. For preserving a round-robin data
                 distribution, existing scaling approaches require all
                 the data to be migrated. Such large data migration
                 results in a long redistribution time as well as a
                 negative impact on application performance. In this
                 article, we present a new approach to RAID-0 scaling
                 called FastScale. First, FastScale minimizes data
                 migration, while maintaining a uniform data
                 distribution. It moves only enough data blocks from old
                 disks to fill an appropriate fraction of new disks.
                 Second, FastScale optimizes data migration with access
                 aggregation and lazy checkpoint. Access aggregation
                 enables data migration to have a larger throughput due
                 to a decrement of disk seeks. Lazy checkpoint minimizes
                 the number of metadata writes without compromising data
                 consistency. Using several real system disk traces, we
                 evaluate the performance of FastScale through
                 comparison with SLAS, one of the most efficient
                 existing scaling approaches. The experiments show that
                 FastScale can reduce redistribution time by up to
                 86.06\% with smaller application I/O latencies. The
                 experiments also illustrate that the performance of
                 RAID-0 scaled using FastScale is almost identical to,
                 or even better than, that of the round-robin RAID-0.",
  acknowledgement = ack-nhfb,
  articleno =    "11",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Bessani:2013:DDS,
  author =       "Alysson Bessani and Miguel Correia and Bruno Quaresma
                 and Fernando Andr{\'e} and Paulo Sousa",
  title =        "{DepSky}: Dependable and Secure Storage in a
                 Cloud-of-Clouds",
  journal =      j-TOS,
  volume =       "9",
  number =       "4",
  pages =        "12:1--12:??",
  month =        nov,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2535929",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Thu Dec 12 18:12:51 MST 2013",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "The increasing popularity of cloud storage services
                 has lead companies that handle critical data to think
                 about using these services for their storage needs.
                 Medical record databases, large biomedical datasets,
                 historical information about power systems and
                 financial data are some examples of critical data that
                 could be moved to the cloud. However, the reliability
                 and security of data stored in the cloud still remain
                 major concerns. In this work we present DepSky, a
                 system that improves the availability, integrity, and
                 confidentiality of information stored in the cloud
                 through the encryption, encoding, and replication of
                 the data on diverse clouds that form a cloud-of-clouds.
                 We deployed our system using four commercial clouds and
                 used PlanetLab to run clients accessing the service
                 from different countries. We observed that our
                 protocols improved the perceived availability, and in
                 most cases, the access latency, when compared with
                 cloud providers individually. Moreover, the monetary
                 costs of using DepSky in this scenario is at most twice
                 the cost of using a single cloud, which is optimal and
                 seems to be a reasonable cost, given the benefits.",
  acknowledgement = ack-nhfb,
  articleno =    "12",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Kwon:2013:HAF,
  author =       "Se Jin Kwon and Hyung-Ju Cho and Tae-Sun Chung",
  title =        "Hybrid Associative Flash Translation Layer for the
                 Performance Optimization of Chip-Level Parallel Flash
                 Memory",
  journal =      j-TOS,
  volume =       "9",
  number =       "4",
  pages =        "13:1--13:??",
  month =        nov,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2535931",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Thu Dec 12 18:12:51 MST 2013",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Flash memory is used widely in the data storage
                 market, particularly low-price MultiLevel Cell (MLC)
                 flash memory, which has been adopted by large-scale
                 storage systems despite its low performance. To
                 overcome the poor performance of MLC flash memory, a
                 system architecture has been designed to optimize
                 chip-level parallelism. This design increases the size
                 of the page unit and the block unit, thereby
                 simultaneously executing operations on multiple chips.
                 Unfortunately, its Flash Translation Layer (FTL)
                 generates many unused sectors in each page, which leads
                 to unnecessary write operations. Furthermore, it reuses
                 an earlier log block scheme, although it generates many
                 erase operations because of its low space utilization.
                 To solve these problems, we propose a hybrid
                 associative FTL (Hybrid-FTL) to enhance the performance
                 of the chip-level parallel flash memory system.
                 Hybrid-FTL reduces the number of write operations by
                 utilizing all of the unused sectors. Furthermore, it
                 reduces the overall number of erase operations by
                 classifying data as hot, cold, or fragment data.
                 Hybrid-FTL requires less mapping information in the
                 DRAM and in the flash memory compared with previous FTL
                 algorithms.",
  acknowledgement = ack-nhfb,
  articleno =    "13",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Xie:2013:EHA,
  author =       "Yulai Xie and Kiran-Kumar Muniswamy-Reddy and Dan Feng
                 and Yan Li and Darrell D. E. Long",
  title =        "Evaluation of a Hybrid Approach for Efficient
                 Provenance Storage",
  journal =      j-TOS,
  volume =       "9",
  number =       "4",
  pages =        "14:1--14:??",
  month =        nov,
  year =         "2013",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2501986",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Thu Dec 12 18:12:51 MST 2013",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Provenance is the metadata that describes the history
                 of objects. Provenance provides new functionality in a
                 variety of areas, including experimental documentation,
                 debugging, search, and security. As a result, a number
                 of groups have built systems to capture provenance.
                 Most of these systems focus on provenance collection, a
                 few systems focus on building applications that use the
                 provenance, but all of these systems ignore an
                 important aspect: efficient long-term storage of
                 provenance. In this article, we first analyze the
                 provenance collected from multiple workloads and
                 characterize the properties of provenance with respect
                 to long-term storage. We then propose a hybrid scheme
                 that takes advantage of the graph structure of
                 provenance data and the inherent duplication in
                 provenance data. Our evaluation indicates that our
                 hybrid scheme, a combination of Web graph compression
                 (adapted for provenance) and dictionary encoding,
                 provides the best trade-off in terms of compression
                 ratio, compression time, and query performance when
                 compared to other compression schemes.",
  acknowledgement = ack-nhfb,
  articleno =    "14",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Lee:2014:UBC,
  author =       "Eunji Lee and Hyokyung Bahn and Sam H. Noh",
  title =        "A Unified Buffer Cache Architecture that Subsumes
                 Journaling Functionality via Nonvolatile Memory",
  journal =      j-TOS,
  volume =       "10",
  number =       "1",
  pages =        "1:1--1:??",
  month =        jan,
  year =         "2014",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2560010",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Wed Feb 5 16:53:47 MST 2014",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/linux.bib;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib;
                 http://www.math.utah.edu/pub/tex/bib/unix.bib",
  abstract =     "Journaling techniques are widely used in modern file
                 systems as they provide high reliability and fast
                 recovery from system failures. However, it reduces the
                 performance benefit of buffer caching as journaling
                 accounts for a bulk of the storage writes in real
                 system environments. To relieve this problem, we
                 present a novel buffer cache architecture that subsumes
                 the functionality of caching and journaling by making
                 use of nonvolatile memory such as PCM or STT-MRAM.
                 Specifically, our buffer cache supports what we call
                 the in-place commit scheme. This scheme avoids logging,
                 but still provides the same journaling effect by simply
                 altering the state of the cached block to frozen. As a
                 frozen block still provides the functionality of a
                 cache block, we show that in-place commit does not
                 degrade cache performance. We implement our scheme on
                 Linux 2.6.38 and measure the throughput and execution
                 time of the scheme with various file I/O benchmarks.
                 The results show that our scheme improves the
                 throughput and execution time by 89\% and 34\% on
                 average, respectively, compared to the existing Linux
                 buffer cache with ext4 without any loss of
                 reliability.",
  acknowledgement = ack-nhfb,
  articleno =    "1",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Ma:2014:FFF,
  author =       "Ao Ma and Chris Dragga and Andrea C. Arpaci-Dusseau
                 and Remzi H. Arpaci-Dusseau and Marshall Kirk
                 McKusick",
  title =        "{Ffsck}: The Fast File-System Checker",
  journal =      j-TOS,
  volume =       "10",
  number =       "1",
  pages =        "2:1--2:??",
  month =        jan,
  year =         "2014",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2560011",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Wed Feb 5 16:53:47 MST 2014",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib;
                 http://www.math.utah.edu/pub/tex/bib/unix.bib",
  abstract =     "Failures, errors, and bugs can corrupt file systems
                 and cause data loss, despite the presence of journals
                 and similar preventive techniques. While consistency
                 checkers such as fsck can detect corruption and repair
                 a damaged image, they are generally created as an
                 afterthought, to be run only at rare intervals. Thus,
                 checkers operate slowly, causing significant downtime
                 for large scale storage systems. We address this
                 dilemma by treating the checker as a key component of
                 the overall file system, rather than a peripheral
                 add-on. To this end, we present a modified ext3 file
                 system, rext 3, to directly support the fast
                 file-system checker, ffsck. Rext3 colocates and
                 self-identifies its metadata blocks, removing the need
                 for costly seeks and tree traversals during checking.
                 These modifications allow ffsck to scan and repair the
                 file system at rates approaching the full sequential
                 bandwidth of the underlying device. In addition, we
                 demonstrate that rext3 generally performs competitively
                 with ext3 and exceeds it in handling random reads and
                 large writes. Finally, we apply our principles to
                 FreeBSD's FFS file system and its checker, doing so in
                 a lightweight fashion that preserves the file-system
                 layout while still providing some of the performance
                 gains from ffsck.",
  acknowledgement = ack-nhfb,
  articleno =    "2",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Lu:2014:SLF,
  author =       "Lanyue Lu and Andrea C. Arpaci-Dusseau and Remzi H.
                 Arpaci-Dusseau and Shan Lu",
  title =        "A Study of {Linux} File System Evolution",
  journal =      j-TOS,
  volume =       "10",
  number =       "1",
  pages =        "3:1--3:??",
  month =        jan,
  year =         "2014",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2560012",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Wed Feb 5 16:53:47 MST 2014",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/linux.bib;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib;
                 http://www.math.utah.edu/pub/tex/bib/unix.bib",
  abstract =     "We conduct a comprehensive study of file-system code
                 evolution. By analyzing eight years of Linux
                 file-system changes across 5079 patches, we derive
                 numerous new (and sometimes surprising) insights into
                 the file-system development process; our results should
                 be useful for both the development of file systems
                 themselves as well as the improvement of bug-finding
                 tools.",
  acknowledgement = ack-nhfb,
  articleno =    "3",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Plank:2014:SDS,
  author =       "James S. Plank and Mario Blaum",
  title =        "Sector-Disk {(SD)} Erasure Codes for Mixed Failure
                 Modes in {RAID} Systems",
  journal =      j-TOS,
  volume =       "10",
  number =       "1",
  pages =        "4:1--4:??",
  month =        jan,
  year =         "2014",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2560013",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Wed Feb 5 16:53:47 MST 2014",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Traditionally, when storage systems employ erasure
                 codes, they are designed to tolerate the failures of
                 entire disks. However, the most common types of
                 failures are latent sector failures, which only affect
                 individual disk sectors, and block failures which arise
                 through wear on SSD's. This article introduces SD
                 codes, which are designed to tolerate combinations of
                 disk and sector failures. As such, they consume far
                 less storage resources than traditional erasure codes.
                 We specify the codes with enough detail for the storage
                 practitioner to employ them, discuss their practical
                 properties, and detail an open-source implementation.",
  acknowledgement = ack-nhfb,
  articleno =    "4",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Choi:2014:THP,
  author =       "Jae Woo Choi and Dong In Shin and Young Jin Yu and
                 Hyeonsang Eom and Heon Young Yeom",
  title =        "Towards High-Performance {SAN} with Fast Storage
                 Devices",
  journal =      j-TOS,
  volume =       "10",
  number =       "2",
  pages =        "5:1--5:??",
  month =        mar,
  year =         "2014",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2577385",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Apr 1 05:59:01 MDT 2014",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Storage area network (SAN) is one of the most popular
                 solutions for constructing server environments these
                 days. In these kinds of server environments, HDD-based
                 storage usually becomes the bottleneck of the overall
                 system, but it is not enough to merely replace the
                 devices with faster ones in order to exploit their high
                 performance. In other words, proper optimizations are
                 needed to fully utilize their performance gains. In
                 this work, we first adopted a DRAM-based SSD as a fast
                 backend-storage in the existing SAN environment, and
                 found significant performance degradation compared to
                 its own capabilities, especially in the case of
                 small-sized random I/O pattern, even though a
                 high-speed network was used. We have proposed three
                 optimizations to solve this problem: (1) removing
                 software overhead in the SAN I/O path; (2) increasing
                 parallelism in the procedures for handling I/O
                 requests; and (3) adopting the temporal merge mechanism
                 to reduce network overheads. We have implemented them
                 as a prototype and found that our approaches make
                 substantial performance improvements by up to 39\% and
                 280\% in terms of both the latency and bandwidth,
                 respectively.",
  acknowledgement = ack-nhfb,
  articleno =    "5",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Mao:2014:RPO,
  author =       "Bo Mao and Hong Jiang and Suzhen Wu and Yinjin Fu and
                 Lei Tian",
  title =        "Read-Performance Optimization for Deduplication-Based
                 Storage Systems in the Cloud",
  journal =      j-TOS,
  volume =       "10",
  number =       "2",
  pages =        "6:1--6:??",
  month =        mar,
  year =         "2014",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2512348",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Apr 1 05:59:01 MDT 2014",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib;
                 http://www.math.utah.edu/pub/tex/bib/virtual-machines.bib",
  abstract =     "Data deduplication has been demonstrated to be an
                 effective technique in reducing the total data
                 transferred over the network and the storage space in
                 cloud backup, archiving, and primary storage systems,
                 such as VM (virtual machine) platforms. However, the
                 performance of restore operations from a deduplicated
                 backup can be significantly lower than that without
                 deduplication. The main reason lies in the fact that a
                 file or block is split into multiple small data chunks
                 that are often located in different disks after
                 deduplication, which can cause a subsequent read
                 operation to invoke many disk IOs involving multiple
                 disks and thus degrade the read performance
                 significantly. While this problem has been by and large
                 ignored in the literature thus far, we argue that the
                 time is ripe for us to pay significant attention to it
                 in light of the emerging cloud storage applications and
                 the increasing popularity of the VM platform in the
                 cloud. This is because, in a cloud storage or VM
                 environment, a simple read request on the client side
                 may translate into a restore operation if the data to
                 be read or a VM suspended by the user was previously
                 deduplicated when written to the cloud or the VM
                 storage server, a likely scenario considering the
                 network bandwidth and storage capacity concerns in such
                 an environment. To address this problem, in this
                 article, we propose SAR, an SSD (solid-state
                 drive)-Assisted Read scheme, that effectively exploits
                 the high random-read performance properties of SSDs and
                 the unique data-sharing characteristic of
                 deduplication-based storage systems by storing in SSDs
                 the unique data chunks with high reference count, small
                 size, and nonsequential characteristics. In this way,
                 many read requests to HDDs are replaced by read
                 requests to SSDs, thus significantly improving the read
                 performance of the deduplication-based storage systems
                 in the cloud. The extensive trace-driven and VM restore
                 evaluations on the prototype implementation of SAR show
                 that SAR outperforms the traditional
                 deduplication-based and flash-based cache schemes
                 significantly, in terms of the average response
                 times.",
  acknowledgement = ack-nhfb,
  articleno =    "6",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Elerath:2014:BMC,
  author =       "Jon G. Elerath and Jiri Schindler",
  title =        "Beyond {MTTDL}: a Closed-Form {RAID 6} Reliability
                 Equation",
  journal =      j-TOS,
  volume =       "10",
  number =       "2",
  pages =        "7:1--7:??",
  month =        mar,
  year =         "2014",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2577386",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Apr 1 05:59:01 MDT 2014",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "We introduce a new closed-form equation for estimating
                 the number of data-loss events for a redundant array of
                 inexpensive disks in a RAID-6 configuration. The
                 equation expresses operational failures, their
                 restorations, latent (sector) defects, and disk media
                 scrubbing by time-based distributions that can
                 represent non-homogeneous Poisson processes. It uses
                 two-parameter Weibull distributions that allows the
                 distributions to take on many different shapes,
                 modeling increasing, decreasing, or constant occurrence
                 rates. This article focuses on the statistical basis of
                 the equation. It also presents time-based distributions
                 of the four processes based on an extensive analysis of
                 field data collected over several years from 10,000s of
                 commercially available systems with 100,000s of disk
                 drives. Our results for RAID-6 groups of size 16
                 indicate that the closed-form expression yields much
                 more accurate results compared to the MTTDL reliability
                 equation and matching computationally-intensive Monte
                 Carlo simulations.",
  acknowledgement = ack-nhfb,
  articleno =    "7",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}

@Article{Desnoyers:2014:AMS,
  author =       "Peter Desnoyers",
  title =        "Analytic Models of {SSD} Write Performance",
  journal =      j-TOS,
  volume =       "10",
  number =       "2",
  pages =        "8:1--8:??",
  month =        mar,
  year =         "2014",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/2577384",
  ISSN =         "1553-3077 (print), 1553-3093 (electronic)",
  ISSN-L =       "1553-3077",
  bibdate =      "Tue Apr 1 05:59:01 MDT 2014",
  bibsource =    "http://www.acm.org/pubs/contents/journals/tos/;
                 http://www.math.utah.edu/pub/tex/bib/tos.bib",
  abstract =     "Solid-state drives (SSDs) update data by writing a new
                 copy, rather than overwriting old data, causing prior
                 copies of the same data to be invalidated. These writes
                 are performed in units of pages, while space is
                 reclaimed in units of multipage erase blocks,
                 necessitating copying of any remaining valid pages in
                 the block before reclamation. The efficiency of this
                 cleaning process greatly affects performance under
                 random workloads; in particular, in SSDs, the write
                 bottleneck is typically internal media throughput, and
                 write amplification due to additional internal copying
                 directly reduces application throughput. We present the
                 first nearly-exact closed-form solution for write
                 amplification under greedy cleaning for
                 uniformly-distributed random traffic, validate its
                 accuracy via simulation, and show that its inaccuracies
                 are negligible for reasonable block sizes and
                 overprovisioning ratios. In addition, we also present
                 the first models which predict performance degradation
                 for both LRW (least-recently-written) cleaning and
                 greedy cleaning under simple nonuniform traffic
                 conditions; simulation results show the first model to
                 be exact and the second to be accurate within 2\%. We
                 extend the LRW model to arbitrary combinations of
                 random traffic and demonstrate its use in predicting
                 cleaning performance for real-world workloads. Using
                 these analytic models, we examine the strategy of
                 separating ``hot'' and ``cold'' data, showing that for
                 our traffic model, such separation eliminates any loss
                 in performance due to nonuniform traffic. We then show
                 how a system which segregates hot and cold data into
                 different block pools may shift free space between
                 these pools in order to achieve improved performance,
                 and how numeric methods may be used with our model to
                 find the optimum operating point, which approaches a
                 write amplification of 1.0 for increasingly skewed
                 traffic. We examine online methods for achieving this
                 optimal operating point and show a control strategy
                 based on our model which achieves high performance for
                 a number of real-world block traces.",
  acknowledgement = ack-nhfb,
  articleno =    "8",
  fjournal =     "ACM Transactions on Storage",
  journal-URL =  "http://portal.acm.org/browse_dl.cfm?idx=J960",
}