bigdata.bib

@misc{Gartner2014,
  AUTHOR="Gartner",
  TITLE="Gartner's 2014 Hype Cycle for Emerging Technologies Maps the Journey to Digital Business",
  howpublished={\url{http://www.gartner.com/newsroom/id/2819918}},
  YEAR=2014
}
@misc{VagateWilfong2014,
  author = {Pamela Vagata and Kevin Wilfong},
  title = {Scaling the Facebook data warehouse to 300 {PB}},
  month = {April},
  year = {2014},
  howpublished={\url{https://code.facebook.com/posts/229861827208629/scaling-the-facebook-data-warehouse-to-300-pb/}}
}
@ARTICLE{Laney2012,
  AUTHOR="Douglas Laney",
  TITLE="The Importance of `Big Data': A Definition",
  JOURNAL="Gartner",
  month = {June},
  YEAR=2012
}
@misc{IBM2013,
  AUTHOR="IBM",
  TITLE="What is big data?",
  howpublished={\url{http://www-01.ibm.com/software/data/bigdata/what-is-big-data.html}},
  YEAR=2013
}
@misc{Top500,
  AUTHOR="Top500.org",
  TITLE="Numerical Wind Tunnel: National Aerospace Laboratory of Japan",
  howpublished={\url{http://www.top500.org/featured/systems/numerical-wind-tunnel-national-aerospace-laboratory-of-japan/}},
  YEAR=2014
}
@misc{Nvidia2014,
  AUTHOR="Wikipedia",
  TITLE="Nvidia Tesla",
  howpublished={\url{http://en.wikipedia.org/wiki/Nvidia_Tesla}},
  YEAR=2014
}
@ARTICLE{NunesKambil2001,
  AUTHOR="Paul F. Nunes and Ajit Kambil",
  TITLE="Personalization? {No} Thanks.",
  JOURNAL="Harvard Business Review",
  howpublished={\url{http://hbr.org/2001/04/personalization-no-thanks/ar/1}},
  month = {April},
  YEAR=2001
}
@inproceedings{Huetal2000,
  author = "J. Hu, and H.R. Wu and A. Jennings and X. Wang",
  title = "Fast and robust equalization: A case study",
  booktitle = "Proceedings of the World Multiconference on Systemics, Cybernetics and Informatics, (SCI 2000), Florida, USA, 23-26 July 2000",
  publisher = "International Institute of Informatics and Systemics", 
  address = "FL, USA",
  pages = "398--403",
  year = "2000"
}
@Book{Conway2000,
  author = {Damian Conway},
  title = {Object {O}riented {P}erl: {A} comprehensive guide to concepts and programming techniques},
  publisher = {Manning Publications Co.},
  year = {2000},
  address = {Connecticut, USA}
}
@misc{YARN2011:279,
  author = {Apache Hadoop},
  title = {ASF JIRA MAPREDUCE-279},
  year = {2011}
}
@misc{Hadoop,
  author = {Apache},
  title = {Hadoop},
  howpublished={\url{http://hadoop.apache.org}}
}
@misc{Tez,
  author = {Apache},
  title = {Tez},
  howpublished={\url{http://tez.apache.org}}
}
@misc{TezTutorial,
  author = {Bikas Saha},
  title = {Apache Tez: A New Chapter in Hadoop Data Processing},
  howpublished={\url{http://hortonworks.com/blog/apache-tez-a-new-chapter-in-hadoop-data-processing/}}
}
@misc{Stinger,
  author = {Alan Gates},
  title = {The Stinger Initiative: Making Apache Hive 100 Times Faster},
  howpublished={\url{http://hortonworks.com/blog/100x-faster-hive/}}
}
@inproceedings{Hindman:2011:MPF,
  author = {Hindman, Benjamin and Konwinski, Andy and Zaharia, Matei and Ghodsi, Ali and Joseph, Anthony D. and Katz, Randy and Shenker, Scott and Stoica, Ion},
  title = {Mesos: A Platform for Fine-grained Resource Sharing in the Data Center},
  booktitle = {Proceedings of the 8th USENIX Conference on Networked Systems Design and Implementation},
  series = {NSDI'11},
  year = {2011},
  location = {Boston, MA},
  pages = {295--308},
  numpages = {14},
  url = {http://dl.acm.org/citation.cfm?id=1972457.1972488},
} 
@inproceedings{Schwarzkopf:2013:OFS,
  author = {Schwarzkopf, Malte and Konwinski, Andy and Abd-El-Malek, Michael and Wilkes, John},
  title = {Omega: Flexible, Scalable Schedulers for Large Compute Clusters},
  booktitle = {Proceedings of the 8th ACM European Conference on Computer Systems},
  series = {EuroSys '13},
  year = {2013},
  location = {Prague, Czech Republic},
  pages = {351--364},
  numpages = {14},
  url = {http://doi.acm.org/10.1145/2465351.2465386},
} 
@inproceedings{Ghodsi:2011:DRF,
  author = {Ghodsi, Ali and Zaharia, Matei and Hindman, Benjamin and Konwinski, Andy and Shenker, Scott and Stoica, Ion},
  title = {Dominant Resource Fairness: Fair Allocation of Multiple Resource Types},
  booktitle = {Proceedings of the 8th USENIX Conference on Networked Systems Design and Implementation},
  series = {NSDI'11},
  year = {2011},
  location = {Boston, MA},
  pages = {323--336},
  numpages = {14},
  url = {http://dl.acm.org/citation.cfm?id=1972457.1972490}
} 
@inproceedings{Ghemawat:2003:GFS,
  author = {Ghemawat, Sanjay and Gobioff, Howard and Leung, Shun-Tak},
  title = {The Google File System},
  booktitle = {Proceedings of the Nineteenth ACM Symposium on Operating Systems Principles},
  series = {SOSP '03},
  year = {2003},
  location = {Bolton Landing, NY, USA},
  pages = {29--43}
}
@techreport{Forum:1994:MMI,
  author = {Forum, Message P},
  title = {MPI: A Message-Passing Interface Standard},
  year = {1994},
  institution = {University of Tennessee},
  address = {Knoxville, TN, USA}
} 
@article{Dean:2008:MSD,
  author = {Dean, Jeffrey and Ghemawat, Sanjay},
  title = {MapReduce: Simplified Data Processing on Large Clusters},
  journal = {Commun. ACM},
  issue_date = {January 2008},
  volume = {51},
  number = {1},
  month = jan,
  year = {2008},
  pages = {107--113}
} 
@book{Gropp:1999:UMA,
  author = {Gropp, William and Lusk, Ewing and Thakur, Rajeev},
  title = {Using MPI-2: Advanced Features of the Message-Passing Interface},
  year = {1999},
  publisher = {MIT Press},
  address = {Cambridge, MA, USA}
} 
@article{McKusick:2009:GEF,
  author = {McKusick, Marshall Kirk and Quinlan, Sean},
  title = {GFS: Evolution on Fast-forward},
  journal = {Queue},
  issue_date = {August 2009},
  volume = {7},
  number = {7},
  month = Aug,
  year = {2009},
  pages = {10--20}
} 
@misc{HDFS,
  AUTHOR="Apache Hadoop",
  TITLE="HDFS Architecture",
  howpublished={\url{http://hadoop.apache.org/docs/current/hadoop-project-dist/hadoop-hdfs/HdfsDesign.html}},
  YEAR=2014
}
@misc{HDFS2010:265,
  author = {Apache Hadoop},
  title = {ASF JIRA HDFS-265},
  year = {2010}
}
@misc{MacLeodClarke2012,
  author = {David MacLeod and Nita Clarke},
  title = {Engaging for Success: enhancing performance through employee engagement},
  year = {2012}
} 
@ARTICLE{ReichheldSasser1990,
  AUTHOR="Frederick F. Reichheld and W. Earl Sasser, Jr.",
  TITLE="Zero Defections: Quality Comes to Services",
  JOURNAL="Harvard Business",
  month = {September},
  YEAR=1990
}
@misc{Accenture14SmartGrid,
  title = {Accenture to Help Thames Water Prove the Benefits of Smart Monitoring Capabilities},
  author = {Accenture},
  year = {2014}
} 
@misc{Accenture13Seattle,
  title = {Accenture Analytics and Smart Building Solutions are helping Seattle boost energy efficiency downtown},
  author = {Accenture},
  year = {2013}
} 
@misc{IndustrialInternetReport2014,
  title = {Industrial Internet Insights report},
  author = {GE and Accenture},
  year = {2014}
} 
@misc{Watson2014,
  AUTHOR="IBM",
  TITLE="Watson",
  howpublished={\url{http://www.ibm.com/smarterplanet/us/en/ibmwatson/}},
  YEAR=2014
}
@misc{Watson2013Healthcare,
  AUTHOR="IBM",
  TITLE="Putting Watson to Work: Watson in Healthcare",
  YEAR=2013
}
@misc{Watson2013Cancer,
  AUTHOR="IBM",
  TITLE="IBM Watson Helps Fight Cancer with Evidence-Based Diagnosis and Treatment Suggestions",
  YEAR=2013
}
@misc{Facebook13Mouse,
  AUTHOR="Lisa Vaas",
  TITLE="Facebook mulls silently tracking users' cursor movements to see which ads we like best",
  YEAR=2013
}
@misc{AdpHcm,
  AUTHOR="ADP",
  TITLE="ADP HCM Solutions for Large Business",
  howpublished={\url{http://www.adp.com/solutions/large-business/products.aspx}},
  YEAR=2014
}
@misc{SmallFiles,
  AUTHOR="Tom White",
  institution = {Cloudera Blog},
  TITLE="The Small Files Problem",
  howpublished={\url{http://blog.cloudera.com/blog/2009/02/the-small-files-problem/}},
  YEAR=2009
}
@misc{Tar2Seq,
  AUTHOR="Stuart Sierra",
  TITLE="A Million Little Files",
  howpublished={\url{http://stuartsierra.com/2008/04/24/a-million-little-files}},
  YEAR=2008
}
@misc{Maven,
  AUTHOR="Apache",
  TITLE="Maven",
  howpublished={\url{http://maven.apache.org}}
}
@misc{Thrift,
  AUTHOR="Apache",
  TITLE="Thrift",
  howpublished={\url{http://thrift.apache.org}}
}
@misc{HdfsThrift,
  AUTHOR="Apache",
  TITLE="{HDFS} {API}s in perl, python, ruby and php",
  howpublished={\url{http://wiki.apache.org/hadoop/HDFS-APIs}}
}
@misc{Sqoop,
  AUTHOR="Apache",
  TITLE="Sqoop",
  howpublished={\url{http://sqoop.apache.org}}
}
@misc{Flume,
  AUTHOR="Apache",
  TITLE="Flume",
  howpublished={\url{http://flume.apache.org}}
}
@misc{Kafka,
  AUTHOR="Apache",
  TITLE="Kafka",
  howpublished={\url{http://kafka.apache.org}}
}
@misc{Chukwa,
  AUTHOR="Apache",
  TITLE="Chukwa",
  howpublished={\url{http://chukwa.apache.org}}
}
@misc{Storm,
  AUTHOR="Apache",
  TITLE="Storm",
  howpublished={\url{http://storm.apache.org}}
}
@misc{HdfsShell,
  AUTHOR="Apache",
  TITLE="File System Shell Guide",
  howpublished={\url{http://hadoop.apache.org/docs/current/hadoop-project-dist/hadoop-common/FileSystemShell.html}}
}
@inproceedings{Pavlo:2009:CAL,
  author = {Pavlo, Andrew and Paulson, Erik and Rasin, Alexander and Abadi, Daniel J. and DeWitt, David J. and Madden, Samuel and Stonebraker, Michael},
  title = {A Comparison of Approaches to Large-scale Data Analysis},
  booktitle = {Proceedings of the 2009 ACM SIGMOD International Conference on Management of Data},
  series = {SIGMOD '09},
  year = {2009},
  location = {Providence, Rhode Island, USA},
  pages = {165--178}
} 
@article{DeWitt:1992:PDS,
  author = {DeWitt, David and Gray, Jim},
  title = {Parallel Database Systems: The Future of High Performance Database Systems},
  journal = {Commun. ACM},
  issue_date = {June 1992},
  volume = {35},
  number = {6},
  month = jun,
  year = {1992},
  pages = {85--98}
} 
@book{Jain:1988:ACD,
  author = {Jain, Anil K. and Dubes, Richard C.},
  title = {Algorithms for Clustering Data},
  year = {1988},
  publisher = {Prentice-Hall, Inc.}
} 
@misc{MapReduceTutorial,
  AUTHOR="Apache",
  TITLE="MapReduce Tutorial",
  howpublished={\url{http://hadoop.apache.org/docs/current/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html}}
}
@inproceedings{Zaharia:2010:SCC,
  author = {Zaharia, Matei and Chowdhury, Mosharaf and Franklin, Michael J. and Shenker, Scott and Stoica, Ion},
  title = {Spark: Cluster Computing with Working Sets},
  booktitle = {Proceedings of the 2Nd USENIX Conference on Hot Topics in Cloud Computing},
  series = {HotCloud'10},
  year = {2010},
  location = {Boston, MA},
} 
@inproceedings{Zaharia:2012:RDD,
  author = {Zaharia, Matei and Chowdhury, Mosharaf and Das, Tathagata and Dave, Ankur and Ma, Justin and McCauley, Murphy and Franklin, Michael J. and Shenker, Scott and Stoica, Ion},
  title = {Resilient Distributed Datasets: A Fault-tolerant Abstraction for In-memory Cluster Computing},
  booktitle = {Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation},
  series = {NSDI'12},
  year = {2012},
  location = {San Jose, CA},
} 
@misc{Spark,
  AUTHOR="Apache",
  TITLE="Spark",
  howpublished={\url{http://spark.apache.org}}
}
@inproceedings{Rowstron:2012:NEG,
  author = {Rowstron, Antony and Narayanan, Dushyanth and Donnelly, Austin and O'Shea, Greg and Douglas, Andrew},
  title = {Nobody Ever Got Fired for Using Hadoop on a Cluster},
  booktitle = {Proceedings of the 1st International Workshop on Hot Topics in Cloud Data Processing},
  series = {HotCDP '12},
  year = {2012},
  location = {Bern, Switzerland},
  pages = {1--5}
} 
@inproceedings{Isard:2007:DDD,
  author = {Isard, Michael and Budiu, Mihai and Yu, Yuan and Birrell, Andrew and Fetterly, Dennis},
  title = {Dryad: Distributed Data-parallel Programs from Sequential Building Blocks},
  booktitle = {Proceedings of the 2Nd ACM SIGOPS/EuroSys European Conference on Computer Systems 2007},
  series = {EuroSys '07},
  year = {2007},
  location = {Lisbon, Portugal},
  pages = {59--72}
} 
@misc{Tachyon,
  AUTHOR="Tachyon Team",
  TITLE="Tachyon Project",
  howpublished={\url{http://tachyon-project.org}}
}
@inproceedings{Brewer:2000:TRD,
  author = {Brewer, Eric A.},
  title = {Towards Robust Distributed Systems (Abstract)},
  booktitle = {Proceedings of the Nineteenth Annual ACM Symposium on Principles of Distributed Computing},
  series = {PODC '00},
  year = {2000},
  location = {Portland, Oregon, USA},
} 
@article{Gilbert:2002:BCF,
  author = {Gilbert, Seth and Lynch, Nancy},
  title = {Brewer's Conjecture and the Feasibility of Consistent, Available, Partition-tolerant Web Services},
  journal = {SIGACT News},
  issue_date = {June 2002},
  volume = {33},
  number = {2},
  month = jun,
  year = {2002},
  pages = {51--59}
} 
@article{Brewer:2012,
  author = {Brewer, Eric A.},
  title = {CAP Twelve Years Later: How the ``Rules'' Have Changed},
  journal = {Computer},
  volume = {45},
  number = {2},
  month = Feb,
  year = {2012},
  pages = {23--29}
} 
@misc{ZooKeeper,
  AUTHOR="Apache",
  TITLE="Zookeeper",
  howpublished={\url{http://zookeeper.apache.org}}
}
@inproceedings{Reed:2008:STO,
  author = {Reed, Benjamin and Junqueira, Flavio P.},
  title = {A Simple Totally Ordered Broadcast Protocol},
  booktitle = {Proceedings of the 2Nd Workshop on Large-Scale Distributed Systems and Middleware},
  series = {LADIS '08},
  year = {2008},
  location = {Yorktown Heights, New York}
}
@article{Lamport:1998:PP,
  author = {Lamport, Leslie},
  title = {The Part-time Parliament},
  journal = {ACM Trans. Comput. Syst.},
  issue_date = {May 1998},
  volume = {16},
  number = {2},
  month = may,
  year = {1998},
  pages = {133--169}
} 
@book{opac:2009,
  title = "Principles of transaction processing",
  author = "Bernstein, Philip A. and Newcomer, Eric",
  series = "The Morgan Kaufmann series in data management systems",
  edition = "Second",
  publisher = "Morgan Kaufmann Publishers",
  address = "Burlington, MA",
  year = 2009
}
@inproceedings{Chang:2006:BDS,
  author = {Chang, Fay and Dean, Jeffrey and Ghemawat, Sanjay and Hsieh, Wilson C. and Wallach, Deborah A. and Burrows, Mike and Chandra, Tushar and Fikes, Andrew and Gruber, Robert E.},
  title = {Bigtable: A Distributed Storage System for Structured Data},
  booktitle = {Proceedings of the 7th USENIX Symposium on Operating Systems Design and Implementation - Volume 7},
  series = {OSDI '06},
  year = {2006},
  location = {Seattle, WA}
} 
@misc{HBase,
  AUTHOR="Apache",
  TITLE="Hbase",
  howpublished={\url{http://hbase.apache.org}}
}
@misc{Accumulo,
  AUTHOR="Apache",
  TITLE="Accumulo",
  howpublished={\url{http://accumulo.apache.org}}
}
@article{Bloom:1970:STH,
  author = {Bloom, Burton H.},
  title = {Space/Time Trade-offs in Hash Coding with Allowable Errors},
  journal = {Commun. ACM},
  issue_date = {July 1970},
  volume = {13},
  number = {7},
  month = jul,
  year = {1970},
  pages = {422--426}
} 
@misc{HBaseMTTR,
  AUTHOR="Nicolas Liochon",
  TITLE="Introduction to HBase Mean Time to Recovery ({MTTR})",
  howpublished={\url{http://hortonworks.com/blog/introduction-to-hbase-mean-time-to-recover-mttr/}}
}
@misc{HBaseCoprocessor,
  AUTHOR="Mingjie Lai and Eugene Koontz and Andrew Purtell",
  TITLE="Coprocessor Introduction",
  howpublished={\url{http://blogs.apache.org/hbase/entry/coprocessor_introduction}}
}
@misc{Riak,
  AUTHOR="Basho",
  TITLE="Riak",
  howpublished={\url{http://basho.com/riak/}}
}
@inproceedings{DeCandia:2007:DAH,
  author = {DeCandia, Giuseppe and Hastorun, Deniz and Jampani, Madan and Kakulapati, Gunavardhan and Lakshman, Avinash and Pilchin, Alex and Sivasubramanian, Swaminathan and Vosshall, Peter and Vogels, Werner},
  title = {Dynamo: {Amazon's} Highly Available Key-value Store},
  booktitle = {Proceedings of Twenty-first ACM SIGOPS Symposium on Operating Systems Principles},
  series = {SOSP '07},
  year = {2007},
  location = {Stevenson, Washington, USA},
  pages = {205--220}
} 
@misc{LevelDB,
  AUTHOR="Jeffrey Dean and Sanjay Ghemawat",
  TITLE="LevelDB",
  howpublished={\url{http://leveldb.org}}
}
@misc{Bitcask,
  AUTHOR= "Justin Sheehy and David Smith",
  TITLE="Bitcask: A Log-Structured Hash Table for Fast Key/Value Data",
  howpublished={\url{http://github.com/basho/basho_docs/raw/master/source/data/bitcask-intro.pdf}}
}
@techreport{CRDT2011,
  author = {Marc Shapiro and Nuno Preguiça and Carlos Baquero and Marek Zawirski},
  title = {A comprehensive study of Convergent and Commutative Replicated Data Types},
  year = {2011},
  number = {RR-7506},
  institution = {INRIA}
} 
@INPROCEEDINGS{Mattern89virtualtime,
  author = {Friedemann Mattern},
  title = {Virtual Time and Global States of Distributed Systems},
  booktitle = {Parallel and Distributed Algorithms},
  year = {1989},
  pages = {215--226}
}
@article{fidge1988timestamps,
  author = {Fidge, C. J.},
  journal = {Proceedings of the 11th Australian Computer Science Conference},
  number = 1,
  pages = {56–66},
  title = {Timestamps in message-passing systems that preserve the partial ordering},
  volume = 10,
  year = 1988
}
@inproceedings{Preguica:2012:BAE,
  author = {Pregui\c{c}a, Nuno and Bauqero, Carlos and Almeida, Paulo S{\'e}rgio and Fonte, Victor and Gon\c{c}alves, Ricardo},
  title = {Brief Announcement: Efficient Causality Tracking in Distributed Storage Systems with Dotted Version Vectors},
  booktitle = {Proceedings of the 2012 ACM Symposium on Principles of Distributed Computing},
  series = {PODC '12},
  year = {2012},
  location = {Madeira, Portugal},
  pages = {335--336}
} 
@misc{Cassandra,
  AUTHOR="Apache",
  TITLE="Cassandra",
  howpublished={\url{http://cassandra.apache.org}}
}
@article{Lakshman:2010:CDS,
  author = {Lakshman, Avinash and Malik, Prashant},
  title = {Cassandra: A Decentralized Structured Storage System},
  journal = {SIGOPS Oper. Syst. Rev.},
  issue_date = {April 2010},
  volume = {44},
  number = {2},
  month = apr,
  year = {2010},
  pages = {35--40}
} 
@MISC{O'Neil96thelog-structured,
  author = {Patrick O'Neil and Edward Cheng and Dieter Gawlick and Elizabeth O'Neil},
  title = {The Log-Structured Merge-Tree (LSM-Tree)},
  year = {1996}
}
@misc{MongoDB,
  AUTHOR="MongoDB",
  TITLE="MongoDB",
  howpublished={\url{https://www.mongodb.com}}
}
@misc{BSON,
  AUTHOR="MongoDB",
  TITLE="BSON",
  howpublished={\url{http://bsonspec.org}}
}
@misc{WiredTiger,
  AUTHOR="MongoDB",
  TITLE="WiredTiger",
  howpublished={\url{http://www.wiredtiger.com}}
}
@misc{ClouderaImpala2014,
  AUTHOR="Cloudera",
  TITLE="New SQL Choices in the Apache Hadoop Ecosystem: Why Impala Continues to Lead",
  howpublished={\url{http://blog.cloudera.com/blog/2014/05/new-sql-choices-in-the-apache-hadoop-ecosystem-why-impala-continues-to-lead/}}
}
@misc{AMPLabBenchmark2014,
  AUTHOR="AMPLab",
  TITLE="Big Data Benchmark",
  howpublished={\url{http://amplab.cs.berkeley.edu/benchmark/}}
}