bigdata.bbl

\begin{thebibliography}{10}

\bibitem{Accenture13Seattle}
Accenture.
\newblock Accenture analytics and smart building solutions are helping seattle
  boost energy efficiency downtown, 2013.

\bibitem{Accenture14SmartGrid}
Accenture.
\newblock Accenture to help thames water prove the benefits of smart monitoring
  capabilities, 2014.

\bibitem{AdpHcm}
ADP.
\newblock Adp hcm solutions for large business.
\newblock \url{http://www.adp.com/solutions/large-business/products.aspx},
  2014.

\bibitem{AMPLabBenchmark2014}
AMPLab.
\newblock Big data benchmark.
\newblock \url{http://amplab.cs.berkeley.edu/benchmark/}.

\bibitem{Accumulo}
Apache.
\newblock Accumulo.
\newblock \url{http://accumulo.apache.org}.

\bibitem{Cassandra}
Apache.
\newblock Cassandra.
\newblock \url{http://cassandra.apache.org}.

\bibitem{Chukwa}
Apache.
\newblock Chukwa.
\newblock \url{http://chukwa.apache.org}.

\bibitem{HdfsShell}
Apache.
\newblock File system shell guide.
\newblock
  \url{http://hadoop.apache.org/docs/current/hadoop-project-dist/hadoop-common/FileSystemShell.html}.

\bibitem{Flume}
Apache.
\newblock Flume.
\newblock \url{http://flume.apache.org}.

\bibitem{Hadoop}
Apache.
\newblock Hadoop.
\newblock \url{http://hadoop.apache.org}.

\bibitem{HBase}
Apache.
\newblock Hbase.
\newblock \url{http://hbase.apache.org}.

\bibitem{HdfsThrift}
Apache.
\newblock {HDFS} {API}s in perl, python, ruby and php.
\newblock \url{http://wiki.apache.org/hadoop/HDFS-APIs}.

\bibitem{Kafka}
Apache.
\newblock Kafka.
\newblock \url{http://kafka.apache.org}.

\bibitem{MapReduceTutorial}
Apache.
\newblock Mapreduce tutorial.
\newblock
  \url{http://hadoop.apache.org/docs/current/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html}.

\bibitem{Maven}
Apache.
\newblock Maven.
\newblock \url{http://maven.apache.org}.

\bibitem{Spark}
Apache.
\newblock Spark.
\newblock \url{http://spark.apache.org}.

\bibitem{Sqoop}
Apache.
\newblock Sqoop.
\newblock \url{http://sqoop.apache.org}.

\bibitem{Storm}
Apache.
\newblock Storm.
\newblock \url{http://storm.apache.org}.

\bibitem{Tez}
Apache.
\newblock Tez.
\newblock \url{http://tez.apache.org}.

\bibitem{Thrift}
Apache.
\newblock Thrift.
\newblock \url{http://thrift.apache.org}.

\bibitem{ZooKeeper}
Apache.
\newblock Zookeeper.
\newblock \url{http://zookeeper.apache.org}.

\bibitem{Riak}
Basho.
\newblock Riak.
\newblock \url{http://basho.com/riak/}.

\bibitem{opac:2009}
Philip~A. Bernstein and Eric Newcomer.
\newblock {\em Principles of transaction processing}.
\newblock The Morgan Kaufmann series in data management systems. Morgan
  Kaufmann Publishers, Burlington, MA, second edition, 2009.

\bibitem{Bloom:1970:STH}
Burton~H. Bloom.
\newblock Space/time trade-offs in hash coding with allowable errors.
\newblock {\em Commun. ACM}, 13(7):422--426, July 1970.

\bibitem{Brewer:2000:TRD}
Eric~A. Brewer.
\newblock Towards robust distributed systems (abstract).
\newblock In {\em Proceedings of the Nineteenth Annual ACM Symposium on
  Principles of Distributed Computing}, PODC '00, 2000.

\bibitem{Brewer:2012}
Eric~A. Brewer.
\newblock Cap twelve years later: How the ``rules'' have changed.
\newblock {\em Computer}, 45(2):23--29, February 2012.

\bibitem{Chang:2006:BDS}
Fay Chang, Jeffrey Dean, Sanjay Ghemawat, Wilson~C. Hsieh, Deborah~A. Wallach,
  Mike Burrows, Tushar Chandra, Andrew Fikes, and Robert~E. Gruber.
\newblock Bigtable: A distributed storage system for structured data.
\newblock In {\em Proceedings of the 7th USENIX Symposium on Operating Systems
  Design and Implementation - Volume 7}, OSDI '06, 2006.

\bibitem{ClouderaImpala2014}
Cloudera.
\newblock New sql choices in the apache hadoop ecosystem: Why impala continues
  to lead.
\newblock
  \url{http://blog.cloudera.com/blog/2014/05/new-sql-choices-in-the-apache-hadoop-ecosystem-why-impala-continues-to-lead/}.

\bibitem{LevelDB}
Jeffrey Dean and Sanjay Ghemawat.
\newblock Leveldb.
\newblock \url{http://leveldb.org}.

\bibitem{Dean:2008:MSD}
Jeffrey Dean and Sanjay Ghemawat.
\newblock Mapreduce: Simplified data processing on large clusters.
\newblock {\em Commun. ACM}, 51(1):107--113, January 2008.

\bibitem{DeCandia:2007:DAH}
Giuseppe DeCandia, Deniz Hastorun, Madan Jampani, Gunavardhan Kakulapati,
  Avinash Lakshman, Alex Pilchin, Swaminathan Sivasubramanian, Peter Vosshall,
  and Werner Vogels.
\newblock Dynamo: {Amazon's} highly available key-value store.
\newblock In {\em Proceedings of Twenty-first ACM SIGOPS Symposium on Operating
  Systems Principles}, SOSP '07, pages 205--220, 2007.

\bibitem{DeWitt:1992:PDS}
David DeWitt and Jim Gray.
\newblock Parallel database systems: The future of high performance database
  systems.
\newblock {\em Commun. ACM}, 35(6):85--98, June 1992.

\bibitem{fidge1988timestamps}
C.~J. Fidge.
\newblock Timestamps in message-passing systems that preserve the partial
  ordering.
\newblock {\em Proceedings of the 11th Australian Computer Science Conference},
  10(1):56–66, 1988.

\bibitem{Forum:1994:MMI}
Message~P Forum.
\newblock Mpi: A message-passing interface standard.
\newblock Technical report, University of Tennessee, Knoxville, TN, USA, 1994.

\bibitem{Gartner2014}
Gartner.
\newblock Gartner's 2014 hype cycle for emerging technologies maps the journey
  to digital business.
\newblock \url{http://www.gartner.com/newsroom/id/2819918}, 2014.

\bibitem{Stinger}
Alan Gates.
\newblock The stinger initiative: Making apache hive 100 times faster.
\newblock \url{http://hortonworks.com/blog/100x-faster-hive/}.

\bibitem{IndustrialInternetReport2014}
GE and Accenture.
\newblock Industrial internet insights report, 2014.

\bibitem{Ghemawat:2003:GFS}
Sanjay Ghemawat, Howard Gobioff, and Shun-Tak Leung.
\newblock The google file system.
\newblock In {\em Proceedings of the Nineteenth ACM Symposium on Operating
  Systems Principles}, SOSP '03, pages 29--43, 2003.

\bibitem{Ghodsi:2011:DRF}
Ali Ghodsi, Matei Zaharia, Benjamin Hindman, Andy Konwinski, Scott Shenker, and
  Ion Stoica.
\newblock Dominant resource fairness: Fair allocation of multiple resource
  types.
\newblock In {\em Proceedings of the 8th USENIX Conference on Networked Systems
  Design and Implementation}, NSDI'11, pages 323--336, 2011.

\bibitem{Gilbert:2002:BCF}
Seth Gilbert and Nancy Lynch.
\newblock Brewer's conjecture and the feasibility of consistent, available,
  partition-tolerant web services.
\newblock {\em SIGACT News}, 33(2):51--59, June 2002.

\bibitem{Gropp:1999:UMA}
William Gropp, Ewing Lusk, and Rajeev Thakur.
\newblock {\em Using MPI-2: Advanced Features of the Message-Passing
  Interface}.
\newblock MIT Press, Cambridge, MA, USA, 1999.

\bibitem{HDFS2010:265}
Apache Hadoop.
\newblock Asf jira hdfs-265, 2010.

\bibitem{YARN2011:279}
Apache Hadoop.
\newblock Asf jira mapreduce-279, 2011.

\bibitem{HDFS}
Apache Hadoop.
\newblock Hdfs architecture.
\newblock
  \url{http://hadoop.apache.org/docs/current/hadoop-project-dist/hadoop-hdfs/HdfsDesign.html},
  2014.

\bibitem{Hindman:2011:MPF}
Benjamin Hindman, Andy Konwinski, Matei Zaharia, Ali Ghodsi, Anthony~D. Joseph,
  Randy Katz, Scott Shenker, and Ion Stoica.
\newblock Mesos: A platform for fine-grained resource sharing in the data
  center.
\newblock In {\em Proceedings of the 8th USENIX Conference on Networked Systems
  Design and Implementation}, NSDI'11, pages 295--308, 2011.

\bibitem{Watson2013Cancer}
IBM.
\newblock Ibm watson helps fight cancer with evidence-based diagnosis and
  treatment suggestions, 2013.

\bibitem{Watson2013Healthcare}
IBM.
\newblock Putting watson to work: Watson in healthcare, 2013.

\bibitem{IBM2013}
IBM.
\newblock What is big data?
\newblock
  \url{http://www-01.ibm.com/software/data/bigdata/what-is-big-data.html},
  2013.

\bibitem{Watson2014}
IBM.
\newblock Watson.
\newblock \url{http://www.ibm.com/smarterplanet/us/en/ibmwatson/}, 2014.

\bibitem{Isard:2007:DDD}
Michael Isard, Mihai Budiu, Yuan Yu, Andrew Birrell, and Dennis Fetterly.
\newblock Dryad: Distributed data-parallel programs from sequential building
  blocks.
\newblock In {\em Proceedings of the 2Nd ACM SIGOPS/EuroSys European Conference
  on Computer Systems 2007}, EuroSys '07, pages 59--72, 2007.

\bibitem{Jain:1988:ACD}
Anil~K. Jain and Richard~C. Dubes.
\newblock {\em Algorithms for Clustering Data}.
\newblock Prentice-Hall, Inc., 1988.

\bibitem{HBaseCoprocessor}
Mingjie Lai, Eugene Koontz, and Andrew Purtell.
\newblock Coprocessor introduction.
\newblock \url{http://blogs.apache.org/hbase/entry/coprocessor_introduction}.

\bibitem{Lakshman:2010:CDS}
Avinash Lakshman and Prashant Malik.
\newblock Cassandra: A decentralized structured storage system.
\newblock {\em SIGOPS Oper. Syst. Rev.}, 44(2):35--40, April 2010.

\bibitem{Lamport:1998:PP}
Leslie Lamport.
\newblock The part-time parliament.
\newblock {\em ACM Trans. Comput. Syst.}, 16(2):133--169, May 1998.

\bibitem{Laney2012}
Douglas Laney.
\newblock The importance of `big data': A definition.
\newblock {\em Gartner}, June 2012.

\bibitem{HBaseMTTR}
Nicolas Liochon.
\newblock Introduction to hbase mean time to recovery ({MTTR}).
\newblock
  \url{http://hortonworks.com/blog/introduction-to-hbase-mean-time-to-recover-mttr/}.

\bibitem{MacLeodClarke2012}
David MacLeod and Nita Clarke.
\newblock Engaging for success: enhancing performance through employee
  engagement, 2012.

\bibitem{Mattern89virtualtime}
Friedemann Mattern.
\newblock Virtual time and global states of distributed systems.
\newblock In {\em Parallel and Distributed Algorithms}, pages 215--226, 1989.

\bibitem{McKusick:2009:GEF}
Marshall~Kirk McKusick and Sean Quinlan.
\newblock Gfs: Evolution on fast-forward.
\newblock {\em Queue}, 7(7):10--20, August 2009.

\bibitem{BSON}
MongoDB.
\newblock Bson.
\newblock \url{http://bsonspec.org}.

\bibitem{MongoDB}
MongoDB.
\newblock Mongodb.
\newblock \url{https://www.mongodb.com}.

\bibitem{WiredTiger}
MongoDB.
\newblock Wiredtiger.
\newblock \url{http://www.wiredtiger.com}.

\bibitem{NunesKambil2001}
Paul~F. Nunes and Ajit Kambil.
\newblock Personalization? {No} thanks.
\newblock {\em Harvard Business Review}, April 2001.

\bibitem{O'Neil96thelog-structured}
Patrick O'Neil, Edward Cheng, Dieter Gawlick, and Elizabeth O'Neil.
\newblock The log-structured merge-tree (lsm-tree), 1996.

\bibitem{Pavlo:2009:CAL}
Andrew Pavlo, Erik Paulson, Alexander Rasin, Daniel~J. Abadi, David~J. DeWitt,
  Samuel Madden, and Michael Stonebraker.
\newblock A comparison of approaches to large-scale data analysis.
\newblock In {\em Proceedings of the 2009 ACM SIGMOD International Conference
  on Management of Data}, SIGMOD '09, pages 165--178, 2009.

\bibitem{Preguica:2012:BAE}
Nuno Pregui\c{c}a, Carlos Bauqero, Paulo~S{\'e}rgio Almeida, Victor Fonte, and
  Ricardo Gon\c{c}alves.
\newblock Brief announcement: Efficient causality tracking in distributed
  storage systems with dotted version vectors.
\newblock In {\em Proceedings of the 2012 ACM Symposium on Principles of
  Distributed Computing}, PODC '12, pages 335--336, 2012.

\bibitem{Reed:2008:STO}
Benjamin Reed and Flavio~P. Junqueira.
\newblock A simple totally ordered broadcast protocol.
\newblock In {\em Proceedings of the 2Nd Workshop on Large-Scale Distributed
  Systems and Middleware}, LADIS '08, 2008.

\bibitem{ReichheldSasser1990}
Frederick~F. Reichheld and Jr. W.~Earl~Sasser.
\newblock Zero defections: Quality comes to services.
\newblock {\em Harvard Business}, September 1990.

\bibitem{Rowstron:2012:NEG}
Antony Rowstron, Dushyanth Narayanan, Austin Donnelly, Greg O'Shea, and Andrew
  Douglas.
\newblock Nobody ever got fired for using hadoop on a cluster.
\newblock In {\em Proceedings of the 1st International Workshop on Hot Topics
  in Cloud Data Processing}, HotCDP '12, pages 1--5, 2012.

\bibitem{TezTutorial}
Bikas Saha.
\newblock Apache tez: A new chapter in hadoop data processing.
\newblock
  \url{http://hortonworks.com/blog/apache-tez-a-new-chapter-in-hadoop-data-processing/}.

\bibitem{Schwarzkopf:2013:OFS}
Malte Schwarzkopf, Andy Konwinski, Michael Abd-El-Malek, and John Wilkes.
\newblock Omega: Flexible, scalable schedulers for large compute clusters.
\newblock In {\em Proceedings of the 8th ACM European Conference on Computer
  Systems}, EuroSys '13, pages 351--364, 2013.

\bibitem{CRDT2011}
Marc Shapiro, Nuno Preguiça, Carlos Baquero, and Marek Zawirski.
\newblock A comprehensive study of convergent and commutative replicated data
  types.
\newblock Technical Report RR-7506, INRIA, 2011.

\bibitem{Bitcask}
Justin Sheehy and David Smith.
\newblock Bitcask: A log-structured hash table for fast key/value data.
\newblock
  \url{http://github.com/basho/basho_docs/raw/master/source/data/bitcask-intro.pdf}.

\bibitem{Tar2Seq}
Stuart Sierra.
\newblock A million little files.
\newblock \url{http://stuartsierra.com/2008/04/24/a-million-little-files},
  2008.

\bibitem{Tachyon}
Tachyon Team.
\newblock Tachyon project.
\newblock \url{http://tachyon-project.org}.

\bibitem{Top500}
Top500.org.
\newblock Numerical wind tunnel: National aerospace laboratory of japan.
\newblock
  \url{http://www.top500.org/featured/systems/numerical-wind-tunnel-national-aerospace-laboratory-of-japan/},
  2014.

\bibitem{Facebook13Mouse}
Lisa Vaas.
\newblock Facebook mulls silently tracking users' cursor movements to see which
  ads we like best, 2013.

\bibitem{VagateWilfong2014}
Pamela Vagata and Kevin Wilfong.
\newblock Scaling the facebook data warehouse to 300 {PB}.
\newblock
  \url{https://code.facebook.com/posts/229861827208629/scaling-the-facebook-data-warehouse-to-300-pb/},
  April 2014.

\bibitem{SmallFiles}
Tom White.
\newblock The small files problem.
\newblock \url{http://blog.cloudera.com/blog/2009/02/the-small-files-problem/},
  2009.

\bibitem{Nvidia2014}
Wikipedia.
\newblock Nvidia tesla.
\newblock \url{http://en.wikipedia.org/wiki/Nvidia_Tesla}, 2014.

\bibitem{Zaharia:2012:RDD}
Matei Zaharia, Mosharaf Chowdhury, Tathagata Das, Ankur Dave, Justin Ma, Murphy
  McCauley, Michael~J. Franklin, Scott Shenker, and Ion Stoica.
\newblock Resilient distributed datasets: A fault-tolerant abstraction for
  in-memory cluster computing.
\newblock In {\em Proceedings of the 9th USENIX Conference on Networked Systems
  Design and Implementation}, NSDI'12, 2012.

\bibitem{Zaharia:2010:SCC}
Matei Zaharia, Mosharaf Chowdhury, Michael~J. Franklin, Scott Shenker, and Ion
  Stoica.
\newblock Spark: Cluster computing with working sets.
\newblock In {\em Proceedings of the 2Nd USENIX Conference on Hot Topics in
  Cloud Computing}, HotCloud'10, 2010.

\end{thebibliography}