{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,12]],"date-time":"2026-11-12T07:30:43Z","timestamp":1794468643177,"version":"4.9.1"},"publisher-location":"New York, NY","reference-count":49,"publisher":"Springer New York","isbn-type":[{"value":"9781461492412","type":"print"},{"value":"9781461492429","type":"electronic"}],"license":[{"start":{"date-parts":[[2013,11,28]],"date-time":"2013-11-28T00:00:00Z","timestamp":1385596800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2013,11,28]],"date-time":"2013-11-28T00:00:00Z","timestamp":1385596800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-1-4614-9242-9_1","type":"book-chapter","created":{"date-parts":[[2014,1,8]],"date-time":"2014-01-08T04:18:53Z","timestamp":1389154733000},"page":"1-39","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["The Family of Map-Reduce"],"prefix":"10.1007","author":[{"given":"Sherif","family":"Sakr","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2013,11,28]]},"reference":[{"issue":"1","key":"1_CR1","first-page":"922","volume":"2","author":"A. Abouzeid","year":"2009","unstructured":"Abouzeid, A., Bajda-Pawlikowski, K., Abadi, D., Rasin, D.A., Silberschatz, A.: HadoopDB: an architectural hybrid of MapReduce and DBMS technologies for analytical workloads. PVLDB 2(1), 922\u2013933 (2009)","journal-title":"PVLDB"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Abouzeid, A., Bajda-Pawlikowski, K., Huang, J., Abadi, D., Silberschatz, A.: HadoopDB in action: building real world applications. In: SIGMOD, Indianapolis, 2010, pp. 1111\u20131114","DOI":"10.1145\/1807167.1807294"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Afrati, F., Ullman, J.: Optimizing joins in a map-reduce environment. In: EDBT, Lausanne, 2010, pp. 99\u2013110","DOI":"10.1145\/1739041.1739056"},{"key":"1_CR4","volume-title":"MapReduce online","author":"P. Alvaro","year":"2010","unstructured":"Alvaro, P., Hellerstein, J., Elmeleegy, K., Condie, T., Conway, N., Sears, R.: MapReduce online. In: NSDI, San Jose, 2010"},{"key":"1_CR5","unstructured":"Armbrust, M., Fox, A., Rean, G., Joseph, A., Katz, R., Konwinski, A., Gunho, L., David, P., Rabkin, A., Stoica, I., Zaharia, M.: Above the clouds: a Berkeley view of cloud computing, Dept. Electrical Eng. and Comput. Sciences, University of California, Berkeley, Tech. Rep. UCB\/EECS, vol. 28, 2009"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Babu, S.: Towards automatic optimization of MapReduce programs. In: SoCC, Indianapolis, 2010, pp. 137\u2013142","DOI":"10.1145\/1807128.1807150"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Bajda-Pawlikowski, K., Abadi, D., Silberschatz, A., Paulson, E.: HadoopDB in action: efficient processing of data warehousing queries in a split execution environment. In: SIGMOD, Athens, 2011, pp. 1165\u20131176","DOI":"10.1145\/1989323.1989447"},{"issue":"1","key":"1_CR8","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1109\/MC.2006.29","volume":"39","author":"G. Bell","year":"2006","unstructured":"Bell, G., Gray, J., Szalay, A.: Petascale computational systems. IEEE Comput. 39(1), 110\u2013112 (2006)","journal-title":"IEEE Comput."},{"issue":"11","key":"1_CR9","first-page":"1272","volume":"4","author":"K. Beyer","year":"2011","unstructured":"Beyer, K., Ercegovac, V., Gemulla, R., Balmin, A., Eltabakh, M., Kanne, C., Ozcan, F., Shekita, E.: Jaql: a scripting language for large scale semistructured data analysis. PVLDB 4(11), 1272\u20131283 (2011)","journal-title":"PVLDB"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Blanas, S., Patel, J., Ercegovac, V., Rao, J., Shekita, E., Tian, Y.: A comparison of join algorithms for log processing in MapReduce. In: SIGMOD, Indianapolis, 2010, pp. 975\u2013986","DOI":"10.1145\/1807167.1807273"},{"issue":"1","key":"1_CR11","first-page":"285","volume":"3","author":"Y. Bu","year":"2010","unstructured":"Bu, Y., Howe, B., Balazinska, M., Ernst, M.: HaLoop: efficient iterative data processing on large clusters. PVLDB 3(1), 285\u2013296 (2010)","journal-title":"PVLDB"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Cary, A., Sun, Z., Hristidis, V., Rishe, N.: Experiences on processing spatial data with MapReduce. In: SSDBM, New Orleans, 2009, pp. 302\u2013319","DOI":"10.1007\/978-3-642-02279-1_24"},{"issue":"2","key":"1_CR13","first-page":"1265","volume":"1","author":"R. Chaiken","year":"2008","unstructured":"Chaiken, R., Jenkins, B., Larson, P., Ramsey, B., Shakib, D., Weaver, S., Zhou, J.: SCOPE: easy and efficient parallel processing of massive data sets. PVLDB 1(2), 1265\u20131276 (2008)","journal-title":"PVLDB"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Chen, R., Weng, X., He, B., Yang, M.: Large graph processing in the cloud. In: SIGMOD, Indianapolis, 2010, pp. 1123\u20131126","DOI":"10.1145\/1807167.1807297"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Das, S., Sismanis, Y., Beyer, K., Gemulla, R., Haas, P., McPherson, J.: Ricardo: integrating R and Hadoop. In: SIGMOD, Indianapolis, 2010, pp. 987\u2013998","DOI":"10.1145\/1807167.1807275"},{"key":"1_CR16","unstructured":"Dean, J., Ghemawat, S.: MapReduce: simplified data processing on large clusters. In: OSDI, San Francisco, 2004, pp. 137\u2013150"},{"issue":"1","key":"1_CR17","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J. Dean","year":"2008","unstructured":"Dean, J., Ghemawat, S.: MapReduce: simplified data processing on large clusters. Commun. ACM 51(1), 107\u2013113 (2008)","journal-title":"Commun. ACM"},{"issue":"1","key":"1_CR18","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1145\/1629175.1629198","volume":"53","author":"J. Dean","year":"2010","unstructured":"Dean, J., Ghemawat, S.: MapReduce: a flexible data processing tool. Commun. ACM 53(1), 72\u201377 (2010)","journal-title":"Commun. ACM"},{"issue":"1","key":"1_CR19","first-page":"518","volume":"3","author":"J. Dittrich","year":"2010","unstructured":"Dittrich, J., Quiane-Ruiz, J., Jindal, A., Kargin, Y., Setty, V., Schad, J.: Hadoop++: making a yellow elephant run like a cheetah (without it even noticing). PVLDB 3(1), 518\u2013529 (2010)","journal-title":"PVLDB"},{"issue":"9","key":"1_CR20","first-page":"575","volume":"4","author":"M. Eltabakh","year":"2011","unstructured":"Eltabakh, M., Tian, Y., Ozcan, F., Gemulla, R., Krettek, A., McPherson, J.: CoHadoop: flexible data placement and its exploitation in Hadoop. PVLDB 4(9), 575\u2013585 (2011)","journal-title":"PVLDB"},{"issue":"7","key":"1_CR21","first-page":"460","volume":"4","author":"G. Francisci Morales","year":"2011","unstructured":"Francisci Morales, G., Gionis, A., Sozio, M.: Social content matching in MapReduce. PVLDB 4(7), 460\u2013469 (2011)","journal-title":"PVLDB"},{"issue":"2","key":"1_CR22","first-page":"1402","volume":"2","author":"E. Friedman","year":"2009","unstructured":"Friedman, E., Pawlowski, P., Cieslewicz, J.: SQL\/MapReduce: a practical approach to self-describing, polymorphic, and parallelizable user-defined functions. PVLDB 2(2), 1402\u20131413 (2009)","journal-title":"PVLDB"},{"issue":"2","key":"1_CR23","first-page":"1414","volume":"2","author":"A. Gates","year":"2009","unstructured":"Gates, A., Natkovich, O., Chopra, S., Kamath, P., Narayanam, S., Olston, C., Reed, B., Srinivasan, S., Srivastava, U.: Building a highlevel data ow system on top of MapReduce: the pig experience. PVLDB 2(2), 1414\u20131425 (2009)","journal-title":"PVLDB"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Ghemawat, S., Gobioff, H., Leung, S.: The Google file system. In: SOSP, Bolton Landing, 2003, pp. 29\u201343","DOI":"10.1145\/1165389.945450"},{"key":"1_CR25","volume-title":"Lessons learned from a year\u2019s worth of benchmarks of large data clouds","author":"Y. Gu","year":"2009","unstructured":"Gu, Y., Grossman, R.: Lessons learned from a year\u2019s worth of benchmarks of large data clouds. In: SC-MTAGS, Portland, 2009"},{"key":"1_CR26","volume-title":"The Fourth Paradigm: Data-Intensive Scientific Discovery","year":"2009","unstructured":"Hey, T., Tansly, S., Tolle, K. (eds.): The Fourth Paradigm: Data-Intensive Scientific Discovery. Microsoft Research, Redmond (2009)"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Isard, M., Budiu, M., Yu, Y., Birrell, A., Fetterly, D.: Dryad: distributed data-parallel programs from sequential building blocks. In: EuroSys, Lisbon, 2007, pp. 59\u201372","DOI":"10.1145\/1272998.1273005"},{"issue":"1","key":"1_CR28","first-page":"472","volume":"3","author":"D. Jiang","year":"2010","unstructured":"Jiang, D., Chin Ooi, B., Shi, L., Wu, S.: The performance of MapReduce: an in-depth study. PVLDB 3(1), 472\u2013483 (2010)","journal-title":"PVLDB"},{"issue":"1","key":"1_CR29","first-page":"129","volume":"3","author":"W. Lang","year":"2010","unstructured":"Lang, W., Patel, J.: Energy management for MapReduce clusters. PVLDB 3(1), 129\u2013139 (2010)","journal-title":"PVLDB"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Lattanzi, S., Moseley, B., Suri, S., Vassilvitskii, S.: Filtering: a method for solving graph problems in MapReduce. In: SPAA, San Jose, 2011, pp. 85\u201394","DOI":"10.1145\/1989493.1989505"},{"key":"1_CR31","volume-title":"Scripting the cloud with Skywriting","author":"D. Murray","year":"2010","unstructured":"Murray, D., Hand, S.: Scripting the cloud with Skywriting. In: HotCloud, USENIX Workshop, Boston, 2010"},{"issue":"1","key":"1_CR32","first-page":"494","volume":"3","author":"T. Nykiel","year":"2010","unstructured":"Nykiel, T., Potamias, M., Mishra, C., Kollios, G., Koudas, N.: MRShare: sharing across multiple queries in MapReduce. PVLDB 3(1), 494\u2013505 (2010)","journal-title":"PVLDB"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Olston, C., Reed, B., Srivastava, U., Kumar, R., Tomkins, A.: Pig latin: a not-so-foreign language for data processing. In: SIGMOD, Vancouver, 2008, pp. 1099\u20131110","DOI":"10.1145\/1376616.1376726"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Pavlo, A., Paulson, E., Rasin, A., Abadi, D., DeWitt, D., Madden, S., Stonebraker, M.: A comparison of approaches to large-scale data analysis. In: SIGMOD, Providence, 2009, pp. 165\u2013178","DOI":"10.1145\/1559845.1559865"},{"issue":"4","key":"1_CR35","first-page":"277","volume":"13","author":"R. Pike","year":"2005","unstructured":"Pike, R., Dorward, S., Griesemer, R., Quinlan, S.: Interpreting the data: parallel analysis with Sawzall. Sci. Program. 13(4), 277\u2013298 (2005)","journal-title":"Sci. Program."},{"key":"1_CR36","volume-title":"Towards scalable RDF graph analytics on MapReduce","author":"P. Ravindra","year":"2010","unstructured":"Ravindra, P., Deshpande, V., Anyanwu, K.: Towards scalable RDF graph analytics on MapReduce. In: MDAC, Raleigh, 2010"},{"issue":"3","key":"1_CR37","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1109\/SURV.2011.032211.00087","volume":"13","author":"S. Sakr","year":"2011","unstructured":"Sakr, S., Liu, A., Batista, D., Alomari, M.: Hive \u2013 a survey of large scale data management approaches in cloud environments. IEEE Commun. Surv. Tutor. 13(3), 311\u2013336 (2011)","journal-title":"IEEE Commun. Surv. Tutor."},{"issue":"1","key":"1_CR38","first-page":"4","volume":"9","author":"M. Stonebraker","year":"1986","unstructured":"Stonebraker, M.: The case for shared nothing. IEEE Database Eng. Bull. 9(1), 4\u20139 (1986)","journal-title":"IEEE Database Eng. Bull."},{"issue":"1","key":"1_CR39","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1145\/1629175.1629197","volume":"53","author":"M. Stonebraker","year":"2010","unstructured":"Stonebraker, M., Abadi, D., DeWitt, D., Madden, S., Paulson, E., Pavlo, A., Rasin, A.: MapReduce and parallel DBMSs: friends or foes? Commun. ACM 53(1), 64\u201371 (2010)","journal-title":"Commun. ACM"},{"issue":"2","key":"1_CR40","first-page":"1626","volume":"2","author":"A. Thusoo","year":"2009","unstructured":"Thusoo, A., Sarma, J., Jain, N., Shao, Z., Chakka, P., Anthony, S., Liu, H., Wyckoff, P., Murthy, R.: Hive \u2013 a warehousing solution over a map-reduce framework. PVLDB 2(2), 1626\u20131629 (2009)","journal-title":"PVLDB"},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Thusoo, A., Sarma, J., Jain, N., Shao, Z., Chakka, P., Anthony, S., Liu, H., Wyckoff, P., Murthy, R.: Hive \u2013 a petabyte scale data warehouse using Hadoop. In: ICDE, Long Beach, 2010, pp. 996\u20131005","DOI":"10.1109\/ICDE.2010.5447738"},{"key":"1_CR42","doi-asserted-by":"crossref","unstructured":"Vernica, R., Carey, M., Li, C.: Efficient parallel set-similarity joins using MapReduce. In: SIGMOD, Indianapolis, 2010, pp. 495\u2013506","DOI":"10.1145\/1807167.1807222"},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"Wang, C., Wang, J., Lin, X., Wang, W., Wang, H., Li, H., Tian, W., Xu, J., Li, R.: MapDupReducer: detecting near duplicates over massive datasets. In: SIGMOD, Indianapolis, 2010, pp. 1119\u20131122","DOI":"10.1145\/1807167.1807296"},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"Xu, Y., Kostamaa, P., Gao, L.: Integrating Hadoop and parallel DBMS. In: SIGMOD, Indianapolis, 2010, pp. 969\u2013974","DOI":"10.1145\/1807167.1807272"},{"key":"1_CR45","doi-asserted-by":"crossref","unstructured":"Yang, H., Parker, D.: Traverse: simplified indexing on large map-reduce-merge clusters. In: DASFAA, Brisbane, 2009, pp. 308\u2013322","DOI":"10.1007\/978-3-642-00887-0_27"},{"key":"1_CR46","doi-asserted-by":"crossref","unstructured":"Yang, H., Dasdan, A., Hsiao, R., Parker, D.: Map-reduce-merge: simplified relational data processing on large clusters. In: SIGMOD, Beijing, 2007, pp. 1029\u20131040","DOI":"10.1145\/1247480.1247602"},{"key":"1_CR47","unstructured":"Yu, Y., Isard, M., Fetterly, D., Budiu, M., Erlingsson, U., Gunda, P., Currey, J.: DryadLINQ: a system for general-purpose distributed data-parallel computing using a high-level language. In: OSDI, San Diego, 2008, pp. 1\u201314"},{"key":"1_CR48","unstructured":"Zaharia, M., Konwinski, A., Joseph, A., Katz, R., Stoica, I.: Improving MapReduce performance in heterogeneous environments. In: OSDI, San Diego, 2008, pp. 29\u201342"},{"key":"1_CR49","doi-asserted-by":"crossref","unstructured":"Zhou, J., Larson, P., Chaiken, R.: Incorporating partitioning and parallel plans into the SCOPE optimizer. In: ICDE, Long Beach, 2010, pp. 1060\u20131071","DOI":"10.1109\/ICDE.2010.5447802"}],"container-title":["Large-Scale Data Analytics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-1-4614-9242-9_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,14]],"date-time":"2023-02-14T04:56:54Z","timestamp":1676350614000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-1-4614-9242-9_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,11,28]]},"ISBN":["9781461492412","9781461492429"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-1-4614-9242-9_1","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/978-1-4614-9242-9","asserted-by":"object"}]},"subject":[],"published":{"date-parts":[[2013,11,28]]},"assertion":[{"value":"28 November 2013","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}