{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T19:37:54Z","timestamp":1742931474260,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319639628"},{"type":"electronic","value":"9783319639628"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-63962-8_206-1","type":"book-chapter","created":{"date-parts":[[2018,8,9]],"date-time":"2018-08-09T01:49:47Z","timestamp":1533779387000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Parallel Join Algorithms in MapReduce"],"prefix":"10.1007","author":[{"given":"Spyros","family":"Blanas","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,3,5]]},"reference":[{"issue":"1","key":"206-1_CR1","first-page":"922","volume":"2","author":"A Abouzeid","year":"2009","unstructured":"Abouzeid A, Bajda-Pawlikowski K, Abadi DJ, Rasin A, Silberschatz A (2009) HadoopDB: an architectural hybrid of mapreduce and DBMS technologies for analytical workloads. PVLDB 2(1):922\u2013933. http:\/\/www.vldb.org\/pvldb\/2\/vldb09-861.pdf","journal-title":"PVLDB"},{"key":"206-1_CR2","doi-asserted-by":"publisher","DOI":"10.1145\/2452376.2452377","volume-title":"Invisible loading: access-driven data transfer from raw files into database systems","author":"A Abouzied","year":"2013","unstructured":"Abouzied A, Abadi DJ, Silberschatz A (2013) Invisible loading: access-driven data transfer from raw files into database systems. In: EDBT"},{"key":"206-1_CR3","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/1739041.1739056","volume-title":"Proceedings of the 13th international conference on extending database technology, EDBT \u201910","author":"FN Afrati","year":"2010","unstructured":"Afrati FN, Ullman JD (2010) Optimizing joins in a map-reduce environment. In: Proceedings of the 13th international conference on extending database technology, EDBT \u201910. ACM, New York, pp 99\u2013110. http:\/\/doi.acm.org\/10.1145\/1739041.1739056"},{"key":"206-1_CR4","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213864","volume-title":"NoDB: efficient query execution on raw data files","author":"I Alagiannis","year":"2012","unstructured":"Alagiannis I, Borovica R, Branco M, Idreos S, Ailamaki A (2012) NoDB: efficient query execution on raw data files. In: SIGMOD"},{"key":"206-1_CR5","unstructured":"AsterixDB (2017) Apache AsterixDB. https:\/\/asterixdb.apache.org\/. Accessed Dec 2017"},{"key":"206-1_CR6","unstructured":"Avro (2017) Apache Avro. https:\/\/avro.apache.org\/. Accessed Dec 2017"},{"key":"206-1_CR7","doi-asserted-by":"publisher","first-page":"1165","DOI":"10.1145\/1989323.1989447","volume-title":"Proceedings of the 2011 ACM SIGMOD international conference on management of data, SIGMOD \u201911","author":"K Bajda-Pawlikowski","year":"2011","unstructured":"Bajda-Pawlikowski K, Abadi DJ, Silberschatz A, Paulson E (2011) Efficient processing of data warehousing queries in a split execution environment. In: Proceedings of the 2011 ACM SIGMOD international conference on management of data, SIGMOD \u201911. ACM, New York, pp 1165\u20131176. http:\/\/doi.acm.org\/10.1145\/1989323.1989447"},{"key":"206-1_CR8","doi-asserted-by":"crossref","unstructured":"Bhatotia P, Wieder A, Rodrigues R, Acar UA, Pasquin R (2011) Incoop: MapReduce for incremental computations. In: Proceedings of the 2nd ACM symposium on cloud computing, SOCC \u201911. ACM, New York, pp 7: 1\u20137:14. http:\/\/doi.acm.org\/10.1145\/2038916.2038923","DOI":"10.1145\/2038916.2038923"},{"key":"206-1_CR9","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807273","volume-title":"A comparison of join algorithms for log processing in MapReduce","author":"S Blanas","year":"2010","unstructured":"Blanas S, Patel JM, Ercegovac V, Rao J, Shekita EJ, Tian Y (2010) A comparison of join algorithms for log processing in MapReduce. In: ACM SIGMOD. http:\/\/doi.acm.org\/10.1145\/1807167.1807273"},{"key":"206-1_CR10","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2612185","volume-title":"Parallel data analysis directly on scientific file formats","author":"S Blanas","year":"2014","unstructured":"Blanas S, Wu K, Byna S, Dong B, Shoshani A (2014) Parallel data analysis directly on scientific file formats. In: SIGMOD"},{"issue":"4","key":"206-1_CR11","first-page":"28","volume":"38","author":"P Carbone","year":"2015","unstructured":"Carbone P, Katsifodimos A, Ewen S, Markl V, Haridi S, Tzoumas K (2015) Apache Flink: stream and batch processing in a single engine. IEEE Data Eng Bull 38(4):28\u201338. http:\/\/sites.computer.org\/debull\/A15dec\/p28.pdf","journal-title":"IEEE Data Eng Bull"},{"key":"206-1_CR12","doi-asserted-by":"crossref","unstructured":"Cheng Y, Rusu F (2015) SCANRAW: a database meta-operator for parallel in-situ processing and loading. TODS 40(3)","DOI":"10.1145\/2818181"},{"key":"206-1_CR13","first-page":"10","volume-title":"Proceedings of the 6th conference on symposium on operating systems design & implementation \u2013 volume 6, OSDI\u201904","author":"J Dean","year":"2004","unstructured":"Dean J, Ghemawat S (2004) Mapreduce: simplified data processing on large clusters. In: Proceedings of the 6th conference on symposium on operating systems design & implementation \u2013 volume 6, OSDI\u201904. USENIX Association, Berkeley, pp 10\u201310. http:\/\/dl.acm.org\/citation.cfm?id=1251254.1251264"},{"key":"206-1_CR14","doi-asserted-by":"publisher","first-page":"1255","DOI":"10.1145\/2463676.2463709","volume-title":"Proceedings of the 2013 ACM SIGMOD international conference on management of data, SIGMOD \u201913","author":"DJ DeWitt","year":"2013","unstructured":"DeWitt DJ, Halverson A, Nehme R, Shankar S, Aguilar-Saborit J, Avanes A, Flasza M, Gramling J (2013) Split query processing in Polybase. In: Proceedings of the 2013 ACM SIGMOD international conference on management of data, SIGMOD \u201913. ACM, New York, pp 1255\u20131266. http:\/\/doi.acm.org\/10.1145\/2463676.2463709"},{"key":"206-1_CR15","unstructured":"Drill (2017) Apache Drill. https:\/\/drill.apache.org\/. Accessed Dec 2017"},{"issue":"9","key":"206-1_CR16","first-page":"575","volume":"4","author":"MY Eltabakh","year":"2011","unstructured":"Eltabakh MY, Tian Y, \u00d6zcan F, Gemulla R, Krettek A, McPherson J (2011) CoHadoop: flexible data placement and its exploitation in Hadoop. PVLDB 4(9):575\u2013585. http:\/\/www.vldb.org\/pvldb\/vol4\/p575-eltabakh.pdf","journal-title":"PVLDB"},{"issue":"7","key":"206-1_CR17","first-page":"419","volume":"4","author":"A Floratou","year":"2011","unstructured":"Floratou A, Patel JM, Shekita EJ, Tata S (2011) Column-oriented storage techniques for mapreduce. PVLDB 4(7):419\u2013429. http:\/\/www.vldb.org\/pvldb\/vol4\/p419-floratou.pdf","journal-title":"PVLDB"},{"key":"206-1_CR18","unstructured":"Hadoop (2017) Apache Hadoop. https:\/\/hadoop.apache.org\/. Accessed Dec 2017"},{"key":"206-1_CR19","doi-asserted-by":"publisher","unstructured":"He Y, Lee R, Huai Y, Shao Z, Jain N, Zhang X, Xu Z (2011) RCFile: a fast and space-efficient data placement structure in MapReduce-based warehouse systems. In: Proceedings of the 27th international conference on data engineering, ICDE 2011, 11\u201316 Apr 2011, Hannover, pp 1199\u20131208. https:\/\/doi.org\/10.1109\/ICDE.2011.5767933","DOI":"10.1109\/ICDE.2011.5767933"},{"issue":"11","key":"206-1_CR20","first-page":"1111","volume":"4","author":"H Herodotou","year":"2011","unstructured":"Herodotou H, Babu S (2011) Profiling, what-if analysis, and cost-based optimization of mapreduce programs. PVLDB 4(11):1111\u20131122. http:\/\/www.vldb.org\/pvldb\/vol4\/p1111-herodotou.pdf","journal-title":"PVLDB"},{"key":"206-1_CR21","unstructured":"Hive (2017) Apache Hive. https:\/\/hive.apache.org\/. Accessed Dec 2017"},{"key":"206-1_CR22","unstructured":"Impala (2017) Apache Impala. https:\/\/impala.apache.org\/. Accessed Dec 2017"},{"key":"206-1_CR23","doi-asserted-by":"crossref","unstructured":"Liu F, Blanas S (2015) Forecasting the cost of processing multi-join queries via hashing for main-memory databases. In: Proceedings of the sixth ACM symposium on cloud computing, SoCC 2015, Kohala Coast, 27\u201329 Aug 2015, pp 153\u2013166. http:\/\/doi.acm.org\/10.1145\/2806777.2806944","DOI":"10.1145\/2806777.2806944"},{"key":"206-1_CR24","doi-asserted-by":"publisher","first-page":"949","DOI":"10.1145\/1989323.1989423","volume-title":"Proceedings of the 2011 ACM SIGMOD international conference on management of data, SIGMOD \u201911","author":"A Okcan","year":"2011","unstructured":"Okcan A, Riedewald M (2011) Processing theta-joins using mapreduce. In: Proceedings of the 2011 ACM SIGMOD international conference on management of data, SIGMOD \u201911. ACM, New York, pp 949\u2013960. http:\/\/doi.acm.org\/10.1145\/1989323.1989423"},{"key":"206-1_CR25","unstructured":"Parquet (2017) Apache Parquet. https:\/\/parquet.apache.org. Accessed Dec 2017"},{"key":"206-1_CR26","unstructured":"Quickstep (2017) Apache Quickstep. https:\/\/quickstep.incubator.apache.org\/. Accessed Dec 2017"},{"key":"206-1_CR27","unstructured":"Spark (2017) Apache Spark. https:\/\/spark.apache.org\/. Accessed Dec 2017"},{"key":"206-1_CR28","first-page":"2","volume-title":"Proceedings of the 9th USENIX conference on networked systems design and implementation, NSDI\u201912","author":"M Zaharia","year":"2012","unstructured":"Zaharia M, Chowdhury M, Das T, Dave A, Ma J, McCauley M, Franklin MJ, Shenker S, Stoica I (2012) Resilient distributed datasets: a fault-tolerant abstraction for in-memory cluster computing. In: Proceedings of the 9th USENIX conference on networked systems design and implementation, NSDI\u201912. USENIX Association, Berkeley, pp 2\u201312. http:\/\/dl.acm.org\/citation.cfm?id=2228298.2228301"}],"container-title":["Encyclopedia of Big Data Technologies"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-63962-8_206-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,10]],"date-time":"2019-05-10T03:05:53Z","timestamp":1557457553000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-63962-8_206-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319639628","9783319639628"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-63962-8_206-1","relation":{},"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"5 March 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}