{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T06:19:01Z","timestamp":1777961941097,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2010,6,6]],"date-time":"2010-06-06T00:00:00Z","timestamp":1275782400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2010,6,6]]},"DOI":"10.1145\/1807167.1807273","type":"proceedings-article","created":{"date-parts":[[2010,6,8]],"date-time":"2010-06-08T12:37:34Z","timestamp":1276000654000},"page":"975-986","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":291,"title":["A comparison of join algorithms for log processing in MaPreduce"],"prefix":"10.1145","author":[{"given":"Spyros","family":"Blanas","sequence":"first","affiliation":[{"name":"University of Wisconsin-Madison, Madison, WI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jignesh M.","family":"Patel","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison, Madison, WI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vuk","family":"Ercegovac","sequence":"additional","affiliation":[{"name":"IBM Almaden Research Center, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Rao","sequence":"additional","affiliation":[{"name":"IBM Almaden Research Center, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eugene J.","family":"Shekita","sequence":"additional","affiliation":[{"name":"IBM Almaden Research Center, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanyuan","family":"Tian","sequence":"additional","affiliation":[{"name":"IBM Almaden Research Center, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2010,6,6]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"http:\/\/www.slideshare.net\/cloudera\/hw09-data-processing-in-the-enterprise.  http:\/\/www.slideshare.net\/cloudera\/hw09-data-processing-in-the-enterprise."},{"key":"e_1_3_2_1_2_1","unstructured":"http:\/\/www.slideshare.net\/cloudera\/hw09-large-scale-transaction-analysis.  http:\/\/www.slideshare.net\/cloudera\/hw09-large-scale-transaction-analysis."},{"key":"e_1_3_2_1_3_1","unstructured":"http:\/\/open.blogs.nytimes.com\/2007\/11\/01\/self-service-prorated-super-computing-fun.  http:\/\/open.blogs.nytimes.com\/2007\/11\/01\/self-service-prorated-super-computing-fun."},{"key":"e_1_3_2_1_4_1","unstructured":"http:\/\/www.slideshare.net\/cloudera\/hw09-hadoop-based-data-mining-platform-for-the-telecom-industry.  http:\/\/www.slideshare.net\/cloudera\/hw09-hadoop-based-data-mining-platform-for-the-telecom-industry."},{"key":"e_1_3_2_1_5_1","unstructured":"http:\/\/wiki.apache.org\/hadoop\/PoweredBy.  http:\/\/wiki.apache.org\/hadoop\/PoweredBy."},{"key":"e_1_3_2_1_6_1","unstructured":"http:\/\/developer.yahoo.net\/blogs\/theater\/archives\/2009\/06\/hadoop summit hadoop and the enterprise.html.  http:\/\/developer.yahoo.net\/blogs\/theater\/archives\/2009\/06\/hadoop summit hadoop and the enterprise.html."},{"key":"e_1_3_2_1_7_1","unstructured":"http:\/\/www.slideshare.net\/prasadc\/hive-percona-2009.  http:\/\/www.slideshare.net\/prasadc\/hive-percona-2009."},{"key":"e_1_3_2_1_8_1","unstructured":"http:\/\/hadoop.apache.org\/.  http:\/\/hadoop.apache.org\/."},{"key":"e_1_3_2_1_9_1","unstructured":"http:\/\/research.yahoo.com\/files\/facebook-hadoop-summit.pdf.  http:\/\/research.yahoo.com\/files\/facebook-hadoop-summit.pdf."},{"key":"e_1_3_2_1_10_1","unstructured":"http:\/\/hadoop.apache.org\/hive\/.  http:\/\/hadoop.apache.org\/hive\/."},{"key":"e_1_3_2_1_11_1","unstructured":"http:\/\/www.jaql.org.  http:\/\/www.jaql.org."},{"key":"e_1_3_2_1_12_1","volume-title":"DBC\/1012 data base computer concepts and facilities","year":"1984","unstructured":"Teradata : DBC\/1012 data base computer concepts and facilities , Teradata Corp., Document No. C02-0001-00, 1984 . Teradata: DBC\/1012 data base computer concepts and facilities, Teradata Corp., Document No. C02-0001-00, 1984."},{"key":"e_1_3_2_1_13_1","volume-title":"Symp. On Comp. Network","author":"Bernstein P. A.","year":"1979","unstructured":"P. A. Bernstein and N. Goodman . Full reducers for relational queries using multi-attribute semijoins . In Symp. On Comp. Network , 1979 . P. A. Bernstein and N. Goodman. Full reducers for relational queries using multi-attribute semijoins. In Symp. On Comp. Network, 1979."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/319628.319650"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.14778\/1454159.1454166"},{"key":"e_1_3_2_1_16_1","volume-title":"OSDI","author":"Dean J.","year":"2004","unstructured":"J. Dean and S. Ghemawat . MapReduce: Simplified data processing on large clusters . In OSDI , 2004 . J. Dean and S. Ghemawat. MapReduce: Simplified data processing on large clusters. In OSDI, 2004."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/129888.129894"},{"key":"e_1_3_2_1_18_1","volume-title":"MapReduce: A major step backwards. Blog post at The Database Column","author":"DeWitt D. J.","year":"2008","unstructured":"D. J. DeWitt and M. Stonebraker . MapReduce: A major step backwards. Blog post at The Database Column , 17 January 2008 . D. J. DeWitt and M. Stonebraker. MapReduce: A major step backwards. Blog post at The Database Column, 17 January 2008."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/945445.945450"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/152610.152611"},{"key":"e_1_3_2_1_21_1","volume-title":"Facebook Inc.","author":"Hammerbacher J.","year":"2008","unstructured":"J. Hammerbacher . Managing a large Hadoop cluster. Presentation , Facebook Inc. , May 2008 . J. Hammerbacher. Managing a large Hadoop cluster. Presentation, Facebook Inc., May 2008."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/128762.128764"},{"key":"e_1_3_2_1_23_1","first-page":"267","volume-title":"USENIX Annual Technical Conference","author":"Olston C.","year":"2008","unstructured":"C. Olston , B. Reed , A. Silberstein , and U. Srivastava . Automatic optimization of parallel dataflow programs . In USENIX Annual Technical Conference , pages 267 -- 273 , 2008 . C. Olston, B. Reed, A. Silberstein, and U. Srivastava. Automatic optimization of parallel dataflow programs. In USENIX Annual Technical Conference, pages 267--273, 2008."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376726"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1559845.1559865"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/67544.66937"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1247480.1247602"}],"event":{"name":"SIGMOD\/PODS '10: International Conference on Management of Data","location":"Indianapolis Indiana USA","acronym":"SIGMOD\/PODS '10","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 2010 ACM SIGMOD International Conference on Management of data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1807167.1807273","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1807167.1807273","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T11:39:33Z","timestamp":1750246773000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1807167.1807273"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,6,6]]},"references-count":27,"alternative-id":["10.1145\/1807167.1807273","10.1145\/1807167"],"URL":"https:\/\/doi.org\/10.1145\/1807167.1807273","relation":{},"subject":[],"published":{"date-parts":[[2010,6,6]]},"assertion":[{"value":"2010-06-06","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}