{"id":"https://openalex.org/W2121142115","doi":"https://doi.org/10.1145/1989323.1989426","title":"A platform for scalable one-pass analytics using MapReduce","display_name":"A platform for scalable one-pass analytics using MapReduce","publication_year":2011,"publication_date":"2011-06-12","ids":{"openalex":"https://openalex.org/W2121142115","doi":"https://doi.org/10.1145/1989323.1989426","mag":"2121142115"},"language":"en","primary_location":{"id":"doi:10.1145/1989323.1989426","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1989323.1989426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078095232","display_name":"Boduo Li","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Boduo Li","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA","University Of Massachusetts Amherst, Amherst, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University Of Massachusetts Amherst, Amherst, MA, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022287795","display_name":"Edward Mazur","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward Mazur","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA","University Of Massachusetts Amherst, Amherst, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University Of Massachusetts Amherst, Amherst, MA, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109548832","display_name":"Yanlei Diao","orcid":"https://orcid.org/0009-0000-7793-9671"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanlei Diao","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA","University Of Massachusetts Amherst, Amherst, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University Of Massachusetts Amherst, Amherst, MA, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101979548","display_name":"Andrew McGregor","orcid":"https://orcid.org/0000-0002-2124-160X"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew McGregor","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA","University Of Massachusetts Amherst, Amherst, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University Of Massachusetts Amherst, Amherst, MA, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032939724","display_name":"Prashant Shenoy","orcid":"https://orcid.org/0000-0002-5435-1901"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prashant Shenoy","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA","University Of Massachusetts Amherst, Amherst, MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University Of Massachusetts Amherst, Amherst, MA, USA#TAB#","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5078095232"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":58.862,"has_fulltext":false,"cited_by_count":151,"citation_normalized_percentile":{"value":0.99877244,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"985","last_page":"996"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8812516927719116},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.7292189598083496},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6823147535324097},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4889284670352936},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4882512390613556},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4859001040458679},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.47512632608413696},{"id":"https://openalex.org/keywords/data-processing","display_name":"Data processing","score":0.4571123421192169},{"id":"https://openalex.org/keywords/batch-processing","display_name":"Batch processing","score":0.44920364022254944},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3415018618106842},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3141738474369049},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3127708435058594},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16010066866874695}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8812516927719116},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.7292189598083496},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6823147535324097},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4889284670352936},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4882512390613556},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4859001040458679},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.47512632608413696},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.4571123421192169},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.44920364022254944},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3415018618106842},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3141738474369049},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3127708435058594},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16010066866874695}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1989323.1989426","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1989323.1989426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.221.7754","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.221.7754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.umass.edu/%7Eyanlei/publications/sopa-sigmod11-long.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.224.3595","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.224.3595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.umass.edu/%7Eboduo/publications/sopa-sigmod11.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.360.3567","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.360.3567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.cs.umass.edu/~boduo/publications/2011SIGMOD-scalla-long.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1501042780","https://openalex.org/W1598064945","https://openalex.org/W1965972569","https://openalex.org/W1997020216","https://openalex.org/W2006355640","https://openalex.org/W2010279913","https://openalex.org/W2041770008","https://openalex.org/W2098935637","https://openalex.org/W2110086534","https://openalex.org/W2112013978","https://openalex.org/W2114103324","https://openalex.org/W2114303224","https://openalex.org/W2115503987","https://openalex.org/W2119400430","https://openalex.org/W2119745055","https://openalex.org/W2122950698","https://openalex.org/W2144620640","https://openalex.org/W2151893987","https://openalex.org/W2154894831","https://openalex.org/W2169486917","https://openalex.org/W2173213060","https://openalex.org/W2200275386","https://openalex.org/W2912802084"],"related_works":["https://openalex.org/W4226266853","https://openalex.org/W4210252074","https://openalex.org/W4245701730","https://openalex.org/W2511794504","https://openalex.org/W2911648135","https://openalex.org/W3092201768","https://openalex.org/W2886451445","https://openalex.org/W3108449883","https://openalex.org/W2551093110","https://openalex.org/W2796632413"],"abstract_inverted_index":{"Today\u2019s":[0],"one-pass":[1,45,93,121],"analytics":[2],"applications":[3],"tend":[4],"to":[5,14,59,83,91,119,141,153,157,189,198,211],"be":[6,60,212],"data-intensive":[7],"in":[8],"nature":[9],"and":[10,54,97,112,146,208],"require":[11,160],"the":[12,37,56,64,85,88,106,180,186,193,216],"ability":[13],"process":[15],"high":[16],"volumes":[17],"of":[18,34,87,100,166,182,201,204],"data":[19,57,134,206],"efficiently.":[20],"MapReduce":[21,39,89,102],"is":[22,41,49],"a":[23,32,74,116,132,147,161],"popular":[24],"programming":[25],"model":[26,40,90],"for":[27,44,110],"processing":[28,53,114,156],"large":[29,162],"datasets":[30],"using":[31,170],"cluster":[33,65],"machines.":[35],"However,":[36],"traditional":[38],"not":[42],"well-suited":[43],"analytics,":[46,122],"since":[47],"it":[48],"geared":[50],"towards":[51],"batch":[52],"requires":[55],"set":[58],"fully":[61],"loaded":[62],"into":[63],"before":[66],"running":[67],"analytical":[68],"queries.":[69],"This":[70],"paper":[71],"examines,":[72],"from":[73],"systems":[75,103],"standpoint,":[76],"what":[77],"architectural":[78],"design":[79],"changes":[80],"are":[81],"necessary":[82],"bring":[84],"benefits":[86],"incremental":[92,120],"analytics.":[94],"Our":[95],"empirical":[96],"theoretical":[98],"analyses":[99],"Hadoop-based":[101,168],"show":[104],"that":[105,137,159,174],"widely-used":[107],"sort-merge":[108],"implementation":[109],"partitioning":[111],"parallel":[113],"poses":[115],"fundamental":[117],"barrier":[118],"despite":[123],"various":[124],"optimizations.":[125],"To":[126],"address":[127],"these":[128],"limitations,":[129],"we":[130],"propose":[131],"new":[133,148,176],"analysis":[135],"platform":[136,177],"employs":[138],"hash":[139],"techniques":[140],"enable":[142],"fast":[143],"in-memory":[144],"processing,":[145],"frequent":[149],"key":[150],"based":[151],"technique":[152],"extend":[154],"such":[155],"workloads":[158,172],"key-state":[163],"space.":[164],"Evaluation":[165],"our":[167,175],"prototype":[169],"real-world":[171],"shows":[173],"significantly":[178],"improves":[179],"progress":[181,188],"map":[183,194],"tasks,":[184],"allows":[185],"reduce":[187],"keep":[190],"up":[191,197],"with":[192,196],"progress,":[195],"3":[199],"orders":[200],"magnitude":[202],"reduction":[203],"internal":[205],"spills,":[207],"enables":[209],"results":[210],"returned":[213],"continuously":[214],"during":[215],"job.":[217],"1.":[218]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":24},{"year":2014,"cited_by_count":31},{"year":2013,"cited_by_count":27},{"year":2012,"cited_by_count":17}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}