{"id":"https://openalex.org/W1993892970","doi":"https://doi.org/10.1109/icde.2010.5447738","title":"Hive - a petabyte scale data warehouse using Hadoop","display_name":"Hive - a petabyte scale data warehouse using Hadoop","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W1993892970","doi":"https://doi.org/10.1109/icde.2010.5447738","mag":"1993892970"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2010.5447738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)","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/A5086564678","display_name":"Ashish Thusoo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashish Thusoo","raw_affiliation_strings":["Facebook Data Infrastructure Team, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Data Infrastructure Team, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027100524","display_name":"Joydeep Sen Sarma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joydeep Sen Sarma","raw_affiliation_strings":["Facebook Data Infrastructure Team, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Data Infrastructure Team, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059659735","display_name":"Namit Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Namit Jain","raw_affiliation_strings":["Facebook Data Infrastructure Team, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Data Infrastructure Team, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112120488","display_name":"Zheng Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheng Shao","raw_affiliation_strings":["Facebook Data Infrastructure Team, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Data Infrastructure Team, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080566229","display_name":"Prasad Chakka","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prasad Chakka","raw_affiliation_strings":["Facebook Data Infrastructure Team, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Data Infrastructure Team, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100404886","display_name":"Ning Zhang","orcid":"https://orcid.org/0000-0002-8781-4925"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ning Zhang","raw_affiliation_strings":["Facebook Data Infrastructure Team, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Data Infrastructure Team, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112772359","display_name":"Suresh Antony","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suresh Antony","raw_affiliation_strings":["Facebook Data Infrastructure Team, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Data Infrastructure Team, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458867","display_name":"Hao Liu","orcid":"https://orcid.org/0000-0003-0510-6501"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Liu","raw_affiliation_strings":["Facebook Data Infrastructure Team, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Data Infrastructure Team, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041172869","display_name":"Raghotham Murthy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raghotham Murthy","raw_affiliation_strings":["Facebook Data Infrastructure Team, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Data Infrastructure Team, USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":160.5662,"has_fulltext":false,"cited_by_count":924,"citation_normalized_percentile":{"value":0.99976865,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"996","last_page":"1005"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9965000152587891,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/petabyte","display_name":"Petabyte","score":0.8814423680305481},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8610460758209229},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.7713217735290527},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.6222159266471863},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.5744236707687378},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.5463162660598755},{"id":"https://openalex.org/keywords/nosql","display_name":"NoSQL","score":0.5176825523376465},{"id":"https://openalex.org/keywords/online-analytical-processing","display_name":"Online analytical processing","score":0.49758365750312805},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46358180046081543},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.42222172021865845},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34741687774658203},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.2766537070274353},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.25025373697280884},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2377755343914032},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.234596848487854}],"concepts":[{"id":"https://openalex.org/C13600138","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Petabyte","level":3,"score":0.8814423680305481},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8610460758209229},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.7713217735290527},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6222159266471863},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5744236707687378},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.5463162660598755},{"id":"https://openalex.org/C2779599972","wikidata":"https://www.wikidata.org/wiki/Q82231","display_name":"NoSQL","level":3,"score":0.5176825523376465},{"id":"https://openalex.org/C201932085","wikidata":"https://www.wikidata.org/wiki/Q642514","display_name":"Online analytical processing","level":3,"score":0.49758365750312805},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46358180046081543},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.42222172021865845},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34741687774658203},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2766537070274353},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25025373697280884},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2377755343914032},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.234596848487854}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icde.2010.5447738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.348.4687","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.348.4687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ucr.edu/%7Etsotras/cs260/F12/Hive.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2114303224","https://openalex.org/W2119400430"],"related_works":["https://openalex.org/W4385834214","https://openalex.org/W2621972978","https://openalex.org/W3129344858","https://openalex.org/W3001928035","https://openalex.org/W4320802139","https://openalex.org/W4301431331","https://openalex.org/W2588045195","https://openalex.org/W2957025774","https://openalex.org/W2889462242","https://openalex.org/W2888933188"],"abstract_inverted_index":{"The":[0,126,150],"size":[1],"of":[2,89,147,195,197,203],"data":[3,47,83,159,181,204],"sets":[4,48],"being":[5,33,207],"collected":[6],"and":[7,43,61,73,142,144,175,185,199,205,213],"analyzed":[8],"in":[9,35,95,120,160,180],"the":[10,53,148,190],"industry":[11],"for":[12,134,210],"business":[13],"intelligence":[14],"is":[15,25,32,57,206],"growing":[16],"rapidly,":[17],"making":[18],"traditional":[19],"warehousing":[20,84],"solutions":[21],"prohibitively":[22],"expensive.":[23],"Hadoop":[24],"a":[26,96,129,166],"popular":[27],"open-source":[28,82],"map-reduce":[29,54,106,122],"implementation":[30],"which":[31,68,102,177],"used":[34,208],"companies":[36],"like":[37,140],"Yahoo,":[38],"Facebook":[39],"etc.":[40],"to":[41,64,71,118,157],"store":[42],"process":[44],"extremely":[45],"large":[46],"on":[49,87],"commodity":[50],"hardware.":[51],"However,":[52],"programming":[55],"model":[56],"very":[58],"low":[59],"level":[60],"requires":[62],"developers":[63],"write":[65],"custom":[66,121,161],"programs":[67],"are":[69,103,109,178],"hard":[70],"maintain":[72],"reuse.":[74],"In":[75,113,188],"this":[76],"paper,":[77],"we":[78],"present":[79],"Hive,":[80],"an":[81],"solution":[85],"built":[86],"top":[88],"Hadoop.":[90,112],"Hive":[91,163,191],"supports":[92],"queries":[93],"expressed":[94],"SQL-like":[97],"declarative":[98],"language":[99,127],"-":[100,169,171],"HiveQL,":[101],"compiled":[104],"into":[105,124],"jobs":[107],"that":[108,172],"executed":[110],"using":[111],"addition,":[114],"HiveQL":[115],"enables":[116],"users":[117,220],"plug":[119],"scripts":[123],"queries.":[125],"includes":[128,165],"type":[130],"system":[131,167],"with":[132],"support":[133],"tables":[135,198],"containing":[136],"primitive":[137],"types,":[138],"collections":[139],"arrays":[141],"maps,":[143],"nested":[145],"compositions":[146],"same.":[149],"underlying":[151],"IO":[152],"libraries":[153],"can":[154],"be":[155],"extended":[156],"query":[158,183,186],"formats.":[162],"also":[164],"catalog":[168],"Metastore":[170],"contains":[173,193],"schemas":[174],"statistics,":[176],"useful":[179],"exploration,":[182],"optimization":[184],"compilation.":[187],"Facebook,":[189],"warehouse":[192],"tens":[194],"thousands":[196],"stores":[200],"over":[201],"700TB":[202],"extensively":[209],"both":[211],"reporting":[212],"ad-hoc":[214],"analyses":[215],"by":[216],"more":[217],"than":[218],"200":[219],"per":[221],"month.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":39},{"year":2020,"cited_by_count":43},{"year":2019,"cited_by_count":57},{"year":2018,"cited_by_count":84},{"year":2017,"cited_by_count":79},{"year":2016,"cited_by_count":93},{"year":2015,"cited_by_count":114},{"year":2014,"cited_by_count":109},{"year":2013,"cited_by_count":108},{"year":2012,"cited_by_count":70}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
