{"id":"https://openalex.org/W2172220707","doi":"https://doi.org/10.1109/icde.2011.5767933","title":"RCFile: A fast and space-efficient data placement structure in MapReduce-based warehouse systems","display_name":"RCFile: A fast and space-efficient data placement structure in MapReduce-based warehouse systems","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2172220707","doi":"https://doi.org/10.1109/icde.2011.5767933","mag":"2172220707"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2011.5767933","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2011.5767933","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE 27th International Conference on Data Engineering","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/A5062587539","display_name":"Yongqiang He","orcid":"https://orcid.org/0000-0003-2950-3050"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yongqiang He","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy and Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy and Sciences, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089560181","display_name":"Rubao Lee","orcid":"https://orcid.org/0009-0006-3588-0193"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rubao Lee","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024496751","display_name":"Yin Huai","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yin Huai","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112120488","display_name":"Zheng Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Zheng Shao","raw_affiliation_strings":["Facebook Data Infrastructure Team"],"affiliations":[{"raw_affiliation_string":"Facebook Data Infrastructure Team","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059659735","display_name":"Namit Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Namit Jain","raw_affiliation_strings":["Facebook Data Infrastructure Team"],"affiliations":[{"raw_affiliation_string":"Facebook Data Infrastructure Team","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376221","display_name":"Xiaodong Zhang","orcid":"https://orcid.org/0000-0002-8380-1019"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodong Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101756701","display_name":"Zhiwei Xu","orcid":"https://orcid.org/0000-0001-7733-8219"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Xu","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy and Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy and Sciences, China","institution_ids":["https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5062587539"],"corresponding_institution_ids":["https://openalex.org/I4210090176"],"apc_list":null,"apc_paid":null,"fwci":77.9117,"has_fulltext":false,"cited_by_count":258,"citation_normalized_percentile":{"value":0.99921442,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1199","last_page":"1208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9968000054359436,"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/T11106","display_name":"Data Management and Algorithms","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8398067355155945},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.7638393640518188},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7468105554580688},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.649340033531189},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5379460453987122},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5360835790634155},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5234053730964661},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.41151106357574463},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4078819453716278},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.24879488348960876},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2324180006980896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8398067355155945},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.7638393640518188},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7468105554580688},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.649340033531189},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5379460453987122},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5360835790634155},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5234053730964661},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.41151106357574463},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4078819453716278},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24879488348960876},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2324180006980896},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icde.2011.5767933","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2011.5767933","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE 27th International Conference on Data Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.185.1419","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.185.1419","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/hpcs/WWW/HTML/publications/papers/TR-11-4.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W100082076","https://openalex.org/W1570477871","https://openalex.org/W1967344300","https://openalex.org/W1993892970","https://openalex.org/W2005112390","https://openalex.org/W2018745370","https://openalex.org/W2058178853","https://openalex.org/W2100542992","https://openalex.org/W2109626831","https://openalex.org/W2110086534","https://openalex.org/W2113640782","https://openalex.org/W2114303224","https://openalex.org/W2114474644","https://openalex.org/W2119528150","https://openalex.org/W2125775320","https://openalex.org/W2130642985","https://openalex.org/W2138512691","https://openalex.org/W2142031898","https://openalex.org/W2157979971","https://openalex.org/W2171543585","https://openalex.org/W2173213060","https://openalex.org/W2624304035","https://openalex.org/W2753710282","https://openalex.org/W3138367763","https://openalex.org/W3149201378","https://openalex.org/W4244180879","https://openalex.org/W6634065580","https://openalex.org/W6638231387","https://openalex.org/W6655396424","https://openalex.org/W6679817081","https://openalex.org/W6680293019","https://openalex.org/W6738874634","https://openalex.org/W7018146823"],"related_works":["https://openalex.org/W2000785801","https://openalex.org/W986318368","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W4390608645","https://openalex.org/W2004734601","https://openalex.org/W2130149817","https://openalex.org/W2990194547","https://openalex.org/W1480123525","https://openalex.org/W2620865396"],"abstract_inverted_index":{"MapReduce-based":[0],"data":[1,11,41,75,80,107,123,137,149,184,205],"warehouse":[2,52,185],"systems":[3,207],"are":[4,131],"playing":[5],"important":[6],"roles":[7],"of":[8,18,64,121,171],"supporting":[9],"big":[10,136,148],"analytics":[12],"to":[13,96],"understand":[14],"quickly":[15],"the":[16,40,51,74,119,161,169,175,188,200],"dynamics":[17],"user":[19],"behavior":[20],"trends":[21],"and":[22,30,62,92,116,157,198,211],"their":[23],"needs":[24],"in":[25,54,110,118,139,160,173,182,209],"typical":[26],"Web":[27],"service":[28],"providers":[29],"social":[31],"network":[32],"sites":[33],"(e.g.,":[34],"Facebook).":[35],"In":[36,142],"such":[37],"a":[38,45,55,147],"system,":[39],"placement":[42,76,108,150],"structure":[43,151],"is":[44],"critical":[46],"factor":[47],"that":[48,129],"can":[49],"affect":[50],"performance":[53],"fundamental":[56],"way.":[57],"Based":[58],"on":[59],"our":[60],"observations":[61],"analysis":[63,124,206],"Facebook":[65,183,210],"production":[66],"systems,":[67],"we":[68,145,167],"have":[69,102],"characterized":[70],"four":[71,176],"requirements":[72],"for":[73,135],"structure:":[77],"(1)":[78],"fast":[79,83],"loading,":[81],"(2)":[82],"query":[84],"processing,":[85],"(3)":[86],"highly":[87,97],"efficient":[88],"storage":[89],"space":[90],"utilization,":[91],"(4)":[93],"strong":[94],"adaptivity":[95],"dynamic":[98],"workload":[99],"patterns.":[100],"We":[101,127],"examined":[103],"three":[104],"commonly":[105],"accepted":[106],"structures":[109],"conventional":[111],"databases,":[112],"namely":[113],"row-stores,":[114],"column-stores,":[115],"hybrid-stores":[117],"context":[120],"large":[122],"using":[125],"MapReduce.":[126],"show":[128,168],"they":[130],"not":[132],"very":[133],"suitable":[134],"processing":[138],"distributed":[140],"systems.":[141],"this":[143],"paper,":[144],"present":[146],"called":[152],"RCFile":[153,172,178],"(Record":[154],"Columnar":[155],"File)":[156],"its":[158],"implementation":[159],"Hadoop":[162],"system.":[163],"With":[164],"intensive":[165],"experiments,":[166],"effectiveness":[170],"satisfying":[174],"requirements.":[177],"has":[179,192],"been":[180,194],"chosen":[181],"system":[186],"as":[187],"default":[189],"option.":[190],"It":[191],"also":[193],"adopted":[195],"by":[196],"Hive":[197],"Pig,":[199],"two":[201],"most":[202],"widely":[203],"used":[204],"developed":[208],"Yahoo!":[212]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":19},{"year":2016,"cited_by_count":35},{"year":2015,"cited_by_count":31},{"year":2014,"cited_by_count":43},{"year":2013,"cited_by_count":30},{"year":2012,"cited_by_count":23}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}