{"id":"https://openalex.org/W2114854276","doi":"https://doi.org/10.14778/1988776.1988778","title":"Column-oriented storage techniques for MapReduce","display_name":"Column-oriented storage techniques for MapReduce","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2114854276","doi":"https://doi.org/10.14778/1988776.1988778","mag":"2114854276"},"language":"en","primary_location":{"id":"doi:10.14778/1988776.1988778","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1988776.1988778","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5020678151","display_name":"Avrilia Floratou","orcid":"https://orcid.org/0009-0007-5760-8657"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Avrilia Floratou","raw_affiliation_strings":["University of Wisconsin--Madison","University of Wisconsin, Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin--Madison","institution_ids":["https://openalex.org/I135310074"]},{"raw_affiliation_string":"University of Wisconsin, Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069237428","display_name":"Jignesh M. Patel","orcid":"https://orcid.org/0000-0003-3653-2538"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jignesh M. Patel","raw_affiliation_strings":["University of Wisconsin--Madison","University of Wisconsin, Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin--Madison","institution_ids":["https://openalex.org/I135310074"]},{"raw_affiliation_string":"University of Wisconsin, Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047853212","display_name":"Eugene J. Shekita","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene J. Shekita","raw_affiliation_strings":["IBM Almaden, Research Center","IBM Almaden Research Center,#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Almaden, Research Center","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Center,#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102945075","display_name":"Sandeep Tata","orcid":"https://orcid.org/0009-0007-7785-5516"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sandeep Tata","raw_affiliation_strings":["IBM Almaden, Research Center","IBM Almaden Research Center,#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Almaden, Research Center","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Center,#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":38.7032,"has_fulltext":false,"cited_by_count":127,"citation_normalized_percentile":{"value":0.99708674,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"4","issue":"7","first_page":"419","last_page":"429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9973999857902527,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8837732076644897},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.8017951250076294},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6162919402122498},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5510514378547668},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4595147669315338},{"id":"https://openalex.org/keywords/column-generation","display_name":"Column generation","score":0.41716066002845764},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.40080526471138},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3949388563632965},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.34750059247016907},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12096908688545227}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8837732076644897},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.8017951250076294},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6162919402122498},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5510514378547668},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4595147669315338},{"id":"https://openalex.org/C168956720","wikidata":"https://www.wikidata.org/wiki/Q3123181","display_name":"Column generation","level":2,"score":0.41716066002845764},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40080526471138},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3949388563632965},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.34750059247016907},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12096908688545227},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/1988776.1988778","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1988776.1988778","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W199215620","https://openalex.org/W1582870960","https://openalex.org/W1967344300","https://openalex.org/W2005112390","https://openalex.org/W2010279913","https://openalex.org/W2035543557","https://openalex.org/W2037874195","https://openalex.org/W2070991879","https://openalex.org/W2074935284","https://openalex.org/W2098935637","https://openalex.org/W2114303224","https://openalex.org/W2123686039","https://openalex.org/W2124851765","https://openalex.org/W2125775320","https://openalex.org/W2130642985","https://openalex.org/W2144839430","https://openalex.org/W2153889808","https://openalex.org/W2156930555","https://openalex.org/W2157355837","https://openalex.org/W2167631575","https://openalex.org/W2172220707","https://openalex.org/W2173213060","https://openalex.org/W2269500048"],"related_works":["https://openalex.org/W2060052838","https://openalex.org/W2692124420","https://openalex.org/W1508800643","https://openalex.org/W1998976244","https://openalex.org/W1998257941","https://openalex.org/W2569002095","https://openalex.org/W2053213682","https://openalex.org/W2464562236","https://openalex.org/W1488119866","https://openalex.org/W2149779860"],"abstract_inverted_index":{"Users":[0],"of":[1,15,31,98,117,134,208,220],"MapReduce":[2,126,156],"often":[3],"run":[4],"into":[5],"performance":[6,92,187,207],"problems":[7,17],"when":[8],"they":[9,18],"scale":[10],"up":[11,125],"their":[12],"workloads.":[13],"Many":[14],"the":[16,95,112,206,209],"encounter":[19],"can":[20,51,64,88,123,158,204],"be":[21,65],"overcome":[22],"by":[23,131,214],"applying":[24],"techniques":[25,39,63,203],"learned":[26],"from":[27],"over":[28,94],"three":[29],"decades":[30],"research":[32],"on":[33,128,190],"parallel":[34],"DBMSs.":[35],"However,":[36],"translating":[37],"these":[38],"to":[40,53,182,197],"a":[41,70,90,104,166,191],"Map-Reduce":[42],"implementation":[43],"such":[44,145],"as":[45,146,215,217],"Hadoop":[46,68,87,118,213],"presents":[47],"unique":[48],"challenges":[49],"that":[50,72,80,108,121,139,177,199],"lead":[52],"new":[54],"design":[55],"choices.":[56],"This":[57],"paper":[58],"describes":[59],"how":[60],"column-oriented":[61,105,201],"storage":[62,84,106,202],"incorporated":[66],"in":[67,69,86,155,212],"way":[71],"preserves":[73],"its":[74],"popular":[75],"programming":[76],"APIs.":[77],"We":[78,101,136],"show":[79,120,138,198],"simply":[81],"using":[82],"binary":[83],"formats":[85],"provide":[89,183],"3x":[91],"boost":[93],"naive":[96],"use":[97],"text":[99],"files.":[100],"then":[102],"introduce":[103,165],"format":[107,171],"is":[109],"compatible":[110],"with":[111,141],"replication":[113],"and":[114,119,149,172],"scheduling":[115],"constraints":[116],"it":[122],"speed":[124],"jobs":[127],"real":[129,192],"workloads":[130],"an":[132,184],"order":[133],"magnitude.":[135,221],"also":[137],"dealing":[140],"complex":[142],"column":[143,170],"types":[144],"arrays,":[147],"maps,":[148],"nested":[150],"records,":[151],"which":[152],"are":[153,195],"common":[154],"jobs,":[157],"incur":[159],"significant":[160],"CPU":[161],"overhead.":[162],"Finally,":[163],"we":[164],"novel":[167],"skip":[168],"list":[169],"lazy":[173],"record":[174],"construction":[175],"strategy":[176],"avoids":[178],"deserializing":[179],"unwanted":[180],"records":[181],"additional":[185],"1.5x":[186],"boost.":[188],"Experiments":[189],"intranet":[193],"crawl":[194],"used":[196],"our":[200],"improve":[205],"map":[210],"phase":[211],"much":[216],"two":[218],"orders":[219]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":23},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":22},{"year":2012,"cited_by_count":17}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}