{"id":"https://openalex.org/W2010279913","doi":"https://doi.org/10.14778/1920841.1920903","title":"The performance of MapReduce","display_name":"The performance of MapReduce","publication_year":2010,"publication_date":"2010-09-01","ids":{"openalex":"https://openalex.org/W2010279913","doi":"https://doi.org/10.14778/1920841.1920903","mag":"2010279913"},"language":"en","primary_location":{"id":"doi:10.14778/1920841.1920903","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1920841.1920903","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/A5077156448","display_name":"Dawei Jiang","orcid":"https://orcid.org/0000-0002-1890-4046"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Dawei Jiang","raw_affiliation_strings":["National University of Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024892041","display_name":"Beng Chin Ooi","orcid":"https://orcid.org/0000-0003-4446-1100"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Beng Chin Ooi","raw_affiliation_strings":["National University of Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072249624","display_name":"Lei Shi","orcid":"https://orcid.org/0000-0002-1170-3911"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lei Shi","raw_affiliation_strings":["National University of Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064646829","display_name":"Sai Wu","orcid":"https://orcid.org/0000-0002-1866-9197"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Sai Wu","raw_affiliation_strings":["National University of Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077156448"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":97.9511,"has_fulltext":false,"cited_by_count":393,"citation_normalized_percentile":{"value":0.99943028,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"3","issue":"1-2","first_page":"472","last_page":"483"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9864000082015991,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9837999939918518,"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":0.8830752968788147},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8413645029067993},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.7393966913223267},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7204504609107971},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6137168407440186},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.5852347016334534},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5404819250106812},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.532170832157135},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5300031900405884},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5090562701225281},{"id":"https://openalex.org/keywords/data-intensive-computing","display_name":"Data-intensive computing","score":0.4853281080722809},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.44825974106788635},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.42610400915145874},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.40990251302719116},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24585816264152527},{"id":"https://openalex.org/keywords/grid-computing","display_name":"Grid computing","score":0.0766567587852478}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8830752968788147},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8413645029067993},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7393966913223267},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7204504609107971},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6137168407440186},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.5852347016334534},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5404819250106812},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.532170832157135},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5300031900405884},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5090562701225281},{"id":"https://openalex.org/C76831024","wikidata":"https://www.wikidata.org/wiki/Q5227096","display_name":"Data-intensive computing","level":4,"score":0.4853281080722809},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.44825974106788635},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42610400915145874},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.40990251302719116},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24585816264152527},{"id":"https://openalex.org/C70429105","wikidata":"https://www.wikidata.org/wiki/Q249999","display_name":"Grid computing","level":3,"score":0.0766567587852478},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/1920841.1920903","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1920841.1920903","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":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1861377444","https://openalex.org/W2044490410","https://openalex.org/W2098935637","https://openalex.org/W2109626831","https://openalex.org/W2110086534","https://openalex.org/W2114303224","https://openalex.org/W2119400430","https://openalex.org/W2122950698","https://openalex.org/W2125775320","https://openalex.org/W2138512691","https://openalex.org/W2154894831","https://openalex.org/W2157355837","https://openalex.org/W2171668176","https://openalex.org/W2173213060"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W4233347783","https://openalex.org/W2910064364","https://openalex.org/W4255224757","https://openalex.org/W2794953737"],"abstract_inverted_index":{"MapReduce":[0,73,122,139],"has":[1,28],"been":[2,29],"widely":[3],"used":[4,200],"for":[5,17,170,196],"large-scale":[6],"data":[7,113,226],"analysis":[8],"in":[9,34,59,103,120,201],"the":[10,35,79,86,160,181,197],"Cloud.":[11],"The":[12],"system":[13,228],"is":[14,51,99,204,219,230],"well":[15],"recognized":[16],"its":[18,26],"elastic":[19,126],"scalability":[20,127],"and":[21,116,128,164,203,234],"fine-grained":[22],"fault":[23],"tolerance":[24],"although":[25],"performance":[27,77,136,161,183],"noted":[30],"to":[31,39,71,88,194,208,222],"be":[32,187],"suboptimal":[33],"database":[36,57,212],"context.":[37],"According":[38],"a":[40,61,67,104,135,142,190,224],"recent":[41],"study":[42,137],"[19],":[43,202],"Hadoop,":[44,163],"an":[45,109],"open":[46],"source":[47],"implementation":[48],"of":[49,63,69,81,95,138,145,151,162,184,192,210],"MapReduce,":[50],"slower":[52],"than":[53],"two":[54],"state-of-the-art":[55],"parallel":[56,211],"systems":[58],"performing":[60],"variety":[62],"analytical":[64],"tasks":[65],"by":[66,176,189],"factor":[68,191],"3.1":[70],"6.5.":[72],"can":[74,123,186],"achieve":[75],"better":[76],"with":[78,148],"allocation":[80],"more":[82,97,206],"compute":[83],"nodes":[84],"from":[85],"cloud":[87,225],"speed":[89],"up":[90],"computation;":[91],"however,":[92],"this":[93,131],"approach":[94],"\"renting":[96],"nodes\"":[98],"not":[100],"cost":[101],"effective":[102],"pay-as-you-go":[105],"environment.":[106],"Users":[107],"desire":[108],"economical":[110],"elastically":[111,232],"scalable":[112,233],"processing":[114,227],"system,":[115],"therefore,":[117],"are":[118],"interested":[119],"whether":[121],"offer":[124],"both":[125,231],"efficiency.":[129],"In":[130],"paper,":[132],"we":[133],"conduct":[134],"(Hadoop)":[140],"on":[141],"100-node":[143],"cluster":[144],"Amazon":[146],"EC2":[147],"various":[149],"levels":[150],"parallelism.":[152],"We":[153,173],"identify":[154],"five":[155],"design":[156],"factors":[157],"that":[158,175,209,217,229],"affect":[159],"investigate":[165],"alternative":[166],"but":[167],"known":[168],"methods":[169],"each":[171],"factor.":[172],"show":[174,216],"carefully":[177],"tuning":[178],"these":[179],"factors,":[180],"overall":[182],"Hadoop":[185],"improved":[188],"2.5":[193],"3.5":[195],"same":[198],"benchmark":[199],"thus":[205],"comparable":[207],"systems.":[213],"Our":[214],"results":[215],"it":[218],"therefore":[220],"possible":[221],"build":[223],"efficient.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":21},{"year":2017,"cited_by_count":28},{"year":2016,"cited_by_count":35},{"year":2015,"cited_by_count":57},{"year":2014,"cited_by_count":61},{"year":2013,"cited_by_count":57},{"year":2012,"cited_by_count":47}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
