{"id":"https://openalex.org/W1996438407","doi":"https://doi.org/10.1109/ipdpsw.2010.5470880","title":"Improving MapReduce performance through data placement in heterogeneous Hadoop clusters","display_name":"Improving MapReduce performance through data placement in heterogeneous Hadoop clusters","publication_year":2010,"publication_date":"2010-04-01","ids":{"openalex":"https://openalex.org/W1996438407","doi":"https://doi.org/10.1109/ipdpsw.2010.5470880","mag":"1996438407"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw.2010.5470880","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2010.5470880","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel &amp; Distributed Processing, Workshops and Phd Forum (IPDPSW)","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/A5001745856","display_name":"Jiong Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiong Xie","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Aubum University, Auburn, AL, USA","Department of Computer Science and Software Engineering, Auburn University, AL 36849-5347, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Aubum University, Auburn, AL, USA","institution_ids":["https://openalex.org/I82497590"]},{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Auburn University, AL 36849-5347, USA","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047865361","display_name":"Shu Yin","orcid":"https://orcid.org/0000-0001-6500-1790"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shu Yin","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Aubum University, Auburn, AL, USA","Department of Computer Science and Software Engineering, Auburn University, AL 36849-5347, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Aubum University, Auburn, AL, USA","institution_ids":["https://openalex.org/I82497590"]},{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Auburn University, AL 36849-5347, USA","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101639518","display_name":"Xiaojun Ruan","orcid":"https://orcid.org/0000-0002-9359-5319"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaojun Ruan","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Aubum University, Auburn, AL, USA","Department of Computer Science and Software Engineering, Auburn University, AL 36849-5347, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Aubum University, Auburn, AL, USA","institution_ids":["https://openalex.org/I82497590"]},{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Auburn University, AL 36849-5347, USA","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109114201","display_name":"Zhiyang Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyang Ding","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Aubum University, Auburn, AL, USA","Department of Computer Science and Software Engineering, Auburn University, AL 36849-5347, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Aubum University, Auburn, AL, USA","institution_ids":["https://openalex.org/I82497590"]},{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Auburn University, AL 36849-5347, USA","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002734812","display_name":"Yun Tian","orcid":"https://orcid.org/0000-0001-5574-2325"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Tian","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Aubum University, Auburn, AL, USA","Department of Computer Science and Software Engineering, Auburn University, AL 36849-5347, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Aubum University, Auburn, AL, USA","institution_ids":["https://openalex.org/I82497590"]},{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Auburn University, AL 36849-5347, USA","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003511661","display_name":"James Majors","orcid":null},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Majors","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Aubum University, Auburn, AL, USA","Department of Computer Science and Software Engineering, Auburn University, AL 36849-5347, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Aubum University, Auburn, AL, USA","institution_ids":["https://openalex.org/I82497590"]},{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Auburn University, AL 36849-5347, USA","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008823812","display_name":"Adam Manzanares","orcid":null},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Manzanares","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Aubum University, Auburn, AL, USA","Department of Computer Science and Software Engineering, Auburn University, AL 36849-5347, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Aubum University, Auburn, AL, USA","institution_ids":["https://openalex.org/I82497590"]},{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Auburn University, AL 36849-5347, USA","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042766429","display_name":"Xiao Qin","orcid":"https://orcid.org/0000-0002-8345-3587"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Qin","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Aubum University, Auburn, AL, USA","Department of Computer Science and Software Engineering, Auburn University, AL 36849-5347, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Aubum University, Auburn, AL, USA","institution_ids":["https://openalex.org/I82497590"]},{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Auburn University, AL 36849-5347, USA","institution_ids":["https://openalex.org/I82497590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5001745856"],"corresponding_institution_ids":["https://openalex.org/I82497590"],"apc_list":null,"apc_paid":null,"fwci":58.9649,"has_fulltext":false,"cited_by_count":381,"citation_normalized_percentile":{"value":0.99851479,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.998199999332428,"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/T11478","display_name":"Caching and Content Delivery","score":0.9976000189781189,"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":0.8826704621315002},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.7803288698196411},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6733013987541199},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5597801208496094},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4968574345111847},{"id":"https://openalex.org/keywords/map-reduce","display_name":"Map reduce","score":0.4890812039375305},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.47420361638069153},{"id":"https://openalex.org/keywords/data-intensive-computing","display_name":"Data-intensive computing","score":0.466764897108078},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.46212929487228394},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.43370530009269714},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.4155381917953491},{"id":"https://openalex.org/keywords/data-processing","display_name":"Data processing","score":0.4103408753871918},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.346943736076355},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.27609848976135254},{"id":"https://openalex.org/keywords/grid-computing","display_name":"Grid computing","score":0.21088579297065735},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.1596144735813141}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8826704621315002},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.7803288698196411},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6733013987541199},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5597801208496094},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4968574345111847},{"id":"https://openalex.org/C3019257732","wikidata":"https://www.wikidata.org/wiki/Q567759","display_name":"Map reduce","level":3,"score":0.4890812039375305},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.47420361638069153},{"id":"https://openalex.org/C76831024","wikidata":"https://www.wikidata.org/wiki/Q5227096","display_name":"Data-intensive computing","level":4,"score":0.466764897108078},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.46212929487228394},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.43370530009269714},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.4155381917953491},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.4103408753871918},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.346943736076355},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27609848976135254},{"id":"https://openalex.org/C70429105","wikidata":"https://www.wikidata.org/wiki/Q249999","display_name":"Grid computing","level":3,"score":0.21088579297065735},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.1596144735813141},{"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdpsw.2010.5470880","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2010.5470880","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel &amp; Distributed Processing, Workshops and Phd Forum (IPDPSW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W78579758","https://openalex.org/W1861377444","https://openalex.org/W1965072957","https://openalex.org/W2037072488","https://openalex.org/W2098935637","https://openalex.org/W2100830825","https://openalex.org/W2103886725","https://openalex.org/W2104644701","https://openalex.org/W2119565742","https://openalex.org/W2119714163","https://openalex.org/W2129817042","https://openalex.org/W2154894831","https://openalex.org/W2173213060","https://openalex.org/W6639193275"],"related_works":["https://openalex.org/W2166218570","https://openalex.org/W2487182083","https://openalex.org/W2887618286","https://openalex.org/W2551950821","https://openalex.org/W3175672129","https://openalex.org/W2547045534","https://openalex.org/W4214810013","https://openalex.org/W2775840505","https://openalex.org/W2751662694","https://openalex.org/W2626058569"],"abstract_inverted_index":{"MapReduce":[0,22,99,135,173],"has":[1,50,121],"become":[2],"an":[3],"important":[4],"distributed":[5],"processing":[6,125],"model":[7],"for":[8,26,56],"large-scale":[9],"data-intensive":[10,161,183],"applications":[11,162],"like":[12],"data":[13,75,83,112,124,138,146,166,177],"mining":[14],"and":[15,74],"web":[16],"indexing.":[17],"Hadoop-an":[18],"open-source":[19],"implementation":[20,36],"of":[21,108,145],"is":[23,63],"widely":[24],"used":[25],"short":[27],"jobs":[28],"requiring":[29],"low":[30],"response":[31],"time.":[32],"The":[33],"current":[34],"Hadoop":[35,134,188],"assumes":[37],"that":[38,65,87,118,164],"computing":[39],"nodes":[40,114,179],"in":[41,46,81,92,115,148,185],"a":[42,116,122,128,133,182,186],"cluster":[43],"are":[44,68,78],"homogeneous":[45],"nature.":[47],"Data":[48],"locality":[49,76],"not":[51,79],"been":[52],"taken":[53],"into":[54],"account":[55],"launching":[57],"speculative":[58],"map":[59],"tasks,":[60],"because":[61],"it":[62],"assumed":[64],"most":[66],"maps":[67],"data-local.":[69],"Unfortunately,":[70],"both":[71],"the":[72,89,98,106,143,172],"homogeneity":[73],"assumptions":[77],"satisfied":[80],"virtualized":[82],"centers.":[84],"We":[85],"show":[86,163],"ignoring":[88],"data-locality":[90],"issue":[91],"heterogeneous":[93,187],"environments":[94],"can":[95,169],"noticeably":[96],"reduce":[97],"performance.":[100,155],"In":[101],"this":[102],"paper,":[103],"we":[104],"address":[105],"problem":[107],"how":[109],"to":[110,151],"place":[111],"across":[113,178],"way":[117],"each":[119,149],"node":[120,150],"balanced":[123],"load.":[126],"Given":[127],"dataintensive":[129],"application":[130,184],"running":[131],"on":[132,158],"cluster,":[136],"our":[137,165],"placement":[139,167],"scheme":[140],"adaptively":[141],"balances":[142],"amount":[144],"stored":[147],"achieve":[152],"improved":[153],"data-processing":[154],"Experimental":[156],"results":[157],"two":[159],"real":[160],"strategy":[168],"always":[170],"improve":[171],"performance":[174],"by":[175],"rebalancing":[176],"before":[180],"performing":[181],"cluster.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":27},{"year":2018,"cited_by_count":34},{"year":2017,"cited_by_count":35},{"year":2016,"cited_by_count":51},{"year":2015,"cited_by_count":54},{"year":2014,"cited_by_count":51},{"year":2013,"cited_by_count":37},{"year":2012,"cited_by_count":33}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
