{"id":"https://openalex.org/W2095977162","doi":"https://doi.org/10.1109/ccgrid.2012.42","title":"Investigation of Data Locality in MapReduce","display_name":"Investigation of Data Locality in MapReduce","publication_year":2012,"publication_date":"2012-05-01","ids":{"openalex":"https://openalex.org/W2095977162","doi":"https://doi.org/10.1109/ccgrid.2012.42","mag":"2095977162"},"language":"en","primary_location":{"id":"doi:10.1109/ccgrid.2012.42","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccgrid.2012.42","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (ccgrid 2012)","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/A5091834117","display_name":"Zhenhua Guo","orcid":"https://orcid.org/0000-0002-8201-0864"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhenhua Guo","raw_affiliation_strings":["School of Informatics and Computing, Indiana University Bloomington, Bloomington, IN, USA","Sch. of Inf. & Comput., Indiana Univ. - Bloomington, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"School of Informatics and Computing, Indiana University Bloomington, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Sch. of Inf. & Comput., Indiana Univ. - Bloomington, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108016089","display_name":"Geoffrey Fox","orcid":"https://orcid.org/0000-0001-8198-4117"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Geoffrey Fox","raw_affiliation_strings":["School of Informatics and Computing, Indiana University Bloomington, Bloomington, IN, USA","Sch. of Inf. & Comput., Indiana Univ. - Bloomington, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"School of Informatics and Computing, Indiana University Bloomington, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Sch. of Inf. & Comput., Indiana Univ. - Bloomington, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101756305","display_name":"Mo Zhou","orcid":"https://orcid.org/0000-0003-3813-4875"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mo Zhou","raw_affiliation_strings":["School of Informatics and Computing, Indiana University Bloomington, Bloomington, IN, USA","Sch. of Inf. & Comput., Indiana Univ. - Bloomington, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"School of Informatics and Computing, Indiana University Bloomington, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Sch. of Inf. & Comput., Indiana Univ. - Bloomington, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091834117"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":36.6983,"has_fulltext":false,"cited_by_count":144,"citation_normalized_percentile":{"value":0.99695784,"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":"419","last_page":"426"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9994999766349792,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.996999979019165,"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/locality","display_name":"Locality","score":0.9350773692131042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8707473874092102},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5502833724021912},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.522713303565979},{"id":"https://openalex.org/keywords/locality-of-reference","display_name":"Locality of reference","score":0.5216629505157471},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.48794931173324585},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.43577560782432556},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12867280840873718},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.11211410164833069}],"concepts":[{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.9350773692131042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8707473874092102},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5502833724021912},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.522713303565979},{"id":"https://openalex.org/C27602214","wikidata":"https://www.wikidata.org/wiki/Q1868547","display_name":"Locality of reference","level":3,"score":0.5216629505157471},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.48794931173324585},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.43577560782432556},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12867280840873718},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.11211410164833069},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ccgrid.2012.42","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccgrid.2012.42","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (ccgrid 2012)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.300.7824","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.300.7824","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://grids.ucs.indiana.edu/ptliupages/publications/InvestigationDataLocalityInMapReduce_CCGrid12_Submitted.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.5299999713897705,"display_name":"Decent work and economic growth"}],"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":18,"referenced_works":["https://openalex.org/W1861377444","https://openalex.org/W2024077218","https://openalex.org/W2072129576","https://openalex.org/W2096125134","https://openalex.org/W2100830825","https://openalex.org/W2102894742","https://openalex.org/W2104549760","https://openalex.org/W2118436132","https://openalex.org/W2119565742","https://openalex.org/W2119738171","https://openalex.org/W2133964524","https://openalex.org/W2138595852","https://openalex.org/W2147865600","https://openalex.org/W3145719002","https://openalex.org/W3149826745","https://openalex.org/W4239670432","https://openalex.org/W6639193275","https://openalex.org/W6681939064"],"related_works":["https://openalex.org/W1555349535","https://openalex.org/W2583128298","https://openalex.org/W2053359564","https://openalex.org/W2161159383","https://openalex.org/W1495260638","https://openalex.org/W1511204342","https://openalex.org/W2369125128","https://openalex.org/W2369223577","https://openalex.org/W2010020348","https://openalex.org/W2085845213"],"abstract_inverted_index":{"Traditional":[0],"HPC":[1,89],"architectures":[2],"separate":[3],"compute":[4,42,74],"nodes":[5,141],"and":[6,57,66,125,142,153,192,204],"storage":[7],"nodes,":[8],"which":[9,68],"are":[10,52],"interconnected":[11],"with":[12,54],"high":[13,29],"speed":[14,30],"links":[15,31],"to":[16,72,75,167,177],"satisfy":[17],"data":[18,84,92,111,131,170,190,195],"access":[19],"requirements":[20],"in":[21,103,113,123,201],"multi-user":[22],"environments.":[23,206],"However,":[24],"the":[25,37,61,101,128,138,147],"capacity":[26],"of":[27,40,63,83,100,121,133,140,181],"those":[28],"is":[32,79,151],"still":[33],"much":[34],"less":[35],"than":[36,163],"aggregate":[38],"bandwidth":[39],"all":[41],"nodes.":[43],"In":[44,106],"Data":[45,77],"Parallel":[46],"Systems":[47],"such":[48,136],"as":[49,137],"GFS/MapReduce,":[50],"clusters":[51],"built":[53],"commodity":[55],"hardware":[56],"each":[58],"node":[59],"takes":[60],"roles":[62],"both":[64,202],"computation":[65],"storage,":[67],"makes":[69],"it":[70],"possible":[71],"bring":[73],"data.":[76],"locality":[78,93,112,132,196],"a":[80,118],"significant":[81],"advantage":[82],"parallel":[85],"systems":[86],"over":[87],"traditional":[88],"systems.":[90],"Good":[91],"reduces":[94],"cross-switch":[95],"network":[96],"traffic":[97],"-":[98],"one":[99,164,166],"bottlenecks":[102],"data-intensive":[104],"computing.":[105],"this":[107],"paper,":[108],"we":[109,116,145,173],"investigate":[110,193],"depth.":[114],"Firstly,":[115],"build":[117],"mathematical":[119],"model":[120],"scheduling":[122,150],"MapReduce":[124],"theoretically":[126],"analyze":[127],"impact":[129,189],"on":[130],"configuration":[134],"factors,":[135],"numbers":[139],"tasks.":[143],"Secondly,":[144],"find":[146],"default":[148],"Hadoop":[149],"non-optimal":[152],"propose":[154],"an":[155],"algorithm":[156],"that":[157],"schedules":[158],"multiple":[159],"tasks":[160],"simultaneously":[161],"rather":[162],"by":[165],"give":[168],"optimal":[169],"locality.":[171],"Thirdly,":[172],"run":[174],"extensive":[175],"experiments":[176],"quantify":[178],"performance":[179],"improvement":[180],"our":[182],"proposed":[183],"algorithms,":[184],"measure":[185],"how":[186,194],"different":[187],"factors":[188],"locality,":[191],"influences":[197],"job":[198],"execution":[199],"time":[200],"single-cluster":[203],"cross-cluster":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":24},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
