{"id":"https://openalex.org/W2005819813","doi":"https://doi.org/10.1109/iscc.2012.6249372","title":"A data locality optimization algorithm for large-scale data processing in Hadoop","display_name":"A data locality optimization algorithm for large-scale data processing in Hadoop","publication_year":2012,"publication_date":"2012-07-01","ids":{"openalex":"https://openalex.org/W2005819813","doi":"https://doi.org/10.1109/iscc.2012.6249372","mag":"2005819813"},"language":"en","primary_location":{"id":"doi:10.1109/iscc.2012.6249372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscc.2012.6249372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Symposium on Computers and Communications (ISCC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102205455","display_name":"Yanrong Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":"Yanrong Zhao","raw_affiliation_strings":["Institute of Computing Technology Chinese Academy of Sciences, Chinese Academy of Sciences, Graduate University, BeiJing, China","Institute of Computing Technology Chinese Academy of Sciences, Graduate University, Chinese Academy of Sciences, BeiJing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences, Chinese Academy of Sciences, Graduate University, BeiJing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences, Graduate University, Chinese Academy of Sciences, BeiJing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442321","display_name":"Weiping Wang","orcid":"https://orcid.org/0000-0002-8618-4992"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":"Weiping Wang","raw_affiliation_strings":["Institute of Computing Technology Chinese Academy of Sciences, Chinese Academy of Sciences, Graduate University, BeiJing, China","Institute of Computing Technology Chinese Academy of Sciences, Graduate University, Chinese Academy of Sciences, BeiJing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences, Chinese Academy of Sciences, Graduate University, BeiJing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences, Graduate University, Chinese Academy of Sciences, BeiJing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101525317","display_name":"Dan Meng","orcid":"https://orcid.org/0000-0002-0872-3540"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":"Dan Meng","raw_affiliation_strings":["Institute of Computing Technology Chinese Academy of Sciences, Chinese Academy of Sciences, Graduate University, BeiJing, China","Institute of Computing Technology Chinese Academy of Sciences, Graduate University, Chinese Academy of Sciences, BeiJing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences, Chinese Academy of Sciences, Graduate University, BeiJing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences, Graduate University, Chinese Academy of Sciences, BeiJing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004051887","display_name":"Xiufeng Yang","orcid":"https://orcid.org/0000-0002-1698-4636"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":"Xiufeng Yang","raw_affiliation_strings":["Institute of Computing Technology Chinese Academy of Sciences, Chinese Academy of Sciences, Graduate University, BeiJing, China","Institute of Computing Technology Chinese Academy of Sciences, Graduate University, Chinese Academy of Sciences, BeiJing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences, Chinese Academy of Sciences, Graduate University, BeiJing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences, Graduate University, Chinese Academy of Sciences, BeiJing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075283916","display_name":"Shubin Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shubin Zhang","raw_affiliation_strings":["Data Platform Department, Tencent, ShenZhen, China","[Data Platform Department Tencent, ShenZhen, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Platform Department, Tencent, ShenZhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"[Data Platform Department Tencent, ShenZhen, China]","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361690","display_name":"Jun Li","orcid":"https://orcid.org/0000-0001-8266-7463"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Li","raw_affiliation_strings":["Data Platform Department, Tencent, ShenZhen, China","[Data Platform Department Tencent, ShenZhen, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Platform Department, Tencent, ShenZhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"[Data Platform Department Tencent, ShenZhen, China]","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102373089","display_name":"Gang Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Guan","raw_affiliation_strings":["Data Platform Department, Tencent, ShenZhen, China","[Data Platform Department Tencent, ShenZhen, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Platform Department, Tencent, ShenZhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"[Data Platform Department Tencent, ShenZhen, China]","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2376,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.47104478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"000655","last_page":"000661"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9997000098228455,"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":0.9997000098228455,"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/T11106","display_name":"Data Management and Algorithms","score":0.9944000244140625,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9925000071525574,"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":0.8717839121818542},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.7247257232666016},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6066836714744568},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.5446020364761353},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4586155414581299},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.4582594335079193},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.43670251965522766},{"id":"https://openalex.org/keywords/data-processing","display_name":"Data processing","score":0.42324405908584595},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.393563449382782},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.34860119223594666},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33913904428482056},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.08497986197471619}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8717839121818542},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.7247257232666016},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6066836714744568},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.5446020364761353},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4586155414581299},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.4582594335079193},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.43670251965522766},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.42324405908584595},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.393563449382782},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34860119223594666},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33913904428482056},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.08497986197471619},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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":1,"locations":[{"id":"doi:10.1109/iscc.2012.6249372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscc.2012.6249372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Symposium on Computers and Communications (ISCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Industry, innovation and infrastructure","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/W1493893823","https://openalex.org/W1494822125","https://openalex.org/W1570477871","https://openalex.org/W1598064945","https://openalex.org/W1645807896","https://openalex.org/W1997020216","https://openalex.org/W2020765652","https://openalex.org/W2078528123","https://openalex.org/W2096125134","https://openalex.org/W2098935637","https://openalex.org/W2100830825","https://openalex.org/W2110086534","https://openalex.org/W2119400430","https://openalex.org/W2122465391","https://openalex.org/W2137077706","https://openalex.org/W2153704625","https://openalex.org/W2154894831","https://openalex.org/W3215028506","https://openalex.org/W6629380029","https://openalex.org/W6629681917","https://openalex.org/W6634065580","https://openalex.org/W6637090028","https://openalex.org/W6680344385"],"related_works":["https://openalex.org/W3214148052","https://openalex.org/W2151692181","https://openalex.org/W794462722","https://openalex.org/W2029625042","https://openalex.org/W4248476017","https://openalex.org/W2807741550","https://openalex.org/W2970426051","https://openalex.org/W1525319740","https://openalex.org/W4247864646","https://openalex.org/W1484210779"],"abstract_inverted_index":{"Data-intensive":[0],"applications":[1],"are":[2],"increasingly":[3],"designed":[4],"to":[5,86,92],"execute":[6],"on":[7,14,39],"large":[8,59],"computing":[9],"clusters.":[10],"Our":[11,128],"previous":[12],"observation":[13],"Tencent":[15,116],"production":[16],"systems":[17],"has":[18,112],"indicated":[19],"that":[20],"join":[21,37,46],"query":[22,38,47],"is":[23,48,68,85],"one":[24],"of":[25,44,61,82,89,136],"the":[26,42,45,65,79,83,132],"most":[27],"important":[28,122],"queries":[29],"in":[30,115,124],"large-scale":[31],"data":[32,90,117],"processing.":[33],"When":[34],"running":[35],"a":[36],"Hive":[40],"system,":[41],"job":[43],"divided":[49],"into":[50],"map":[51],"phase":[52],"and":[53,56,107,119,134],"reduce":[54],"phase,":[55],"requires":[57],"transferring":[58],"amounts":[60],"intermediate":[62],"results":[63],"over":[64],"network,":[66],"which":[67],"inefficient.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73],"proposed":[74],"an":[75,121],"algorithm":[76,84],"called":[77],"CHMJ,":[78],"general":[80],"idea":[81],"take":[87],"advantage":[88],"locality":[91],"accelerate":[93],"calculation.":[94],"It":[95],"includes":[96],"four":[97],"parts,":[98],"Data":[99],"distribution":[100],"strategy,":[101],"Parallel":[102],"HashMapJoin":[103],"Algorithm,":[104],"CoLocation":[105],"Scheduling":[106],"Delay":[108],"scheduling":[109],"strategy.":[110],"CHMJ":[111],"been":[113],"adopted":[114],"warehouse,":[118],"plays":[120],"role":[123],"Tencent's":[125],"daily":[126],"operations.":[127],"relevant":[129],"experiments":[130],"demonstrate":[131],"feasibility":[133],"efficiency":[135],"our":[137],"solution.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
