{"id":"https://openalex.org/W2515208787","doi":"https://doi.org/10.1109/tcc.2016.2607738","title":"A Data Skew Oriented Reduce Placement Algorithm Based on Sampling","display_name":"A Data Skew Oriented Reduce Placement Algorithm Based on Sampling","publication_year":2016,"publication_date":"2016-09-09","ids":{"openalex":"https://openalex.org/W2515208787","doi":"https://doi.org/10.1109/tcc.2016.2607738","mag":"2515208787"},"language":"en","primary_location":{"id":"doi:10.1109/tcc.2016.2607738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcc.2016.2607738","pdf_url":null,"source":{"id":"https://openalex.org/S2492498579","display_name":"IEEE Transactions on Cloud Computing","issn_l":"2168-7161","issn":["2168-7161","2372-0018"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cloud Computing","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/A5008574161","display_name":"Zhuo Tang","orcid":"https://orcid.org/0000-0001-9081-8153"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuo Tang","raw_affiliation_strings":["College of Information Science and Engineering, Hunan University, and National Supercomputing Center in Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0001-9081-8153","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, and National Supercomputing Center in Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084782621","display_name":"Wen Ma","orcid":"https://orcid.org/0000-0003-3488-8100"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Ma","raw_affiliation_strings":["College of Information Science and Engineering, Hunan University, and National Supercomputing Center in Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, and National Supercomputing Center in Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078793726","display_name":"Kenli Li","orcid":"https://orcid.org/0000-0002-2635-7716"},"institutions":[{"id":"https://openalex.org/I157455823","display_name":"SUNY New Paltz","ror":"https://ror.org/03j3dv688","country_code":"US","type":"education","lineage":["https://openalex.org/I157455823"]},{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Kenli Li","raw_affiliation_strings":["College of Information Science and Engineering, Hunan University, and National Supercomputing Center in Changsha, Hunan, China","Department of Computer Science, State University of New York, New Paltz, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-2635-7716","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, and National Supercomputing Center in Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"Department of Computer Science, State University of New York, New Paltz, NY, USA","institution_ids":["https://openalex.org/I157455823"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087894632","display_name":"Keqin Li","orcid":"https://orcid.org/0000-0001-5224-4048"},"institutions":[{"id":"https://openalex.org/I157455823","display_name":"SUNY New Paltz","ror":"https://ror.org/03j3dv688","country_code":"US","type":"education","lineage":["https://openalex.org/I157455823"]},{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Keqin Li","raw_affiliation_strings":["College of Information Science and Engineering, Hunan University, and National Supercomputing Center in Changsha, Hunan, China","Department of Computer Science, State University of New York, New Paltz, NY, USA"],"raw_orcid":"https://orcid.org/0000-0001-5224-4048","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan University, and National Supercomputing Center in Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"Department of Computer Science, State University of New York, New Paltz, NY, USA","institution_ids":["https://openalex.org/I157455823"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.1195,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.97383508,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"8","issue":"4","first_page":"1149","last_page":"1161"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9929999709129333,"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":0.9891999959945679,"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":0.8275600671768188},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.648904025554657},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5666087865829468},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4965696930885315},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4761107861995697},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.47446686029434204},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4635927081108093},{"id":"https://openalex.org/keywords/data-transmission","display_name":"Data transmission","score":0.4103279411792755},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.38604509830474854},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.33535873889923096},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12749648094177246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8275600671768188},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.648904025554657},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5666087865829468},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4965696930885315},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4761107861995697},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.47446686029434204},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4635927081108093},{"id":"https://openalex.org/C557945733","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Data transmission","level":2,"score":0.4103279411792755},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.38604509830474854},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.33535873889923096},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12749648094177246},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcc.2016.2607738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcc.2016.2607738","pdf_url":null,"source":{"id":"https://openalex.org/S2492498579","display_name":"IEEE Transactions on Cloud Computing","issn_l":"2168-7161","issn":["2168-7161","2372-0018"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cloud Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G5850822618","display_name":"\u503e\u659c\u4efb\u52a1\u8c03\u5ea6\u6a21\u578b\u53ca\u5176\u5728\u533b\u7597\u5927\u6570\u636e\u5904\u7406\u4e2d\u7684\u5e94\u7528\u7814\u7a76","funder_award_id":"61572176","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8367730789","display_name":null,"funder_award_id":"2015AA015303","funder_id":"https://openalex.org/F4320335773","funder_display_name":"National High-tech Research and Development Program"}],"funders":[{"id":"https://openalex.org/F4320309644","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322191","display_name":"Hunan University","ror":"https://ror.org/05htk5m33"},{"id":"https://openalex.org/F4320335773","display_name":"National High-tech Research and Development Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1968196581","https://openalex.org/W1974396493","https://openalex.org/W1976914761","https://openalex.org/W1980720402","https://openalex.org/W1993667637","https://openalex.org/W2005005648","https://openalex.org/W2020133428","https://openalex.org/W2022678927","https://openalex.org/W2024077218","https://openalex.org/W2040722314","https://openalex.org/W2041958520","https://openalex.org/W2047745331","https://openalex.org/W2057279099","https://openalex.org/W2060650311","https://openalex.org/W2079031056","https://openalex.org/W2080131844","https://openalex.org/W2091842814","https://openalex.org/W2096791558","https://openalex.org/W2098935637","https://openalex.org/W2112173609","https://openalex.org/W2120755171","https://openalex.org/W2134952300","https://openalex.org/W2140509629","https://openalex.org/W2143108641","https://openalex.org/W2151487638","https://openalex.org/W2156441202","https://openalex.org/W2165769837","https://openalex.org/W2199389590","https://openalex.org/W3141604153","https://openalex.org/W4255423389","https://openalex.org/W4285719527","https://openalex.org/W6655761483","https://openalex.org/W6673643799","https://openalex.org/W6683267612"],"related_works":["https://openalex.org/W4290802965","https://openalex.org/W97789383","https://openalex.org/W3087516072","https://openalex.org/W4289406402","https://openalex.org/W2727156679","https://openalex.org/W1556451512","https://openalex.org/W1555349535","https://openalex.org/W2067997904","https://openalex.org/W4387423656","https://openalex.org/W4389136702"],"abstract_inverted_index":{"For":[0],"frequent":[1],"disk":[2],"I/O":[3],"and":[4,11,42,115,126,146,157,182],"large":[5],"data":[6,15,54,67,138,212,223],"transmissions":[7],"among":[8,118],"different":[9],"racks":[10,52],"physical":[12,135],"nodes,":[13],"intermediate":[14,106],"communication":[16],"has":[17,233],"become":[18],"the":[19,46,57,65,81,87,93,101,105,113,119,123,169,177,195,204,209,221,226,230],"most":[20,25],"important":[21],"performance":[22,149],"bottle-neck":[23],"in":[24,108,143,184],"running":[26],"Hadoop":[27,144],"systems.":[28],"This":[29],"paper":[30,74],"proposes":[31],"a":[32,76],"reduce":[33,43,127,218],"placement":[34],"algorithm":[35,78],"called":[36],"CORP":[37,142,190],"to":[38,92,132],"schedule":[39],"related":[40,124],"map":[41,71,125],"tasks":[44,128,199],"on":[45,100,229],"near":[47],"nodes":[48,136],"of":[49,59,89,96,104,179,197,225],"clusters":[50],"or":[51],"for":[53,79,137,167,208],"locality.":[55,139],"Because":[56],"number":[58],"keys":[60],"cannot":[61],"be":[62,130],"counted":[63],"until":[64],"input":[66,82],"are":[68],"processed":[69],"by":[70,111],"tasks,":[72],"this":[73],"applies":[75],"reservoir":[77],"sampling":[80],"data,":[83],"which":[84,173],"can":[85,129,174,191],"bring":[86],"distribution":[88,102],"keys/values":[90],"closer":[91],"overall":[94],"situation":[95],"original":[97],"data.":[98],"Based":[99],"matrix":[103],"results":[107,187],"each":[109],"partition,":[110],"calculating":[112],"distance":[114],"cost":[116],"matrices":[117],"cross":[120],"node":[121],"communication,":[122],"scheduled":[131],"relatively":[133],"nearby":[134],"We":[140],"implement":[141],"2.4.0":[145],"evaluate":[147],"its":[148],"using":[150],"three":[151],"widely":[152],"used":[153],"benchmarks:":[154],"Sort,":[155],"Grep,":[156],"Join.":[158],"In":[159],"these":[160],"experiments,":[161],"an":[162],"evaluation":[163],"model":[164],"is":[165],"proposed":[166],"selecting":[168],"appropriate":[170],"sample":[171],"rates,":[172],"comprehensively":[175],"consider":[176],"importance":[178],"cost,":[180],"effect,":[181],"variance":[183],"sampling.":[185],"Experimental":[186],"show":[188],"that":[189],"not":[192],"only":[193],"improve":[194],"balance":[196],"reduces":[198],"effectively":[200],"but":[201],"also":[202],"decreases":[203],"job":[205],"execution":[206],"time":[207],"lower":[210],"inner":[211],"communication.":[213],"Compared":[214],"with":[215],"some":[216],"other":[217],"scheduling":[219],"algorithms,":[220],"average":[222],"transmission":[224],"entire":[227],"system":[228],"core":[231],"switch":[232],"been":[234],"reduced":[235],"substantially.":[236]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
