{"id":"https://openalex.org/W1984596556","doi":"https://doi.org/10.1109/padsw.2014.7097828","title":"MRTune: A simulator for performance tuning of MapReduce jobs with skewed data","display_name":"MRTune: A simulator for performance tuning of MapReduce jobs with skewed data","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W1984596556","doi":"https://doi.org/10.1109/padsw.2014.7097828","mag":"1984596556"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/padsw.2014.7097828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5060842602","display_name":"Xibo Zhou","orcid":"https://orcid.org/0000-0003-3525-4062"},"institutions":[{"id":"https://openalex.org/I4210159029","display_name":"Guangzhou HKUST Fok Ying Tung Research Institute","ror":"https://ror.org/05cvbj479","country_code":"CN","type":"facility","lineage":["https://openalex.org/I200769079","https://openalex.org/I4210159029"]},{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"funder","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"funder","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Xibo Zhou","raw_affiliation_strings":["Guangzhou HKUST Fok Ying Tung Research Institute, Hong Kong University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Guangzhou HKUST Fok Ying Tung Research Institute, Hong Kong University of Science and Technology, China","institution_ids":["https://openalex.org/I4210159029","https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100513359","display_name":"Wuman Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159029","display_name":"Guangzhou HKUST Fok Ying Tung Research Institute","ror":"https://ror.org/05cvbj479","country_code":"CN","type":"facility","lineage":["https://openalex.org/I200769079","https://openalex.org/I4210159029"]},{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"funder","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"funder","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Wuman Luo","raw_affiliation_strings":["Guangzhou HKUST Fok Ying Tung Research Institute, Hong Kong University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Guangzhou HKUST Fok Ying Tung Research Institute, Hong Kong University of Science and Technology, China","institution_ids":["https://openalex.org/I4210159029","https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046813626","display_name":"Haoyu Tan","orcid":"https://orcid.org/0000-0001-5673-452X"},"institutions":[{"id":"https://openalex.org/I4210159029","display_name":"Guangzhou HKUST Fok Ying Tung Research Institute","ror":"https://ror.org/05cvbj479","country_code":"CN","type":"facility","lineage":["https://openalex.org/I200769079","https://openalex.org/I4210159029"]},{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"funder","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"funder","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Haoyu Tan","raw_affiliation_strings":["Guangzhou HKUST Fok Ying Tung Research Institute, Hong Kong University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Guangzhou HKUST Fok Ying Tung Research Institute, Hong Kong University of Science and Technology, China","institution_ids":["https://openalex.org/I4210159029","https://openalex.org/I200769079","https://openalex.org/I889458895"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":4,"citation_normalized_percentile":{"value":0.459727,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":79,"max":80},"biblio":{"volume":"11","issue":null,"first_page":"352","last_page":"359"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9999,"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":0.9999,"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":0.9991,"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":0.995,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.90250266},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.68451405},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.61325914},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5682347},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.54212004},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.5116015},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.5022266},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47493178},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3776727},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.16020367},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14427587},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/padsw.2014.7097828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":15,"referenced_works":["https://openalex.org/W1673310716","https://openalex.org/W1834532152","https://openalex.org/W2007227498","https://openalex.org/W2030059621","https://openalex.org/W2032812664","https://openalex.org/W2057420573","https://openalex.org/W2090732649","https://openalex.org/W2096385147","https://openalex.org/W2116319227","https://openalex.org/W2118900647","https://openalex.org/W2128912667","https://openalex.org/W2136374084","https://openalex.org/W2156441202","https://openalex.org/W2173213060","https://openalex.org/W2294316975"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W4206777497","https://openalex.org/W3090563135","https://openalex.org/W2960264696","https://openalex.org/W2908016214","https://openalex.org/W2497432351","https://openalex.org/W2258317757","https://openalex.org/W2104929755","https://openalex.org/W2066208787"],"abstract_inverted_index":{"MapReduce":[0,38,76,159,167,212,229,263],"is":[1,26,29,72,100,124,190,243],"a":[2,37,134,157,199,262],"programming":[3,24],"model":[4,25],"designed":[5],"by":[6],"Google":[7],"that":[8,222],"has":[9],"been":[10],"widely":[11],"used":[12],"for":[13,36,163],"both":[14],"high":[15,232],"performance":[16,34,52],"computing":[17],"and":[18,47,58,85,109,144,179,234,258],"big":[19],"data":[20,143,176,189,242,256],"processing.":[21],"Although":[22],"the":[23,41,44,51,55,59,75,90,93,103,110,131,141,145,150,171,185,196,202,226,237,253],"simple,":[27],"it":[28,123],"very":[30],"challenging":[31],"to":[32,68,73,251],"conduct":[33,247],"tuning":[35],"job,":[39],"considering":[40],"complexities":[42],"of":[43,54,82,112,115,133,149,166,174,188,198,204,228,240,255],"configuration":[45,83,146],"parameters":[46,84],"various":[48],"tradeoffs":[49],"between":[50],"gain":[53],"optimization":[56,86],"approaches":[57],"extra":[60],"overhead":[61],"they":[62],"bring":[63],"about.":[64],"One":[65],"naive":[66],"way":[67],"address":[69],"this":[70,153],"issue":[71],"run":[74,114],"jobs":[77,213,230],"repeatedly":[78],"using":[79,139],"different":[80],"combinations":[81,104],"methods,":[87],"then":[88],"select":[89],"one":[91,113],"with":[92,214,231],"shortest":[94],"running":[95],"time.":[96],"However,":[97],"real":[98,137],"execution":[99,138],"impractical":[101],"because":[102],"may":[105,118],"be":[106,119],"too":[107,120],"many":[108],"time":[111],"each":[116],"combination":[117],"long.":[121],"Therefore,":[122],"desirable":[125],"if":[126],"we":[127,155],"can":[128,180,194,224],"efficiently":[129],"estimate":[130,195,225],"runtime":[132,164,197,227],"job":[135,200],"without":[136],"only":[140],"input":[142,175,217,241],"parameter":[147],"settings":[148],"cluster.":[151],"In":[152],"paper,":[154],"propose":[156],"novel":[158],"simulator":[160],"called":[161],"MRTune":[162,169,193,210,223],"estimation":[165],"jobs.":[168],"takes":[170],"key":[172,186,238],"distribution":[173,187,239],"into":[177],"consideration":[178],"work":[181],"well":[182],"even":[183],"when":[184],"skewed.":[191,244],"Moreover,":[192],"in":[201],"presence":[203],"unpredictable":[205],"task":[206,259],"failures.":[207],"We":[208,245],"evaluate":[209],"implementing":[211],"Zipfian":[215],"distributed":[216],"data.":[218],"The":[219],"result":[220],"shows":[221],"accuracy":[233],"efficiency":[235],"while":[236],"also":[246],"two":[248],"case":[249],"studies":[250],"analyse":[252],"impact":[254],"skew":[257],"failures":[260],"on":[261],"job.":[264]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W1984596556","counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-03-23T12:29:11.422125","created_date":"2016-06-24"}