{"id":"https://openalex.org/W2067005380","doi":"https://doi.org/10.1109/iiswc.2012.6402895","title":"Workload characterization on a production Hadoop cluster: A case study on Taobao","display_name":"Workload characterization on a production Hadoop cluster: A case study on Taobao","publication_year":2012,"publication_date":"2012-11-01","ids":{"openalex":"https://openalex.org/W2067005380","doi":"https://doi.org/10.1109/iiswc.2012.6402895","mag":"2067005380"},"language":"en","primary_location":{"id":"doi:10.1109/iiswc.2012.6402895","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iiswc.2012.6402895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Symposium on Workload Characterization (IISWC)","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/A5101544944","display_name":"Zujie Ren","orcid":"https://orcid.org/0000-0002-9985-9805"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zujie Ren","raw_affiliation_strings":["School of Computer Science and Technology, Hangzhou Dianzi University, China","School of Computer, Science and Technology, Hangzhou Dianzi University, China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hangzhou Dianzi University, China","institution_ids":["https://openalex.org/I50760025"]},{"raw_affiliation_string":"School of Computer, Science and Technology, Hangzhou Dianzi University, China,","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026554755","display_name":"Xianghua Xu","orcid":"https://orcid.org/0000-0001-9832-5804"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianghua Xu","raw_affiliation_strings":["School of Computer Science and Technology, Hangzhou Dianzi University, China","School of Computer, Science and Technology, Hangzhou Dianzi University, China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hangzhou Dianzi University, China","institution_ids":["https://openalex.org/I50760025"]},{"raw_affiliation_string":"School of Computer, Science and Technology, Hangzhou Dianzi University, China,","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082606335","display_name":"Jian Wan","orcid":"https://orcid.org/0000-0001-9882-3029"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Wan","raw_affiliation_strings":["School of Computer Science and Technology, Hangzhou Dianzi University, China","School of Computer, Science and Technology, Hangzhou Dianzi University, China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Hangzhou Dianzi University, China","institution_ids":["https://openalex.org/I50760025"]},{"raw_affiliation_string":"School of Computer, Science and Technology, Hangzhou Dianzi University, China,","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100651611","display_name":"Weisong Shi","orcid":"https://orcid.org/0000-0001-5864-4675"},"institutions":[{"id":"https://openalex.org/I185443292","display_name":"Wayne State University","ror":"https://ror.org/01070mq45","country_code":"US","type":"education","lineage":["https://openalex.org/I185443292"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weisong Shi","raw_affiliation_strings":["Department of Computer Science, Wayne State University, Detroit, USA","Department of Computer Science, Wayne State University, Detroit, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Wayne State University, Detroit, USA","institution_ids":["https://openalex.org/I185443292"]},{"raw_affiliation_string":"Department of Computer Science, Wayne State University, Detroit, USA#TAB#","institution_ids":["https://openalex.org/I185443292"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101634614","display_name":"Min Zhou","orcid":"https://orcid.org/0000-0002-3008-4749"},"institutions":[{"id":"https://openalex.org/I4210129769","display_name":"Tao Systems (United States)","ror":"https://ror.org/03nt2eg08","country_code":"US","type":"company","lineage":["https://openalex.org/I4210129769"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Zhou","raw_affiliation_strings":["Taobao, Inc., Hangzhou, China","Taobao, Inc., Hangzhou, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taobao, Inc., Hangzhou, China","institution_ids":["https://openalex.org/I4210129769"]},{"raw_affiliation_string":"Taobao, Inc., Hangzhou, China#TAB#","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":106,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9980999827384949,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9850999712944031,"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/workload","display_name":"Workload","score":0.8450188636779785},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.802501916885376},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.509987473487854},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48537003993988037},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.46332472562789917},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.44096454977989197},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.4249497652053833},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3926495313644409},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3278788924217224},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.26813462376594543},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.20553061366081238}],"concepts":[{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.8450188636779785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.802501916885376},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.509987473487854},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48537003993988037},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.46332472562789917},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.44096454977989197},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.4249497652053833},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3926495313644409},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3278788924217224},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26813462376594543},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20553061366081238},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"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/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iiswc.2012.6402895","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iiswc.2012.6402895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Symposium on Workload Characterization (IISWC)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.360.5580","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.360.5580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.wayne.edu/~weisong/papers/ren12-taobao.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W110612056","https://openalex.org/W228898923","https://openalex.org/W1558306065","https://openalex.org/W1558516248","https://openalex.org/W1598064945","https://openalex.org/W1966212613","https://openalex.org/W1970212427","https://openalex.org/W1985229168","https://openalex.org/W2002001916","https://openalex.org/W2018844593","https://openalex.org/W2026824323","https://openalex.org/W2058181149","https://openalex.org/W2096125134","https://openalex.org/W2103312864","https://openalex.org/W2103315535","https://openalex.org/W2109341366","https://openalex.org/W2110528713","https://openalex.org/W2111022129","https://openalex.org/W2111556044","https://openalex.org/W2117339850","https://openalex.org/W2119565742","https://openalex.org/W2126540184","https://openalex.org/W2130010548","https://openalex.org/W2132353061","https://openalex.org/W2136070119","https://openalex.org/W2146874446","https://openalex.org/W2153896652","https://openalex.org/W2160821994","https://openalex.org/W2163291889","https://openalex.org/W2170994858","https://openalex.org/W2173213060","https://openalex.org/W2335835805","https://openalex.org/W4239670432","https://openalex.org/W4302402754","https://openalex.org/W6604455612","https://openalex.org/W6677331330","https://openalex.org/W6703025197"],"related_works":["https://openalex.org/W2000785801","https://openalex.org/W986318368","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W4390608645","https://openalex.org/W2004734601","https://openalex.org/W2130149817","https://openalex.org/W2990194547","https://openalex.org/W1480123525","https://openalex.org/W3136989197"],"abstract_inverted_index":{"MapReduce":[0,43,79],"is":[1,45,95],"becoming":[2],"the":[3,40,46,55,96,109,131,134,173],"state-of-the-art":[4],"computing":[5],"paradigm":[6],"for":[7,162,196],"processing":[8],"large-scale":[9,66],"datasets":[10],"on":[11,78],"a":[12,65,83,88,144],"large":[13],"cluster":[14,91],"with":[15,143,159],"tens":[16],"or":[17],"thousands":[18],"of":[19,42,61,136,146,151,178],"nodes.":[20],"It":[21],"has":[22,69],"been":[23,71],"widely":[24],"used":[25],"in":[26,64,101,108,180],"various":[27],"fields":[28],"such":[29],"as":[30,111],"e-commerce,":[31],"Web":[32],"search,":[33],"social":[34],"networks,":[35],"and":[36,53,138,141,156,170,175],"scientific":[37],"computation.":[38],"Understanding":[39],"characteristics":[41,177],"workloads":[44],"key":[47],"to":[48,125,192],"achieving":[49],"better":[50],"configuration":[51],"decisions":[52],"improving":[54],"system":[56],"throughput.":[57],"However,":[58],"workload":[59,85,116,132,152],"characterization":[60,153],"MapReduce,":[62],"especially":[63],"production":[67,182],"environment,":[68],"not":[70],"well":[72],"studied":[73],"yet.":[74],"To":[75],"gain":[76],"insight":[77],"workloads,":[80],"we":[81,186],"collected":[82],"two-week":[84],"trace":[86,117],"from":[87,122],"2,000-node":[89],"Hadoop":[90,179],"at":[92,133],"Taobao,":[93],"which":[94,165],"biggest":[97],"online":[98],"e-commerce":[99,163],"enterprise":[100],"Asia,":[102],"ranked":[103],"14":[104],"<sup":[105],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[106],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">th</sup>":[107],"world":[110],"reported":[112],"by":[113],"Alexa.":[114],"The":[115,149],"covered":[118],"912,157":[119],"jobs,":[120],"logged":[121],"Dec.":[123,126],"4":[124],"20,":[127],"2011.":[128],"We":[129],"characterized":[130],"granularity":[135],"job":[137,176,189],"task,":[139],"respectively":[140],"concluded":[142],"set":[145],"interesting":[147],"observations.":[148],"results":[150],"are":[154],"representative":[155],"generally":[157],"consistent":[158],"data":[160],"platforms":[161],"websites,":[164],"can":[166],"help":[167],"other":[168],"researchers":[169],"engineers":[171],"understand":[172],"performance":[174,198],"their":[181],"environments.":[183],"In":[184],"addition,":[185],"use":[187],"these":[188],"analysis":[190],"statistics":[191],"derive":[193],"several":[194],"implications":[195],"potential":[197],"optimization":[199],"solutions.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":21},{"year":2015,"cited_by_count":17},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":10}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
