{"id":"https://openalex.org/W1974534485","doi":"https://doi.org/10.1109/iiswc.2012.6402909","title":"A storage-centric analysis of MapReduce workloads: File popularity, temporal locality and arrival patterns","display_name":"A storage-centric analysis of MapReduce workloads: File popularity, temporal locality and arrival patterns","publication_year":2012,"publication_date":"2012-11-01","ids":{"openalex":"https://openalex.org/W1974534485","doi":"https://doi.org/10.1109/iiswc.2012.6402909","mag":"1974534485"},"language":"en","primary_location":{"id":"doi:10.1109/iiswc.2012.6402909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iiswc.2012.6402909","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/A5071047865","display_name":"Cristina L. Abad","orcid":"https://orcid.org/0000-0002-9263-673X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cristina L. Abad","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, USA","University of Illinois at Urbana\u2013Champaign, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana\u2013Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082335132","display_name":"Nathan Roberts","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathan Roberts","raw_affiliation_strings":["Yahoo! Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Inc., USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102981342","display_name":"Yi Lu","orcid":"https://orcid.org/0000-0002-6768-7893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Lu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, USA","University of Illinois at Urbana\u2013Champaign, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana\u2013Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065622216","display_name":"Roy H. Campbell","orcid":"https://orcid.org/0000-0002-3754-7777"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roy H. Campbell","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, USA","University of Illinois at Urbana\u2013Champaign, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana\u2013Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"100","last_page":"109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9993000030517578,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991000294685364,"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/T11478","display_name":"Caching and Content Delivery","score":0.9983000159263611,"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":0.8820550441741943},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.7586468458175659},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7051130533218384},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.673751175403595},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.5765936374664307},{"id":"https://openalex.org/keywords/distributed-file-system","display_name":"Distributed File System","score":0.48549774289131165},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4827510714530945},{"id":"https://openalex.org/keywords/file-server","display_name":"File server","score":0.4677349030971527},{"id":"https://openalex.org/keywords/file-system","display_name":"File system","score":0.447429895401001},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.44689705967903137},{"id":"https://openalex.org/keywords/computer-data-storage","display_name":"Computer data storage","score":0.4385250210762024},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3782731592655182}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8820550441741943},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.7586468458175659},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7051130533218384},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.673751175403595},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5765936374664307},{"id":"https://openalex.org/C152043487","wikidata":"https://www.wikidata.org/wiki/Q1229600","display_name":"Distributed File System","level":2,"score":0.48549774289131165},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4827510714530945},{"id":"https://openalex.org/C4373008","wikidata":"https://www.wikidata.org/wiki/Q513349","display_name":"File server","level":2,"score":0.4677349030971527},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.447429895401001},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.44689705967903137},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.4385250210762024},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3782731592655182},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iiswc.2012.6402909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iiswc.2012.6402909","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1985790218","https://openalex.org/W2000042664","https://openalex.org/W2025669595","https://openalex.org/W2074899371","https://openalex.org/W2094469165","https://openalex.org/W2100595504","https://openalex.org/W2104993419","https://openalex.org/W2105818147","https://openalex.org/W2110374314","https://openalex.org/W2112053513","https://openalex.org/W2119501598","https://openalex.org/W2119738171","https://openalex.org/W2128796442","https://openalex.org/W2138543759","https://openalex.org/W2139274913","https://openalex.org/W2146320425","https://openalex.org/W2150106407","https://openalex.org/W2163291889","https://openalex.org/W2173213060","https://openalex.org/W3103362336","https://openalex.org/W6676551325"],"related_works":["https://openalex.org/W2953559629","https://openalex.org/W1480425691","https://openalex.org/W3042976586","https://openalex.org/W2488366707","https://openalex.org/W2571822082","https://openalex.org/W2225892199","https://openalex.org/W2593536136","https://openalex.org/W1987221064","https://openalex.org/W3046553064","https://openalex.org/W1920242583"],"abstract_inverted_index":{"A":[0],"huge":[1],"increase":[2],"in":[3],"data":[4],"storage":[5,18,37,50,121],"and":[6,23,73,80,91,99],"processing":[7],"requirements":[8],"has":[9],"lead":[10],"to":[11,55],"Big":[12,35,48],"Data,":[13],"for":[14],"which":[15],"next":[16],"generation":[17],"systems":[19],"are":[20],"being":[21],"designed":[22],"implemented.":[24],"However,":[25],"we":[26],"have":[27],"a":[28,52,57],"limited":[29],"understanding":[30],"of":[31,34,43,47,59,83,106,114],"the":[32,41,75,84,104,111,120],"workloads":[33,117],"Data":[36,49],"systems.":[38],"We":[39,62,86],"consider":[40],"case":[42],"one":[44],"common":[45],"type":[46],"cluster:":[51],"cluster":[53],"dedicated":[54],"supporting":[56],"mix":[58],"MapReduce":[60,116],"jobs.":[61],"analyze":[63],"6-month":[64],"traces":[65],"from":[66,97],"two":[67],"large":[68],"Hadoop":[69],"clusters":[70],"at":[71],"Yahoo!":[72],"characterize":[74],"file":[76],"popularity,":[77],"temporal":[78],"locality,":[79],"arrival":[81],"patterns":[82],"workloads.":[85,102],"identify":[87],"several":[88],"interesting":[89],"properties":[90],"compare":[92],"them":[93],"with":[94,119],"previous":[95],"observations":[96],"web":[98],"media":[100],"server":[101],"To":[103],"best":[105],"our":[107],"knowledge,":[108],"this":[109],"is":[110],"first":[112],"study":[113],"how":[115],"interact":[118],"layer.":[122]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
