{"id":"https://openalex.org/W182307532","doi":null,"title":"Building a high-performance deduplication system","display_name":"Building a high-performance deduplication system","publication_year":2011,"publication_date":"2011-06-15","ids":{"openalex":"https://openalex.org/W182307532","mag":"182307532"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.307.87","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.307.87","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.usenix.org/legacy/events/atc11/tech/final_files/GuoEfstathopoulos.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5073020523","display_name":"Fanglu Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1308906816","display_name":"NortonLifeLock (United States)","ror":"https://ror.org/0449t3a80","country_code":"US","type":"company","lineage":["https://openalex.org/I1308906816","https://openalex.org/I4405258830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fanglu Guo","raw_affiliation_strings":["Symantec Research Labs, Symantec Corporation, Culver City, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Symantec Research Labs, Symantec Corporation, Culver City, CA","institution_ids":["https://openalex.org/I1308906816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090509743","display_name":"Petros Efstathopoulos","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1308906816","display_name":"NortonLifeLock (United States)","ror":"https://ror.org/0449t3a80","country_code":"US","type":"company","lineage":["https://openalex.org/I1308906816","https://openalex.org/I4405258830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Petros Efstathopoulos","raw_affiliation_strings":["Symantec Research Labs, Symantec Corporation, Culver City, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Symantec Research Labs, Symantec Corporation, Culver City, CA","institution_ids":["https://openalex.org/I1308906816"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1308906816"],"apc_list":null,"apc_paid":null,"fwci":22.4025,"has_fulltext":false,"cited_by_count":172,"citation_normalized_percentile":{"value":0.99547135,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9980000257492065,"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":0.9980000257492065,"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/T11269","display_name":"Algorithms and Data Compression","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.00039999998989515007,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-deduplication","display_name":"data deduplication","score":0.9449999928474426},{"id":"https://openalex.org/keywords/throughput-optimization","display_name":"throughput maximization","score":0.5199999809265137},{"id":"https://openalex.org/keywords/energy-efficiency","display_name":"energy efficiency","score":0.6570000052452087}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.8572047352790833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8541728854179382},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7884018421173096},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.7411437630653381},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5758028030395508},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5526012182235718},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.5459363460540771},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4537217915058136},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.43321722745895386},{"id":"https://openalex.org/C13600138","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Petabyte","level":3,"score":0.4125768542289734},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.37175071239471436},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.31164103746414185},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2521250247955322},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2059175670146942},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.08936846256256104},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.307.87","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.307.87","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.usenix.org/legacy/events/atc11/tech/final_files/GuoEfstathopoulos.pdf","raw_type":"text"},{"id":"mag:182307532","doi":null,"is_oa":false,"landing_page_url":"https://static.usenix.org/event/atc11/tech/final_files/GuoEfstathopoulos.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306421113","display_name":"USENIX Annual Technical Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"USENIX Annual Technical Conference","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5378999710083008,"display_name":"Industry, innovation and infrastructure"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W24740120","https://openalex.org/W69510097","https://openalex.org/W200233886","https://openalex.org/W1576397915","https://openalex.org/W1599186236","https://openalex.org/W1614703486","https://openalex.org/W1929726975","https://openalex.org/W1971212200","https://openalex.org/W2113154035","https://openalex.org/W2121133177","https://openalex.org/W2123767107","https://openalex.org/W2132627996","https://openalex.org/W2133806194"],"related_works":["https://openalex.org/W12581771","https://openalex.org/W1939696404","https://openalex.org/W2472668849","https://openalex.org/W1969126835","https://openalex.org/W2133806194","https://openalex.org/W5335935","https://openalex.org/W2959395236","https://openalex.org/W3161187608","https://openalex.org/W2188247367","https://openalex.org/W2266666071"],"abstract_inverted_index":{"Modern":[0],"deduplication":[1,69,82,106,139,220],"has":[2],"become":[3,72],"quite":[4],"effective":[5,14],"at":[6],"eliminating":[7],"duplicates":[8],"in":[9],"data,":[10],"thus":[11],"multiplying":[12],"the":[13,66,78,88,96,110,120],"capacity":[15,32],"of":[16,43,80,95,124,145,167,207,219],"disk-based":[17],"backup":[18],"systems,":[19,54],"and":[20,51,92,128,141,158,183,186,213],"enabling":[21],"them":[22,59],"as":[23],"realistic":[24],"tape":[25],"replacements.":[26],"Despite":[27],"these":[28],"improvements,":[29],"single-node":[30,116,176],"raw":[31],"is":[33,201],"still":[34],"mostly":[35],"limited":[36],"to":[37,47,49,60,62,113,134,147,203,205],"tens":[38],"or":[39,216],"a":[40,125],"few":[41],"hundreds":[42],"terabytes,":[44],"forcing":[45],"users":[46],"resort":[48],"complex":[50],"costly":[52],"multi-node":[53],"which":[55],"usually":[56],"only":[57],"allow":[58],"scale":[61,133,204],"singledigit":[63],"petabytes.":[64],"As":[65],"opportunities":[67],"for":[68],"efficiency":[70],"optimizations":[71],"scarce,":[73],"we":[74,102,152,162,174],"are":[75],"challenged":[76],"with":[77,164,210],"task":[79],"designing":[81],"systems":[83],"that":[84],"will":[85],"effectively":[86],"address":[87],"capacity,":[89,136],"throughput,":[90,212],"management":[91],"energy":[93],"requirements":[94],"petascale":[97],"age.":[98],"In":[99,172],"this":[100],"paper":[101],"present":[103],"our":[104],"high-performance":[105],"prototype,":[107],"designed":[108],"from":[109],"ground":[111],"up":[112],"optimize":[114,188],"overall":[115],"performance,":[117],"by":[118,178,190],"making":[119],"best":[121],"possible":[122],"use":[123],"node\u2019s":[126],"resources,":[127],"achieve":[129],"three":[130],"important":[131],"goals:":[132],"large":[135],"provide":[137],"good":[138],"efficiency,":[140],"near-raw-disk":[142],"throughput.":[143],"Instead":[144],"trying":[146],"improve":[148,175],"duplicate":[149],"detection":[150],"algorithms,":[151],"focus":[153],"on":[154],"system":[155,169],"design":[156],"aspects":[157],"introduce":[159],"novel":[160],"mechanisms\u2014that":[161],"combine":[163],"careful":[165],"implementations":[166],"known":[168],"engineering":[170],"techniques.":[171],"particular,":[173],"scalability":[177],"introducing":[179],"progressive":[180],"sampled":[181],"indexing":[182],"grouped":[184],"markand-sweep,":[185],"also":[187],"throughput":[189],"utilizing":[191],"an":[192],"event-driven,":[193],"multi-threaded":[194],"client-server":[195],"interaction":[196],"model.":[197],"Our":[198],"prototype":[199],"implementation":[200],"able":[202],"billions":[206],"stored":[208],"objects,":[209],"high":[211],"very":[214],"little":[215],"no":[217],"degradation":[218],"efficiency.":[221],"1":[222]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":22},{"year":2015,"cited_by_count":18},{"year":2014,"cited_by_count":21},{"year":2013,"cited_by_count":18},{"year":2012,"cited_by_count":18}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}
