{"id":"https://openalex.org/W2401572102","doi":"https://doi.org/10.1145/2876509","title":"Efficient Deduplication in a Distributed Primary Storage Infrastructure","display_name":"Efficient Deduplication in a Distributed Primary Storage Infrastructure","publication_year":2016,"publication_date":"2016-05-20","ids":{"openalex":"https://openalex.org/W2401572102","doi":"https://doi.org/10.1145/2876509","mag":"2401572102"},"language":"en","primary_location":{"id":"doi:10.1145/2876509","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2876509","pdf_url":null,"source":{"id":"https://openalex.org/S158124317","display_name":"ACM Transactions on Storage","issn_l":"1553-3077","issn":["1553-3077","1553-3093"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Storage","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://repositorio.inesctec.pt/handle/123456789/4218","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054409160","display_name":"Jo\u00e3o Paulo","orcid":"https://orcid.org/0000-0001-9752-2822"},"institutions":[{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]},{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Jo\u00e3o Paulo","raw_affiliation_strings":["High-Assurance Software Lab (HASLab), INESC TEC, and University of Minho, Braga, Portugal"],"affiliations":[{"raw_affiliation_string":"High-Assurance Software Lab (HASLab), INESC TEC, and University of Minho, Braga, Portugal","institution_ids":["https://openalex.org/I99682543","https://openalex.org/I4210166615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065441606","display_name":"Jos\u00e9 Pereira","orcid":"https://orcid.org/0000-0002-3341-9217"},"institutions":[{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]},{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Pereira","raw_affiliation_strings":["High-Assurance Software Lab (HASLab), INESC TEC, and University of Minho, Braga, Portugal"],"affiliations":[{"raw_affiliation_string":"High-Assurance Software Lab (HASLab), INESC TEC, and University of Minho, Braga, Portugal","institution_ids":["https://openalex.org/I99682543","https://openalex.org/I4210166615"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5054409160"],"corresponding_institution_ids":["https://openalex.org/I4210166615","https://openalex.org/I99682543"],"apc_list":null,"apc_paid":null,"fwci":7.6215,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.97074354,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"12","issue":"4","first_page":"1","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.9976999759674072,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9976999759674072,"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":0.9975000023841858,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9972000122070312,"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/data-deduplication","display_name":"Data deduplication","score":0.9638168811798096},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8889556527137756},{"id":"https://openalex.org/keywords/backup","display_name":"Backup","score":0.7441664338111877},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5943335294723511},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.563198983669281},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5338999032974243},{"id":"https://openalex.org/keywords/virtual-machine","display_name":"Virtual machine","score":0.5217345952987671},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.5083572268486023},{"id":"https://openalex.org/keywords/multitenancy","display_name":"Multitenancy","score":0.46857118606567383},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.46649739146232605},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.45951831340789795},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.38956332206726074},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.33322474360466003},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.09737825393676758},{"id":"https://openalex.org/keywords/software-as-a-service","display_name":"Software as a service","score":0.08060100674629211}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9638168811798096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8889556527137756},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.7441664338111877},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5943335294723511},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.563198983669281},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5338999032974243},{"id":"https://openalex.org/C25344961","wikidata":"https://www.wikidata.org/wiki/Q192726","display_name":"Virtual machine","level":2,"score":0.5217345952987671},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5083572268486023},{"id":"https://openalex.org/C69016650","wikidata":"https://www.wikidata.org/wiki/Q1364211","display_name":"Multitenancy","level":5,"score":0.46857118606567383},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.46649739146232605},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.45951831340789795},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.38956332206726074},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.33322474360466003},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.09737825393676758},{"id":"https://openalex.org/C175133352","wikidata":"https://www.wikidata.org/wiki/Q1254596","display_name":"Software as a service","level":4,"score":0.08060100674629211},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2876509","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2876509","pdf_url":null,"source":{"id":"https://openalex.org/S158124317","display_name":"ACM Transactions on Storage","issn_l":"1553-3077","issn":["1553-3077","1553-3093"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Storage","raw_type":"journal-article"},{"id":"pmh:oai:repositorio.inesctec.pt:123456789/4218","is_oa":true,"landing_page_url":"http://repositorio.inesctec.pt/handle/123456789/4218","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"},{"id":"pmh:oai:repositorium.sdum.uminho.pt:1822/52875","is_oa":false,"landing_page_url":"http://hdl.handle.net/1822/52875","pdf_url":null,"source":{"id":"https://openalex.org/S4306401240","display_name":"Reposit\u00f3riUM (Universidade do Minho)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99682543","host_organization_name":"University of Minho","host_organization_lineage":["https://openalex.org/I99682543"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"},{"id":"pmh:oai:repositorium.uminho.pt:1822/52875","is_oa":false,"landing_page_url":"https://hdl.handle.net/1822/52875","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"journal article"}],"best_oa_location":{"id":"pmh:oai:repositorio.inesctec.pt:123456789/4218","is_oa":true,"landing_page_url":"http://repositorio.inesctec.pt/handle/123456789/4218","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"},"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W6847055","https://openalex.org/W26020480","https://openalex.org/W69510097","https://openalex.org/W122845700","https://openalex.org/W125480971","https://openalex.org/W174289249","https://openalex.org/W178328500","https://openalex.org/W182307532","https://openalex.org/W193648907","https://openalex.org/W200233886","https://openalex.org/W1474119323","https://openalex.org/W1521407587","https://openalex.org/W1568472162","https://openalex.org/W1576397915","https://openalex.org/W1856507064","https://openalex.org/W1969126835","https://openalex.org/W1971212200","https://openalex.org/W1971739358","https://openalex.org/W2003696547","https://openalex.org/W2012359782","https://openalex.org/W2029433591","https://openalex.org/W2033062224","https://openalex.org/W2047484077","https://openalex.org/W2055899630","https://openalex.org/W2096670209","https://openalex.org/W2110322986","https://openalex.org/W2128593562","https://openalex.org/W2133806194","https://openalex.org/W2146532238","https://openalex.org/W2147407897","https://openalex.org/W2149993626","https://openalex.org/W2153158407","https://openalex.org/W2156468933","https://openalex.org/W2156719566","https://openalex.org/W2157240622","https://openalex.org/W2218546124","https://openalex.org/W2264040388","https://openalex.org/W2281363974","https://openalex.org/W2583401777","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4285245558","https://openalex.org/W1437397736","https://openalex.org/W2048606985","https://openalex.org/W2375056709","https://openalex.org/W4301155776","https://openalex.org/W2012359782","https://openalex.org/W2952411620","https://openalex.org/W2348132657","https://openalex.org/W2179326652","https://openalex.org/W4223960471"],"abstract_inverted_index":{"A":[0],"large":[1],"amount":[2],"of":[3,10,26,67,101,110,152,194],"duplicate":[4],"data":[5,135],"typically":[6],"exists":[7],"across":[8],"volumes":[9],"virtual":[11,42,102,184],"machines":[12,43,185],"in":[13,83,186],"cloud":[14,85],"computing":[15],"infrastructures.":[16,29],"Deduplication":[17],"allows":[18,179],"reclaiming":[19],"these":[20,68],"duplicates":[21],"while":[22],"improving":[23],"the":[24,187,192],"cost-effectiveness":[25],"large-scale":[27],"multitenant":[28],"However,":[30],"traditional":[31],"archival":[32],"and":[33,92,138,146,166,178,183],"backup":[34],"deduplication":[35,48,75,100,144,165],"systems":[36,49,69],"impose":[37],"prohibitive":[38],"storage":[39,71,113,168],"overhead":[40,72,145,160],"for":[41,142],"hosting":[44],"latency-sensitive":[45],"applications.":[46],"Primary":[47],"reduce":[50,70],"such":[51],"penalty":[52],"but":[53],"rely":[54,133],"on":[55,108,134],"special":[56],"cluster":[57],"filesystems,":[58],"centralized":[59,115],"components,":[60],"or":[61,116],"restrictive":[62],"workload":[63],"assumptions.":[64],"Also,":[65,129,173],"some":[66],"by":[73],"confining":[74],"to":[76],"off-peak":[77],"periods":[78],"that":[79,96,157],"may":[80],"be":[81],"scarce":[82],"a":[84,90,123],"environment.":[86],"We":[87],"present":[88],"DEDIS,":[89],"dependable":[91],"fully":[93],"decentralized":[94],"system":[95],"performs":[97],"cluster-wide":[98],"off-line":[99],"machines\u2019":[103],"primary":[104],"volumes.":[105],"DEDIS":[106,130,181],"works":[107],"top":[109],"any":[111],"unsophisticated":[112],"backend,":[114],"distributed,":[117],"as":[118,120],"long":[119],"it":[121],"exports":[122],"basic":[124],"shared":[125],"block":[126],"device":[127],"interface.":[128],"does":[131],"not":[132],"locality":[136],"assumptions":[137],"incorporates":[139],"novel":[140],"optimizations":[141],"reducing":[143],"increasing":[147],"its":[148],"reliability.":[149],"The":[150],"evaluation":[151],"an":[153],"open-source":[154],"prototype":[155],"shows":[156],"minimal":[158],"I/O":[159,169],"is":[161],"achievable":[162],"even":[163],"when":[164],"intensive":[167],"are":[170],"executed":[171],"simultaneously.":[172],"our":[174],"design":[175],"scales":[176],"out":[177],"collocating":[180],"components":[182],"same":[188],"servers,":[189],"thus,":[190],"sparing":[191],"need":[193],"additional":[195],"hardware.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}