{"id":"https://openalex.org/W4408399693","doi":"https://doi.org/10.1109/tpds.2025.3551306","title":"The Design of a High-Performance Fine-Grained Deduplication Framework for Backup Storage","display_name":"The Design of a High-Performance Fine-Grained Deduplication Framework for Backup Storage","publication_year":2025,"publication_date":"2025-03-13","ids":{"openalex":"https://openalex.org/W4408399693","doi":"https://doi.org/10.1109/tpds.2025.3551306"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2025.3551306","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2025.3551306","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"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/A5021153181","display_name":"Xiangyu Zou","orcid":"https://orcid.org/0000-0001-5104-8301"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Zou","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, Harbin Institute of Technology, Shenzhen, China","Harbin Institute of Technology, Shenzhen"],"raw_orcid":"https://orcid.org/0000-0001-5104-8301","affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050928208","display_name":"Wen Xia","orcid":"https://orcid.org/0000-0003-4093-6391"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Xia","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, Harbin Institute of Technology, Shenzhen, China","Harbin Institute of Technology, Shenzhen"],"raw_orcid":"https://orcid.org/0000-0003-4093-6391","affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091766663","display_name":"Philip Shilane","orcid":"https://orcid.org/0000-0003-1235-0502"},"institutions":[{"id":"https://openalex.org/I4210149435","display_name":"DELL (United States)","ror":"https://ror.org/05rejmm18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210149435"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip Shilane","raw_affiliation_strings":["Dell Technologies, Round Rock, TX, USA","Dell Technologies"],"raw_orcid":"https://orcid.org/0000-0003-1235-0502","affiliations":[{"raw_affiliation_string":"Dell Technologies, Round Rock, TX, USA","institution_ids":["https://openalex.org/I4210149435"]},{"raw_affiliation_string":"Dell Technologies","institution_ids":["https://openalex.org/I4210149435"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458457","display_name":"Haijun Zhang","orcid":"https://orcid.org/0000-0002-1648-0227"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haijun Zhang","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, Harbin Institute of Technology, Shenzhen, China","Harbin Institute of Technology, Shenzhen"],"raw_orcid":"https://orcid.org/0000-0002-1648-0227","affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100328995","display_name":"Xuan Wang","orcid":"https://orcid.org/0000-0002-3512-0649"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Wang","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, Harbin Institute of Technology, Shenzhen, China","Harbin Institute of Technology, Shenzhen"],"raw_orcid":"https://orcid.org/0000-0002-3512-0649","affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1081,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76360053,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"36","issue":"5","first_page":"945","last_page":"960"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9743000268936157,"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/T11478","display_name":"Caching and Content Delivery","score":0.9743000268936157,"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":0.9431999921798706,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9157999753952026,"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":0.8911101222038269},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8446807265281677},{"id":"https://openalex.org/keywords/backup","display_name":"Backup","score":0.8067789077758789},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4495394229888916},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4461647868156433},{"id":"https://openalex.org/keywords/computer-data-storage","display_name":"Computer data storage","score":0.4288256764411926},{"id":"https://openalex.org/keywords/storage-management","display_name":"Storage management","score":0.4229600727558136}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.8911101222038269},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8446807265281677},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.8067789077758789},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4495394229888916},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4461647868156433},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.4288256764411926},{"id":"https://openalex.org/C2984984529","wikidata":"https://www.wikidata.org/wiki/Q7619925","display_name":"Storage management","level":2,"score":0.4229600727558136}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2025.3551306","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2025.3551306","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4100129303","display_name":null,"funder_award_id":"62472127","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5449262284","display_name":null,"funder_award_id":"2023A1515110072","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W46106265","https://openalex.org/W1418704970","https://openalex.org/W1969335064","https://openalex.org/W1971212200","https://openalex.org/W1988145820","https://openalex.org/W2009191935","https://openalex.org/W2010150514","https://openalex.org/W2013592197","https://openalex.org/W2029433591","https://openalex.org/W2056980397","https://openalex.org/W2073370301","https://openalex.org/W2107551255","https://openalex.org/W2110322986","https://openalex.org/W2113222340","https://openalex.org/W2119631914","https://openalex.org/W2129610259","https://openalex.org/W2132069633","https://openalex.org/W2147407897","https://openalex.org/W2148885851","https://openalex.org/W2343548694","https://openalex.org/W2346147088","https://openalex.org/W2475932436","https://openalex.org/W2516668814","https://openalex.org/W2983201557","https://openalex.org/W3023701944","https://openalex.org/W3033148464","https://openalex.org/W3097040955","https://openalex.org/W3156357774","https://openalex.org/W3174127842","https://openalex.org/W3202721467","https://openalex.org/W3216568576","https://openalex.org/W6600884019","https://openalex.org/W6604953292","https://openalex.org/W6605032692","https://openalex.org/W6607453207","https://openalex.org/W6608138927","https://openalex.org/W6628419871","https://openalex.org/W6638808162","https://openalex.org/W6640045128","https://openalex.org/W6640739288","https://openalex.org/W6679804201","https://openalex.org/W6683485282","https://openalex.org/W6687744917","https://openalex.org/W6697566756","https://openalex.org/W6717023391","https://openalex.org/W6735783352","https://openalex.org/W6759234905","https://openalex.org/W6760689153","https://openalex.org/W6765751454","https://openalex.org/W6781779593","https://openalex.org/W6790796689","https://openalex.org/W6799530017"],"related_works":["https://openalex.org/W1437397736","https://openalex.org/W4285245558","https://openalex.org/W2048606985","https://openalex.org/W2375056709","https://openalex.org/W2012359782","https://openalex.org/W2952411620","https://openalex.org/W4301155776","https://openalex.org/W2348132657","https://openalex.org/W2354924268","https://openalex.org/W3008013744"],"abstract_inverted_index":{"Fine-grained":[0],"deduplication":[1,11,40,54,59,94,99,124,158,186],"(also":[2],"known":[3],"as":[4],"delta":[5,111],"compression)":[6],"can":[7],"achieve":[8],"a":[9,109,128,152,184],"better":[10,153,171],"ratio":[12,100],"compared":[13],"to":[14,60,71,92,117,135],"chunk-level":[15,58,93],"deduplication.":[16,104],"This":[17],"technique":[18],"removes":[19],"not":[20],"only":[21],"identical":[22],"chunks":[23],"but":[24,30],"also":[25],"reduces":[26],"redundancies":[27],"between":[28],"similar":[29],"non-identical":[31],"chunks.":[32],"Nevertheless,":[33],"it":[34],"introduces":[35],"considerable":[36],"I/O":[37,73],"overhead":[38,74],"in":[39,122,140],"and":[41,51,75,113,126,132,174],"restore":[42,142,179],"processes,":[43],"hindering":[44],"the":[45,97,123,141,164],"performance":[46,154],"of":[47,102],"these":[48],"two":[49],"processes":[50],"rendering":[52],"fine-grained":[53,87,103,157],"less":[55],"popular":[56],"than":[57,155],"date.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65,82],"explore":[66],"various":[67],"issues":[68],"that":[69,149],"lead":[70],"additional":[72],"tackle":[76],"them":[77],"using":[78],"several":[79],"techniques.":[80],"Moreover,":[81],"introduce":[83],"MeGA,":[84],"which":[85],"attains":[86],"deduplication/restore":[88],"speed":[89,173],"nearly":[90],"equivalent":[91],"while":[95,182],"maintaining":[96],"significant":[98],"benefit":[101],"Specifically,":[105,160],"MeGA":[106,150,161],"employs":[107],"(1)":[108],"backup-workflow-oriented":[110],"selector":[112],"cache-centric":[114],"resemblance":[115],"detection":[116],"mitigate":[118],"poor":[119,137],"spatial/temporal":[120,138],"locality":[121,139],"process,":[125],"(2)":[127],"delta-friendly":[129],"data":[130],"layout":[131],"\u201cAlways-Forward-Reference\u201d":[133],"traversal":[134],"address":[136],"workflow.":[143],"Evaluations":[144],"on":[145],"four":[146],"datasets":[147],"show":[148],"achieves":[151],"other":[156],"approaches.":[159],"significantly":[162],"outperforms":[163],"traditional":[165],"greedy":[166],"approach,":[167],"providing":[168],"10\u201346":[169],"times":[170,176],"backup":[172],"30\u2013105":[175],"more":[177],"efficient":[178],"speed,":[180],"all":[181],"preserving":[183],"high":[185],"ratio.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}