{"id":"https://openalex.org/W3207131661","doi":"https://doi.org/10.1145/3459626","title":"Improving the Performance of Deduplication-Based Backup Systems via Container Utilization Based Hot Fingerprint Entry Distilling","display_name":"Improving the Performance of Deduplication-Based Backup Systems via Container Utilization Based Hot Fingerprint Entry Distilling","publication_year":2021,"publication_date":"2021-10-15","ids":{"openalex":"https://openalex.org/W3207131661","doi":"https://doi.org/10.1145/3459626","mag":"3207131661"},"language":"en","primary_location":{"id":"doi:10.1145/3459626","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459626","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101017703","display_name":"Zhang Datong","orcid":null},"institutions":[{"id":"https://openalex.org/I159948400","display_name":"Jinan University","ror":"https://ror.org/02xe5ns62","country_code":"CN","type":"education","lineage":["https://openalex.org/I159948400"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Datong Zhang","raw_affiliation_strings":["Department of Computer Science, Jinan University, Guangzhou, Guangdong Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Jinan University, Guangzhou, Guangdong Province, China","institution_ids":["https://openalex.org/I159948400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073135288","display_name":"Yuhui Deng","orcid":"https://orcid.org/0000-0002-1522-8943"},"institutions":[{"id":"https://openalex.org/I159948400","display_name":"Jinan University","ror":"https://ror.org/02xe5ns62","country_code":"CN","type":"education","lineage":["https://openalex.org/I159948400"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhui Deng","raw_affiliation_strings":["Department of Computer Science, Jinan University, Guangzhou, Guangdong Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Jinan University, Guangzhou, Guangdong Province, China","institution_ids":["https://openalex.org/I159948400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100753053","display_name":"Yi Zhou","orcid":"https://orcid.org/0000-0002-1460-322X"},"institutions":[{"id":"https://openalex.org/I199172307","display_name":"Columbus State University","ror":"https://ror.org/002nf6z37","country_code":"US","type":"education","lineage":["https://openalex.org/I199172307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Zhou","raw_affiliation_strings":["TSYS School of Computer Science, Columbus State University, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TSYS School of Computer Science, Columbus State University, GA, USA","institution_ids":["https://openalex.org/I199172307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079326914","display_name":"Yifeng Zhu","orcid":"https://orcid.org/0000-0001-7438-8149"},"institutions":[{"id":"https://openalex.org/I7947594","display_name":"University of Maine","ror":"https://ror.org/01adr0w49","country_code":"US","type":"education","lineage":["https://openalex.org/I2802397601","https://openalex.org/I7947594"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifeng Zhu","raw_affiliation_strings":["School of Electrical and Computer Engineering, University of Maine, Orono, ME, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, University of Maine, Orono, ME, USA","institution_ids":["https://openalex.org/I7947594"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042766429","display_name":"Xiao Qin","orcid":"https://orcid.org/0000-0002-8345-3587"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Qin","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Auburn University, Alabama, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Auburn University, Alabama, USA","institution_ids":["https://openalex.org/I82497590"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3261,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.93190811,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"17","issue":"4","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.9998999834060669,"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":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9973000288009644,"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/T10237","display_name":"Cryptography and Data Security","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/backup","display_name":"Backup","score":0.9326834678649902},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.8844024538993835},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.8792776465415955},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8283865451812744},{"id":"https://openalex.org/keywords/container","display_name":"Container (type theory)","score":0.5143364667892456},{"id":"https://openalex.org/keywords/fingerprint-recognition","display_name":"Fingerprint recognition","score":0.4370255768299103},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38282641768455505},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2905444800853729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2033502757549286},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06162959337234497}],"concepts":[{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.9326834678649902},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.8844024538993835},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.8792776465415955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8283865451812744},{"id":"https://openalex.org/C2781018962","wikidata":"https://www.wikidata.org/wiki/Q5164884","display_name":"Container (type theory)","level":2,"score":0.5143364667892456},{"id":"https://openalex.org/C168406668","wikidata":"https://www.wikidata.org/wiki/Q178022","display_name":"Fingerprint recognition","level":3,"score":0.4370255768299103},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38282641768455505},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2905444800853729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2033502757549286},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06162959337234497},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3459626","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459626","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8320700071","display_name":"\u57fa\u4e8e\u70ed\u5faa\u73af\u7684\u5927\u89c4\u6a21\u5206\u5e03\u5f0f\u5b58\u50a8\u7cfb\u7edf\u6570\u636e\u653e\u7f6e\u7b56\u7565\u7814\u7a76","funder_award_id":"62072214","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W120798314","https://openalex.org/W1437397736","https://openalex.org/W1969126835","https://openalex.org/W1969949656","https://openalex.org/W1979162731","https://openalex.org/W1997349095","https://openalex.org/W2027016098","https://openalex.org/W2033062224","https://openalex.org/W2067545467","https://openalex.org/W2123845384","https://openalex.org/W2147407897","https://openalex.org/W2156468933","https://openalex.org/W2172174733","https://openalex.org/W2285144687","https://openalex.org/W2792376237","https://openalex.org/W2912574597","https://openalex.org/W2986445348","https://openalex.org/W2998583855"],"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/W3014822659","https://openalex.org/W2117826006"],"abstract_inverted_index":{"Data":[0],"deduplication":[1],"techniques":[2],"construct":[3],"an":[4,287],"index":[5,23,93,215,361],"consisting":[6],"of":[7,16,21,86,145,177,189,281,334,359,394],"fingerprint":[8,78,98,101,105,131,136,140,144,155,164,170,183,201,211,229],"entries":[9,123,171,184,212,230],"to":[10,53,82,126,197,216,231,250,299,319,391,410,415],"identify":[11,269,320],"and":[12,25,103,220,323,364,371,400],"eliminate":[13],"duplicated":[14,31,271],"copies":[15],"repeating":[17],"data.":[18],"The":[19],"bottleneck":[20],"disk-based":[22],"lookup":[24],"data":[26,38,55],"fragmentation":[27],"caused":[28],"by":[29,362,389,408],"eliminating":[30],"chunks":[32,48,253,272,322],"are":[33,129,304],"two":[34,60,69,311],"challenging":[35],"issues":[36],"in":[37],"deduplication.":[39],"Deduplication-based":[40],"backup":[41,88,147,235,387],"systems":[42],"generally":[43],"employ":[44],"containers":[45,128],"storing":[46],"contiguous":[47],"together":[49],"with":[50,109,378,396],"their":[51],"fingerprints":[52,303],"preserve":[54],"locality":[56],"for":[57,173,186,260],"alleviating":[58,242],"the":[59,84,92,134,178,181,187,190,214,261,274,282,324,330,335,345,355,360,368,372,379,385,397,403,416,423],"issues,":[61,70],"which":[62,300],"is":[63,116,150,159],"still":[64],"inadequate.":[65],"To":[66,277],"address":[67],"these":[68],"we":[71,285],"propose":[72,286],"a":[73,113,118,139,153,162,174,199,233,248,264,296,392],"container":[74,108,120],"utilization":[75,110,219],"based":[76],"hot":[77,97,130,169,200,302],"entry":[79,141,202],"distilling":[80,203],"strategy":[81,290],"improve":[83,217],"performance":[85],"deduplication-based":[87,234],"systems.":[89],"We":[90,166],"divide":[91],"into":[94,344],"three":[95],"parts:":[96],"entries,":[99,102,137],"fragmented":[100,154,228,239,252,275,325],"useless":[104,163,210],"entries.":[106,132],"A":[107],"smaller":[111],"than":[112],"given":[114],"threshold":[115],"called":[117,291],"sparse":[119],".":[121,207,293],"Fingerprint":[122],"that":[124,168,263],"point":[125],"non-sparse":[127],"For":[133],"remaining":[135,182],"if":[138],"matches":[142],"any":[143],"forthcoming":[146],"chunks,":[148,240],"it":[149,158,413],"classified":[151,160],"as":[152,161,254],"entry.":[156,165],"Otherwise,":[157],"observe":[167],"account":[172,185],"small":[175],"part":[176],"index,":[179],"whereas":[180],"majority":[188],"index.":[191],"This":[192,257],"intriguing":[193],"observation":[194],"inspires":[195],"us":[196],"develop":[198],"approach":[204,353],"named":[205],"HID":[206,208,226,246,289],"segregates":[209],"from":[213],"memory":[218,357],"bypass":[221],"disk":[222,317,405],"accesses.":[223],"In":[224,306],"addition,":[225],"separates":[227],"make":[232],"system":[236],"directly":[237,268],"rewrite":[238],"thereby":[241],"adverse":[243],"fragmentation.":[244],"Moreover,":[245],"introduces":[247],"feature":[249,258],"treat":[251],"unique":[255,321],"chunks.":[256],"compensates":[259],"shortcoming":[262],"Bloom":[265,297,337],"filter":[266],"cannot":[267],"certain":[270],"(i.e.,":[273],"chunks).":[276],"take":[278],"full":[279],"advantage":[280],"preceding":[283],"feature,":[284],"evolved":[288],"EHID":[292,294,309,315,328,343,383,401,419],"incorporates":[295],"filter,":[298],"only":[301],"mapped.":[305],"doing":[307],"so,":[308],"exhibits":[310],"salient":[312,340],"features:":[313],"(i)":[314],"avoids":[316],"accesses":[318],"chunks;":[326],"(ii)":[327],"slashes":[329],"false":[331],"positive":[332],"rate":[333],"integrated":[336],"filter.":[338],"These":[339],"features":[341],"push":[342],"high-efficiency":[346],"mode.":[347],"Our":[348],"experimental":[349],"results":[350],"show":[351],"our":[352],"reduces":[354,402],"average":[356,386,404],"overhead":[358],"34.11%":[363],"25.13%":[365],"when":[366,412],"using":[367],"Linux":[369,398],"dataset":[370],"FSL":[373,417],"dataset,":[374,399],"respectively.":[375],"Furthermore,":[376],"compared":[377],"state-of-the-art":[380],"method":[381],"HAR,":[382],"boosts":[384],"throughput":[388],"up":[390,409],"factor":[393],"2.25":[395],"I/O":[406],"traffic":[407],"66.21%":[411],"comes":[414],"dataset.":[418],"also":[420],"marginally":[421],"improves":[422],"system's":[424],"restore":[425],"performance.":[426]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}