{"id":"https://openalex.org/W4309561352","doi":"https://doi.org/10.1145/3568426","title":"InDe: An Inline Data Deduplication Approach via Adaptive Detection of Valid Container Utilization","display_name":"InDe: An Inline Data Deduplication Approach via Adaptive Detection of Valid Container Utilization","publication_year":2022,"publication_date":"2022-11-19","ids":{"openalex":"https://openalex.org/W4309561352","doi":"https://doi.org/10.1145/3568426"},"language":"en","primary_location":{"id":"doi:10.1145/3568426","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3568426","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/A5023813000","display_name":"Lifang Lin","orcid":"https://orcid.org/0000-0003-1991-0293"},"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":true,"raw_author_name":"Lifang Lin","raw_affiliation_strings":["Department of Computer Science, Jinan University, Guangzhou, Guangdong Province, China"],"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"],"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/0000-0003-0020-847X"},"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"],"affiliations":[{"raw_affiliation_string":"TSYS School of Computer Science, Columbus State University, GA, USA","institution_ids":["https://openalex.org/I199172307"]}]},{"author_position":"last","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":["Department of Electrical and Computer Engineering, University of Maine, Orono, ME, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Maine, Orono, ME, USA","institution_ids":["https://openalex.org/I7947594"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023813000"],"corresponding_institution_ids":["https://openalex.org/I159948400"],"apc_list":null,"apc_paid":null,"fwci":1.8452,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.86078749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"19","issue":"1","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9983999729156494,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9919999837875366,"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":0.8621129989624023},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.8419878482818604},{"id":"https://openalex.org/keywords/backup","display_name":"Backup","score":0.755466639995575},{"id":"https://openalex.org/keywords/container","display_name":"Container (type theory)","score":0.7016078233718872},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.5904948711395264},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5110408067703247},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4118974804878235},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3364362120628357},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.27768468856811523},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09405690431594849}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8621129989624023},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.8419878482818604},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.755466639995575},{"id":"https://openalex.org/C2781018962","wikidata":"https://www.wikidata.org/wiki/Q5164884","display_name":"Container (type theory)","level":2,"score":0.7016078233718872},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.5904948711395264},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5110408067703247},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4118974804878235},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3364362120628357},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27768468856811523},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09405690431594849},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"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:10.1145/3568426","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3568426","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/G5985830393","display_name":null,"funder_award_id":"2021B1515120048","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G8320700071","display_name":null,"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"},{"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":23,"referenced_works":["https://openalex.org/W120798314","https://openalex.org/W1437397736","https://openalex.org/W2010150514","https://openalex.org/W2031725441","https://openalex.org/W2033062224","https://openalex.org/W2069003154","https://openalex.org/W2088383790","https://openalex.org/W2142606934","https://openalex.org/W2245628559","https://openalex.org/W2345185127","https://openalex.org/W2625784407","https://openalex.org/W2758980874","https://openalex.org/W2792376237","https://openalex.org/W2800515890","https://openalex.org/W2810972659","https://openalex.org/W2884779095","https://openalex.org/W2912893741","https://openalex.org/W3014193728","https://openalex.org/W3046779769","https://openalex.org/W3158219979","https://openalex.org/W3207131661","https://openalex.org/W4240241513","https://openalex.org/W4285776552"],"related_works":["https://openalex.org/W3183948672","https://openalex.org/W1531601525","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"],"abstract_inverted_index":{"Inline":[0],"deduplication":[1,117],"removes":[2],"redundant":[3],"data":[4,8,19,31,76,79],"in":[5,106,144,274,281],"real-time":[6],"as":[7,50],"is":[9,63],"being":[10],"sent":[11],"to":[12,37,43,89,130,155,176,194,199,214],"the":[13,39,73,138,150,157,181,200,208,227,235,262,282,310,318],"storage":[14,120],"system.":[15],"However,":[16],"it":[17],"causes":[18],"fragmentation:":[20],"logically":[21],"consecutive":[22],"chunks":[23,49,52,105,154,218],"are":[24,84],"physically":[25],"scattered":[26],"across":[27],"various":[28],"containers":[29,96,179,221,267,280],"after":[30],"deduplication.":[32],"Many":[33],"rewrite":[34,186,195,242],"algorithms":[35,58,303],"aim":[36],"alleviate":[38],"performance":[40,159],"degradation":[41],"due":[42],"fragmentation":[44],"by":[45,268,313],"rewriting":[46],"fragmented":[47,64],"duplicate":[48,217],"unique":[51],"into":[53],"new":[54],"containers.":[55,108,197],"Unfortunately,":[56],"these":[57],"determine":[59],"whether":[60],"a":[61,67,100,127,185,257],"chunk":[62],"based":[65,246],"on":[66,247],"simple":[68],"pre-set":[69],"fixed":[70],"value,":[71],"ignoring":[72],"variance":[74],"of":[75,94,103,140,152,203,210,234,251,261,265,271],"characteristics":[77],"between":[78],"segments.":[80],"Accordingly,":[81],"when":[82],"backups":[83],"restored,":[85],"they":[86],"often":[87],"fail":[88],"select":[90],"an":[91,115,167],"appropriate":[92,178],"set":[93],"old":[95,141,211,266],"for":[97,119,180,222],"rewrite,":[98],"generating":[99],"substantial":[101],"number":[102,139,209],"invalid":[104],"retrieved":[107],"To":[109,230],"address":[110],"this":[111],"issue,":[112],"we":[113,238],"propose":[114,240],"inline":[116],"approach":[118],"systems,":[121],"called":[122,244],"InDe":[123,147,288],",":[124,175],"which":[125],"uses":[126],"greedy":[128],"algorithm":[129,187,243],"detect":[131],"valid":[132,170,191,252,263],"container":[133,142,171,192,212,253],"utilization":[134,193,264],"and":[135,277,305],"dynamically":[136,206],"adjusts":[137,207],"references":[143,213],"each":[145,223],"segment.":[146],"fully":[148],"leverages":[149],"distribution":[151,202],"duplicated":[153],"improve":[156],"restore":[158,228,311],"while":[160,315],"maintaining":[161],"high":[162],"backup":[163,292,320],"performance.":[164,321],"We":[165,183,285],"define":[166],"effectiveness":[168],"metric,":[169],"referenced":[172,279],"counts":[173],"(VCRC)":[174],"identify":[177],"rewrite.":[182],"design":[184],"F-greedy":[188,205],"that":[189,298],"detects":[190],"low-VCRC":[196],"According":[198],"VCRC":[201],"containers,":[204],"only":[215],"share":[216],"with":[219,300],"high-utilization":[220],"segment,":[224],"thereby":[225],"improving":[226],"speed.":[229],"take":[231],"full":[232],"advantage":[233],"above":[236],"features,":[237],"further":[239],"another":[241],"F-greedy+":[245,255],"adaptive":[248],"interval":[249],"detection":[250],"utilization.":[254],"makes":[256],"more":[258],"accurate":[259],"estimation":[260],"detecting":[269],"trends":[270],"VCRC\u2019s":[272],"change":[273],"two":[275,301],"directions":[276],"selecting":[278],"global":[283],"scope.":[284],"quantitatively":[286],"evaluate":[287],"using":[289],"three":[290],"real-world":[291],"workloads.":[293],"The":[294],"experimental":[295],"results":[296],"show":[297],"compared":[299],"state-of-the-art":[302],"(Capping":[304],"SMR),":[306],"our":[307],"scheme":[308],"improves":[309],"speed":[312],"1.3\u00d7\u20132.4\u00d7":[314],"achieving":[316],"almost":[317],"same":[319]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
