{"id":"https://openalex.org/W4285326791","doi":"https://doi.org/10.1109/icpads53394.2021.00042","title":"Improving Restore Performance of Deduplication Systems via a Greedy Rewriting Scheme","display_name":"Improving Restore Performance of Deduplication Systems via a Greedy Rewriting Scheme","publication_year":2021,"publication_date":"2021-12-01","ids":{"openalex":"https://openalex.org/W4285326791","doi":"https://doi.org/10.1109/icpads53394.2021.00042"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads53394.2021.00042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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":false,"raw_author_name":"Lifang Lin","raw_affiliation_strings":["Jinan University,Department of Computer Science,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"Jinan University,Department of Computer Science,Guangzhou,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"]},{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhui Deng","raw_affiliation_strings":["Jinan University,Department of Computer Science,Guangzhou,China","Wuhan National Laboratory for Optoelectronics, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Jinan University,Department of Computer Science,Guangzhou,China","institution_ids":["https://openalex.org/I159948400"]},{"raw_affiliation_string":"Wuhan National Laboratory for Optoelectronics, Wuhan, China","institution_ids":["https://openalex.org/I4210138186"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100753053","display_name":"Yi Zhou","orcid":null},"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, Columbus, US"],"affiliations":[{"raw_affiliation_string":"TSYS School of Computer Science Columbus State University, Columbus, US","institution_ids":["https://openalex.org/I199172307"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":57},"biblio":{"volume":null,"issue":null,"first_page":"291","last_page":"298"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9993,"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":0.9993,"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":0.9992,"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":0.9969,"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":0.62228316}],"concepts":[{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.86005485},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8031949},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.799217},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.62228316},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.53611296},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.53176624},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.48167336},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.46449235},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.38717023},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.38504538},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3189631},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.23139027},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13828158},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12899074},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.122011274},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads53394.2021.00042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":32,"referenced_works":["https://openalex.org/W120798314","https://openalex.org/W1437397736","https://openalex.org/W1553098517","https://openalex.org/W1576397915","https://openalex.org/W1856507064","https://openalex.org/W1901266868","https://openalex.org/W1929726975","https://openalex.org/W1969126835","https://openalex.org/W200233886","https://openalex.org/W2004286258","https://openalex.org/W2010150514","https://openalex.org/W2027016098","https://openalex.org/W2033062224","https://openalex.org/W2054570356","https://openalex.org/W2119172358","https://openalex.org/W2158935814","https://openalex.org/W2172174733","https://openalex.org/W2285144687","https://openalex.org/W24740120","https://openalex.org/W2605532879","https://openalex.org/W2606291150","https://openalex.org/W2741255062","https://openalex.org/W2758980874","https://openalex.org/W2791757048","https://openalex.org/W2792376237","https://openalex.org/W2810972659","https://openalex.org/W2915462855","https://openalex.org/W2986445348","https://openalex.org/W3158219979","https://openalex.org/W3207131661","https://openalex.org/W69510097","https://openalex.org/W939203190"],"related_works":["https://openalex.org/W4301155776","https://openalex.org/W4285245558","https://openalex.org/W3183948672","https://openalex.org/W2952411620","https://openalex.org/W2375056709","https://openalex.org/W2348132657","https://openalex.org/W2048606985","https://openalex.org/W2012359782","https://openalex.org/W1531601525","https://openalex.org/W1437397736"],"abstract_inverted_index":{"Data":[0],"deduplication":[1],"has":[2],"been":[3],"widely":[4],"used":[5],"to":[6,37,56,68,91,133,140],"improve":[7,92],"storage":[8,161],"space":[9],"utilization,":[10],"however,":[11],"it":[12],"is":[13],"baffled":[14],"by":[15,44,186],"data":[16],"fragmen-tation:":[17],"logically":[18],"consecutive":[19],"chunks":[20,32,71],"physically":[21],"scattered":[22],"across":[23],"various":[24],"containers.":[25,143],"Many":[26],"rewriting":[27,29,89],"schemes,":[28],"fragment-ed":[30],"duplicate":[31],"into":[33],"new":[34],"containers,":[35],"attempt":[36],"alleviate":[38],"the":[39,58,74,115,130,134,179,183],"restore":[40,93,156,180],"performance":[41,94],"degradation":[42],"caused":[43],"fragmentation.":[45],"Unfortunately,":[46],"these":[47],"schemes":[48,172],"rely":[49],"on":[50,148],"a":[51,86,122],"fixed":[52],"threshold":[53,88,131],"and":[54,160,174],"fail":[55],"choose":[57],"appropriate":[59,116],"set":[60],"of":[61,136,155,182],"old":[62],"containers":[63,76,117],"for":[64,118],"rewriting,":[65],"which":[66],"leads":[67],"substantial":[69],"redundant":[70],"existing":[72],"in":[73,153],"retrieved":[75],"when":[77],"restoring":[78],"backups.":[79],"To":[80],"address":[81],"this":[82],"issue,":[83],"we":[84],"propose":[85],"flexible":[87],"scheme":[90,177],"while":[95,190],"maintaining":[96],"high":[97],"backup":[98,151,158,193],"performance.":[99,194],"We":[100,120,144],"define":[101],"an":[102],"effectiveness":[103],"metric":[104],"-":[105,111,188],"valid":[106],"container":[107],"reference":[108],"counts":[109],"(VCRC)":[110],"that":[112,127,167],"facilitates":[113],"identifying":[114],"rewriting.":[119],"design":[121],"greedy-algorithm-based":[123],"algorithm":[124],"called":[125],"F-greedy":[126,147],"dynamically":[128],"adjusts":[129],"according":[132],"distribution":[135],"containers'":[137],"VCRC,":[138],"aiming":[139],"rewrite":[141],"low-VCRC":[142],"quantitatively":[145],"evaluate":[146],"three":[149],"real-world":[150],"datasets":[152],"terms":[154],"performance,":[157,159],"overhead.":[162],"The":[163],"empirical":[164],"results":[165],"show":[166],"compared":[168],"with":[169],"two":[170],"state-of-the-art":[171],"(Capping":[173],"SMR),":[175],"our":[176],"improves":[178],"speed":[181],"exiting":[184],"algorithms":[185],"1.3x":[187],"2.4x":[189],"achieving":[191],"similar":[192]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4285326791","counts_by_year":[],"updated_date":"2025-01-02T10:12:12.161239","created_date":"2022-07-14"}