{"id":"https://openalex.org/W2990640343","doi":"https://doi.org/10.4236/jsea.2019.1211029","title":"dCACH: Content Aware Clustered and Hierarchical Distributed Deduplication","display_name":"dCACH: Content Aware Clustered and Hierarchical Distributed Deduplication","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2990640343","doi":"https://doi.org/10.4236/jsea.2019.1211029","mag":"2990640343"},"language":"en","primary_location":{"id":"doi:10.4236/jsea.2019.1211029","doi":"https://doi.org/10.4236/jsea.2019.1211029","is_oa":true,"landing_page_url":"https://doi.org/10.4236/jsea.2019.1211029","pdf_url":"https://content.scirp.org/pdf/jsea_2019112615581440.pdf","source":{"id":"https://openalex.org/S33096572","display_name":"Journal of Software Engineering and Applications","issn_l":"1945-3116","issn":["1945-3116","1945-3124"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":"https://openalex.org/P4310320480","host_organization_name":"Scientific Research Publishing","host_organization_lineage":["https://openalex.org/P4310320480"],"host_organization_lineage_names":["Scientific Research Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software Engineering and Applications","raw_type":"journal-article"},"parent_works":[],"lineage":["https://openalex.org/W2990640343"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://content.scirp.org/pdf/jsea_2019112615581440.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017569694","display_name":"Girum Dagnaw","orcid":"https://orcid.org/0000-0001-9442-8857","observed_orcids":["https://orcid.org/0000-0001-9442-8857"]},"institutions":[{"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"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Girum Dagnaw","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan National Laboratory for Optoelectronics, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan National Laboratory for Optoelectronics, Wuhan, China","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015061573","display_name":"Ke Zhou","orcid":"https://orcid.org/0000-0002-2161-8796","observed_orcids":["https://orcid.org/0000-0002-2161-8796","https://orcid.org/0000-0003-3346-2749"]},"institutions":[{"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"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Zhou","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan National Laboratory for Optoelectronics, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan National Laboratory for Optoelectronics, Wuhan, China","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100403939","display_name":"Hua Wang","orcid":"https://orcid.org/0000-0002-2798-7322","observed_orcids":["https://orcid.org/0000-0002-2798-7322"]},"institutions":[{"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"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Wang","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan National Laboratory for Optoelectronics, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan National Laboratory for Optoelectronics, Wuhan, China","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2532,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.5721717,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":"12","issue":"11","first_page":"460","last_page":"490"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9976000189781189,"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":0.9976000189781189,"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/T11269","display_name":"Algorithms and Data Compression","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.0006000000284984708,"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/bloom-filter","display_name":"Bloom filter","score":0.8220000267028809},{"id":"https://openalex.org/keywords/backup-storage","display_name":"backup storage","score":0.4880000054836273},{"id":"https://openalex.org/keywords/locality","display_name":"locality","score":0.39800000190734863},{"id":"https://openalex.org/keywords/communication-overhead","display_name":"communication overhead","score":0.5139999985694885}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.8328558206558228},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.832778811454773},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.7977883815765381},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6198154091835022},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5539796948432922},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5304996967315674},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.46883243322372437},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.466019868850708},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.44194701313972473},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4271194636821747},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.42289304733276367},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3281855583190918},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22722795605659485},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.11809483170509338},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4236/jsea.2019.1211029","doi":"https://doi.org/10.4236/jsea.2019.1211029","is_oa":true,"landing_page_url":"https://doi.org/10.4236/jsea.2019.1211029","pdf_url":"https://content.scirp.org/pdf/jsea_2019112615581440.pdf","source":{"id":"https://openalex.org/S33096572","display_name":"Journal of Software Engineering and Applications","issn_l":"1945-3116","issn":["1945-3116","1945-3124"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":"https://openalex.org/P4310320480","host_organization_name":"Scientific Research Publishing","host_organization_lineage":["https://openalex.org/P4310320480"],"host_organization_lineage_names":["Scientific Research Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software Engineering and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.4236/jsea.2019.1211029","doi":"https://doi.org/10.4236/jsea.2019.1211029","is_oa":true,"landing_page_url":"https://doi.org/10.4236/jsea.2019.1211029","pdf_url":"https://content.scirp.org/pdf/jsea_2019112615581440.pdf","source":{"id":"https://openalex.org/S33096572","display_name":"Journal of Software Engineering and Applications","issn_l":"1945-3116","issn":["1945-3116","1945-3124"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":"https://openalex.org/P4310320480","host_organization_name":"Scientific Research Publishing","host_organization_lineage":["https://openalex.org/P4310320480"],"host_organization_lineage_names":["Scientific Research Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software Engineering and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5378999710083008,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G2413230818","display_name":null,"funder_award_id":"61821003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4064077786","display_name":null,"funder_award_id":"2016YFB08004 02","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5064772619","display_name":null,"funder_award_id":"No. 61821003","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2990640343.pdf","grobid_xml":"https://content.openalex.org/works/W2990640343.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W5335935","https://openalex.org/W26020480","https://openalex.org/W69510097","https://openalex.org/W141925461","https://openalex.org/W200233886","https://openalex.org/W1490390347","https://openalex.org/W1545493325","https://openalex.org/W1969067141","https://openalex.org/W1969126835","https://openalex.org/W1974299302","https://openalex.org/W1991800036","https://openalex.org/W1993284846","https://openalex.org/W2012359782","https://openalex.org/W2041741449","https://openalex.org/W2047484077","https://openalex.org/W2052894589","https://openalex.org/W2056980397","https://openalex.org/W2081193615","https://openalex.org/W2123845384","https://openalex.org/W2126116376","https://openalex.org/W2132627996","https://openalex.org/W2133806194","https://openalex.org/W2133893097","https://openalex.org/W2134792144","https://openalex.org/W2157870327","https://openalex.org/W2158935814","https://openalex.org/W2160127232","https://openalex.org/W2161273259","https://openalex.org/W2281363974","https://openalex.org/W2345185127","https://openalex.org/W2346147088","https://openalex.org/W2475932436","https://openalex.org/W2522160996","https://openalex.org/W2621279243","https://openalex.org/W2793900539","https://openalex.org/W2800515890","https://openalex.org/W2810972659","https://openalex.org/W2876349725","https://openalex.org/W2916086000","https://openalex.org/W2917755701","https://openalex.org/W3145042860","https://openalex.org/W3150003982"],"related_works":["https://openalex.org/W2917755701","https://openalex.org/W69510097","https://openalex.org/W2378402762","https://openalex.org/W3102408035","https://openalex.org/W2188247367","https://openalex.org/W1929726975","https://openalex.org/W2935106878","https://openalex.org/W2026837079","https://openalex.org/W2055899630","https://openalex.org/W4320061018"],"abstract_inverted_index":{"In":[0,72],"deduplication,":[1],"index-lookup":[2],"disk":[3],"bottleneck":[4],"is":[5,28,49,194,254,270,289],"a":[6,38,78,87,104,120,213,257,261,280,291,294],"major":[7],"obstacle":[8],"which":[9,85,131],"limits":[10],"the":[11,20,52,133,141,175,181,200,206,224,275],"throughput":[12],"of":[13,22,40,89,106,109,145,157,177,215,226,277],"backup":[14],"processes.":[15],"One":[16],"way":[17,48],"to":[18,29,50,154,173,219,243,249,272],"minimize":[19],"effect":[21,65],"this":[23,59,73],"issue":[24],"and":[25,44,66,81,93,123,127,159,187,196,209,237],"boost":[26],"speed":[27,276],"use":[30,225],"very":[31],"high":[32,69],"course-grained":[33],"chunks":[34,149],"for":[35,103,116,229],"deduplication":[36,53,83,97,172,297],"at":[37,180,205],"cost":[39,239],"low":[41,235],"storage":[42,62,134,221],"saving":[43],"limited":[45],"scalability.":[46],"Another":[47],"distribute":[51],"process":[54],"among":[55,148],"multiple":[56],"nodes":[57],"but":[58],"approach":[60],"introduces":[61],"node":[63,135,251,296],"island":[64,136],"also":[67],"incurs":[68],"communication":[70,236,282],"cost.":[71],"paper,":[74],"we":[75],"explore":[76],"dCACH,":[77],"content-aware":[79],"clustered":[80],"hierarchical":[82,171],"system,":[84],"implements":[86,170],"hybrid":[88],"inline":[90],"course":[91],"grained":[92],"offline":[94],"fine-grained":[95],"distributed":[96,264],"where":[98,184],"routing":[99,130,212],"decisions":[100],"are":[101,191],"made":[102],"set":[105,214],"files":[107,158,186,217],"instead":[108],"single":[110,250,295],"files.":[111],"It":[112,169,269],"utilizes":[113],"bloom":[114,227],"filters":[115],"detecting":[117],"similarity":[118,230],"between":[119,232],"data":[121,125],"stream":[122],"previous":[124],"streams":[126,233],"performs":[128],"stateful":[129],"solves":[132],"problem.":[137],"Moreover,":[138],"it":[139,241],"exploits":[140],"negligibly":[142],"small":[143],"amount":[144],"content":[146],"shared":[147],"from":[150],"different":[151],"file":[152],"types":[153],"create":[155],"groups":[156],"deduplicate":[160],"each":[161],"group":[162],"in":[163],"their":[164],"own":[165],"fingerprint":[166,178],"index":[167],"space.":[168],"reduce":[174],"size":[176],"indexes":[179],"global":[182,207],"level,":[183],"only":[185],"big":[188,201],"sized":[189,202],"segments":[190,203],"deduplicated.":[192],"Locality":[193],"created":[195],"exploited":[197],"first":[198],"using":[199,256],"deduplicated":[204],"level":[208],"second":[210],"by":[211],"consecutive":[216],"together":[218],"one":[220],"node.":[222],"Furthermore,":[223],"filter":[228],"detection":[231],"has":[234],"computation":[238],"while":[240,284],"enables":[242],"achieve":[244],"duplicate":[245,286],"elimination":[246,287],"performance":[247],"comparable":[248],"deduplication.":[252],"dCACH":[253],"evaluated":[255],"prototype":[258],"deployed":[259],"on":[260,290],"server":[262],"environment":[263],"over":[265],"four":[266],"separate":[267],"machines.":[268],"shown":[271],"have":[273],"10\u00d7":[274],"Extreme_Binn":[278],"with":[279,293],"minimal":[281],"overhead,":[283],"its":[285],"effectiveness":[288],"par":[292],"system.":[298]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2019-12-05T00:00:00"}
