{"id":"https://openalex.org/W2133806194","doi":"https://doi.org/10.1109/msst.2010.5496987","title":"MAD2: A scalable high-throughput exact deduplication approach for network backup services","display_name":"MAD2: A scalable high-throughput exact deduplication approach for network backup services","publication_year":2010,"publication_date":"2010-05-01","ids":{"openalex":"https://openalex.org/W2133806194","doi":"https://doi.org/10.1109/msst.2010.5496987","mag":"2133806194"},"language":"en","primary_location":{"id":"doi:10.1109/msst.2010.5496987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msst.2010.5496987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th Symposium on Mass Storage Systems and Technologies (MSST)","raw_type":"proceedings-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/A5029818101","display_name":"Jiansheng Wei","orcid":"https://orcid.org/0000-0001-8518-4088"},"institutions":[{"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"]},{"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":true,"raw_author_name":"Jiansheng Wei","raw_affiliation_strings":["School of Computer, Huazhong University of Science and Technology, Wuhan, China","Wuhan National Laboratory of Optoelectronics, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Wuhan National Laboratory of Optoelectronics, Wuhan, China","institution_ids":["https://openalex.org/I4210138186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054285749","display_name":"Hong Jiang","orcid":"https://orcid.org/0000-0002-1477-9751"},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Jiang","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Nebraska, Lincoln, Lincolnshire, NE, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Nebraska, Lincoln, Lincolnshire, NE, USA","institution_ids":["https://openalex.org/I114395901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015061573","display_name":"Ke Zhou","orcid":"https://orcid.org/0000-0002-2161-8796"},"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":["School of Computer, Huazhong University of Science and Technology, Wuhan, China","Wuhan National Laboratory of Optoelectronics, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Wuhan National Laboratory of Optoelectronics, Wuhan, China","institution_ids":["https://openalex.org/I4210138186"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057421680","display_name":"Dan Feng","orcid":"https://orcid.org/0000-0002-4674-6006"},"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":"Dan Feng","raw_affiliation_strings":["School of Computer, Huazhong University of Science and Technology, Wuhan, China","Wuhan National Laboratory of Optoelectronics, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Wuhan National Laboratory of Optoelectronics, Wuhan, China","institution_ids":["https://openalex.org/I4210138186"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5029818101"],"corresponding_institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":8.9411,"has_fulltext":false,"cited_by_count":89,"citation_normalized_percentile":{"value":0.98084619,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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":0.996399998664856,"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":0.9083031415939331},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8302943706512451},{"id":"https://openalex.org/keywords/backup","display_name":"Backup","score":0.7281625866889954},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6396727561950684},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5831275582313538},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.5079999566078186},{"id":"https://openalex.org/keywords/backup-software","display_name":"Backup software","score":0.5004732608795166},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.46363040804862976},{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.4592052102088928},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.4344102144241333},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34735071659088135},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2994784116744995},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24447166919708252},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.0887683629989624}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9083031415939331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8302943706512451},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.7281625866889954},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6396727561950684},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5831275582313538},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.5079999566078186},{"id":"https://openalex.org/C503016453","wikidata":"https://www.wikidata.org/wiki/Q4839801","display_name":"Backup software","level":3,"score":0.5004732608795166},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.46363040804862976},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.4592052102088928},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.4344102144241333},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34735071659088135},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2994784116744995},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24447166919708252},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0887683629989624},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/msst.2010.5496987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msst.2010.5496987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th Symposium on Mass Storage Systems and Technologies (MSST)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.178.1535","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.178.1535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://storageconference.org/2010/Papers/MSST/Wei.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W24740120","https://openalex.org/W69510097","https://openalex.org/W162607394","https://openalex.org/W174289249","https://openalex.org/W200233886","https://openalex.org/W1490390347","https://openalex.org/W1508926177","https://openalex.org/W1536854407","https://openalex.org/W1576397915","https://openalex.org/W1587463421","https://openalex.org/W1609518033","https://openalex.org/W1614703486","https://openalex.org/W1847423537","https://openalex.org/W1969126835","https://openalex.org/W1971212200","https://openalex.org/W1975868314","https://openalex.org/W1993284846","https://openalex.org/W1993865637","https://openalex.org/W2026839093","https://openalex.org/W2028928922","https://openalex.org/W2053449578","https://openalex.org/W2056980397","https://openalex.org/W2094224023","https://openalex.org/W2095844164","https://openalex.org/W2107745473","https://openalex.org/W2121133177","https://openalex.org/W2123482462","https://openalex.org/W2123767107","https://openalex.org/W2123845384","https://openalex.org/W2131287008","https://openalex.org/W2132069633","https://openalex.org/W2132627996","https://openalex.org/W2134792144","https://openalex.org/W2140733653","https://openalex.org/W2149993626","https://openalex.org/W2151388636","https://openalex.org/W2156719566","https://openalex.org/W2158049821","https://openalex.org/W2160127232","https://openalex.org/W2162194245","https://openalex.org/W2163059190","https://openalex.org/W2167736695","https://openalex.org/W2167898414","https://openalex.org/W2170708842","https://openalex.org/W4243055721","https://openalex.org/W4243255773","https://openalex.org/W4246164361","https://openalex.org/W4253431371","https://openalex.org/W4254263397","https://openalex.org/W6601060166","https://openalex.org/W6602837329","https://openalex.org/W6606654109","https://openalex.org/W6607057542","https://openalex.org/W6608138927","https://openalex.org/W6629455298","https://openalex.org/W6630499100","https://openalex.org/W6632163548","https://openalex.org/W6634463810","https://openalex.org/W6636190696","https://openalex.org/W6638825795","https://openalex.org/W6663785121","https://openalex.org/W6679743691","https://openalex.org/W6679804201","https://openalex.org/W6680744948","https://openalex.org/W6681940154","https://openalex.org/W6684507281","https://openalex.org/W6684662427","https://openalex.org/W6685107875"],"related_works":["https://openalex.org/W2939925694","https://openalex.org/W2354454611","https://openalex.org/W2348132657","https://openalex.org/W4285245558","https://openalex.org/W2952411620","https://openalex.org/W2012359782","https://openalex.org/W4301155776","https://openalex.org/W2375056709","https://openalex.org/W2048606985","https://openalex.org/W1437397736"],"abstract_inverted_index":{"Deduplication":[0],"has":[1],"been":[2],"widely":[3],"used":[4,140],"in":[5,146,179,204,248],"disk-based":[6],"secondary":[7],"storage":[8,55,65,202,224,263],"systems":[9],"to":[10,32,70,75,117,141,159,169,181,195,208],"improve":[11],"space":[12],"efficiency.":[13],"However,":[14],"there":[15],"are":[16,68],"two":[17],"challenges":[18],"facing":[19],"scalable":[20,90],"high-throughput":[21,91],"deduplication":[22,49,93,120,246,251,255],"storage.":[23],"The":[24,51],"first":[25],"is":[26,53,177],"the":[27,33,42,48,54,78,83,105,110,119,143,222,243],"duplicate-lookup":[28],"disk":[29],"bottleneck":[30],"due":[31],"large":[34],"size":[35],"of":[36,225,250,257],"data":[37,62,102,144,164,186,198],"index":[38,158],"that":[39,67,231,239],"usually":[40],"exceeds":[41],"available":[43],"RAM":[44],"space,":[45],"which":[46],"limits":[47],"throughput.":[50],"second":[52],"node":[56],"island":[57],"effect":[58],"resulting":[59],"from":[60],"duplicate":[61,101],"among":[63,200],"multiple":[64,201],"nodes":[66,203],"difficult":[69],"eliminate.":[71],"Existing":[72],"approaches":[73,247],"fail":[74],"completely":[76],"eliminate":[77],"duplicates":[79],"while":[80],"simultaneously":[81],"addressing":[82],"challenges.":[84],"This":[85],"paper":[86],"proposes":[87],"MAD2,":[88],"a":[89,131,156,171,191,213,227,254],"exact":[92],"approach":[94,220],"for":[95,261],"network":[96,233],"backup":[97,206,234],"services.":[98,235],"MAD2":[99,127,149,180,189,219,240],"eliminates":[100],"both":[103],"at":[104,109,258],"file":[106],"level":[107,112],"and":[108,122,184],"chunk":[111],"by":[113],"employing":[114],"four":[115],"techniques":[116],"accelerate":[118],"process":[121],"evenly":[123,196],"distribute":[124,197],"data.":[125],"First,":[126],"organizes":[128],"fingerprints":[129],"into":[130],"Hash":[132],"Bucket":[133],"Matrix":[134],"(HBM),":[135],"whose":[136],"rows":[137],"can":[138],"be":[139],"preserve":[142],"locality":[145],"backups.":[147],"Second,":[148],"uses":[150],"Bloom":[151],"Filter":[152],"Array":[153],"(BFA)":[154],"as":[155],"quick":[157],"quickly":[160],"identify":[161],"non-duplicate":[162],"incoming":[163],"objects":[165,199],"or":[166],"indicate":[167],"where":[168],"find":[170],"possible":[172],"duplicate.":[173],"Third,":[174],"Dual":[175],"Cache":[176],"integrated":[178],"effectively":[182],"capture":[183],"exploit":[185],"locality.":[187],"Finally,":[188],"employs":[190],"DHT-based":[192],"Load-Balance":[193],"technique":[194],"their":[205],"sequences":[207],"further":[209],"enhance":[210],"performance":[211],"with":[212],"well-balanced":[214],"load.":[215],"We":[216],"evaluate":[217],"our":[218],"on":[221],"backend":[223],"B-Cloud,":[226],"research-oriented":[228],"distributed":[229],"system":[230],"provides":[232],"Experimental":[236],"results":[237],"show":[238],"significantly":[241],"outperforms":[242],"state-of-the-art":[244],"approximate":[245],"terms":[249],"efficiency,":[252],"supporting":[253],"throughput":[256],"least":[259],"100MB/s":[260],"each":[262],"component.":[264]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
