{"id":"https://openalex.org/W2058716449","doi":"https://doi.org/10.1631/jzus.c0910445","title":"Scalable high performance de-duplication backup via hash join","display_name":"Scalable high performance de-duplication backup via hash join","publication_year":2010,"publication_date":"2010-05-01","ids":{"openalex":"https://openalex.org/W2058716449","doi":"https://doi.org/10.1631/jzus.c0910445","mag":"2058716449"},"language":"en","primary_location":{"id":"doi:10.1631/jzus.c0910445","doi":"https://doi.org/10.1631/jzus.c0910445","is_oa":false,"landing_page_url":"https://doi.org/10.1631/jzus.c0910445","pdf_url":null,"source":{"id":"https://openalex.org/S199067057","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"1869-1951","issn":["1869-1951","1869-196X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1"],"host_organization":"https://openalex.org/P4310311937","host_organization_name":"Zhejiang University Press","host_organization_lineage":["https://openalex.org/P4310311937","https://openalex.org/P4360969398"],"host_organization_lineage_names":["Zhejiang University Press","Zhejiang University"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Zhejiang University SCIENCE C","raw_type":"journal-article"},"parent_works":[],"lineage":["https://openalex.org/W2058716449"],"child_works_count":0,"type":"article","is_traditional":true,"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/A5102939723","display_name":"Tianming Yang","orcid":"https://orcid.org/0000-0002-2119-548X","observed_orcids":["https://orcid.org/0000-0002-2119-548X"]},"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":"Tian-ming Yang","raw_affiliation_strings":["Wuhan National Laboratory for Optoelectronics, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, 430074, China","Huazhong University of Science and Technology,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan National Laboratory for Optoelectronics, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, 430074, China","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]},{"raw_affiliation_string":"Huazhong University of Science and Technology,","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057421680","display_name":"Dan Feng","orcid":"https://orcid.org/0000-0002-4674-6006","observed_orcids":["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":true,"raw_author_name":"Dan Feng","raw_affiliation_strings":["Wuhan National Laboratory for Optoelectronics, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, 430074, China","Huazhong University of Science and Technology,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan National Laboratory for Optoelectronics, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, 430074, China","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]},{"raw_affiliation_string":"Huazhong University of Science and Technology,","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110066710","display_name":"Zhongying Niu","orcid":null,"observed_orcids":[]},"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":"Zhong-ying Niu","raw_affiliation_strings":["Wuhan National Laboratory for Optoelectronics, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, 430074, China","Huazhong University of Science and Technology,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan National Laboratory for Optoelectronics, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, 430074, China","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]},{"raw_affiliation_string":"Huazhong University of Science and Technology,","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035494769","display_name":"Yaping Wan","orcid":"https://orcid.org/0000-0001-9215-5488","observed_orcids":["https://orcid.org/0000-0001-9215-5488","https://orcid.org/0009-0001-6274-7199"]},"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":"Ya-ping Wan","raw_affiliation_strings":["Wuhan National Laboratory for Optoelectronics, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, 430074, China","Huazhong University of Science and Technology,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan National Laboratory for Optoelectronics, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, 430074, China","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]},{"raw_affiliation_string":"Huazhong University of Science and Technology,","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5057421680"],"corresponding_institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.7292,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75772493,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":95},"biblio":{"volume":"11","issue":"5","first_page":"315","last_page":"327"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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/T10317","display_name":"Advanced Database Systems and Queries","score":9.999999747378752e-05,"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/hash-join","display_name":"hash join","score":0.9800000190734863},{"id":"https://openalex.org/keywords/distributed-storage","display_name":"distributed storage","score":0.890999972820282},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.5849999785423279},{"id":"https://openalex.org/keywords/write-throughput","display_name":"write throughput","score":0.7279999852180481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8644740581512451},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.8346123695373535},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.7498267889022827},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7468706369400024},{"id":"https://openalex.org/C503016453","wikidata":"https://www.wikidata.org/wiki/Q4839801","display_name":"Backup software","level":3,"score":0.6646772027015686},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5742725729942322},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5285099148750305},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5279079079627991},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.48508086800575256},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4619901776313782},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.440559983253479},{"id":"https://openalex.org/C188805328","wikidata":"https://www.wikidata.org/wiki/Q4060691","display_name":"Hash join","level":3,"score":0.4326152801513672},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.41073644161224365},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.35172325372695923},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2558613717556},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.17109635472297668},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09648913145065308},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1631/jzus.c0910445","doi":"https://doi.org/10.1631/jzus.c0910445","is_oa":false,"landing_page_url":"https://doi.org/10.1631/jzus.c0910445","pdf_url":null,"source":{"id":"https://openalex.org/S199067057","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"1869-1951","issn":["1869-1951","1869-196X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1"],"host_organization":"https://openalex.org/P4310311937","host_organization_name":"Zhejiang University Press","host_organization_lineage":["https://openalex.org/P4310311937","https://openalex.org/P4360969398"],"host_organization_lineage_names":["Zhejiang University Press","Zhejiang University"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Zhejiang University SCIENCE C","raw_type":"journal-article"},{"id":"mag:3149805267","doi":null,"is_oa":false,"landing_page_url":"http://www.cqvip.com/qk/89589X/201005/33797338.html","pdf_url":null,"source":{"id":"https://openalex.org/S199067057","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"1869-1951","issn":["1869-1951","1869-196X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1"],"host_organization":"https://openalex.org/P4310311937","host_organization_name":"Zhejiang University Press","host_organization_lineage":["https://openalex.org/P4310311937","https://openalex.org/P4360969398"],"host_organization_lineage_names":["Zhejiang University Press","Zhejiang University"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"\u6d59\u6c5f\u5927\u5b66\u5b66\u62a5\uff1aC\u5377\u82f1\u6587\u7248","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5378999710083008,"display_name":"Industry, innovation and infrastructure"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2757614","https://openalex.org/W24740120","https://openalex.org/W69510097","https://openalex.org/W200233886","https://openalex.org/W1508926177","https://openalex.org/W1514871965","https://openalex.org/W1576397915","https://openalex.org/W1969126835","https://openalex.org/W1993284846","https://openalex.org/W1995625544","https://openalex.org/W2035897349","https://openalex.org/W2056980397","https://openalex.org/W2123845384","https://openalex.org/W2149993626","https://openalex.org/W2156719566","https://openalex.org/W2160127232","https://openalex.org/W2169486917"],"related_works":["https://openalex.org/W2047484077","https://openalex.org/W2472668849","https://openalex.org/W7097006266","https://openalex.org/W2086762122","https://openalex.org/W1969126835","https://openalex.org/W2165676343","https://openalex.org/W2133806194","https://openalex.org/W2133901913","https://openalex.org/W4308536703","https://openalex.org/W2107551255"],"abstract_inverted_index":{"Apart":[0],"from":[1,61],"high":[2,13,15,116],"space":[3],"efficiency,":[4],"other":[5],"demanding":[6],"requirements":[7],"for":[8,19,84],"enterprise":[9],"de-duplication":[10,48,74,88,140],"backup":[11,75,89,141],"are":[12],"performance,":[14],"scalability,":[16],"and":[17,82,100,107,130,151,156],"availability":[18],"large-scale":[20,155],"distributed":[21,149,157],"environments.":[22],"The":[23],"main":[24],"challenge":[25],"is":[26,146],"reducing":[27],"the":[28,40,91,97],"significant":[29],"disk":[30,41,57,102,112],"input/output":[31],"(I/O)":[32],"overhead":[33],"as":[34],"a":[35,72,134],"result":[36],"of":[37,104,136],"constantly":[38],"accessing":[39],"to":[42,55,78,138,148,154],"identify":[43],"duplicate":[44,53,65],"chunks.":[45],"Existing":[46],"inline":[47],"approaches":[49],"mainly":[50],"rely":[51],"on":[52],"locality":[54,66],"avoid":[56],"bottleneck,":[58],"thus":[59,152],"suffering":[60],"degradation":[62],"under":[63],"poor":[64],"workload.":[67],"This":[68],"paper":[69],"presents":[70],"Chunkfarm,":[71],"post-processing":[73],"system":[76],"designed":[77],"improve":[79],"capacity,":[80],"throughput,":[81],"scalability":[83],"de-duplication.":[85],"Chunkfarm":[86,132],"performs":[87],"using":[90],"hash":[92],"join":[93],"algorithm,":[94],"which":[95],"turns":[96],"notoriously":[98],"random":[99],"small":[101],"I/Os":[103],"fingerprint":[105,128],"lookups":[106],"updates":[108],"into":[109],"large":[110],"sequential":[111],"I/Os,":[113],"hence":[114,145],"achieving":[115],"write":[117],"throughput":[118],"not":[119],"influenced":[120],"by":[121,126],"workload":[122],"locality.":[123],"More":[124],"importantly,":[125],"decentralizing":[127],"lookup":[129],"update,":[131],"supports":[133],"cluster":[135],"servers":[137],"perform":[139],"in":[142],"parallel;":[143],"it":[144],"conducive":[147],"implementation":[150],"applicable":[153],"storage":[158],"systems.":[159]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}
