{"id":"https://openalex.org/W4414898693","doi":"https://doi.org/10.1109/cluster59342.2025.11186466","title":"Revisiting Fragmentation for Deduplication in Clustered Primary Storage Systems","display_name":"Revisiting Fragmentation for Deduplication in Clustered Primary Storage Systems","publication_year":2025,"publication_date":"2025-09-02","ids":{"openalex":"https://openalex.org/W4414898693","doi":"https://doi.org/10.1109/cluster59342.2025.11186466"},"language":"en","primary_location":{"id":"doi:10.1109/cluster59342.2025.11186466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster59342.2025.11186466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Cluster Computing (CLUSTER)","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/A5008829405","display_name":"Lin Wang","orcid":"https://orcid.org/0000-0003-0881-9689"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Wang","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065831190","display_name":"Yuchong Hu","orcid":"https://orcid.org/0000-0003-1265-7141"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchong Hu","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086710888","display_name":"Shilong Mao","orcid":null},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilong Mao","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027223167","display_name":"Mingqi Li","orcid":"https://orcid.org/0000-0002-4332-7762"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingqi Li","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ziling Duan","orcid":null},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziling Duan","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101476215","display_name":"Yue Huang","orcid":null},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Huang","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109277027","display_name":"Leihua Qin","orcid":null},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leihua Qin","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070711778","display_name":"Dan Feng","orcid":"https://orcid.org/0000-0002-2650-0797"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Feng","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100678103","display_name":"Zehui Chen","orcid":"https://orcid.org/0000-0003-4055-3008"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zehui Chen","raw_affiliation_strings":["Huawei Technologies Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ruliang Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ruliang Dong","raw_affiliation_strings":["Huawei Technologies Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd","institution_ids":["https://openalex.org/I4210160618"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"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":0.37253888,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.9797999858856201,"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"}},"topics":[{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.9797999858856201,"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":0.9422000050544739,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9215999841690063,"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":0.9379000067710876},{"id":"https://openalex.org/keywords/backup","display_name":"Backup","score":0.8720999956130981},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.565500020980835},{"id":"https://openalex.org/keywords/fragmentation","display_name":"Fragmentation (computing)","score":0.5300999879837036},{"id":"https://openalex.org/keywords/cloud-storage","display_name":"Cloud storage","score":0.4609000086784363},{"id":"https://openalex.org/keywords/garbage-collection","display_name":"Garbage collection","score":0.3711000084877014},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.3377000093460083},{"id":"https://openalex.org/keywords/auxiliary-memory","display_name":"Auxiliary memory","score":0.3336000144481659}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9379000067710876},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.8720999956130981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577000260353088},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.565500020980835},{"id":"https://openalex.org/C191015642","wikidata":"https://www.wikidata.org/wiki/Q1132459","display_name":"Fragmentation (computing)","level":2,"score":0.5300999879837036},{"id":"https://openalex.org/C2777059624","wikidata":"https://www.wikidata.org/wiki/Q914359","display_name":"Cloud storage","level":3,"score":0.4609000086784363},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4341000020503998},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.375900000333786},{"id":"https://openalex.org/C105122174","wikidata":"https://www.wikidata.org/wiki/Q322202","display_name":"Garbage collection","level":3,"score":0.3711000084877014},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3303999900817871},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3046000003814697},{"id":"https://openalex.org/C503016453","wikidata":"https://www.wikidata.org/wiki/Q4839801","display_name":"Backup software","level":3,"score":0.3018999993801117},{"id":"https://openalex.org/C24885549","wikidata":"https://www.wikidata.org/wiki/Q339678","display_name":"Distributed data store","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.26840001344680786},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C2984984529","wikidata":"https://www.wikidata.org/wiki/Q7619925","display_name":"Storage management","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cluster59342.2025.11186466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster59342.2025.11186466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Cluster Computing (CLUSTER)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8639766853","display_name":null,"funder_award_id":"62272185","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"To":[0],"improve":[1],"storage":[2,7,40,72,156],"efficiency":[3],"in":[4,18,37,54,68,92,122,137,191],"large-scale":[5],"clustered":[6,38,70,154],"systems,":[8,157],"deduplication":[9,36,67,94,113,151,241],"that":[10,59,84,88,168,180,202,220],"removes":[11],"duplicate":[12],"chunks":[13,189],"has":[14],"been":[15],"widely":[16],"deployed":[17],"distributed":[19,22],"ways.":[20],"Many":[21],"deduplication-related":[23],"studies":[24,32],"focus":[25,33],"on":[26,34,144],"backup":[27,55,93],"storage,":[28],"and":[29,125,196,215],"some":[30],"recent":[31],"deploying":[35],"primary":[39,71,155],"systems":[41],"which":[42,159],"store":[43],"active":[44],"data.":[45],"While":[46],"fragmentation":[47,62,91,102,206],"is":[48,129],"one":[49],"of":[50,225],"the":[51,69,76,100,112,132,145,172,182,192,204,221],"traditional":[52,90],"challenges":[53],"deduplication,":[56],"we":[57,82,118,147],"observe":[58],"a":[60,162],"new":[61,101],"problem":[63],"arises":[64],"when":[65],"performing":[66],"system":[73],"due":[74],"to":[75,96,170,232],"system's":[77],"concurrent":[78],"file":[79,194],"writes.":[80],"However,":[81],"find":[83],"existing":[85],"state-of-the-art":[86],"methods":[87,121,136],"address":[89],"fail":[95],"work":[97],"effectively":[98],"for":[99,153],"problem,":[103],"as":[104],"they":[105],"significantly":[106],"incur":[107],"additional":[108],"redundancy":[109],"or":[110],"lower":[111],"ratio.":[114],"In":[115],"this":[116],"paper,":[117],"revisit":[119],"fragmentation-solving":[120],"memory":[123,138],"management":[124],"our":[126,216],"main":[127],"idea":[128],"inspired":[130],"by":[131,186,208,230],"classic":[133],"garbage":[134],"collection":[135],"management:":[139],"relocating":[140,166,178],"fragments":[141],"consecutively.":[142],"Based":[143],"idea,":[146],"propose":[148],"an":[149,175,198],"effective":[150],"mechanism":[152],"ReoDedup,":[158],"applies:":[160],"i)":[161],"cosine-similarity":[163],"based":[164,177],"chunk":[165],"algorithm":[167],"aims":[169],"minimize":[171],"fragmentation;":[173],"ii)":[174],"adjacency-table":[176],"heuristic":[179],"reduces":[181],"relocating's":[183],"time":[184],"complexity":[185],"placing":[187],"two":[188],"residing":[190],"same":[193],"consecutively;":[195],"iii)":[197],"indexremapping":[199],"update":[200],"scheme":[201],"alleviates":[203],"extra":[205],"caused":[207],"updates.":[209],"We":[210],"implement":[211],"ReoDedup":[212,226],"atop":[213],"Ceph":[214],"cloud":[217],"experiments":[218],"show":[219],"average":[222],"read":[223],"throughput":[224],"can":[227],"be":[228],"increased":[229],"up":[231],"<tex":[233],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[234],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$1.72":[235],"\\times$</tex>":[236],"over":[237],"state-of-thearts,":[238],"without":[239],"any":[240],"ratio":[242],"loss.":[243]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
