{"id":"https://openalex.org/W7147740763","doi":"https://doi.org/10.1109/tpds.2026.3678624","title":"Improving the Restore Performance of Fine-Grained Deduplication on Docker Container Image Storage","display_name":"Improving the Restore Performance of Fine-Grained Deduplication on Docker Container Image Storage","publication_year":2026,"publication_date":"2026-03-31","ids":{"openalex":"https://openalex.org/W7147740763","doi":"https://doi.org/10.1109/tpds.2026.3678624"},"language":null,"primary_location":{"id":"doi:10.1109/tpds.2026.3678624","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2026.3678624","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5069460570","display_name":"Haoliang Tan","orcid":"https://orcid.org/0009-0003-9919-1926"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoliang Tan","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0003-9919-1926","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenhao Ou","orcid":"https://orcid.org/0009-0000-3959-9805"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Ou","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0000-3959-9805","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121538595","display_name":"Xiangyu Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Zou","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-5104-8301","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132718795","display_name":"Lisha Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lisha Qin","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132624547","display_name":"Cai Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cai Deng","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-7717-6990","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040547391","display_name":"Zhaoquan Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoquan Gu","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-7546-852X","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132558454","display_name":"Wen Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Xia","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-4093-6391","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"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":0.53167646,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"6","first_page":"1247","last_page":"1264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.6421999931335449,"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":0.6421999931335449,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.20419999957084656,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.019099999219179153,"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":0.98089998960495},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6690000295639038},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6331999897956848},{"id":"https://openalex.org/keywords/container","display_name":"Container (type theory)","score":0.5597000122070312},{"id":"https://openalex.org/keywords/image-restoration","display_name":"Image restoration","score":0.3774000108242035},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3741999864578247},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.33169999718666077}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.98089998960495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8496999740600586},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6690000295639038},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6331999897956848},{"id":"https://openalex.org/C2781018962","wikidata":"https://www.wikidata.org/wiki/Q5164884","display_name":"Container (type theory)","level":2,"score":0.5597000122070312},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4287000000476837},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.3774000108242035},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3741999864578247},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C65377053","wikidata":"https://www.wikidata.org/wiki/Q1572121","display_name":"Image file formats","level":3,"score":0.3294000029563904},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.32739999890327454},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3043000102043152},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3043000102043152},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.26019999384880066}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2026.3678624","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2026.3678624","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1704661371","display_name":null,"funder_award_id":"62502119","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4100129303","display_name":null,"funder_award_id":"62472127","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5449262284","display_name":null,"funder_award_id":"2023A1515110072","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"growth":[2],"of":[3,76,85,98,133,218,228],"container":[4,78,102,119],"images":[5,134],"leads":[6],"to":[7,37,54,60,73,94,176,196,224],"heavy":[8],"storage":[9,31],"pressures":[10],"on":[11,125,140,203],"image":[12,34,41,50,103,120,165,174,207],"registries.":[13,104,121],"Fine-grained":[14],"deduplication,":[15,189,220,231],"such":[16],"as":[17],"at":[18],"the":[19,30,74,77,95,129,179,204,213,225],"file":[20],"and":[21,184,193,199],"chunk":[22],"levels,":[23],"is":[24,123,222],"a":[25,91,112,136,156],"promising":[26],"technique":[27],"for":[28,118],"reducing":[29],"space":[32],"in":[33,58,81,101],"registries,":[35],"compared":[36],"Docker's":[38],"native":[39,229],"coarse-grained":[40],"layer":[42],"deduplication.":[43],"However,":[44],"fine-grained":[45,99,114,219],"deduplication":[46,68,83,100,115,182,195,236],"often":[47],"incurs":[48],"significant":[49],"restoration":[51,62],"latency":[52],"due":[53],"fragmented":[55,162,200],"I/Os,":[56],"resulting":[57,80],"up":[59],"8\u00d7":[61],"I/O":[63,216],"slowdowns.":[64],"Moreover,":[65],"existing":[66],"restore-optimized":[67],"techniques":[69],"are":[70],"not":[71],"tailored":[72,117],"characteristics":[75],"image,":[79],"low":[82],"ratios":[84],"images.":[86],"Consequently,":[87],"restoring":[88],"performance":[89,227],"remains":[90],"critical":[92],"barrier":[93],"practical":[96],"adoption":[97],"To":[105],"address":[106],"this":[107,141],"challenge,":[108],"we":[109],"propose":[110],"MiDedup,":[111],"restore-friendly":[113],"approach":[116],"MiDedup":[122,143,211],"built":[124],"an":[126],"underexplored":[127],"observation:":[128],"redundancy":[130],"across":[131],"layers":[132,175],"follows":[135],"non-uniform":[137],"distribution.":[138],"Based":[139],"insight,":[142],"introduces":[144],"three":[145],"core":[146],"techniques:":[147],"\u2460":[148],"Across-layer-aware":[149],"reorganization,":[150],"which":[151,170,190,221],"reorganizes":[152],"deduplicated":[153],"data":[154],"into":[155],"compact,":[157],"sequential":[158],"layout,":[159],"significantly":[160],"reduces":[161,212],"I/Os":[163],"during":[164],"restore.":[166],"\u2461":[167],"Popularity-aware":[168],"rewriting,":[169],"selectively":[171],"rewrites":[172],"hot":[173],"further":[177],"improve":[178],"balance":[180],"between":[181],"ratio":[183],"restore":[185,215,226],"performance.":[186],"\u2462":[187],"Hybrid-granularity":[188],"combines":[191],"file-level":[192],"chunk-level":[194],"reduce":[197],"metadata":[198],"data.":[201],"Experiments":[202],"real-world":[205],"Docker":[206],"dataset":[208],"show":[209],"that":[210],"50\u201380%":[214],"overhead":[217],"comparable":[223],"layer-level":[230],"while":[232],"achieving":[233],"1.2\u20137.3\u00d7":[234],"higher":[235],"ratios.":[237]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-02T00:00:00"}
