{"id":"https://openalex.org/W2799944323","doi":"https://doi.org/10.1145/3183890","title":"Cluster and Single-Node Analysis of Long-Term Deduplication Patterns","display_name":"Cluster and Single-Node Analysis of Long-Term Deduplication Patterns","publication_year":2018,"publication_date":"2018-05-11","ids":{"openalex":"https://openalex.org/W2799944323","doi":"https://doi.org/10.1145/3183890","mag":"2799944323"},"language":"en","primary_location":{"id":"doi:10.1145/3183890","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3183890","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3183890","source":{"id":"https://openalex.org/S158124317","display_name":"ACM Transactions on Storage","issn_l":"1553-3077","issn":["1553-3077","1553-3093"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Storage","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3183890","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102303518","display_name":"Zhen \u201cJason\u201d Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen \u201cJason\u201d Sun","raw_affiliation_strings":["National University of Defense Technology, Hunan, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Hunan, P.R.China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056117639","display_name":"Geoff Kuenning","orcid":"https://orcid.org/0000-0002-3882-2072"},"institutions":[{"id":"https://openalex.org/I133543626","display_name":"Harvey Mudd College","ror":"https://ror.org/025ecfn45","country_code":"US","type":"education","lineage":["https://openalex.org/I133543626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Geoff Kuenning","raw_affiliation_strings":["Harvey Mudd College, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvey Mudd College, CA, USA","institution_ids":["https://openalex.org/I133543626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037667483","display_name":"Sonam Mandal","orcid":"https://orcid.org/0000-0002-2108-304X"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sonam Mandal","raw_affiliation_strings":["Stony Brook University, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091766663","display_name":"Philip Shilane","orcid":"https://orcid.org/0000-0003-1235-0502"},"institutions":[{"id":"https://openalex.org/I4210149435","display_name":"DELL (United States)","ror":"https://ror.org/05rejmm18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210149435"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip Shilane","raw_affiliation_strings":["Dell EMC, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dell EMC, PA, USA","institution_ids":["https://openalex.org/I4210149435"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045054131","display_name":"Vasily Tarasov","orcid":"https://orcid.org/0000-0003-1424-9977"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vasily Tarasov","raw_affiliation_strings":["IBM Research, California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, California, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023506057","display_name":"Nong Xiao","orcid":"https://orcid.org/0000-0002-2166-977X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nong Xiao","raw_affiliation_strings":["National University of Defense Technology, Hunan, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Hunan, P.R.China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064923375","display_name":"Erez Zadok","orcid":"https://orcid.org/0000-0001-5248-9184"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erez Zadok","raw_affiliation_strings":["Stony Brook University, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4679,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.91602927,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"14","issue":"2","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9991000294685364,"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/T11478","display_name":"Caching and Content Delivery","score":0.9958000183105469,"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":0.9605731964111328},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8655177354812622},{"id":"https://openalex.org/keywords/backup","display_name":"Backup","score":0.8081623315811157},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5451253652572632},{"id":"https://openalex.org/keywords/chunking","display_name":"Chunking (psychology)","score":0.4948250651359558},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.42811664938926697},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3967892527580261}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9605731964111328},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8655177354812622},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.8081623315811157},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5451253652572632},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.4948250651359558},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.42811664938926697},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3967892527580261},{"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/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3183890","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3183890","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3183890","source":{"id":"https://openalex.org/S158124317","display_name":"ACM Transactions on Storage","issn_l":"1553-3077","issn":["1553-3077","1553-3093"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Storage","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3183890","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3183890","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3183890","source":{"id":"https://openalex.org/S158124317","display_name":"ACM Transactions on Storage","issn_l":"1553-3077","issn":["1553-3077","1553-3093"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Storage","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G198637370","display_name":null,"funder_award_id":"61433019 and U1435217","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2488474977","display_name":"CSR: Medium: Collaborative Research: Workload-Aware Storage Architectures for Optimal Performance and Energy Efficiency","funder_award_id":"1302246","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3503641551","display_name":null,"funder_award_id":"CNS-1251137, CNS- 1302246, CNS-1305360, and CNS-1622832","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3557789263","display_name":"CRI-CI-ADDO-EN: National File System Trace Repository","funder_award_id":"1305360","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3582114861","display_name":null,"funder_award_id":"61433019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4921008954","display_name":null,"funder_award_id":"2015AA015305","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5438799548","display_name":null,"funder_award_id":"2015AA015305","funder_id":"https://openalex.org/F4320335773","funder_display_name":"National High-tech Research and Development Program"},{"id":"https://openalex.org/G5457632371","display_name":"BIGDATA: Small: DCM: Collaborative Research: An efficient, versatile, scalable, and portable storage system for scientific data containers","funder_award_id":"1251137","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G644350245","display_name":null,"funder_award_id":"2016-2017","funder_id":"https://openalex.org/F4320312927","funder_display_name":"Dell EMC"},{"id":"https://openalex.org/G6513744832","display_name":null,"funder_award_id":"U1435217","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G762955194","display_name":null,"funder_award_id":"CNS-1251137, CNS-1302246, CNS-1305360, and CNS-1622832","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G838204608","display_name":null,"funder_award_id":"CNS-1302246","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320312927","display_name":"Dell EMC","ror":"https://ror.org/05rejmm18"},{"id":"https://openalex.org/F4320316505","display_name":"NetApp","ror":"https://ror.org/05c4cm338"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335773","display_name":"National High-tech Research and Development Program","ror":null},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2799944323.pdf","grobid_xml":"https://content.openalex.org/works/W2799944323.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W22807665","https://openalex.org/W26020480","https://openalex.org/W69510097","https://openalex.org/W120798314","https://openalex.org/W178328500","https://openalex.org/W182307532","https://openalex.org/W200233886","https://openalex.org/W1445823765","https://openalex.org/W1454188553","https://openalex.org/W1474119323","https://openalex.org/W1521407587","https://openalex.org/W1545493325","https://openalex.org/W1626210897","https://openalex.org/W1856507064","https://openalex.org/W1963568712","https://openalex.org/W1969126835","https://openalex.org/W1971212200","https://openalex.org/W2016947394","https://openalex.org/W2036874012","https://openalex.org/W2047484077","https://openalex.org/W2055899630","https://openalex.org/W2088271809","https://openalex.org/W2110322986","https://openalex.org/W2133806194","https://openalex.org/W2134792144","https://openalex.org/W2138061848","https://openalex.org/W2147407897","https://openalex.org/W2153158407","https://openalex.org/W2156865561","https://openalex.org/W2158935814","https://openalex.org/W2281363974","https://openalex.org/W2293794372","https://openalex.org/W2322976455","https://openalex.org/W2408052048","https://openalex.org/W2570363240","https://openalex.org/W2604571800","https://openalex.org/W2606291150"],"related_works":["https://openalex.org/W4285245558","https://openalex.org/W1437397736","https://openalex.org/W2048606985","https://openalex.org/W2375056709","https://openalex.org/W2474612884","https://openalex.org/W4301155776","https://openalex.org/W2012359782","https://openalex.org/W2952411620","https://openalex.org/W3156188733","https://openalex.org/W2348132657"],"abstract_inverted_index":{"Deduplication":[0],"has":[1],"become":[2],"essential":[3,79],"in":[4,114],"disk-based":[5],"backup":[6,16,41],"systems,":[7],"but":[8,180],"there":[9],"have":[10],"been":[11],"few":[12],"long-term":[13],"studies":[14,20],"of":[15,23,38,54,78,107,150,189],"workloads.":[17],"Most":[18],"past":[19],"either":[21],"were":[22],"a":[24,31,40,57,76,128,147,169],"small":[25,220],"static":[26],"snapshot":[27],"or":[28],"covered":[29],"only":[30],"short":[32],"period":[33],"that":[34,121,165,197],"was":[35,96],"not":[36],"representative":[37],"how":[39],"system":[42],"evolves":[43],"over":[44,65],"time.":[45],"For":[46,89,135],"this":[47],"article,":[48],"we":[49,110,139],"first":[50],"collected":[51],"21":[52],"months":[53],"data":[55,120,186],"from":[56,227],"shared":[58],"user":[59],"file":[60],"system;":[61],"33":[62],"users":[63,123],"and":[64,86,103,145,160,221,230,234],"4,000":[66],"snapshots":[67],"are":[68,201],"covered.":[69],"We":[70,163,194,223],"then":[71],"analyzed":[72],"the":[73,119],"dataset,":[74],"examining":[75],"variety":[77],"characteristics":[80],"across":[81,192],"two":[82],"dimensions:":[83],"single-node":[84,90,229],"deduplication":[85,91,116,131,137,156,171,217,232,239],"cluster":[87,136,204,231],"deduplication.":[88],"analysis,":[92,138],"our":[93,108],"primary":[94],"focus":[95],"individual-user":[97],"data.":[98],"Despite":[99],"apparently":[100],"similar":[101],"roles":[102],"behavior":[104],"among":[105],"all":[106],"users,":[109],"found":[111,164,196],"significant":[112],"differences":[113],"their":[115,151,213],"ratios.":[117],"Moreover,":[118],"some":[122],"share":[124],"with":[125,153],"others":[126],"had":[127],"much":[129],"higher":[130,170],"ratio":[132,172],"than":[133,173],"average.":[134],"implemented":[140],"seven":[141],"published":[142],"data-routing":[143,210],"algorithms":[144],"created":[146],"detailed":[148],"comparison":[149],"performance":[152],"respect":[154],"to":[155,184],"ratio,":[157],"load":[158],"distribution,":[159],"communication":[161],"overhead.":[162],"per-file":[166],"routing":[167,174],"achieves":[168],"by":[175],"super-chunk":[176],"(multiple":[177],"consecutive":[178],"chunks),":[179],"it":[181],"also":[182,195],"leads":[183],"high":[185],"skew":[187],"(imbalance":[188],"space":[190],"usage":[191],"nodes).":[193],"large":[198],"chunking":[199],"sizes":[200],"better":[202],"for":[203,237],"deduplication,":[205],"as":[206],"they":[207],"significantly":[208],"reduce":[209],"overhead,":[211],"while":[212],"negative":[214],"impact":[215],"on":[216],"ratios":[218],"is":[219],"acceptable.":[222],"draw":[224],"interesting":[225],"conclusions":[226],"both":[228],"analysis":[233],"make":[235],"recommendations":[236],"future":[238],"systems":[240],"design.":[241]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
