{"id":"https://openalex.org/W2110322986","doi":"https://doi.org/10.1145/2078861.2078864","title":"A study of practical deduplication","display_name":"A study of practical deduplication","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2110322986","doi":"https://doi.org/10.1145/2078861.2078864","mag":"2110322986"},"language":"en","primary_location":{"id":"doi:10.1145/2078861.2078864","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2078861.2078864","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090981855","display_name":"Dutch T. Meyer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]},{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA","GB"],"is_corresponding":true,"raw_author_name":"Dutch T. Meyer","raw_affiliation_strings":["The University of British Columbia, Microsoft Research"],"affiliations":[{"raw_affiliation_string":"The University of British Columbia, Microsoft Research","institution_ids":["https://openalex.org/I4210164937","https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108541497","display_name":"William J. Bolosky","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"William J. Bolosky","raw_affiliation_strings":["Microsoft Research","Microsoft research#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft research#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5090981855"],"corresponding_institution_ids":["https://openalex.org/I141945490","https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":45.3341,"has_fulltext":false,"cited_by_count":468,"citation_normalized_percentile":{"value":0.99931816,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"7","issue":"4","first_page":"1","last_page":"20"},"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9986000061035156,"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":0.9854999780654907,"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/computer-science","display_name":"Computer science","score":0.8653199672698975},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.8553953766822815},{"id":"https://openalex.org/keywords/backup","display_name":"Backup","score":0.6687045097351074},{"id":"https://openalex.org/keywords/computer-file","display_name":"Computer file","score":0.6336857080459595},{"id":"https://openalex.org/keywords/versioning-file-system","display_name":"Versioning file system","score":0.596140444278717},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5664911866188049},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5634661316871643},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.5594865679740906},{"id":"https://openalex.org/keywords/file-system","display_name":"File system","score":0.5171684622764587},{"id":"https://openalex.org/keywords/journaling-file-system","display_name":"Journaling file system","score":0.4960046708583832},{"id":"https://openalex.org/keywords/torrent-file","display_name":"Torrent file","score":0.48058152198791504},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.43171918392181396},{"id":"https://openalex.org/keywords/unix-file-types","display_name":"Unix file types","score":0.42125117778778076},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4108971059322357},{"id":"https://openalex.org/keywords/stub-file","display_name":"Stub file","score":0.31864166259765625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8653199672698975},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.8553953766822815},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.6687045097351074},{"id":"https://openalex.org/C95637964","wikidata":"https://www.wikidata.org/wiki/Q82753","display_name":"Computer file","level":2,"score":0.6336857080459595},{"id":"https://openalex.org/C166807848","wikidata":"https://www.wikidata.org/wiki/Q3445065","display_name":"Versioning file system","level":4,"score":0.596140444278717},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5664911866188049},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5634661316871643},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5594865679740906},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.5171684622764587},{"id":"https://openalex.org/C2225880","wikidata":"https://www.wikidata.org/wiki/Q579047","display_name":"Journaling file system","level":3,"score":0.4960046708583832},{"id":"https://openalex.org/C40350719","wikidata":"https://www.wikidata.org/wiki/Q2451637","display_name":"Torrent file","level":4,"score":0.48058152198791504},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.43171918392181396},{"id":"https://openalex.org/C21729314","wikidata":"https://www.wikidata.org/wiki/Q7896858","display_name":"Unix file types","level":4,"score":0.42125117778778076},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4108971059322357},{"id":"https://openalex.org/C13674803","wikidata":"https://www.wikidata.org/wiki/Q7627301","display_name":"Stub file","level":3,"score":0.31864166259765625},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2078861.2078864","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2078861.2078864","pdf_url":null,"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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.362.8612","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.362.8612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.usenix.org/legacy/events/fast11/tech/full_papers/Meyer.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W30877809","https://openalex.org/W69510097","https://openalex.org/W174289249","https://openalex.org/W200233886","https://openalex.org/W1490390347","https://openalex.org/W1517965180","https://openalex.org/W1576397915","https://openalex.org/W1929726975","https://openalex.org/W1969126835","https://openalex.org/W1971212200","https://openalex.org/W2035379912","https://openalex.org/W2067182386","https://openalex.org/W2070834743","https://openalex.org/W2123845384","https://openalex.org/W2128593562","https://openalex.org/W2132627996","https://openalex.org/W2135652458","https://openalex.org/W2140815597","https://openalex.org/W2160127232","https://openalex.org/W2170432965","https://openalex.org/W2171796885","https://openalex.org/W2912574597","https://openalex.org/W2916086000","https://openalex.org/W4231676608","https://openalex.org/W4253910652","https://openalex.org/W4381612226"],"related_works":["https://openalex.org/W1990666357","https://openalex.org/W4313226861","https://openalex.org/W2058294301","https://openalex.org/W4210915796","https://openalex.org/W130417735","https://openalex.org/W2342627122","https://openalex.org/W2090783200","https://openalex.org/W4389858212","https://openalex.org/W3042208251","https://openalex.org/W2922086451"],"abstract_inverted_index":{"We":[0,18,38,71],"collected":[1],"file":[2,61,74,85,94],"system":[3,86],"content":[4],"data":[5,21,28],"from":[6],"857":[7],"desktop":[8],"computers":[9],"at":[10],"Microsoft":[11],"over":[12],"a":[13],"span":[14],"of":[15,27,36,47,51,59,65,93],"4":[16],"weeks.":[17],"analyzed":[19],"the":[20,24,48,52,66,91],"to":[22,97],"determine":[23],"relative":[25],"efficacy":[26],"deduplication,":[29],"particularly":[30],"considering":[31],"whole-file":[32,41],"versus":[33],"block-level":[34,55],"elimination":[35],"redundancy.":[37],"found":[39],"that":[40,77,90],"deduplication":[42,56],"achieves":[43],"about":[44],"three":[45],"quarters":[46],"space":[49],"savings":[50,67],"most":[53],"aggressive":[54],"for":[57,68],"storage":[58],"live":[60],"systems,":[62],"and":[63,82],"87%":[64],"backup":[69],"images.":[70],"also":[72],"studied":[73],"fragmentation,":[75],"finding":[76,89],"it":[78],"is":[79],"not":[80],"prevalent,":[81],"updated":[83],"prior":[84],"metadata":[87],"studies,":[88],"distribution":[92],"sizes":[95],"continues":[96],"skew":[98],"toward":[99],"very":[100],"large":[101],"unstructured":[102],"files.":[103]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":34},{"year":2021,"cited_by_count":37},{"year":2020,"cited_by_count":35},{"year":2019,"cited_by_count":36},{"year":2018,"cited_by_count":36},{"year":2017,"cited_by_count":34},{"year":2016,"cited_by_count":51},{"year":2015,"cited_by_count":38},{"year":2014,"cited_by_count":33},{"year":2013,"cited_by_count":30},{"year":2012,"cited_by_count":21}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
