{"id":"https://openalex.org/W2157240622","doi":"https://doi.org/10.1109/icdcs.2002.1022312","title":"Reclaiming space from duplicate files in a serverless distributed file system","display_name":"Reclaiming space from duplicate files in a serverless distributed file system","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W2157240622","doi":"https://doi.org/10.1109/icdcs.2002.1022312","mag":"2157240622"},"language":"en","primary_location":{"id":"doi:10.1109/icdcs.2002.1022312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdcs.2002.1022312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 22nd International Conference on Distributed Computing Systems","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/A5073038911","display_name":"John R. Douceur","orcid":null},"institutions":[{"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":["US"],"is_corresponding":true,"raw_author_name":"J.R. Douceur","raw_affiliation_strings":["Microsoft Research Limited, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060789723","display_name":"Atul Adya","orcid":"https://orcid.org/0000-0001-8767-6908"},"institutions":[{"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":["US"],"is_corresponding":false,"raw_author_name":"A. Adya","raw_affiliation_strings":["Microsoft Research Limited, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108541497","display_name":"William J. Bolosky","orcid":null},"institutions":[{"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":["US"],"is_corresponding":false,"raw_author_name":"W.J. Bolosky","raw_affiliation_strings":["Microsoft Research Limited, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082959774","display_name":"P\u00e1l Simon","orcid":null},"institutions":[{"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":["US"],"is_corresponding":false,"raw_author_name":"P. Simon","raw_affiliation_strings":["Microsoft Research Limited, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067638065","display_name":"Marvin Theimer","orcid":null},"institutions":[{"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":["US"],"is_corresponding":false,"raw_author_name":"M. Theimer","raw_affiliation_strings":["Microsoft Research Limited, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5073038911"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":4.9604,"has_fulltext":false,"cited_by_count":641,"citation_normalized_percentile":{"value":0.95711667,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"617","last_page":"624"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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":0.9998999834060669,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9987000226974487,"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":0.9983999729156494,"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":0.8168594837188721},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6805948615074158},{"id":"https://openalex.org/keywords/file-system","display_name":"File system","score":0.6293882727622986},{"id":"https://openalex.org/keywords/replication","display_name":"Replication (statistics)","score":0.6111263632774353},{"id":"https://openalex.org/keywords/computer-file","display_name":"Computer file","score":0.5523276925086975},{"id":"https://openalex.org/keywords/self-certifying-file-system","display_name":"Self-certifying File System","score":0.5447200536727905},{"id":"https://openalex.org/keywords/file-control-block","display_name":"File Control Block","score":0.5411021709442139},{"id":"https://openalex.org/keywords/torrent-file","display_name":"Torrent file","score":0.5297221541404724},{"id":"https://openalex.org/keywords/versioning-file-system","display_name":"Versioning file system","score":0.47324663400650024},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.46966421604156494},{"id":"https://openalex.org/keywords/journaling-file-system","display_name":"Journaling file system","score":0.459328830242157},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.4397088289260864},{"id":"https://openalex.org/keywords/ssh-file-transfer-protocol","display_name":"SSH File Transfer Protocol","score":0.4288623631000519},{"id":"https://openalex.org/keywords/distributed-file-system","display_name":"Distributed File System","score":0.4274994134902954},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4160262942314148},{"id":"https://openalex.org/keywords/device-file","display_name":"Device file","score":0.2570928931236267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8168594837188721},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6805948615074158},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.6293882727622986},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.6111263632774353},{"id":"https://openalex.org/C95637964","wikidata":"https://www.wikidata.org/wiki/Q82753","display_name":"Computer file","level":2,"score":0.5523276925086975},{"id":"https://openalex.org/C82820731","wikidata":"https://www.wikidata.org/wiki/Q2640620","display_name":"Self-certifying File System","level":3,"score":0.5447200536727905},{"id":"https://openalex.org/C180500224","wikidata":"https://www.wikidata.org/wiki/Q1412592","display_name":"File Control Block","level":4,"score":0.5411021709442139},{"id":"https://openalex.org/C40350719","wikidata":"https://www.wikidata.org/wiki/Q2451637","display_name":"Torrent file","level":4,"score":0.5297221541404724},{"id":"https://openalex.org/C166807848","wikidata":"https://www.wikidata.org/wiki/Q3445065","display_name":"Versioning file system","level":4,"score":0.47324663400650024},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.46966421604156494},{"id":"https://openalex.org/C2225880","wikidata":"https://www.wikidata.org/wiki/Q579047","display_name":"Journaling file system","level":3,"score":0.459328830242157},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.4397088289260864},{"id":"https://openalex.org/C88520388","wikidata":"https://www.wikidata.org/wiki/Q1126823","display_name":"SSH File Transfer Protocol","level":4,"score":0.4288623631000519},{"id":"https://openalex.org/C152043487","wikidata":"https://www.wikidata.org/wiki/Q1229600","display_name":"Distributed File System","level":2,"score":0.4274994134902954},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4160262942314148},{"id":"https://openalex.org/C193769178","wikidata":"https://www.wikidata.org/wiki/Q14679","display_name":"Device file","level":3,"score":0.2570928931236267},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icdcs.2002.1022312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdcs.2002.1022312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 22nd International Conference on Distributed Computing Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.15.3749","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.15.3749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/~adya/pubs/ICDCS2002.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.67.9910","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.67.9910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/sn/Farsite/MSR-TR-2002-30.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.68.6812","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.68.6812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/farsite/ICDCS2002.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.8.7586","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.8.7586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/~adya/pubs/MSR-TR-2002-30.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":60,"referenced_works":["https://openalex.org/W177705293","https://openalex.org/W1490586645","https://openalex.org/W1496940124","https://openalex.org/W1525865893","https://openalex.org/W1613874182","https://openalex.org/W1650006494","https://openalex.org/W1650675509","https://openalex.org/W1660562555","https://openalex.org/W1881553382","https://openalex.org/W1890449996","https://openalex.org/W1895828570","https://openalex.org/W1915606614","https://openalex.org/W2000876023","https://openalex.org/W2005373714","https://openalex.org/W2016657252","https://openalex.org/W2025413686","https://openalex.org/W2052267638","https://openalex.org/W2056363353","https://openalex.org/W2056980397","https://openalex.org/W2088590034","https://openalex.org/W2115457697","https://openalex.org/W2115599946","https://openalex.org/W2123845384","https://openalex.org/W2126087831","https://openalex.org/W2138816444","https://openalex.org/W2146889157","https://openalex.org/W2147929033","https://openalex.org/W2154909745","https://openalex.org/W2155204045","https://openalex.org/W2157240622","https://openalex.org/W2158049821","https://openalex.org/W2163059190","https://openalex.org/W2163351355","https://openalex.org/W2163598690","https://openalex.org/W2165028605","https://openalex.org/W2167898414","https://openalex.org/W2169196622","https://openalex.org/W2170489924","https://openalex.org/W2171796885","https://openalex.org/W2174507869","https://openalex.org/W2942827234","https://openalex.org/W3162105941","https://openalex.org/W4230805115","https://openalex.org/W4250390143","https://openalex.org/W4299418846","https://openalex.org/W4300480330","https://openalex.org/W6607257297","https://openalex.org/W6629902689","https://openalex.org/W6631563883","https://openalex.org/W6636388380","https://openalex.org/W6636872130","https://openalex.org/W6636975353","https://openalex.org/W6637202848","https://openalex.org/W6639646868","https://openalex.org/W6678832241","https://openalex.org/W6682311248","https://openalex.org/W6682976012","https://openalex.org/W6683798602","https://openalex.org/W6684479765","https://openalex.org/W6685043173"],"related_works":["https://openalex.org/W2342627122","https://openalex.org/W4313226861","https://openalex.org/W1572832495","https://openalex.org/W2622848439","https://openalex.org/W4389858212","https://openalex.org/W2098881120","https://openalex.org/W4320083224","https://openalex.org/W2058294301","https://openalex.org/W4250364891","https://openalex.org/W3042208251"],"abstract_inverted_index":{"The":[0],"Farsite":[1],"distributed":[2],"file":[3,10,36,68,110],"system":[4,129],"provides":[5],"availability":[6],"by":[7,48],"replicating":[8],"each":[9],"onto":[11],"multiple":[12],"desktop":[13,35],"computers.":[14],"Since":[15],"this":[16,59],"replication":[17],"consumes":[18],"significant":[19],"storage":[20],"space,":[21],"it":[22,64],"is":[23,46,130],"important":[24],"to":[25,55,62,80],"reclaim":[26,56],"used":[27],"space":[28,45,57,85],"where":[29],"possible.":[30],"Measurement":[31],"of":[32,42,86],"over":[33],"500":[34],"systems":[37],"shows":[38],"that":[39,125],"nearly":[40],"half":[41],"all":[43],"consumed":[44],"occupied":[47],"duplicate":[49,78],"files.":[50],"We":[51],"present":[52],"a":[53,87,103,116],"mechanism":[54,71],"from":[58],"incidental":[60],"duplication":[61],"make":[63],"available":[65],"for":[66,108],"controlled":[67],"replication.":[69],"Our":[70],"includes:":[72],"(1)":[73],"convergent":[74],"encryption,":[75],"which":[76],"enables":[77],"files":[79,93],"be":[81],"coalesced":[82],"into":[83],"the":[84,92,126],"single":[88],"file,":[89],"even":[90],"if":[91],"are":[94],"encrypted":[95],"with":[96],"different":[97],"users'":[98],"keys;":[99],"and":[100,112,134],"(2)":[101],"SALAD,":[102],"Self-Arranging":[104],"Lossy":[105],"Associative":[106],"Database":[107],"aggregating":[109],"content":[111],"location":[113],"information":[114],"in":[115],"decentralized,":[117],"scalable,":[118,131],"fault-tolerant":[119],"manner.":[120],"Large-scale":[121],"simulation":[122],"experiments":[123],"show":[124],"duplicate-file":[127],"coalescing":[128],"highly":[132],"effective,":[133],"fault-tolerant.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":31},{"year":2024,"cited_by_count":39},{"year":2023,"cited_by_count":42},{"year":2022,"cited_by_count":40},{"year":2021,"cited_by_count":32},{"year":2020,"cited_by_count":51},{"year":2019,"cited_by_count":35},{"year":2018,"cited_by_count":50},{"year":2017,"cited_by_count":65},{"year":2016,"cited_by_count":49},{"year":2015,"cited_by_count":67},{"year":2014,"cited_by_count":28},{"year":2013,"cited_by_count":22},{"year":2012,"cited_by_count":22}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
