{"id":"https://openalex.org/W2031252661","doi":"https://doi.org/10.1145/1496909.1496926","title":"Efficient detection of large-scale redundancy in enterprise file systems","display_name":"Efficient detection of large-scale redundancy in enterprise file systems","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2031252661","doi":"https://doi.org/10.1145/1496909.1496926","mag":"2031252661"},"language":"en","primary_location":{"id":"doi:10.1145/1496909.1496926","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1496909.1496926","pdf_url":null,"source":{"id":"https://openalex.org/S50071195","display_name":"ACM SIGOPS Operating Systems Review","issn_l":"0163-5980","issn":["0163-5980","1943-586X"],"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 SIGOPS Operating Systems Review","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/A5077348567","display_name":"George Forman","orcid":"https://orcid.org/0000-0003-2179-4930"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"George Forman","raw_affiliation_strings":["Hewlett-Packard Labs, Palo Alto, CA","Hewlett-Packard Laboratories, Palo Alto. Ca#TAB#"],"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Palo Alto, CA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett-Packard Laboratories, Palo Alto. Ca#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088426443","display_name":"Kave Eshghi","orcid":"https://orcid.org/0000-0003-3374-3145"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kave Eshghi","raw_affiliation_strings":["Hewlett-Packard Labs, Palo Alto, CA","Hewlett-Packard Laboratories, Palo Alto. Ca#TAB#"],"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Palo Alto, CA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett-Packard Laboratories, Palo Alto. Ca#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005334284","display_name":"Jaap Suermondt","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaap Suermondt","raw_affiliation_strings":["Hewlett-Packard Labs, Palo Alto, CA","Hewlett-Packard Laboratories, Palo Alto. Ca#TAB#"],"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Palo Alto, CA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett-Packard Laboratories, Palo Alto. Ca#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077348567"],"corresponding_institution_ids":["https://openalex.org/I1324840837"],"apc_list":null,"apc_paid":null,"fwci":2.9004,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.91117322,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"43","issue":"1","first_page":"84","last_page":"91"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995999932289124,"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":0.9995999932289124,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9832000136375427,"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":0.98089998960495,"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":0.8817828893661499},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.682633638381958},{"id":"https://openalex.org/keywords/directory","display_name":"Directory","score":0.6503586173057556},{"id":"https://openalex.org/keywords/mirroring","display_name":"Mirroring","score":0.6251361966133118},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4536527693271637},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3757550120353699},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.29886674880981445}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8817828893661499},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.682633638381958},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.6503586173057556},{"id":"https://openalex.org/C189645446","wikidata":"https://www.wikidata.org/wiki/Q350865","display_name":"Mirroring","level":2,"score":0.6251361966133118},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4536527693271637},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3757550120353699},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.29886674880981445},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1496909.1496926","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1496909.1496926","pdf_url":null,"source":{"id":"https://openalex.org/S50071195","display_name":"ACM SIGOPS Operating Systems Review","issn_l":"0163-5980","issn":["0163-5980","1943-586X"],"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 SIGOPS Operating Systems Review","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.365.957","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.365.957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hpl.hp.com/news/2009/jan-mar/pdf/forman_osr_crc_27.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2081193615","https://openalex.org/W2123767107","https://openalex.org/W2128593562","https://openalex.org/W2146889157","https://openalex.org/W2157240622"],"related_works":["https://openalex.org/W2357291590","https://openalex.org/W1510236503","https://openalex.org/W192310729","https://openalex.org/W626755136","https://openalex.org/W1596201972","https://openalex.org/W2160425906","https://openalex.org/W2226504690","https://openalex.org/W1567302830","https://openalex.org/W2361419644","https://openalex.org/W1485627940"],"abstract_inverted_index":{"In":[0],"order":[1],"to":[2,21,55],"catch":[3],"and":[4,67],"reduce":[5],"waste":[6],"in":[7,71],"the":[8],"exponentially":[9],"increasing":[10],"demand":[11],"for":[12,34],"disk":[13],"storage,":[14],"we":[15],"have":[16],"developed":[17],"very":[18],"efficient":[19],"technology":[20],"detect":[22],"approximate":[23],"duplication":[24,30],"of":[25,39],"large":[26],"directory":[27],"hierarchies.":[28],"Such":[29],"can":[31],"be":[32,56],"caused,":[33],"example,":[35,63],"by":[36,41],"unnecessary":[37],"mirroring":[38],"repositories":[40],"uncoordinated":[42],"employees":[43],"or":[44,49],"departments.":[45],"Identifying":[46],"these":[47],"duplicate":[48],"near-duplicate":[50],"hierarchies":[51],"allows":[52],"appropriate":[53],"action":[54],"taken":[57],"at":[58],"a":[59],"high":[60],"level.":[61],"For":[62],"one":[64,72],"could":[65],"coordinate":[66],"consolidate":[68],"multiple":[69],"copies":[70],"location.":[73]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
