{"id":"https://openalex.org/W1969126835","doi":"https://doi.org/10.1109/mascot.2009.5366623","title":"Extreme Binning: Scalable, parallel deduplication for chunk-based file backup","display_name":"Extreme Binning: Scalable, parallel deduplication for chunk-based file backup","publication_year":2009,"publication_date":"2009-09-01","ids":{"openalex":"https://openalex.org/W1969126835","doi":"https://doi.org/10.1109/mascot.2009.5366623","mag":"1969126835"},"language":"en","primary_location":{"id":"doi:10.1109/mascot.2009.5366623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mascot.2009.5366623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Modeling, Analysis &amp; Simulation of Computer and Telecommunication Systems","raw_type":"proceedings-article"},"type":"conference-paper","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/A5058889435","display_name":"Deepavali Bhagwat","orcid":null},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. Bhagwat","raw_affiliation_strings":["University of California, Santa Cruz, CA, USA","University of California, 1156 High Street Santa Cruz, CA 95064"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Santa Cruz, CA, USA","institution_ids":["https://openalex.org/I185103710"]},{"raw_affiliation_string":"University of California, 1156 High Street Santa Cruz, CA 95064","institution_ids":["https://openalex.org/I185103710"]}]},{"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":"K. Eshghi","raw_affiliation_strings":["Hewlett Packard Laboratories, Palo Alto, CA, USA","Hewlett Packard Labs, 1501 Page Mill Rd, Palo Alto, CA 94304"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett Packard Laboratories, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett Packard Labs, 1501 Page Mill Rd, Palo Alto, CA 94304","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029994088","display_name":"Darrell D. E. Long","orcid":"https://orcid.org/0000-0002-0822-0740"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D.D.E. Long","raw_affiliation_strings":["University of California, Santa Cruz, CA, USA","University of California, 1156 High Street Santa Cruz, CA 95064"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Santa Cruz, CA, USA","institution_ids":["https://openalex.org/I185103710"]},{"raw_affiliation_string":"University of California, 1156 High Street Santa Cruz, CA 95064","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025642451","display_name":"Mark Lillibridge","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":"M. Lillibridge","raw_affiliation_strings":["Hewlett Packard Laboratories, Palo Alto, CA, USA","Hewlett Packard Labs, 1501 Page Mill Rd, Palo Alto, CA 94304"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett Packard Laboratories, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett Packard Labs, 1501 Page Mill Rd, Palo Alto, CA 94304","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.4936,"has_fulltext":false,"cited_by_count":328,"citation_normalized_percentile":{"value":0.99579891,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9993000030517578,"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":0.8824124336242676},{"id":"https://openalex.org/keywords/backup","display_name":"Backup","score":0.844251811504364},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.8120901584625244},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7186691761016846},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5972480177879333},{"id":"https://openalex.org/keywords/backup-software","display_name":"Backup software","score":0.5573806762695312},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4727148711681366},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.4723723232746124},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.4514332413673401},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4425920248031616},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.36731240153312683},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3450300693511963}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8824124336242676},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.844251811504364},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.8120901584625244},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7186691761016846},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5972480177879333},{"id":"https://openalex.org/C503016453","wikidata":"https://www.wikidata.org/wiki/Q4839801","display_name":"Backup software","level":3,"score":0.5573806762695312},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4727148711681366},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4723723232746124},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4514332413673401},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4425920248031616},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36731240153312683},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3450300693511963},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/mascot.2009.5366623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mascot.2009.5366623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Modeling, Analysis &amp; Simulation of Computer and Telecommunication Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.214.8386","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.214.8386","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/personal/Mark_Lillibridge/Extreme/final.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.467.1985","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.467.1985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://users.soe.ucsc.edu/~darrell/Papers/PID934231.pdf","raw_type":"text"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt0tt8q4ht","is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/0tt8q4ht","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2648413381","display_name":"PETASCALE OF DATA STORAGE INSTITUTE","funder_award_id":"FC02-06ER25768","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G612067694","display_name":"PETASCALE OF DATA STORAGE INSTITUTE","funder_award_id":"DEFC0206ER25768","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320334742","display_name":"Data Storage Institute","ror":"https://ror.org/03k5xes38"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W66778775","https://openalex.org/W69510097","https://openalex.org/W89823361","https://openalex.org/W137089333","https://openalex.org/W162607394","https://openalex.org/W174289249","https://openalex.org/W200233886","https://openalex.org/W1490390347","https://openalex.org/W1508926177","https://openalex.org/W1576397915","https://openalex.org/W1957582590","https://openalex.org/W1963535513","https://openalex.org/W1975868314","https://openalex.org/W1978855656","https://openalex.org/W1998817683","https://openalex.org/W2028928922","https://openalex.org/W2056980397","https://openalex.org/W2104210894","https://openalex.org/W2123482462","https://openalex.org/W2123767107","https://openalex.org/W2123845384","https://openalex.org/W2131287008","https://openalex.org/W2132069633","https://openalex.org/W2141641405","https://openalex.org/W2149993626","https://openalex.org/W2156719566","https://openalex.org/W2158049821","https://openalex.org/W2167898414","https://openalex.org/W2745750801","https://openalex.org/W2916086000","https://openalex.org/W3145042860","https://openalex.org/W4236944670","https://openalex.org/W4243055721","https://openalex.org/W6602654064","https://openalex.org/W6602837329","https://openalex.org/W6603735688","https://openalex.org/W6605588685","https://openalex.org/W6607057542","https://openalex.org/W6608138927","https://openalex.org/W6629455298","https://openalex.org/W6630499100","https://openalex.org/W6634463810","https://openalex.org/W6644964241","https://openalex.org/W6681940154"],"related_works":["https://openalex.org/W2348132657","https://openalex.org/W4285245558","https://openalex.org/W2952411620","https://openalex.org/W2012359782","https://openalex.org/W4301155776","https://openalex.org/W2375056709","https://openalex.org/W3156188733","https://openalex.org/W2474612884","https://openalex.org/W2048606985","https://openalex.org/W1437397736"],"abstract_inverted_index":{"Data":[0],"deduplication":[1,45,58],"is":[2,144,163],"an":[3],"essential":[4],"and":[5,18,103,159],"critical":[6],"component":[7],"of":[8,23,36,68,81,86,101,130],"backup":[9,26,33,62,119,134,161],"systems.":[10],"Essential,":[11],"because":[12,20],"it":[13],"reduces":[14],"storage":[15],"space":[16],"requirements,":[17],"critical,":[19],"the":[21,24,128],"performance":[22],"entire":[25],"operation":[27],"depends":[28],"on":[29,92],"its":[30],"throughput.":[31,51,117,141],"Traditional":[32],"workloads":[34,63],"consist":[35],"large":[37],"data":[38,171],"streams":[39],"with":[40,71,122,127,165,175],"high":[41],"locality,":[42,87,102],"which":[43,114],"existing":[44,88],"techniques":[46,89],"require":[47],"to":[48,84,139,151],"provide":[49],"reasonable":[50,116],"We":[52],"present":[53],"Extreme":[54,95,123],"Binning,":[55],"a":[56,78,147],"scalable":[57],"technique":[59],"for":[60,109,156],"non-traditional":[61],"that":[64],"are":[65],"made":[66],"up":[67],"individual":[69],"files":[70,76],"no":[72,166],"locality":[73],"among":[74],"consecutive":[75],"in":[77],"given":[79],"window":[80],"time.":[82],"Due":[83],"lack":[85],"perform":[90],"poorly":[91],"these":[93],"workloads.":[94],"Binning":[96,124],"exploits":[97],"file":[98,143],"similarity":[99],"instead":[100],"makes":[104],"only":[105,152],"one":[106,153],"disk":[107],"access":[108],"chunk":[110],"lookup":[111],"per":[112],"file,":[113],"gives":[115],"Multi-node":[118],"systems":[120],"built":[121],"scale":[125],"gracefully":[126],"amount":[129],"input":[131],"data;":[132],"more":[133],"nodes":[135],"can":[136],"be":[137],"added":[138],"boost":[140],"Each":[142],"allocated":[145],"using":[146],"stateless":[148],"routing":[149],"algorithm":[150],"node,":[154],"allowing":[155],"maximum":[157],"parallelization,":[158],"each":[160],"node":[162],"autonomous":[164],"dependency":[167],"across":[168],"nodes,":[169],"making":[170],"management":[172],"tasks":[173],"robust":[174],"low":[176],"overhead.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":32},{"year":2015,"cited_by_count":31},{"year":2014,"cited_by_count":32},{"year":2013,"cited_by_count":39},{"year":2012,"cited_by_count":30}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}
