{"id":"https://openalex.org/W2028546326","doi":"https://doi.org/10.1109/msst.2012.6232390","title":"BloomStore: Bloom-Filter based memory-efficient key-value store for indexing of data deduplication on flash","display_name":"BloomStore: Bloom-Filter based memory-efficient key-value store for indexing of data deduplication on flash","publication_year":2012,"publication_date":"2012-04-01","ids":{"openalex":"https://openalex.org/W2028546326","doi":"https://doi.org/10.1109/msst.2012.6232390","mag":"2028546326"},"language":"en","primary_location":{"id":"doi:10.1109/msst.2012.6232390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msst.2012.6232390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"012 IEEE 28th Symposium on Mass Storage Systems and Technologies (MSST)","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/A5062515720","display_name":"Guanlin Lu","orcid":"https://orcid.org/0000-0002-9735-8521"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]},{"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":"Guanlin Lu","raw_affiliation_strings":["EMC2, Santa Clara, CA, USA","EMC2, Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EMC2, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I16269868"]},{"raw_affiliation_string":"EMC2, Santa Clara, CA","institution_ids":["https://openalex.org/I4210149435"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102428516","display_name":"Young Jin Nam","orcid":null},"institutions":[{"id":"https://openalex.org/I9323808","display_name":"Daegu University","ror":"https://ror.org/01zqccq48","country_code":"KR","type":"education","lineage":["https://openalex.org/I9323808"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Young Jin Nam","raw_affiliation_strings":["Daegu University, Gyeongbuk, South Korea","Daegu University, Gyeongbuk, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Daegu University, Gyeongbuk, South Korea","institution_ids":["https://openalex.org/I9323808"]},{"raw_affiliation_string":"Daegu University, Gyeongbuk, Korea","institution_ids":["https://openalex.org/I9323808"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004446054","display_name":"David H. C. Du","orcid":"https://orcid.org/0009-0000-6244-1336"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David H. C. Du","raw_affiliation_strings":["University of Minnesota, Minneapolis, MN, USA","University of Minnesota , Minneapolis, Mn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]},{"raw_affiliation_string":"University of Minnesota , Minneapolis, Mn","institution_ids":["https://openalex.org/I130238516"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.6885,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":{"value":0.98282141,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"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/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/T11478","display_name":"Caching and Content Delivery","score":0.9986000061035156,"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":0.866969108581543},{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.8541711568832397},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8347001075744629},{"id":"https://openalex.org/keywords/associative-array","display_name":"Associative array","score":0.6904665231704712},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6327787041664124},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5911362767219543},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.589402973651886},{"id":"https://openalex.org/keywords/flash-memory","display_name":"Flash memory","score":0.5239812731742859},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5128288865089417},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.49174025654792786},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.38590067625045776},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3100000023841858},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2306801974773407},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.22529393434524536},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.20909595489501953}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.866969108581543},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.8541711568832397},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8347001075744629},{"id":"https://openalex.org/C168781493","wikidata":"https://www.wikidata.org/wiki/Q80585","display_name":"Associative array","level":2,"score":0.6904665231704712},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6327787041664124},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5911362767219543},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.589402973651886},{"id":"https://openalex.org/C2776531357","wikidata":"https://www.wikidata.org/wiki/Q174077","display_name":"Flash memory","level":2,"score":0.5239812731742859},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5128288865089417},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.49174025654792786},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.38590067625045776},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3100000023841858},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2306801974773407},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.22529393434524536},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.20909595489501953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/msst.2012.6232390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msst.2012.6232390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"012 IEEE 28th Symposium on Mass Storage Systems and Technologies (MSST)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.361.5885","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.361.5885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://storageconference.org/2012/Papers/26.Flash.2.BloomStore.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W200233886","https://openalex.org/W1521407587","https://openalex.org/W1838765419","https://openalex.org/W1967930269","https://openalex.org/W2020930775","https://openalex.org/W2077850713","https://openalex.org/W2087946700","https://openalex.org/W2110322986","https://openalex.org/W2110423232","https://openalex.org/W2112479717","https://openalex.org/W2119764208","https://openalex.org/W2123845384","https://openalex.org/W2133394135","https://openalex.org/W2134552038","https://openalex.org/W2149509741","https://openalex.org/W2154829922","https://openalex.org/W2205436351","https://openalex.org/W2585172182","https://openalex.org/W2912601938","https://openalex.org/W4285719527","https://openalex.org/W6608138927","https://openalex.org/W6631269574","https://openalex.org/W6638678886","https://openalex.org/W6676700842"],"related_works":["https://openalex.org/W3008420177","https://openalex.org/W2942719460","https://openalex.org/W2371981271","https://openalex.org/W141925461","https://openalex.org/W3113874423","https://openalex.org/W2806950186","https://openalex.org/W2081869611","https://openalex.org/W3176416739","https://openalex.org/W744786805","https://openalex.org/W2150999591"],"abstract_inverted_index":{"Due":[0],"to":[1,50,61,110,131,163,203,236],"its":[2,85,141,238],"better":[3,252],"scalability,":[4],"Key-Value":[5],"(KV)":[6],"store":[7,32,56,111,114,121,178,245],"has":[8],"superseded":[9],"traditional":[10],"relational":[11],"databases":[12],"for":[13],"many":[14],"applications,":[15],"such":[16],"as":[17],"data":[18,67,159],"deduplication,":[19,68],"on-line":[20],"multi-player":[21],"gaming,":[22],"and":[23,28,39,84,222,227,256],"Internet":[24],"services":[25],"like":[26],"Amazon":[27],"Facebook.":[29],"The":[30,54,190],"KV":[31,40,55,113,120,134,150,177,220,228,244],"efficiently":[33],"supports":[34],"two":[35],"operations":[36],"(key":[37],"lookup":[38,254],"pair":[41],"insertion)":[42],"through":[43],"an":[44],"index":[45,65,127,132,158,186,199,225],"structure":[46,128,160,187,200,226],"that":[47,152,209],"maps":[48],"keys":[49],"their":[51],"associated":[52],"values.":[53],"is":[57,81,95,107,201],"also":[58],"commonly":[59],"used":[60],"implement":[62],"the":[63,78,96,103,112,119,146,157,168,194,242,247,258],"chunk":[64,71,87],"in":[66,116,129,206],"where":[69],"a":[70,82,99,123,182,210,216,250],"ID":[72],"(SHA1":[73],"value":[74],"computed":[75],"based":[76,185,268],"on":[77,137,179,233,269],"chunk's":[79],"content)":[80],"key":[83,253],"associative":[86],"metadata":[88],"(e.g.,":[89],"physical":[90],"storage":[91],"location,":[92],"stream":[93],"ID)":[94],"value.":[97],"For":[98],"deduplication":[100,273],"system,":[101],"typically":[102],"number":[104,148,218],"of":[105,149,193,219],"chunks":[106],"too":[108],"large":[109,124,217],"solely":[115],"RAM.":[117],"Thus,":[118],"maintains":[122],"(hash-table":[125],"based)":[126],"RAM":[130,143,162,207,212,266],"all":[133],"pairs":[135,151,221,229],"stored":[136,205,231],"secondary":[138],"storage.":[139],"Hence,":[140],"available":[142],"space":[144,169,213],"limits":[145],"maximum":[147],"can":[153,165,214],"be":[154,204],"stored.":[155],"Moving":[156],"from":[161],"flash":[164,180,234],"possibly":[166],"overcome":[167],"limitation.":[170],"In":[171],"this":[172],"paper,":[173],"we":[174],"propose":[175],"efficient":[176],"with":[181,241,262,272],"Bloom":[183],"Filter":[184],"called":[188],"BloomStore.":[189],"unique":[191],"features":[192],"BloomStore":[195,248],"include":[196],"(1)":[197],"no":[198],"required":[202],"so":[208],"small":[211],"support":[215],"(2)":[223],"both":[224],"are":[230],"compactly":[232],"memory":[235],"improve":[237],"performance.":[239],"Compared":[240],"state-of-the-art":[243],"designs,":[246],"achieves":[249],"significantly":[251],"performance":[255,261],"roughly":[257],"same":[259],"insertion":[260],"multiple":[263],"times":[264],"less":[265],"usage":[267],"our":[270],"experiments":[271],"workloads.":[274]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}