{"id":"https://openalex.org/W2346097572","doi":"https://doi.org/10.1109/tc.2015.2455979","title":"Leveraging Data Deduplication to Improve the Performance of Primary Storage Systems in the Cloud","display_name":"Leveraging Data Deduplication to Improve the Performance of Primary Storage Systems in the Cloud","publication_year":2015,"publication_date":"2015-07-13","ids":{"openalex":"https://openalex.org/W2346097572","doi":"https://doi.org/10.1109/tc.2015.2455979","mag":"2346097572"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2015.2455979","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-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/A5003486125","display_name":"Bo Mao","orcid":"https://orcid.org/0000-0002-4819-4583"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"funder","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Mao","raw_affiliation_strings":["Software School of Xiamen University"],"affiliations":[{"raw_affiliation_string":"Software School of Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054285749","display_name":"Hong Jiang","orcid":"https://orcid.org/0000-0002-1477-9751"},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"funder","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Jiang","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Nebraska-Lincoln, Lincoln, NE"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Nebraska-Lincoln, Lincoln, NE","institution_ids":["https://openalex.org/I114395901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100743604","display_name":"Suzhen Wu","orcid":"https://orcid.org/0000-0002-3589-9621"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"funder","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Suzhen Wu","raw_affiliation_strings":["Computer Science Department of Xiamen University, Xiamen, Fujian, China"],"affiliations":[{"raw_affiliation_string":"Computer Science Department of Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100777330","display_name":"Lei Tian","orcid":"https://orcid.org/0000-0001-5449-3232"},"institutions":[],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Tian","raw_affiliation_strings":["Tintri, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Tintri, Mountain View, CA, USA","institution_ids":[]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.717,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":49,"citation_normalized_percentile":{"value":0.938565,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"65","issue":"6","first_page":"1775","last_page":"1788"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9993,"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":0.9993,"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":0.9991,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9803,"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":0.9344801},{"id":"https://openalex.org/keywords/data-redundancy","display_name":"Data redundancy","score":0.46019223},{"id":"https://openalex.org/keywords/cloud-storage","display_name":"Cloud storage","score":0.4161514},{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.4137665}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9344801},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.83581054},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.61841434},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5427679},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.53445375},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.46019223},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.45140278},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.4394727},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.41966653},{"id":"https://openalex.org/C2777059624","wikidata":"https://www.wikidata.org/wiki/Q914359","display_name":"Cloud storage","level":3,"score":0.4161514},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.4137665},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3904384},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.36094558},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3355275},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.29410806}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2015.2455979","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation","award_id":"NSF-CNS-1016609"},{"funder":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation","award_id":"NSF-CNS-1116606"},{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"61100033"},{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"61402385"},{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"61472336"},{"funder":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities","award_id":"20720140515"}],"datasets":[],"versions":[],"referenced_works_count":45,"referenced_works":["https://openalex.org/W11345677","https://openalex.org/W120798314","https://openalex.org/W126194223","https://openalex.org/W1474119323","https://openalex.org/W1513710683","https://openalex.org/W1541467180","https://openalex.org/W1558370646","https://openalex.org/W1569338333","https://openalex.org/W1592162257","https://openalex.org/W1603008491","https://openalex.org/W174289249","https://openalex.org/W178328500","https://openalex.org/W1860107648","https://openalex.org/W1928720092","https://openalex.org/W1964089084","https://openalex.org/W1971212200","https://openalex.org/W1973294118","https://openalex.org/W1979162731","https://openalex.org/W1984731420","https://openalex.org/W1988596907","https://openalex.org/W1990900012","https://openalex.org/W2016947394","https://openalex.org/W2027492079","https://openalex.org/W2036627877","https://openalex.org/W2059595900","https://openalex.org/W2110322986","https://openalex.org/W2124632914","https://openalex.org/W2125914539","https://openalex.org/W2135050683","https://openalex.org/W2144554431","https://openalex.org/W2146266204","https://openalex.org/W2147407897","https://openalex.org/W2149289471","https://openalex.org/W2150864656","https://openalex.org/W2158935814","https://openalex.org/W2160127232","https://openalex.org/W2161234420","https://openalex.org/W2167002207","https://openalex.org/W2167208373","https://openalex.org/W2182621605","https://openalex.org/W2642383336","https://openalex.org/W4230077428","https://openalex.org/W4241190282","https://openalex.org/W67191628","https://openalex.org/W87143622"],"related_works":["https://openalex.org/W4378228047","https://openalex.org/W3132887183","https://openalex.org/W3008013744","https://openalex.org/W2560948934","https://openalex.org/W2360751420","https://openalex.org/W2333486029","https://openalex.org/W2169841341","https://openalex.org/W2077135008","https://openalex.org/W2076214235","https://openalex.org/W1892538828"],"abstract_inverted_index":{"With":[0],"the":[1,7,21,40,57,89,126,134,141,150,172,185,189,194,209,230],"explosive":[2],"growth":[3],"in":[4,20,35,39,88,96,133,208,229],"data":[5,18,31,47,82,99,173],"volume,":[6],"I/O":[8,58,74,111,119,127,231],"bottleneck":[9],"has":[10],"become":[11],"an":[12,176,240],"increasingly":[13],"daunting":[14],"challenge":[15],"for":[16],"big":[17],"analytics":[19],"Cloud.":[22,41],"Recent":[23],"studies":[24,44],"have":[25,199],"shown":[26],"that":[27,46,61,224,251],"moderate":[28],"to":[29,65,76,84,124,148,170,183,236],"high":[30,67],"redundancy":[32,48],"clearly":[33],"exists":[34],"primary":[36,85,130,153],"storage":[37,86,131,154],"systems":[38,87,132,155],"Our":[42],"experimental":[43],"reveal":[45],"exhibits":[49],"a":[50,109,117,145,163,201,206],"much":[51],"higher":[52],"level":[53],"of":[54,129,140,152,160,203,221,242],"intensity":[55],"on":[56,62,101,104,216],"path":[59],"than":[60,116,259],"disks":[63],"due":[64],"relatively":[66],"temporal":[68],"access":[69],"locality":[70],"associated":[71],"with":[72,239],"small":[73],"requests":[75],"redundant":[77],"data.":[78],"Moreover,":[79,245],"directly":[80],"applying":[81],"deduplication":[83,166],"Cloud":[90,135],"will":[91],"likely":[92],"cause":[93],"space":[94],"contention":[95,187],"memory":[97,178,186],"and":[98,156,175,193],"fragmentation":[100,174],"disks.":[102],"Based":[103],"these":[105],"observations,":[106],"we":[107],"propose":[108],"performance-oriented":[110],"deduplication,":[112,120,161],"called":[113,168,181],"POD,":[114],"rather":[115],"capacity-oriented":[118],"exemplified":[121],"by":[122,234],"iDedup,":[123],"improve":[125],"performance":[128,151,158,232],"without":[136],"sacrificing":[137],"capacity":[138,257],"savings":[139,258],"latter.":[142],"POD":[143,204,222,225,252],"takes":[144],"two-pronged":[146],"approach":[147],"improving":[149],"minimizing":[157],"overhead":[159],"namely,":[162],"request-based":[164],"selective":[165],"technique,":[167],"Select-Dedupe,":[169],"alleviate":[171],"adaptive":[177],"management":[179],"scheme,":[180],"iCache,":[182],"ease":[184],"between":[188],"bursty":[190,195],"read":[191],"traffic":[192],"write":[196],"traffic.":[197],"We":[198],"implemented":[200],"prototype":[202,219],"as":[205],"module":[207],"Linux":[210],"operating":[211],"system.":[212],"The":[213],"experiments":[214],"conducted":[215],"our":[217,246],"lightweight":[218],"implementation":[220],"show":[223,250],"significantly":[226],"outperforms":[227],"iDedup":[228],"measure":[233],"up":[235],"87.9":[237],"percent":[238],"average":[241],"58.8":[243],"percent.":[244],"evaluation":[247],"results":[248],"also":[249],"achieves":[253],"comparable":[254],"or":[255],"better":[256],"iDedup.":[260]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2346097572","counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3}],"updated_date":"2025-04-18T23:23:48.294521","created_date":"2016-06-24"}