{"id":"https://openalex.org/W2618141211","doi":"https://doi.org/10.1007/978-3-319-59665-5_4","title":"$${\\textsc {DDFlasks}}$$: Deduplicated Very Large Scale Data Store","display_name":"$${\\textsc {DDFlasks}}$$: Deduplicated Very Large Scale Data Store","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2618141211","doi":"https://doi.org/10.1007/978-3-319-59665-5_4","mag":"2618141211"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-59665-5_4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-59665-5_4","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://inria.hal.science/hal-01800122","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101911512","display_name":"Francisco Maia","orcid":"https://orcid.org/0000-0003-0729-4569"},"institutions":[{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]},{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Francisco Maia","raw_affiliation_strings":["HASLab, INESC TEC, University of Minho, Braga, Portugal"],"affiliations":[{"raw_affiliation_string":"HASLab, INESC TEC, University of Minho, Braga, Portugal","institution_ids":["https://openalex.org/I99682543","https://openalex.org/I4210166615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054409160","display_name":"Jo\u00e3o Paulo","orcid":"https://orcid.org/0000-0001-9752-2822"},"institutions":[{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]},{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Paulo","raw_affiliation_strings":["HASLab, INESC TEC, University of Minho, Braga, Portugal"],"affiliations":[{"raw_affiliation_string":"HASLab, INESC TEC, University of Minho, Braga, Portugal","institution_ids":["https://openalex.org/I99682543","https://openalex.org/I4210166615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023270031","display_name":"F\u00e1bio Coelho","orcid":"https://orcid.org/0000-0002-0188-6400"},"institutions":[{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]},{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"F\u00e1bio Coelho","raw_affiliation_strings":["HASLab, INESC TEC, University of Minho, Braga, Portugal"],"affiliations":[{"raw_affiliation_string":"HASLab, INESC TEC, University of Minho, Braga, Portugal","institution_ids":["https://openalex.org/I99682543","https://openalex.org/I4210166615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022271014","display_name":"Francisco Neves","orcid":"https://orcid.org/0000-0003-2165-5375"},"institutions":[{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]},{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Francisco Neves","raw_affiliation_strings":["HASLab, INESC TEC, University of Minho, Braga, Portugal"],"affiliations":[{"raw_affiliation_string":"HASLab, INESC TEC, University of Minho, Braga, Portugal","institution_ids":["https://openalex.org/I99682543","https://openalex.org/I4210166615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065441606","display_name":"Jos\u00e9 Pereira","orcid":"https://orcid.org/0000-0002-3341-9217"},"institutions":[{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]},{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Pereira","raw_affiliation_strings":["HASLab, INESC TEC, University of Minho, Braga, Portugal"],"affiliations":[{"raw_affiliation_string":"HASLab, INESC TEC, University of Minho, Braga, Portugal","institution_ids":["https://openalex.org/I99682543","https://openalex.org/I4210166615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080138945","display_name":"Rui Oliveira","orcid":"https://orcid.org/0000-0003-3408-7346"},"institutions":[{"id":"https://openalex.org/I4210166615","display_name":"INESC TEC","ror":"https://ror.org/05fa8ka61","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210125590","https://openalex.org/I4210166615"]},{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Rui Oliveira","raw_affiliation_strings":["HASLab, INESC TEC, University of Minho, Braga, Portugal"],"affiliations":[{"raw_affiliation_string":"HASLab, INESC TEC, University of Minho, Braga, Portugal","institution_ids":["https://openalex.org/I99682543","https://openalex.org/I4210166615"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101911512"],"corresponding_institution_ids":["https://openalex.org/I4210166615","https://openalex.org/I99682543"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08161469,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10742","display_name":"Peer-to-Peer Network 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/T10742","display_name":"Peer-to-Peer Network 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/T11478","display_name":"Caching and Content Delivery","score":0.9994999766349792,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9979000091552734,"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":0.8766187429428101},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.8471572399139404},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6479979157447815},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5977910757064819},{"id":"https://openalex.org/keywords/distributed-data-store","display_name":"Distributed data store","score":0.5970878601074219},{"id":"https://openalex.org/keywords/computer-data-storage","display_name":"Computer data storage","score":0.5554215908050537},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5473594069480896},{"id":"https://openalex.org/keywords/storage-area-network","display_name":"Storage area network","score":0.4324125647544861},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.34149330854415894},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3248150944709778},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16523513197898865}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8766187429428101},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.8471572399139404},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6479979157447815},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5977910757064819},{"id":"https://openalex.org/C24885549","wikidata":"https://www.wikidata.org/wiki/Q339678","display_name":"Distributed data store","level":2,"score":0.5970878601074219},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.5554215908050537},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5473594069480896},{"id":"https://openalex.org/C67646966","wikidata":"https://www.wikidata.org/wiki/Q237576","display_name":"Storage area network","level":3,"score":0.4324125647544861},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34149330854415894},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3248150944709778},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16523513197898865},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/978-3-319-59665-5_4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-59665-5_4","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:HAL:hal-01800122v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01800122","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"17th IFIP International Conference on Distributed Applications and Interoperable Systems (DAIS), Jun 2017, Neuch\u00e2tel, Switzerland. pp.51-66, &#x27E8;10.1007/978-3-319-59665-5_4&#x27E9;","raw_type":"Conference papers"},{"id":"pmh:oai:repositorio.inesctec.pt:123456789/4222","is_oa":true,"landing_page_url":"http://repositorio.inesctec.pt/handle/123456789/4222","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference object"},{"id":"pmh:oai:repositorio:123456789/4389","is_oa":false,"landing_page_url":"http://repositorio.inesctec.pt/handle/123456789/4389","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Publication"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01800122v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01800122","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"17th IFIP International Conference on Distributed Applications and Interoperable Systems (DAIS), Jun 2017, Neuch\u00e2tel, Switzerland. pp.51-66, &#x27E8;10.1007/978-3-319-59665-5_4&#x27E9;","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W5335935","https://openalex.org/W24740120","https://openalex.org/W26020480","https://openalex.org/W69510097","https://openalex.org/W95244180","https://openalex.org/W1576397915","https://openalex.org/W1969126835","https://openalex.org/W1975868314","https://openalex.org/W1981420413","https://openalex.org/W2022162666","https://openalex.org/W2055899630","https://openalex.org/W2056980397","https://openalex.org/W2058237148","https://openalex.org/W2087946700","https://openalex.org/W2110322986","https://openalex.org/W2118428193","https://openalex.org/W2150013559","https://openalex.org/W2153704625","https://openalex.org/W2156468933","https://openalex.org/W2157240622","https://openalex.org/W2162733677","https://openalex.org/W2281363974","https://openalex.org/W2998583855","https://openalex.org/W4243055721","https://openalex.org/W4249823756"],"related_works":["https://openalex.org/W3008013744","https://openalex.org/W2884042376","https://openalex.org/W2615141153","https://openalex.org/W2077135008","https://openalex.org/W223870977","https://openalex.org/W2994530202","https://openalex.org/W2021496484","https://openalex.org/W4387682279","https://openalex.org/W2785349009","https://openalex.org/W1826586879"],"abstract_inverted_index":{"With":[0],"the":[1,126,164],"increasing":[2],"number":[3,35],"of":[4,36,47,131],"connected":[5],"devices,":[6],"it":[7,107],"becomes":[8],"essential":[9],"to":[10,64,96,101,108,148,174,179,188],"find":[11],"novel":[12],"data":[13,29,69,79],"management":[14,30],"solutions":[15],"that":[16,170],"can":[17],"leverage":[18],"their":[19],"computational":[20],"and":[21,44,57,59,89,128,163,181,194],"storage":[22,87,112,133,176],"capabilities.":[23],"However,":[24],"developing":[25],"very":[26],"large":[27],"scale":[28,73],"systems":[31,39,134],"requires":[32],"tackling":[33],"a":[34,83,109,116,136,156,192],"interesting":[37],"distributed":[38,111],"challenges,":[40],"namely":[41],"continuous":[42],"failures":[43],"high":[45],"levels":[46],"node":[48],"churn.":[49],"In":[50,119,140],"this":[51,78,141],"context,":[52],"epidemic-based":[53],"protocols":[54],"proved":[55],"suitable":[56],"effective":[58],"have":[60],"been":[61],"successfully":[62],"used":[63],"build":[65],"DataFlasks,":[66],"an":[67,98],"epidemic":[68],"store":[70,80],"for":[71],"massive":[72],"systems.":[74],"Ensuring":[75],"resiliency":[76,127],"in":[77,86,155],"comes":[81],"with":[82,146],"significant":[84,122],"cost":[85],"resources":[88],"network":[90,183],"bandwidth":[91,184],"consumption.":[92],"Deduplication":[93],"has":[94],"proven":[95],"be":[97],"efficient":[99],"technique":[100],"reduce":[102],"both":[103],"costs":[104],"but,":[105],"applying":[106],"large-scale":[110],"system":[113,152],"is":[114,135,153,172],"not":[115],"trivial":[117],"task.":[118],"fact,":[120],"achieving":[121],"space-savings":[123],"without":[124],"compromising":[125],"decentralized":[129],"design":[130,149],"these":[132],"relevant":[137],"research":[138],"challenge.":[139],"paper,":[142],"we":[143],"extend":[144],"DataFlasks":[145],"deduplication":[147,171],"DDFlasks.":[150],"This":[151],"evaluated":[154],"real":[157],"world":[158],"scenario":[159],"using":[160],"Wikipedia":[161],"snapshots,":[162],"results":[165],"are":[166],"twofold.":[167],"We":[168],"show":[169],"able":[173],"decrease":[175,182],"consumption":[177,185],"up":[178,187],"63%":[180],"by":[186],"20%,":[189],"while":[190],"maintaining":[191],"fully-decentralized":[193],"resilient":[195],"design.":[196]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
