{"id":"https://openalex.org/W2972863894","doi":"https://doi.org/10.1109/nas.2019.8834729","title":"Towards Cluster-wide Deduplication Based on Ceph","display_name":"Towards Cluster-wide Deduplication Based on Ceph","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W2972863894","doi":"https://doi.org/10.1109/nas.2019.8834729","mag":"2972863894"},"language":"en","primary_location":{"id":"doi:10.1109/nas.2019.8834729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nas.2019.8834729","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Networking, Architecture and Storage (NAS)","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/A5100376308","display_name":"Jinpeng Wang","orcid":"https://orcid.org/0000-0001-5764-9589"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinpeng Wang","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030110566","display_name":"Yang Wang","orcid":"https://orcid.org/0000-0001-7322-4062"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Wang","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040490687","display_name":"Hekang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hekang Wang","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012757772","display_name":"Kejiang Ye","orcid":"https://orcid.org/0000-0001-6133-407X"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kejiang Ye","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012773300","display_name":"Chengzhong Xu","orcid":"https://orcid.org/0000-0001-9480-0356"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengzhong Xu","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004997843","display_name":"Shuibing He","orcid":"https://orcid.org/0000-0002-7075-4153"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuibing He","raw_affiliation_strings":["Zhejiang University, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036840192","display_name":"Lingfang Zeng","orcid":"https://orcid.org/0000-0003-3130-3015"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingfang Zeng","raw_affiliation_strings":["Huazhong University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100376308"],"corresponding_institution_ids":["https://openalex.org/I4210145761"],"apc_list":null,"apc_paid":null,"fwci":0.3537,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.63341836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9987999796867371,"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":0.9976000189781189,"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":0.9612821340560913},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8241185545921326},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6214814186096191},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5913367867469788},{"id":"https://openalex.org/keywords/slicing","display_name":"Slicing","score":0.5311350226402283},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4854724705219269},{"id":"https://openalex.org/keywords/computer-data-storage","display_name":"Computer data storage","score":0.47722533345222473},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.4201434552669525},{"id":"https://openalex.org/keywords/distributed-data-store","display_name":"Distributed data store","score":0.4149245619773865},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3863416910171509},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37098127603530884},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36707815527915955},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3519979417324066},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.276645690202713},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.1107049286365509},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09977713227272034}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9612821340560913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8241185545921326},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6214814186096191},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5913367867469788},{"id":"https://openalex.org/C2776190703","wikidata":"https://www.wikidata.org/wiki/Q488148","display_name":"Slicing","level":2,"score":0.5311350226402283},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4854724705219269},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.47722533345222473},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.4201434552669525},{"id":"https://openalex.org/C24885549","wikidata":"https://www.wikidata.org/wiki/Q339678","display_name":"Distributed data store","level":2,"score":0.4149245619773865},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3863416910171509},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37098127603530884},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36707815527915955},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3519979417324066},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.276645690202713},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.1107049286365509},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09977713227272034},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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":1,"locations":[{"id":"doi:10.1109/nas.2019.8834729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nas.2019.8834729","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Networking, Architecture and Storage (NAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7099999785423279,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W200233886","https://openalex.org/W1474119323","https://openalex.org/W1576397915","https://openalex.org/W1877461462","https://openalex.org/W1947728686","https://openalex.org/W1975200978","https://openalex.org/W1999984505","https://openalex.org/W2016947394","https://openalex.org/W2056980397","https://openalex.org/W2107745473","https://openalex.org/W2109706326","https://openalex.org/W2125401295","https://openalex.org/W2189138427","https://openalex.org/W2228753927","https://openalex.org/W2475932436","https://openalex.org/W2545424303","https://openalex.org/W2604964870","https://openalex.org/W2607244263","https://openalex.org/W2808357789","https://openalex.org/W2963108782","https://openalex.org/W4230077428","https://openalex.org/W4253233651","https://openalex.org/W6608138927","https://openalex.org/W6634463810","https://openalex.org/W6640739288","https://openalex.org/W6736132691"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W2994530202","https://openalex.org/W1513660145","https://openalex.org/W2290204549","https://openalex.org/W2084547067","https://openalex.org/W3129662905","https://openalex.org/W1834679979","https://openalex.org/W2353225269"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"design":[4],"an":[5],"efficient":[6],"deduplication":[7,23,119],"algorithm":[8,18,53,74,88,141],"based":[9,80],"on":[10,48,81],"the":[11,32,52,55,67,72,77,90,94,107,116,126,140,147,153,160],"distributed":[12],"storage":[13,34,98,103,148],"architecture":[14],"of":[15,57,84,109],"Ceph.":[16,45],"The":[17,87,135],"uses":[19,71],"on-line":[20],"block-level":[21],"data":[22,27,33,68,78,92],"technology":[24],"to":[25,65,75,115],"complete":[26],"slicing,":[28],"which":[29,97],"neither":[30],"affects":[31],"process":[35],"in":[36,44,131],"Ceph":[37,58],"nor":[38],"alter":[39],"other":[40],"interfaces":[41],"and":[42,70,118,124,158],"functions":[43],"Without":[46],"relying":[47],"any":[49],"central":[50],"node,":[51],"maintains":[54],"characteristics":[56],"by":[59],"designing":[60],"a":[61],"special":[62],"hash":[63],"object":[64],"store":[66],"fingerprint,":[69],"CRUSH":[73],"judge":[76],"duplication":[79],"calculation,":[82],"instead":[83],"global":[85],"search.":[86],"replaces":[89],"duplicate":[91,161],"with":[93,101,113],"deduplicated":[95],"objects,":[96],"their":[99],"fingerprints":[100],"less":[102],"space.":[104],"We":[105],"compare":[106],"effects":[108],"different":[110],"block":[111,129],"sizes":[112],"respect":[114],"performance":[117],"rates":[120],"through":[121],"experimental":[122,136],"studies,":[123],"select":[125],"most":[127],"appropriate":[128],"size":[130],"our":[132],"prototype":[133],"implementation.":[134],"results":[137],"show":[138],"that":[139],"can":[142],"not":[143],"only":[144],"effectively":[145],"save":[146],"space":[149],"but":[150],"also":[151],"improve":[152],"bandwidth":[154],"utilization":[155],"when":[156],"reading":[157],"writing":[159],"data.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-01-20T17:24:06.736184","created_date":"2025-10-10T00:00:00"}
