{"id":"https://openalex.org/W2945335752","doi":"https://doi.org/10.1145/3319647.3325834","title":"SS-CDC: a two-stage parallel content-defined chunking for deduplicating backup storage","display_name":"SS-CDC: a two-stage parallel content-defined chunking for deduplicating backup storage","publication_year":2019,"publication_date":"2019-05-22","ids":{"openalex":"https://openalex.org/W2945335752","doi":"https://doi.org/10.1145/3319647.3325834","mag":"2945335752"},"language":"en","primary_location":{"id":"doi:10.1145/3319647.3325834","doi":"https://doi.org/10.1145/3319647.3325834","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3319647.3325834","pdf_url":null,"source":{"id":"https://openalex.org/S4306417568","display_name":"ACM International Conference on Systems and Storage","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM International Conference on Systems and Storage","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5006663833","display_name":"Fan Ni","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fan Ni","raw_affiliation_strings":["University of Texas at Arlington and NetApp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington and NetApp","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102973268","display_name":"Xing Lin","orcid":"https://orcid.org/0000-0001-9620-2704","observed_orcids":["https://orcid.org/0000-0001-9620-2704"]},"institutions":[{"id":"https://openalex.org/I1283576576","display_name":"NetApp (United States)","ror":"https://ror.org/05c4cm338","country_code":"US","type":"company","lineage":["https://openalex.org/I1283576576"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xing Lin","raw_affiliation_strings":["NetApp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetApp","institution_ids":["https://openalex.org/I1283576576"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101421445","display_name":"Song Jiang","orcid":"https://orcid.org/0000-0002-1681-9008","observed_orcids":["https://orcid.org/0000-0002-1681-9008"]},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Song Jiang","raw_affiliation_strings":["University of Texas at Arlington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2471,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.88823298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"86","last_page":"96"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9965999722480774,"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":0.9965999722480774,"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/T11269","display_name":"Algorithms and Data Compression","score":0.0017000000225380063,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.000699999975040555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-deduplication","display_name":"data deduplication","score":0.8899999856948853},{"id":"https://openalex.org/keywords/content-defined-chunking","display_name":"content-defined chunking","score":0.9559999704360962},{"id":"https://openalex.org/keywords/storage-efficiency","display_name":"storage efficiency","score":0.7789999842643738},{"id":"https://openalex.org/keywords/file-segmentation","display_name":"file segmentation","score":0.5870000123977661},{"id":"https://openalex.org/keywords/storage-systems","display_name":"storage systems","score":0.34599998593330383}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9637303352355957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8199384212493896},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.6533586978912354},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.42390698194503784},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.36650514602661133},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36464518308639526},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13576099276542664}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3319647.3325834","doi":"https://doi.org/10.1145/3319647.3325834","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3319647.3325834","pdf_url":null,"source":{"id":"https://openalex.org/S4306417568","display_name":"ACM International Conference on Systems and Storage","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM International Conference on Systems and Storage","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332162","display_name":"Centers for Disease Control and Prevention","ror":"https://ror.org/042twtr12"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W22807665","https://openalex.org/W87636713","https://openalex.org/W182307532","https://openalex.org/W200233886","https://openalex.org/W1521996498","https://openalex.org/W1626210897","https://openalex.org/W1871705262","https://openalex.org/W1969335064","https://openalex.org/W2008185810","https://openalex.org/W2045202139","https://openalex.org/W2056980397","https://openalex.org/W2073643620","https://openalex.org/W2351279544","https://openalex.org/W2481696877","https://openalex.org/W2998583855"],"related_works":["https://openalex.org/W2986445348","https://openalex.org/W3001182873","https://openalex.org/W4312554896","https://openalex.org/W3014193728","https://openalex.org/W2935106878","https://openalex.org/W4304820092","https://openalex.org/W2351279544","https://openalex.org/W1521996498","https://openalex.org/W7128783105","https://openalex.org/W7127400837"],"abstract_inverted_index":{"Data":[0],"deduplication":[1,27,77],"has":[2],"been":[3],"widely":[4],"used":[5,24],"in":[6,25,38,67],"storage":[7,11],"systems":[8,28],"to":[9,32],"improve":[10],"efficiency":[12],"and":[13,34,48,59],"I/O":[14],"performance.":[15],"In":[16],"particular,":[17],"content-defined":[18],"variable-size":[19],"chunking":[20],"(CDC)":[21],"is":[22,45],"often":[23],"data":[26,37],"for":[29],"its":[30],"capability":[31],"detect":[33],"remove":[35],"duplicate":[36],"modified":[39],"files.":[40],"However,":[41],"the":[42,61],"CDC":[43],"algorithm":[44,62],"very":[46],"compute-intensive":[47],"inherently":[49],"sequential.":[50],"Efforts":[51],"on":[52,64],"accelerating":[53],"it":[54],"by":[55],"segmenting":[56],"a":[57,71],"file":[58],"running":[60],"independently":[63],"each":[65],"segment":[66],"parallel":[68],"come":[69],"at":[70],"cost":[72],"of":[73,76],"substantial":[74],"degradation":[75],"ratio.":[78]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2019-05-29T00:00:00"}
