{"id":"https://openalex.org/W2476238358","doi":"https://doi.org/10.1109/tpds.2016.2594070","title":"PDFS: Partially Dedupped File System for Primary Workloads","display_name":"PDFS: Partially Dedupped File System for Primary Workloads","publication_year":2016,"publication_date":"2016-07-26","ids":{"openalex":"https://openalex.org/W2476238358","doi":"https://doi.org/10.1109/tpds.2016.2594070","mag":"2476238358"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2016.2594070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2016.2594070","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5100845251","display_name":"Hongliang Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongliang Yu","raw_affiliation_strings":["Computer Science Department, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437208","display_name":"Xu Zhang","orcid":"https://orcid.org/0000-0002-1882-736X"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu Zhang","raw_affiliation_strings":["Facebook Inc., Los Angeles, CA"],"affiliations":[{"raw_affiliation_string":"Facebook Inc., Los Angeles, CA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037512766","display_name":"Wei Huang","orcid":"https://orcid.org/0000-0001-5671-6524"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Huang","raw_affiliation_strings":["Computer Science Department, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108050911","display_name":"Weimin Zheng","orcid":"https://orcid.org/0000-0002-4450-5428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weimin Zheng","raw_affiliation_strings":["Computer Science Department, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100845251"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.5791,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.7109643,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"28","issue":"3","first_page":"863","last_page":"876"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":1.0,"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":1.0,"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":0.9976000189781189,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8285868167877197},{"id":"https://openalex.org/keywords/file-system","display_name":"File system","score":0.5571534037590027},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.45641499757766724},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4160863161087036},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32576853036880493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8285868167877197},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.5571534037590027},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.45641499757766724},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4160863161087036},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32576853036880493}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2016.2594070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2016.2594070","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W6847055","https://openalex.org/W69510097","https://openalex.org/W120798314","https://openalex.org/W174289249","https://openalex.org/W178328500","https://openalex.org/W200233886","https://openalex.org/W1236737278","https://openalex.org/W1418704970","https://openalex.org/W1437397736","https://openalex.org/W1474119323","https://openalex.org/W1502916507","https://openalex.org/W1521407587","https://openalex.org/W1534481387","https://openalex.org/W1568472162","https://openalex.org/W1580997674","https://openalex.org/W1588132832","https://openalex.org/W1607538671","https://openalex.org/W1969126835","https://openalex.org/W1988596907","https://openalex.org/W1998817683","https://openalex.org/W2016947394","https://openalex.org/W2029433591","https://openalex.org/W2051751274","https://openalex.org/W2056980397","https://openalex.org/W2096670209","https://openalex.org/W2103919011","https://openalex.org/W2110322986","https://openalex.org/W2128593562","https://openalex.org/W2132069633","https://openalex.org/W2146889157","https://openalex.org/W2147407897","https://openalex.org/W2147717514","https://openalex.org/W2152921908","https://openalex.org/W2156468933","https://openalex.org/W2158433455","https://openalex.org/W2162006472","https://openalex.org/W2216311525","https://openalex.org/W2217916065","https://openalex.org/W2281363974","https://openalex.org/W2285144687","https://openalex.org/W2293855639","https://openalex.org/W2585172182","https://openalex.org/W3023628574","https://openalex.org/W4230077428","https://openalex.org/W6602837329","https://openalex.org/W6604953292","https://openalex.org/W6607057542","https://openalex.org/W6607150254","https://openalex.org/W6608138927","https://openalex.org/W6628128319","https://openalex.org/W6628219055","https://openalex.org/W6628275343","https://openalex.org/W6629956336","https://openalex.org/W6631269574","https://openalex.org/W6632020668","https://openalex.org/W6634665569","https://openalex.org/W6635572855","https://openalex.org/W6675513912","https://openalex.org/W6676700842","https://openalex.org/W6679663036","https://openalex.org/W6688535418","https://openalex.org/W6688881698","https://openalex.org/W6695688771","https://openalex.org/W6696105951"],"related_works":["https://openalex.org/W1604898313","https://openalex.org/W2117014006","https://openalex.org/W1513409726","https://openalex.org/W1505619784","https://openalex.org/W1579874608","https://openalex.org/W1601407282","https://openalex.org/W2362282263","https://openalex.org/W1494728318","https://openalex.org/W3029509610","https://openalex.org/W2121854243"],"abstract_inverted_index":{"Primary":[0],"storage":[1],"dedup":[2,87,97,117,134],"is":[3,47],"difficult":[4],"to":[5,11,98],"be":[6],"accomplished":[7],"because":[8],"of":[9,60,69,113,141],"challenges":[10],"achieve":[12],"low":[13],"IO":[14,27,75],"latency":[15,76],"and":[16,34,77,89],"high":[17],"throughput":[18,78],"while":[19],"eliminating":[20],"data":[21,55,62,66,86],"redundancy":[22],"effectively":[23],"in":[24,63],"the":[25,36,70,99,114],"critical":[26],"Path.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32],"design":[33,94],"implement":[35],"PDFS,":[37],"a":[38,50],"partially":[39],"dedupped":[40],"file":[41,131],"system":[42],"for":[43,57,101],"primary":[44,103],"workloads,":[45],"which":[46],"built":[48],"on":[49],"generalized":[51],"framework":[52],"using":[53],"partial":[54],"lookup":[56],"efficient":[58],"searching":[59],"redundant":[61],"quickly":[64],"chosen":[65],"subsets":[67],"instead":[68],"whole":[71],"data.":[72],"PDFS":[73,109,142],"improves":[74],"systematically":[79],"by":[80],"techniques":[81],"including":[82],"write":[83,90],"path":[84],"optimization,":[85],"parallelization":[88],"order":[91],"preserving.":[92],"Such":[93],"choices":[95],"bring":[96],"masses":[100],"general":[102],"workloads.":[104],"Experimental":[105],"results":[106],"show":[107],"that":[108],"achieves":[110],"74-99":[111],"percent":[112],"theoretical":[115],"maximum":[116],"ratio":[118],"with":[119,128],"very":[120],"small":[121],"or":[122],"even":[123],"negative":[124],"performance":[125],"degradations":[126],"compared":[127],"main":[129],"stream":[130],"systems":[132],"without":[133],"support.":[135],"Discussions":[136],"about":[137],"varied":[138],"configuring":[139],"experiences":[140],"are":[143],"also":[144],"carried":[145],"out.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}