{"id":"https://openalex.org/W200233886","doi":null,"title":"Avoiding the disk bottleneck in the data domain deduplication file system","display_name":"Avoiding the disk bottleneck in the data domain deduplication file system","publication_year":2008,"publication_date":"2008-02-26","ids":{"openalex":"https://openalex.org/W200233886","mag":"200233886"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.360.3741","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.360.3741","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.usenix.org/legacy/event/fast08/tech/full_papers/zhu/zhu.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Benjamin Zhu","orcid":"https://orcid.org/0000-0003-1840-3564","observed_orcids":["https://orcid.org/0000-0003-1840-3564"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benjamin Zhu","raw_affiliation_strings":["DATA DOMAIN INC"],"raw_orcid":"https://orcid.org/0000-0003-1840-3564","affiliations":[{"raw_affiliation_string":"DATA DOMAIN INC","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li Kai","orcid":"https://orcid.org/0000-0002-4094-6154","observed_orcids":["https://orcid.org/0000-0002-4094-6154"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Kai","raw_affiliation_strings":["Data Domain, Inc. and Princeton University#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-4094-6154","affiliations":[{"raw_affiliation_string":"Data Domain, Inc. and Princeton University#TAB#","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079487698","display_name":"Hugo Patterson","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hugo Patterson","raw_affiliation_strings":["DATA DOMAIN INC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DATA DOMAIN INC","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":60.5227,"has_fulltext":false,"cited_by_count":707,"citation_normalized_percentile":{"value":0.99847422,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"18","last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","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/T11269","display_name":"Algorithms and Data Compression","score":9.999999747378752e-05,"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/T10317","display_name":"Advanced Database Systems and Queries","score":9.999999747378752e-05,"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":0.7820000052452087},{"id":"https://openalex.org/keywords/backup-storage","display_name":"backup storage","score":0.5490000247955322},{"id":"https://openalex.org/keywords/in-memory-data-structures","display_name":"in-memory data structures","score":0.7059999704360962},{"id":"https://openalex.org/keywords/enterprise-data-security","display_name":"enterprise data security","score":0.7260000109672546}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.887626588344574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8620068430900574},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7110809087753296},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.614436686038971},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5796915888786316},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5534675717353821},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.5381698608398438},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5097185969352722},{"id":"https://openalex.org/C202623185","wikidata":"https://www.wikidata.org/wiki/Q375176","display_name":"Disk buffer","level":3,"score":0.4934738874435425},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4812721610069275},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.45601704716682434},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3647070825099945},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.22450393438339233},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.360.3741","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.360.3741","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.usenix.org/legacy/event/fast08/tech/full_papers/zhu/zhu.pdf","raw_type":"text"},{"id":"mag:200233886","doi":null,"is_oa":false,"landing_page_url":"https://static.usenix.org/event/fast08/tech/full_papers/zhu/zhu.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418422","display_name":"File and Storage Technologies","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":null,"is_accepted":false,"is_published":false,"raw_source_name":"File and Storage Technologies","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4943999946117401,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1576397915","https://openalex.org/W1609518033","https://openalex.org/W1993284846","https://openalex.org/W1993865637","https://openalex.org/W2007842132","https://openalex.org/W2026839093","https://openalex.org/W2053449578","https://openalex.org/W2056980397","https://openalex.org/W2094224023","https://openalex.org/W2107745473","https://openalex.org/W2121133177","https://openalex.org/W2123845384","https://openalex.org/W2132627996","https://openalex.org/W2140733653","https://openalex.org/W2155463028","https://openalex.org/W2156719566","https://openalex.org/W2157740020","https://openalex.org/W2170708842"],"related_works":["https://openalex.org/W7099928587","https://openalex.org/W1978971465","https://openalex.org/W2607426441","https://openalex.org/W2038908732","https://openalex.org/W69510097","https://openalex.org/W2281363974","https://openalex.org/W7097125055","https://openalex.org/W2990640343","https://openalex.org/W1969126835","https://openalex.org/W2026837079"],"abstract_inverted_index":{"Disk-based":[0],"deduplication":[1,118,190],"storage":[2,8],"has":[3],"emerged":[4],"as":[5],"the":[6,91,114,123,130,165,168,186],"new-generation":[7],"system":[9,80,120,202],"for":[10,46,103,138,154,189,221,227],"enterprise":[11,47],"data":[12,21,25,48,72,136,147],"protection":[13,49],"to":[14,23,35,60,67,86,98,121,150,173,203],"replace":[15],"tape":[16],"libraries.":[17],"Deduplication":[18],"removes":[19],"redundant":[20],"segments":[22,73,93,172],"compress":[24],"into":[26],"a":[27,78,133,146,198],"highly":[28],"compact":[29,134],"form":[30],"and":[31,69,94,158,217,224],"makes":[32],"it":[33],"economical":[34],"store":[36,87],"backups":[37,59],"on":[38,77],"disk":[39,124,187],"instead":[40],"of":[41,90,167,170,185,191,214],"tape.":[42],"A":[43,63],"crucial":[44],"requirement":[45],"is":[50,66],"high":[51,175],"throughput,":[52],"typically":[53],"over":[54],"100":[55,219],"MB/sec,":[56],"which":[57,163],"enables":[58],"complete":[61],"quickly.":[62],"significant":[64],"challenge":[65],"identify":[68],"eliminate":[70],"duplicate":[71,171],"at":[74,205],"this":[75],"rate":[76],"low-cost":[79],"that":[81],"cannot":[82],"afford":[83],"enough":[84],"RAM":[85],"an":[88,100],"index":[89,102],"stored":[92],"may":[95],"be":[96],"forced":[97],"access":[99],"on-disk":[101,152],"every":[104],"input":[105],"segment.":[106],"This":[107],"paper":[108],"describes":[109],"three":[110],"techniques":[111,127,196],"employed":[112],"in":[113],"production":[115],"Data":[116],"Domain":[117],"file":[119],"relieve":[122],"bottleneck.":[125],"These":[126,195],"include:":[128],"(1)":[129],"Summary":[131],"Vector,":[132],"in-memory":[135],"structure":[137],"identifying":[139],"new":[140],"segments;":[141,157],"(2)":[142],"Stream-Informed":[143],"Segment":[144],"Layout,":[145],"layout":[148],"method":[149],"improve":[151],"locality":[153,166],"sequentially":[155],"accessed":[156],"(3)":[159],"Locality":[160],"Preserved":[161],"Caching,":[162],"maintains":[164],"fingerprints":[169],"achieve":[174,218],"cache":[176],"hit":[177],"ratios.":[178],"Together,":[179],"they":[180],"can":[181],"remove":[182],"99":[183],"%":[184,207],"accesses":[188],"real":[192],"world":[193],"workloads.":[194],"enable":[197],"modern":[199],"two-socket":[200],"dual-core":[201],"run":[204],"90":[206],"CPU":[208],"utilization":[209],"with":[210],"only":[211],"one":[212],"shelf":[213],"15":[215],"disks":[216],"MB/sec":[220,226],"single-stream":[222],"throughput":[223],"210":[225],"multi-stream":[228],"throughput.":[229],"1":[230]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":28},{"year":2021,"cited_by_count":34},{"year":2020,"cited_by_count":34},{"year":2019,"cited_by_count":33},{"year":2018,"cited_by_count":51},{"year":2017,"cited_by_count":48},{"year":2016,"cited_by_count":63},{"year":2015,"cited_by_count":68},{"year":2014,"cited_by_count":67},{"year":2013,"cited_by_count":66},{"year":2012,"cited_by_count":71}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}
