{"id":"https://openalex.org/W2092970258","doi":"https://doi.org/10.1145/2421648.2421657","title":"Space savings and design considerations in variable length deduplication","display_name":"Space savings and design considerations in variable length deduplication","publication_year":2012,"publication_date":"2012-12-18","ids":{"openalex":"https://openalex.org/W2092970258","doi":"https://doi.org/10.1145/2421648.2421657","mag":"2092970258"},"language":"en","primary_location":{"id":"doi:10.1145/2421648.2421657","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2421648.2421657","pdf_url":null,"source":{"id":"https://openalex.org/S50071195","display_name":"ACM SIGOPS Operating Systems Review","issn_l":"0163-5980","issn":["0163-5980","1943-586X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGOPS Operating Systems Review","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/A5041963958","display_name":"Giridhar Appaji Nag Yasa","orcid":null},"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":true,"raw_author_name":"Giridhar Appaji Nag Yasa","raw_affiliation_strings":["NetApp Inc"],"affiliations":[{"raw_affiliation_string":"NetApp Inc","institution_ids":["https://openalex.org/I1283576576"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061637205","display_name":"P. C. Nagesh","orcid":null},"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":"P. C. Nagesh","raw_affiliation_strings":["NetApp Inc"],"affiliations":[{"raw_affiliation_string":"NetApp Inc","institution_ids":["https://openalex.org/I1283576576"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5041963958"],"corresponding_institution_ids":["https://openalex.org/I1283576576"],"apc_list":null,"apc_paid":null,"fwci":0.75806771,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.73973648,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"46","issue":"3","first_page":"57","last_page":"64"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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":0.9998999834060669,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9984999895095825,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9984999895095825,"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":0.983039379119873},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8560500144958496},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.763156533241272},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6097561120986938},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.48551249504089355},{"id":"https://openalex.org/keywords/backup","display_name":"Backup","score":0.4781528413295746},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.4699086546897888},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3821236789226532},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15252098441123962},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.07664349675178528}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.983039379119873},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8560500144958496},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.763156533241272},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6097561120986938},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.48551249504089355},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.4781528413295746},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.4699086546897888},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3821236789226532},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15252098441123962},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.07664349675178528},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2421648.2421657","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2421648.2421657","pdf_url":null,"source":{"id":"https://openalex.org/S50071195","display_name":"ACM SIGOPS Operating Systems Review","issn_l":"0163-5980","issn":["0163-5980","1943-586X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGOPS Operating Systems Review","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W69510097","https://openalex.org/W178328500","https://openalex.org/W200233886","https://openalex.org/W1576397915","https://openalex.org/W1600255172","https://openalex.org/W1609518033","https://openalex.org/W1984081611","https://openalex.org/W2007842132","https://openalex.org/W2056980397","https://openalex.org/W2103358620","https://openalex.org/W2128593562","https://openalex.org/W2130286559","https://openalex.org/W2134792144","https://openalex.org/W2146889157","https://openalex.org/W2153158407","https://openalex.org/W2281363974","https://openalex.org/W2911837627","https://openalex.org/W2915025126","https://openalex.org/W3145042860"],"related_works":["https://openalex.org/W2955195711","https://openalex.org/W1437397736","https://openalex.org/W4285245558","https://openalex.org/W2048606985","https://openalex.org/W2375056709","https://openalex.org/W4301155776","https://openalex.org/W2012359782","https://openalex.org/W2952411620","https://openalex.org/W3156188733","https://openalex.org/W2348132657"],"abstract_inverted_index":{"Explosion":[0],"of":[1,6,15,18,29,73,82,86,95,103,135,150,183,189,200,205],"data":[2,7,62,184,201],"growth":[3],"and":[4,75,113,120,123,146,154,185],"duplication":[5],"in":[8,35,57,70,111,161],"enterprises":[9],"has":[10],"led":[11],"to":[12,139,253,259],"the":[13,27,60,71,80,83,167,206,212,220,224,231,255],"deployment":[14],"a":[16,47,100,115,129,148,151,195,260],"variety":[17],"deduplication":[19,24,36,51,130,157,237],"technologies.":[20],"However":[21],"not":[22,64,179,216],"all":[23],"technologies":[25],"serve":[26],"needs":[28],"every":[30],"workload.":[31],"Most":[32],"prior":[33],"research":[34],"concentrates":[37],"on":[38],"fixed":[39,48,261],"block":[40,44,49,65,155,217,262],"size":[41,45],"(or":[42],"variable":[43,152,227],"at":[46],"boundary)":[50],"which":[52],"provides":[53,251],"sub-optimal":[54],"space":[55,256],"efficiency":[56],"workloads":[58,89],"where":[59],"duplicate":[61,104],"is":[63,159,209,223],"aligned.":[66,218],"Workloads":[67],"also":[68,108],"differ":[69],"nature":[72,112],"operations":[74],"their":[76],"priorities":[77],"thereby":[78],"affecting":[79],"choice":[81],"right":[84],"flavor":[85],"deduplication.":[87,263],"Object":[88],"for":[90,226],"instance,":[91],"hold":[92],"multiple":[93],"versions":[94,188,204],"archived":[96],"documents":[97],"that":[98,132,158,249],"have":[99],"high":[101],"degree":[102],"data.":[105,140],"They":[106],"are":[107,164,191,214],"write-once":[109],"read-many":[110],"follow":[114],"whole":[116,196],"object":[117,175,208],"GET,":[118],"PUT":[119],"DELETE":[121],"model":[122],"would":[124],"be":[125],"better":[126],"served":[127],"by":[128,166],"strategy":[131],"takes":[133],"care":[134],"nonblock":[136],"aligned":[137],"changes":[138,213],"In":[141],"this":[142,250],"paper,":[143],"we":[144],"describe":[145],"evaluate":[147],"hybrid":[149],"length":[153,228],"based":[156],"hierarchical":[160,236],"nature.":[162],"We":[163,239],"motivated":[165],"following":[168],"insights":[169,233],"from":[170,246],"real":[171],"world":[172],"data:":[173],"(a)":[174],"workload":[176],"applications":[177],"do":[178,180],"in-place":[181],"modification":[182],"hence":[186],"new":[187],"objects":[190],"written":[192],"again":[193],"as":[194],"(b)":[197],"significant":[198],"amount":[199],"among":[202],"different":[203],"same":[207],"shareable":[210],"but":[211],"usually":[215],"While":[219],"second":[221],"point":[222],"basis":[225],"technique,":[229],"both":[230],"above":[232],"motivate":[234],"our":[235],"strategy.":[238],"show":[240],"through":[241],"experiments":[242],"with":[243],"production":[244],"data-sets":[245],"enterprise":[247],"environments":[248],"up":[252],"twice":[254],"savings":[257],"compared":[258]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
