{"id":"https://openalex.org/W2147407897","doi":"https://doi.org/10.1145/1837915.1837921","title":"I/O Deduplication","display_name":"I/O Deduplication","publication_year":2010,"publication_date":"2010-09-01","ids":{"openalex":"https://openalex.org/W2147407897","doi":"https://doi.org/10.1145/1837915.1837921","mag":"2147407897"},"language":"en","primary_location":{"id":"doi:10.1145/1837915.1837921","doi":"https://doi.org/10.1145/1837915.1837921","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1837915.1837921","pdf_url":null,"source":{"id":"https://openalex.org/S158124317","display_name":"ACM Transactions on Storage","issn_l":"1553-3077","issn":["1553-3077","1553-3093"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-a","cwts-core","dongbi-a","jufo-1","norway-1","poland-70","russia-white-list-3"],"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 Transactions on Storage","raw_type":"journal-article"},"volume":null,"type":"article","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/A5036652714","display_name":"Ricardo Koller","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ricardo Koller","raw_affiliation_strings":["Florida International University, Miami, FL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Florida International University, Miami, FL","institution_ids":["https://openalex.org/I19700959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052356609","display_name":"Raju Rangaswami","orcid":"https://orcid.org/0009-0000-5243-9451","observed_orcids":["https://orcid.org/0009-0000-5243-9451"]},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raju Rangaswami","raw_affiliation_strings":["Florida International University, Miami, FL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Florida International University, Miami, FL","institution_ids":["https://openalex.org/I19700959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I19700959"],"apc_list":null,"apc_paid":null,"fwci":24.0303,"has_fulltext":false,"cited_by_count":261,"citation_normalized_percentile":{"value":0.9960128,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"6","issue":"3","first_page":"1","last_page":"26"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.0,"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/T11269","display_name":"Algorithms and Data Compression","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/storage-optimization","display_name":"storage optimization","score":0.8029999732971191},{"id":"https://openalex.org/keywords/content-similarity","display_name":"content similarity","score":0.8830000162124634},{"id":"https://openalex.org/keywords/disk-i-o-performance","display_name":"disk I/O performance","score":0.949999988079071}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9921447038650513},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8767533302307129},{"id":"https://openalex.org/C2775937380","wikidata":"https://www.wikidata.org/wiki/Q1232589","display_name":"Replica","level":2,"score":0.835094690322876},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.6508780121803284},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.5019192695617676},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4895959496498108},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.4568200707435608},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24667015671730042},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1837915.1837921","doi":"https://doi.org/10.1145/1837915.1837921","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1837915.1837921","pdf_url":null,"source":{"id":"https://openalex.org/S158124317","display_name":"ACM Transactions on Storage","issn_l":"1553-3077","issn":["1553-3077","1553-3093"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-a","cwts-core","dongbi-a","jufo-1","norway-1","poland-70","russia-white-list-3"],"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 Transactions on Storage","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.8381","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.8381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.fiu.edu/%7Eraju/WWW/publications/acmtos2010/paper.pdf","raw_type":"text"},{"id":"mag:2583401777","doi":null,"is_oa":false,"landing_page_url":"https://www.usenix.org/events/fast10/tech/full_papers/koller.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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4262054693","display_name":null,"funder_award_id":"CNS-0747038CNS-0821345IIS-0837716","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"},{"id":"https://openalex.org/G6146173945","display_name":null,"funder_award_id":"CNS-0747038CNS-0821345IIS-0837716","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"}],"funders":[{"id":"https://openalex.org/F4320337388","display_name":"Division of Computer and Network Systems","ror":"https://ror.org/02rdzmk74"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W41212852","https://openalex.org/W69510097","https://openalex.org/W133196353","https://openalex.org/W174289249","https://openalex.org/W200233886","https://openalex.org/W1489843519","https://openalex.org/W1498936153","https://openalex.org/W1558370646","https://openalex.org/W1576397915","https://openalex.org/W1589276590","https://openalex.org/W1633637678","https://openalex.org/W1806231964","https://openalex.org/W1860107648","https://openalex.org/W2001122975","https://openalex.org/W2007842132","https://openalex.org/W2041516144","https://openalex.org/W2049526731","https://openalex.org/W2053449578","https://openalex.org/W2056980397","https://openalex.org/W2058293287","https://openalex.org/W2080232995","https://openalex.org/W2103939416","https://openalex.org/W2121542813","https://openalex.org/W2122244530","https://openalex.org/W2123845384","https://openalex.org/W2125788329","https://openalex.org/W2128946566","https://openalex.org/W2132627996","https://openalex.org/W2140733653","https://openalex.org/W2140815597","https://openalex.org/W2147420644","https://openalex.org/W2149993626","https://openalex.org/W2158310845","https://openalex.org/W2164705534","https://openalex.org/W2216311525","https://openalex.org/W2294212370","https://openalex.org/W2912230285","https://openalex.org/W4231676608"],"related_works":["https://openalex.org/W2583401777","https://openalex.org/W2346097572","https://openalex.org/W2615422159","https://openalex.org/W7221283170","https://openalex.org/W3015469686","https://openalex.org/W2113154035","https://openalex.org/W1988596907","https://openalex.org/W2593701234","https://openalex.org/W4378228047","https://openalex.org/W2992247304"],"abstract_inverted_index":{"Duplication":[0],"of":[1,40,55,74,80,90,105,118],"data":[2],"in":[3,101],"storage":[4,15,71],"systems":[5],"is":[6,58],"becoming":[7],"increasingly":[8],"common.":[9],"We":[10],"introduce":[11],"I/O":[12,23,27,35,37,64,103],"Deduplication,":[13],"a":[14,91],"optimization":[16],"that":[17,116],"utilizes":[18],"content":[19,81],"similarity":[20,82],"for":[21,83],"improving":[22],"performance":[24,104,127],"by":[25,60],"eliminating":[26],"operations":[28],"and":[29,50,86],"reducing":[30],"the":[31,119,125],"mechanical":[32],"delays":[33],"during":[34],"operations.":[36],"Deduplication":[38],"consists":[39],"three":[41,120],"main":[42],"techniques:":[43],"content-based":[44],"caching,":[45],"dynamic":[46],"replica":[47],"retrieval":[48],",":[49],"selective":[51],"duplication":[52],".":[53],"Each":[54],"these":[56,95,110],"techniques":[57,121],"motivated":[59],"our":[61],"observations":[62],"with":[63],"workload":[65],"traces":[66],"obtained":[67],"from":[68],"actively-used":[69],"production":[70],"systems,":[72],"all":[73],"which":[75],"revealed":[76],"surprisingly":[77],"high":[78],"levels":[79],"both":[84],"stored":[85],"accessed":[87],"data.":[88],"Evaluation":[89],"prototype":[92],"implementation":[93],"using":[94],"workloads":[96],"showed":[97,115],"an":[98],"overall":[99,126],"improvement":[100],"disk":[102],"28":[106],"to":[107,124],"47%":[108],"across":[109],"workloads.":[111],"Further":[112],"breakdown":[113],"also":[114],"each":[117],"contributed":[122],"significantly":[123],"improvement.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":18},{"year":2017,"cited_by_count":20},{"year":2016,"cited_by_count":25},{"year":2015,"cited_by_count":20},{"year":2014,"cited_by_count":19},{"year":2013,"cited_by_count":20},{"year":2012,"cited_by_count":20}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}
