{"id":"https://openalex.org/W2616099150","doi":"https://doi.org/10.1109/tpds.2017.2706686","title":"aHDFS: An Erasure-Coded Data Archival System for Hadoop Clusters","display_name":"aHDFS: An Erasure-Coded Data Archival System for Hadoop Clusters","publication_year":2017,"publication_date":"2017-05-19","ids":{"openalex":"https://openalex.org/W2616099150","doi":"https://doi.org/10.1109/tpds.2017.2706686","mag":"2616099150"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2017.2706686","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_indexed_in_scopus":true,"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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"acceptedVersion","is_accepted":true,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.1109/tpds.2017.2706686","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021685090","display_name":"Yuanqi Chen","orcid":"https://orcid.org/0000-0002-0439-4559"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuanqi Chen","raw_affiliation_strings":["[Department of Computer Science and Software Engineering, Shelby Center for Engineering Technology, Samuel Ginn College of Engineering, Auburn University, AL]"],"affiliations":[{"raw_affiliation_string":"[Department of Computer Science and Software Engineering, Shelby Center for Engineering Technology, Samuel Ginn College of Engineering, Auburn University, AL]","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100753053","display_name":"Yi Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Zhou","raw_affiliation_strings":["[Department of Computer Science and Software Engineering, Shelby Center for Engineering Technology, Samuel Ginn College of Engineering, Auburn University, AL]"],"affiliations":[{"raw_affiliation_string":"[Department of Computer Science and Software Engineering, Shelby Center for Engineering Technology, Samuel Ginn College of Engineering, Auburn University, AL]","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020988249","display_name":"Shubbhi Taneja","orcid":"https://orcid.org/0000-0002-2403-9407"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shubbhi Taneja","raw_affiliation_strings":["[Department of Computer Science and Software Engineering, Shelby Center for Engineering Technology, Samuel Ginn College of Engineering, Auburn University, AL]"],"affiliations":[{"raw_affiliation_string":"[Department of Computer Science and Software Engineering, Shelby Center for Engineering Technology, Samuel Ginn College of Engineering, Auburn University, AL]","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042766429","display_name":"Xiao Qin","orcid":"https://orcid.org/0000-0002-8345-3587"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Qin","raw_affiliation_strings":["[Department of Computer Science and Software Engineering, Shelby Center for Engineering Technology, Samuel Ginn College of Engineering, Auburn University, AL]"],"affiliations":[{"raw_affiliation_string":"[Department of Computer Science and Software Engineering, Shelby Center for Engineering Technology, Samuel Ginn College of Engineering, Auburn University, AL]","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101526535","display_name":"Jianzhong Huang","orcid":"https://orcid.org/0000-0003-0568-4168"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]},{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzhong Huang","raw_affiliation_strings":["Wuhan National Lab. for Optoelectronics, Huazhong University of Science and Technology (HUST), Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"Wuhan National Lab. for Optoelectronics, Huazhong University of Science and Technology (HUST), Wuhan, Hubei, China","institution_ids":["https://openalex.org/I47720641","https://openalex.org/I4210138186"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.126,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":16,"citation_normalized_percentile":{"value":0.88022,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":90},"biblio":{"volume":"28","issue":"11","first_page":"3060","last_page":"3073"},"is_retracted":false,"is_paratext":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":0.9973,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9896,"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/shuffling","display_name":"Shuffling","score":0.5030927},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.4692267},{"id":"https://openalex.org/keywords/associative-array","display_name":"Associative array","score":0.4123261}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8425871},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.64478296},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5685798},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.53752625},{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.5030927},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.49416235},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.4692267},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.46851397},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.43051416},{"id":"https://openalex.org/C168781493","wikidata":"https://www.wikidata.org/wiki/Q80585","display_name":"Associative array","level":2,"score":0.4123261},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.41006494},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.35319746},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2017.2706686","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_indexed_in_scopus":true,"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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"acceptedVersion","is_accepted":true,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2017.2706686","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_indexed_in_scopus":true,"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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"acceptedVersion","is_accepted":true,"is_published":false},"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation","award_id":"IIS-1618669"},{"funder":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation","award_id":"CCF-0845257"},{"funder":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation","award_id":"CNS-0917137"},{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"61572209"},{"funder":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities","award_id":"HUST: 2015MS006"}],"datasets":[],"versions":[],"referenced_works_count":33,"referenced_works":["https://openalex.org/W1510496002","https://openalex.org/W1515553635","https://openalex.org/W154253821","https://openalex.org/W1576397915","https://openalex.org/W1605552180","https://openalex.org/W180607499","https://openalex.org/W1905719725","https://openalex.org/W2003829707","https://openalex.org/W2004958263","https://openalex.org/W2014405145","https://openalex.org/W2018478911","https://openalex.org/W2026527452","https://openalex.org/W2029467255","https://openalex.org/W2035324862","https://openalex.org/W2054526666","https://openalex.org/W2073108794","https://openalex.org/W2086797542","https://openalex.org/W2099905591","https://openalex.org/W2119528150","https://openalex.org/W2119565742","https://openalex.org/W2120396387","https://openalex.org/W2131645490","https://openalex.org/W2138744797","https://openalex.org/W2148575324","https://openalex.org/W2150620836","https://openalex.org/W2156719566","https://openalex.org/W2173213060","https://openalex.org/W2594712981","https://openalex.org/W3163634073","https://openalex.org/W330091898","https://openalex.org/W4243708007","https://openalex.org/W4301006390","https://openalex.org/W52352892"],"related_works":["https://openalex.org/W6847055","https://openalex.org/W4366492512","https://openalex.org/W4285281676","https://openalex.org/W3003962028","https://openalex.org/W2926840673","https://openalex.org/W2789535578","https://openalex.org/W2517154368","https://openalex.org/W2121854243","https://openalex.org/W2058189720","https://openalex.org/W1976720595"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"an":[5],"erasure-coded":[6],"data":[7,25,49,54,109,114],"archival":[8,38,50,110],"system":[9,32],"called":[10],"aHDFS":[11,147,184],"for":[12,141],"Hadoop":[13,29,118,151],"clusters,":[14],"where":[15],"RS(k":[16],"+":[17],"r;":[18],"k)":[19],"codes":[20],"are":[21],"employed":[22],"to":[23,99,101,127],"archive":[24],"replicas":[26],"in":[27,44,65,74,116,136,148],"the":[28,48,71,79,84,95,122,137,186],"distributed":[30],"file":[31],"or":[33],"HDFS.":[34],"We":[35,145],"develop":[36],"two":[37],"strategies":[39],"(i.e.,":[40],"aHDFS-Grouping":[41,76,158],"and":[42,159,165,173,190,195],"aHDFS-Pipeline)":[43],"aHDFSto":[45],"speed":[46,161],"up":[47,162],"process.":[51],"aHDFS-Groupinga":[52],"MapReduce-based":[53],"archiving":[55],"scheme":[56],"-":[57],"keeps":[58],"each":[59],"mapper's":[60],"intermediate":[61,80],"output":[62],"Key-Value":[63,97],"pairs":[64,82],"a":[66,108,117,128,149,169],"local":[67,72,131],"key-value":[68,81,90,125,132],"store.":[69,133],"With":[70],"store":[73],"place,":[75],"merges":[77],"all":[78],"with":[83],"same":[85],"key":[86],"into":[87],"one":[88],"single":[89,96,124],"pair,":[91],"followed":[92],"by":[93,168,192],"shuffling":[94],"pair":[98,126],"reducers":[100],"generate":[102],"final":[103],"parity":[104,143],"blocks.":[105,144],"aHDFS-Pipeline":[106,120,160],"forms":[107],"pipeline":[111,138],"using":[112],"multiple":[113],"node":[115,135],"cluster.":[119,152],"delivers":[121],"merged":[123],"subsequent":[129],"node's":[130],"Last":[134],"is":[139,179],"responsible":[140],"outputting":[142],"implement":[146],"real-world":[150],"The":[153],"experimental":[154],"results":[155],"show":[156],"that":[157],"Baseline's":[163],"shuffle":[164],"reduce":[166],"phases":[167],"factor":[170],"of":[171,188],"10":[172],"5,":[174],"respectively.":[175,198],"When":[176],"block":[177],"size":[178],"larger":[180],"than":[181],"32":[182],"MB,":[183],"improves":[185],"performance":[187],"HDFS-RAID":[189],"HDFS-EC":[191],"approximately":[193],"31.8":[194],"15.7":[196],"percent,":[197]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2616099150","counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2025-01-19T14:26:47.718679","created_date":"2017-05-26"}