{"id":"https://openalex.org/W2119738171","doi":"https://doi.org/10.1109/msst.2010.5496972","title":"The Hadoop Distributed File System","display_name":"The Hadoop Distributed File System","publication_year":2010,"publication_date":"2010-05-01","ids":{"openalex":"https://openalex.org/W2119738171","doi":"https://doi.org/10.1109/msst.2010.5496972","mag":"2119738171"},"language":"en","primary_location":{"id":"doi:10.1109/msst.2010.5496972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msst.2010.5496972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th Symposium on Mass Storage Systems and Technologies (MSST)","raw_type":"proceedings-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/A5057751006","display_name":"Konstantin V. Shvachko","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Konstantin Shvachko","raw_affiliation_strings":["Yahoo, Inc., Sunnyvale, CA, USA","Yahoo! Sunnyvale, California USA"],"affiliations":[{"raw_affiliation_string":"Yahoo, Inc., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Sunnyvale, California USA","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064863685","display_name":"Hairong Kuang","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Hairong Kuang","raw_affiliation_strings":["Yahoo, Inc., Sunnyvale, CA, USA","Yahoo! Sunnyvale, California USA"],"affiliations":[{"raw_affiliation_string":"Yahoo, Inc., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Sunnyvale, California USA","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083303224","display_name":"Sanjay Radia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Sanjay Radia","raw_affiliation_strings":["Yahoo, Inc., Sunnyvale, CA, USA","Yahoo! Sunnyvale, California USA"],"affiliations":[{"raw_affiliation_string":"Yahoo, Inc., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Sunnyvale, California USA","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087931705","display_name":"Robert J. Chansler","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Robert Chansler","raw_affiliation_strings":["Yahoo, Inc., Sunnyvale, CA, USA","Yahoo! Sunnyvale, California USA"],"affiliations":[{"raw_affiliation_string":"Yahoo, Inc., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Sunnyvale, California USA","institution_ids":["https://openalex.org/I1325784139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057751006"],"corresponding_institution_ids":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":397.1017,"has_fulltext":false,"cited_by_count":4812,"citation_normalized_percentile":{"value":0.99997896,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998000264167786,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9997000098228455,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.8414528369903564},{"id":"https://openalex.org/keywords/petabyte","display_name":"Petabyte","score":0.8013111352920532},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.7903007864952087},{"id":"https://openalex.org/keywords/distributed-file-system","display_name":"Distributed File System","score":0.7830948233604431},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.7204435467720032},{"id":"https://openalex.org/keywords/distributed-data-store","display_name":"Distributed data store","score":0.55186927318573},{"id":"https://openalex.org/keywords/file-system","display_name":"File system","score":0.5240424275398254},{"id":"https://openalex.org/keywords/file-server","display_name":"File server","score":0.519217312335968},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.4996156692504883},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.46105945110321045},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4207608997821808},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.2964789867401123}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8414528369903564},{"id":"https://openalex.org/C13600138","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Petabyte","level":3,"score":0.8013111352920532},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.7903007864952087},{"id":"https://openalex.org/C152043487","wikidata":"https://www.wikidata.org/wiki/Q1229600","display_name":"Distributed File System","level":2,"score":0.7830948233604431},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.7204435467720032},{"id":"https://openalex.org/C24885549","wikidata":"https://www.wikidata.org/wiki/Q339678","display_name":"Distributed data store","level":2,"score":0.55186927318573},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.5240424275398254},{"id":"https://openalex.org/C4373008","wikidata":"https://www.wikidata.org/wiki/Q513349","display_name":"File server","level":2,"score":0.519217312335968},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.4996156692504883},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.46105945110321045},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4207608997821808},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2964789867401123}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/msst.2010.5496972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msst.2010.5496972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th Symposium on Mass Storage Systems and Technologies (MSST)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.178.989","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.178.989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://storageconference.org/2010/Papers/MSST/Shvachko.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1598064945","https://openalex.org/W1999984505","https://openalex.org/W2021534030","https://openalex.org/W2023502337","https://openalex.org/W2100077456","https://openalex.org/W2110086534","https://openalex.org/W2110298485","https://openalex.org/W2119565742","https://openalex.org/W2122465391","https://openalex.org/W2131894525","https://openalex.org/W2142031898","https://openalex.org/W2168229136","https://openalex.org/W2277359368","https://openalex.org/W2610848972","https://openalex.org/W2913298375","https://openalex.org/W3162803548","https://openalex.org/W4239670432","https://openalex.org/W6635687051","https://openalex.org/W6650418438","https://openalex.org/W6676560735","https://openalex.org/W6679481876","https://openalex.org/W6694713699"],"related_works":["https://openalex.org/W2614151974","https://openalex.org/W1480425691","https://openalex.org/W2571822082","https://openalex.org/W3042976586","https://openalex.org/W2550058611","https://openalex.org/W2621922713","https://openalex.org/W2488366707","https://openalex.org/W2119738171","https://openalex.org/W1987221064","https://openalex.org/W1920242583"],"abstract_inverted_index":{"The":[0],"Hadoop":[1],"Distributed":[2],"File":[3],"System":[4],"(HDFS)":[5],"is":[6],"designed":[7],"to":[8,16,24,76],"store":[9],"very":[10],"large":[11,29],"data":[12,19,82],"sets":[13,20],"reliably,":[14],"and":[15,39,47,70],"stream":[17],"those":[18],"at":[21,61,83],"high":[22],"bandwidth":[23],"user":[25,41],"applications.":[26],"In":[27],"a":[28],"cluster,":[30],"thousands":[31],"of":[32,68,80],"servers":[33],"both":[34],"host":[35],"directly":[36],"attached":[37],"storage":[38,46],"execute":[40],"application":[42],"tasks.":[43],"By":[44],"distributing":[45],"computation":[48],"across":[49],"many":[50],"servers,":[51],"the":[52,66],"resource":[53],"can":[54],"grow":[55],"with":[56],"demand":[57],"while":[58],"remaining":[59],"economical":[60],"every":[62],"size.":[63],"We":[64],"describe":[65],"architecture":[67],"HDFS":[69,75],"report":[71],"on":[72],"experience":[73],"using":[74],"manage":[77],"25":[78],"petabytes":[79],"enterprise":[81],"Yahoo!.":[84]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":117},{"year":2024,"cited_by_count":107},{"year":2023,"cited_by_count":200},{"year":2022,"cited_by_count":229},{"year":2021,"cited_by_count":294},{"year":2020,"cited_by_count":351},{"year":2019,"cited_by_count":425},{"year":2018,"cited_by_count":505},{"year":2017,"cited_by_count":499},{"year":2016,"cited_by_count":521},{"year":2015,"cited_by_count":557},{"year":2014,"cited_by_count":432},{"year":2013,"cited_by_count":304},{"year":2012,"cited_by_count":152}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
