{"id":"https://openalex.org/W4221131764","doi":"https://doi.org/10.1145/3503646.3524296","title":"Understanding the performance of erasure codes in hadoop distributed file system","display_name":"Understanding the performance of erasure codes in hadoop distributed file system","publication_year":2022,"publication_date":"2022-03-24","ids":{"openalex":"https://openalex.org/W4221131764","doi":"https://doi.org/10.1145/3503646.3524296"},"language":"en","primary_location":{"id":"doi:10.1145/3503646.3524296","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503646.3524296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Challenges and Opportunities of Efficient and Performant Storage Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-03890398","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018106912","display_name":"Jad Darrous","orcid":"https://orcid.org/0000-0003-4573-4529"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210117005","display_name":"Laboratoire des Sciences du Num\u00e9rique de Nantes","ror":"https://ror.org/02snf8m58","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100445878","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I4210117005","https://openalex.org/I4210124215","https://openalex.org/I4210127572","https://openalex.org/I4210139971","https://openalex.org/I97188460","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I4210127572","display_name":"IMT Atlantique","ror":"https://ror.org/030hj3061","country_code":"FR","type":"education","lineage":["https://openalex.org/I205703379","https://openalex.org/I4210127572"]},{"id":"https://openalex.org/I97188460","display_name":"Nantes Universit\u00e9","ror":"https://ror.org/03gnr7b55","country_code":"FR","type":"education","lineage":["https://openalex.org/I97188460"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jad Darrous","raw_affiliation_strings":["IMT Atlantique, Nantes, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IMT Atlantique, Nantes, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210117005","https://openalex.org/I4210127572","https://openalex.org/I97188460"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090305095","display_name":"Shadi Ibrahim","orcid":"https://orcid.org/0000-0002-4306-5280"},"institutions":[{"id":"https://openalex.org/I140863075","display_name":"Myriad (Germany)","ror":"https://ror.org/033sa9s17","country_code":"DE","type":"company","lineage":["https://openalex.org/I140863075","https://openalex.org/I4210166221"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["DE","FR"],"is_corresponding":false,"raw_author_name":"Shadi Ibrahim","raw_affiliation_strings":["Univ. Rennes, Rennes, France","MYRIADS - Design and Implementation of Autonomous Distributed Systems (Campus de Beaulieu 35042 Rennes cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Rennes, Rennes, France","institution_ids":["https://openalex.org/I56067802"]},{"raw_affiliation_string":"MYRIADS - Design and Implementation of Autonomous Distributed Systems (Campus de Beaulieu 35042 Rennes cedex - France)","institution_ids":["https://openalex.org/I140863075"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24","last_page":"32"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9995999932289124,"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":0.9941999912261963,"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/computer-science","display_name":"Computer science","score":0.8319600820541382},{"id":"https://openalex.org/keywords/distributed-file-system","display_name":"Distributed File System","score":0.7666674852371216},{"id":"https://openalex.org/keywords/replication","display_name":"Replication (statistics)","score":0.7414512038230896},{"id":"https://openalex.org/keywords/erasure-code","display_name":"Erasure code","score":0.7394486665725708},{"id":"https://openalex.org/keywords/distributed-data-store","display_name":"Distributed data store","score":0.6248056292533875},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.5445776581764221},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.507023811340332},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4773678481578827},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4584720730781555},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.44833168387413025},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.44369128346443176},{"id":"https://openalex.org/keywords/file-system","display_name":"File system","score":0.4350968897342682},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.39978304505348206},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2671962082386017},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.2069702446460724},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07464599609375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8319600820541382},{"id":"https://openalex.org/C152043487","wikidata":"https://www.wikidata.org/wiki/Q1229600","display_name":"Distributed File System","level":2,"score":0.7666674852371216},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.7414512038230896},{"id":"https://openalex.org/C137529215","wikidata":"https://www.wikidata.org/wiki/Q5385031","display_name":"Erasure code","level":3,"score":0.7394486665725708},{"id":"https://openalex.org/C24885549","wikidata":"https://www.wikidata.org/wiki/Q339678","display_name":"Distributed data store","level":2,"score":0.6248056292533875},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.5445776581764221},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.507023811340332},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4773678481578827},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4584720730781555},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.44833168387413025},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.44369128346443176},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.4350968897342682},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.39978304505348206},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2671962082386017},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2069702446460724},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07464599609375},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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":2,"locations":[{"id":"doi:10.1145/3503646.3524296","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503646.3524296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Challenges and Opportunities of Efficient and Performant Storage Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03890398v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-03890398","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"CHEOPS 22 - Proceedings of the Workshop on Challenges and Opportunities of Efficient and Performant Storage Systems, Apr 2022, Rennes, France. pp.24-32, ⟨10.1145/3503646.3524296⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-03890398v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-03890398","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"CHEOPS 22 - Proceedings of the Workshop on Challenges and Opportunities of Efficient and Performant Storage Systems, Apr 2022, Rennes, France. pp.24-32, ⟨10.1145/3503646.3524296⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G1370646635","display_name":"Big Data Processing: Beyond Hadoop!","funder_award_id":"ANR-16-CE25-0014","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1496637959","https://openalex.org/W1822772607","https://openalex.org/W2096125134","https://openalex.org/W2096893233","https://openalex.org/W2099602864","https://openalex.org/W2119738171","https://openalex.org/W2130373037","https://openalex.org/W2138744797","https://openalex.org/W2139274913","https://openalex.org/W2150620836","https://openalex.org/W2173213060","https://openalex.org/W2240943048","https://openalex.org/W2295280497","https://openalex.org/W2545520215","https://openalex.org/W2735440174","https://openalex.org/W2808200030","https://openalex.org/W2808383901","https://openalex.org/W2903455402","https://openalex.org/W2912506132","https://openalex.org/W2912574597","https://openalex.org/W2912918068","https://openalex.org/W2954992200","https://openalex.org/W2964854139","https://openalex.org/W4238584892","https://openalex.org/W4253724857"],"related_works":["https://openalex.org/W2963163039","https://openalex.org/W2807749388","https://openalex.org/W2623177195","https://openalex.org/W4294555231","https://openalex.org/W2095952791","https://openalex.org/W1667838839","https://openalex.org/W1480425691","https://openalex.org/W2532270758","https://openalex.org/W2086474248","https://openalex.org/W2728364329"],"abstract_inverted_index":{"Replication":[0],"has":[1,28,92],"been":[2,93],"successfully":[3],"employed":[4,53],"and":[5,24,45,125,137,151],"practiced":[6],"to":[7,58,64],"ensure":[8],"high":[9,61],"data":[10,66,87,113,130],"availability":[11],"in":[12,33,40,75,132,156,169],"large-scale":[13],"distributed":[14],"storage":[15,36,110],"systems.":[16],"However,":[17,70],"with":[18,71],"the":[19,65,72,83,96,108,127,165,174],"relentless":[20],"growth":[21],"of":[22,35,42,86,100,129],"generated":[23],"collected":[25],"data,":[26],"replication":[27,59,136,155],"become":[29],"expensive":[30],"not":[31],"only":[32],"terms":[34,41],"cost":[37,44],"but":[38],"also":[39],"network":[43],"hardware":[46],"cost.":[47],"Traditionally,":[48],"erasure":[49],"coding":[50],"(EC)":[51],"is":[52,80,107,144,164],"as":[54],"a":[55,145],"cost-efficient":[56],"alternative":[57],"when":[60],"access":[62],"latency":[63],"can":[67,153],"be":[68],"tolerated.":[69],"continuous":[73],"reduction":[74],"its":[76],"CPU":[77],"overhead,":[78],"EC":[79,91,143],"performed":[81],"on":[82],"critical":[84],"path":[85],"access.":[88],"For":[89],"instance,":[90],"integrated":[94],"into":[95],"last":[97],"major":[98],"release":[99],"Hadoop":[101],"Distributed":[102],"File":[103],"System":[104],"(HDFS)":[105],"which":[106],"primary":[109],"backend":[111],"for":[112,148],"analytic":[114],"frameworks":[115],"(e.g.,":[116],"Hadoop,":[117],"Spark,":[118],"etc.).":[119],"In":[120],"this":[121],"work,":[122],"we":[123,160],"measure":[124],"compare":[126],"performance":[128,175],"accesses":[131],"HDFS":[133,170],"under":[134,176],"both":[135],"EC.":[138,177],"Our":[139],"analysis":[140],"indicates":[141],"that":[142,162,171],"feasible":[146],"solution":[147],"data-intensive":[149],"applications":[150],"it":[152,163],"outperform":[154],"many":[157],"scenarios.":[158],"Furthermore,":[159],"demonstrate":[161],"block":[166],"placement":[167],"algorithm":[168],"mostly":[172],"impacts":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}