{"id":"https://openalex.org/W1498140008","doi":"https://doi.org/10.14778/2824032.2824085","title":"FP-Hadoop","display_name":"FP-Hadoop","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W1498140008","doi":"https://doi.org/10.14778/2824032.2824085","mag":"1498140008"},"language":"en","primary_location":{"id":"doi:10.14778/2824032.2824085","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2824032.2824085","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal-lirmm.ccsd.cnrs.fr/lirmm-01162362","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051179094","display_name":"Miguel Liroz-Gistau","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101743","display_name":"Laboratoire d'Informatique, de Robotique et de Micro\u00e9lectronique de Montpellier","ror":"https://ror.org/013yean28","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I151295451","https://openalex.org/I19894307","https://openalex.org/I4210101743","https://openalex.org/I4210159245","https://openalex.org/I4405261681"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Miguel Liroz-Gistau","raw_affiliation_strings":["Inria & LIRMM, Montpellier, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria & LIRMM, Montpellier, France","institution_ids":["https://openalex.org/I4210101743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070807320","display_name":"Reza Akbarinia","orcid":"https://orcid.org/0000-0003-0372-0241"},"institutions":[{"id":"https://openalex.org/I4210101743","display_name":"Laboratoire d'Informatique, de Robotique et de Micro\u00e9lectronique de Montpellier","ror":"https://ror.org/013yean28","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I151295451","https://openalex.org/I19894307","https://openalex.org/I4210101743","https://openalex.org/I4210159245","https://openalex.org/I4405261681"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Reza Akbarinia","raw_affiliation_strings":["Inria & LIRMM, Montpellier, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria & LIRMM, Montpellier, France","institution_ids":["https://openalex.org/I4210101743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041964026","display_name":"Patrick Valduriez","orcid":"https://orcid.org/0000-0001-6506-7538"},"institutions":[{"id":"https://openalex.org/I4210101743","display_name":"Laboratoire d'Informatique, de Robotique et de Micro\u00e9lectronique de Montpellier","ror":"https://ror.org/013yean28","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I151295451","https://openalex.org/I19894307","https://openalex.org/I4210101743","https://openalex.org/I4210159245","https://openalex.org/I4405261681"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Patrick Valduriez","raw_affiliation_strings":["Inria & LIRMM, Montpellier, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria & LIRMM, Montpellier, France","institution_ids":["https://openalex.org/I4210101743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210101743"],"apc_list":null,"apc_paid":null,"fwci":2.4379,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.90555375,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"8","issue":"12","first_page":"1856","last_page":"1859"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9968000054359436,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9958000183105469,"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":0.8498618602752686},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7655462622642517},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.7608754634857178},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7248461246490479},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.6215837597846985},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.54132479429245},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5010643005371094},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.45416149497032166},{"id":"https://openalex.org/keywords/data-intensive-computing","display_name":"Data-intensive computing","score":0.4492253363132477},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.42595288157463074},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3326367735862732},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3274775743484497},{"id":"https://openalex.org/keywords/grid-computing","display_name":"Grid computing","score":0.0776452124118805}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8498618602752686},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7655462622642517},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.7608754634857178},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7248461246490479},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.6215837597846985},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.54132479429245},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5010643005371094},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.45416149497032166},{"id":"https://openalex.org/C76831024","wikidata":"https://www.wikidata.org/wiki/Q5227096","display_name":"Data-intensive computing","level":4,"score":0.4492253363132477},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.42595288157463074},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3326367735862732},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3274775743484497},{"id":"https://openalex.org/C70429105","wikidata":"https://www.wikidata.org/wiki/Q249999","display_name":"Grid computing","level":3,"score":0.0776452124118805},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/2824032.2824085","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2824032.2824085","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:HAL:lirmm-01162362v1","is_oa":true,"landing_page_url":"https://hal-lirmm.ccsd.cnrs.fr/lirmm-01162362","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the VLDB Endowment (PVLDB), 2015, 8 (12), pp.1856-1867. ⟨10.14778/2824032.2824085⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:HAL:lirmm-01162362v1","is_oa":true,"landing_page_url":"https://hal-lirmm.ccsd.cnrs.fr/lirmm-01162362","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the VLDB Endowment (PVLDB), 2015, 8 (12), pp.1856-1867. ⟨10.14778/2824032.2824085⟩","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2131975293","https://openalex.org/W2140509629","https://openalex.org/W2173213060"],"related_works":["https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W2944444143","https://openalex.org/W3041531047","https://openalex.org/W2794953737","https://openalex.org/W1927287081","https://openalex.org/W3099307300"],"abstract_inverted_index":{"Big":[0],"data":[1,26,66],"parallel":[2,129],"frameworks,":[3],"such":[4],"as":[5],"MapReduce":[6,69],"or":[7],"Spark":[8],"have":[9],"been":[10],"praised":[11],"for":[12],"their":[13],"high":[14,34],"scalability":[15],"and":[16,144,150,170,188,194,204,207],"performance,":[17],"but":[18],"show":[19],"poor":[20],"performance":[21,156],"in":[22,38,68,83,97,128,167,173,192],"the":[23,39,55,105,118,122,131,182,184,202,205,211,222,225],"case":[24],"of":[25,36,57,86,121,134,142,210],"skew.":[27],"There":[28],"are":[29,91],"important":[30],"cases":[31],"where":[32],"a":[33,60,75,101,140,208],"percentage":[35],"processing":[37],"reduce":[40,80,95,168],"side":[41],"ends":[42],"up":[43],"being":[44],"done":[45,127],"by":[46,93,99],"only":[47,115],"one":[48,116],"node.":[49],"In":[50,71],"this":[51],"demonstration,":[52,179],"we":[53,180],"illustrate":[54],"use":[56],"FP-Hadoop":[58,193],",":[59,82],"system":[61],"that":[62],"efficiently":[63],"deals":[64],"with":[65],"skew":[67],"jobs.":[70],"FP-Hadoop,":[72,143],"there":[73],"is":[74],"new":[76],"phase,":[77,107],"called":[78],"intermediate":[79,87,94,111],"(IR)":[81],"which":[84],"blocks":[85],"values,":[88],"constructed":[89],"dynamically,":[90],"processed":[92],"workers":[96],"parallel,":[98],"using":[100,130],"scheduling":[102],"strategy.":[103],"Within":[104],"IR":[106],"even":[108],"if":[109],"all":[110,135],"values":[112],"belong":[113],"to":[114,159,186,220],"key,":[117],"main":[119],"part":[120],"reducing":[123],"work":[124],"can":[125,197,214],"be":[126],"computing":[132],"resources":[133],"available":[136],"workers.":[137],"We":[138,153],"implemented":[139],"prototype":[141],"conducted":[145],"extensive":[146],"experiments":[147],"over":[148],"synthetic":[149],"real":[151],"datasets.":[152],"achieve":[154],"excellent":[155],"gains":[157],"compared":[158],"native":[160],"Hadoop,":[161],"e.g.":[162],"more":[163],"than":[164],"10":[165],"times":[166,172],"time":[169],"5":[171],"total":[174],"execution":[175],"time.":[176],"During":[177],"our":[178],"give":[181],"users":[183],"possibility":[185],"execute":[187],"compare":[189,217],"job":[190,203],"executions":[191],"Hadoop.":[195],"They":[196,213],"retrieve":[198],"general":[199],"information":[200],"about":[201],"tasks":[206],"summary":[209],"phases.":[212],"also":[215],"visually":[216],"different":[218],"configurations":[219],"explore":[221],"difference":[223],"between":[224],"approaches.":[226]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2016-06-24T00:00:00"}