{"id":"https://openalex.org/W2767478150","doi":"https://doi.org/10.1002/cpe.4367","title":"Performance comparison between Hadoop and Spark frameworks using HiBench benchmarks","display_name":"Performance comparison between Hadoop and Spark frameworks using HiBench benchmarks","publication_year":2017,"publication_date":"2017-11-12","ids":{"openalex":"https://openalex.org/W2767478150","doi":"https://doi.org/10.1002/cpe.4367","mag":"2767478150"},"language":"en","primary_location":{"id":"doi:10.1002/cpe.4367","is_oa":false,"landing_page_url":"https://doi.org/10.1002/cpe.4367","pdf_url":null,"source":{"id":"https://openalex.org/S11065456","display_name":"Concurrency and Computation Practice and Experience","issn_l":"1532-0626","issn":["1532-0626","1532-0634"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Concurrency and Computation: Practice and Experience","raw_type":"journal-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/A5045803635","display_name":"Yassir Samadi","orcid":"https://orcid.org/0000-0002-9354-8256"},"institutions":[{"id":"https://openalex.org/I126477371","display_name":"Mohammed V University","ror":"https://ror.org/00r8w8f84","country_code":"MA","type":"education","lineage":["https://openalex.org/I126477371"]},{"id":"https://openalex.org/I4210115519","display_name":"Centre de Recherche en Informatique","ror":"https://ror.org/020cdve92","country_code":"FR","type":"facility","lineage":["https://openalex.org/I190752583","https://openalex.org/I2746051580","https://openalex.org/I4210091621","https://openalex.org/I4210115519","https://openalex.org/I70768539"]}],"countries":["FR","MA"],"is_corresponding":true,"raw_author_name":"Yassir Samadi","raw_affiliation_strings":["National School of Computer Science and Systems Analysis Mohammed V University Rabat Morocco","Centre de Recherche en Informatique","National School of Computer Science and Systems Analysis Mohammed V University  Rabat Morocco"],"raw_orcid":"https://orcid.org/0000-0002-9354-8256","affiliations":[{"raw_affiliation_string":"National School of Computer Science and Systems Analysis Mohammed V University Rabat Morocco","institution_ids":["https://openalex.org/I126477371"]},{"raw_affiliation_string":"Centre de Recherche en Informatique","institution_ids":["https://openalex.org/I4210115519"]},{"raw_affiliation_string":"National School of Computer Science and Systems Analysis Mohammed V University  Rabat Morocco","institution_ids":["https://openalex.org/I126477371"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112733980","display_name":"Mostapha Zbakh","orcid":"https://orcid.org/0000-0002-1408-3850"},"institutions":[{"id":"https://openalex.org/I126477371","display_name":"Mohammed V University","ror":"https://ror.org/00r8w8f84","country_code":"MA","type":"education","lineage":["https://openalex.org/I126477371"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Mostapha Zbakh","raw_affiliation_strings":["National School of Computer Science and Systems Analysis Mohammed V University Rabat Morocco","National School of Computer Science and Systems Analysis Mohammed V University  Rabat Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National School of Computer Science and Systems Analysis Mohammed V University Rabat Morocco","institution_ids":["https://openalex.org/I126477371"]},{"raw_affiliation_string":"National School of Computer Science and Systems Analysis Mohammed V University  Rabat Morocco","institution_ids":["https://openalex.org/I126477371"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057912061","display_name":"Claude Tadonki","orcid":"https://orcid.org/0000-0003-1194-6400"},"institutions":[{"id":"https://openalex.org/I4210115519","display_name":"Centre de Recherche en Informatique","ror":"https://ror.org/020cdve92","country_code":"FR","type":"facility","lineage":["https://openalex.org/I190752583","https://openalex.org/I2746051580","https://openalex.org/I4210091621","https://openalex.org/I4210115519","https://openalex.org/I70768539"]},{"id":"https://openalex.org/I70768539","display_name":"\u00c9cole Nationale Sup\u00e9rieure des Mines de Paris","ror":"https://ror.org/04y8cs423","country_code":"FR","type":"education","lineage":["https://openalex.org/I190752583","https://openalex.org/I2746051580","https://openalex.org/I70768539"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Claude Tadonki","raw_affiliation_strings":["MINES ParisTech / CRI Paris France","Centre de Recherche en Informatique","MINES ParisTech / CRI  Paris France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MINES ParisTech / CRI Paris France","institution_ids":["https://openalex.org/I70768539"]},{"raw_affiliation_string":"Centre de Recherche en Informatique","institution_ids":["https://openalex.org/I4210115519"]},{"raw_affiliation_string":"MINES ParisTech / CRI  Paris France","institution_ids":["https://openalex.org/I70768539"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045803635"],"corresponding_institution_ids":["https://openalex.org/I126477371","https://openalex.org/I4210115519"],"apc_list":{"value":5140,"currency":"USD","value_usd":5140},"apc_paid":null,"fwci":11.0214,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.98208307,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"30","issue":"12","first_page":null,"last_page":null},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9945999979972839,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.8637806177139282},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8633636236190796},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.8379829525947571},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6806321740150452},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6270187497138977},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6000480651855469},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5310835242271423},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.5107603073120117},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5023269653320312},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4586908519268036},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.43116453289985657},{"id":"https://openalex.org/keywords/data-intensive-computing","display_name":"Data-intensive computing","score":0.43077513575553894},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.42129766941070557},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.2644639313220978},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.26156866550445557},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23257288336753845},{"id":"https://openalex.org/keywords/grid-computing","display_name":"Grid computing","score":0.15804103016853333},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.07755520939826965}],"concepts":[{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.8637806177139282},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8633636236190796},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8379829525947571},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6806321740150452},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6270187497138977},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6000480651855469},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5310835242271423},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.5107603073120117},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5023269653320312},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4586908519268036},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.43116453289985657},{"id":"https://openalex.org/C76831024","wikidata":"https://www.wikidata.org/wiki/Q5227096","display_name":"Data-intensive computing","level":4,"score":0.43077513575553894},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.42129766941070557},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2644639313220978},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26156866550445557},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23257288336753845},{"id":"https://openalex.org/C70429105","wikidata":"https://www.wikidata.org/wiki/Q249999","display_name":"Grid computing","level":3,"score":0.15804103016853333},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.07755520939826965},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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:10.1002/cpe.4367","is_oa":false,"landing_page_url":"https://doi.org/10.1002/cpe.4367","pdf_url":null,"source":{"id":"https://openalex.org/S11065456","display_name":"Concurrency and Computation Practice and Experience","issn_l":"1532-0626","issn":["1532-0626","1532-0634"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Concurrency and Computation: Practice and Experience","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-01678981v1","is_oa":false,"landing_page_url":"https://minesparis-psl.hal.science/hal-01678981","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Concurrency and Computation: Practice and Experience, 2017, Sp\u00e9cial Issue paper, ⟨10.1002/cpe.4367⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1123101191","https://openalex.org/W1755261609","https://openalex.org/W1965602589","https://openalex.org/W1980376525","https://openalex.org/W2011020535","https://openalex.org/W2023628927","https://openalex.org/W2048310536","https://openalex.org/W2078082072","https://openalex.org/W2091351040","https://openalex.org/W2119565742","https://openalex.org/W2122465391","https://openalex.org/W2131975293","https://openalex.org/W2158865579","https://openalex.org/W2189465200","https://openalex.org/W2261525379","https://openalex.org/W2275530856","https://openalex.org/W2328386379","https://openalex.org/W2392917251","https://openalex.org/W2550375374","https://openalex.org/W2556483642","https://openalex.org/W2586475558","https://openalex.org/W2995564009","https://openalex.org/W4238584892","https://openalex.org/W4245810980","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2944444143","https://openalex.org/W3041531047","https://openalex.org/W1927287081","https://openalex.org/W3099307300"],"abstract_inverted_index":{"Summary":[0],"Big":[1,41,92,108,131,167],"Data":[2,42,132,168],"has":[3],"become":[4],"one":[5],"of":[6,10,21,29,39,73,91,99,151,163,176,191,209,245,277],"the":[7,27,89,97,115,173,189,207,243,252,262,291,311],"major":[8,183,280],"areas":[9],"research":[11],"for":[12,166,205,234,303],"cloud":[13,184],"service":[14],"providers":[15],"due":[16],"to":[17,34,56,66,105,145,271,293],"a":[18,125,148,182,274,304],"large":[19,37,159,275],"amount":[20,72,150,276],"data":[22,152,232,278,292],"produced":[23],"every":[24],"day":[25],"and":[26,32,50,65,68,82,123,140,155,161,224,298,317],"inefficiency":[28],"traditional":[30],"algorithms":[31],"technologies":[33,55],"handle":[35],"these":[36,192,246],"amounts":[38],"data.":[40],"with":[43,230,273],"its":[44],"characteristics":[45],"such":[46],"as":[47],"volume,":[48],"variety,":[49],"veracity":[51],"(3V)":[52],"requires":[53,284],"efficient":[54,268],"process":[57,67,147],"in":[58,88,153,179,279,301],"real":[59],"time.":[60],"To":[61,187],"solve":[62],"this":[63,70,119],"problem":[64],"analyze":[69],"vast":[71,149],"data,":[74],"there":[75],"are":[76,85,143],"many":[77],"powerful":[78],"tools":[79],"like":[80,307],"Hadoop":[81,138,178,270],"Spark,":[83],"which":[84,107,200],"mainly":[86],"used":[87,144],"context":[90],"Data.":[93],"They":[94],"work":[95],"following":[96],"principles":[98],"parallel":[100,154],"computing.":[101],"The":[102,213],"challenge":[103],"is":[104,111,201,215,266],"specify":[106],"Data's":[109],"tool":[110],"better":[112],"depending":[113],"on":[114,135,158,218,251,314],"processing":[116],"context.":[117],"In":[118],"paper,":[120],"we":[121,195,260],"present":[122,172],"discuss":[124],"performance":[126,190,244,315],"comparison":[127,214],"between":[128],"two":[129,193],"popular":[130],"frameworks":[133,247],"deployed":[134],"virtual":[136],"machines.":[137],"MapReduce":[139],"Apache":[141,177],"Spark":[142,265,283],"efficiently":[146],"distributed":[156],"mode":[157],"clusters,":[160],"both":[162],"them":[164,300],"suit":[165],"processing.":[169],"We":[170,226],"also":[171],"execution":[174,221],"results":[175,240,259],"Amazon":[180],"EC2,":[181],"computing":[185],"environment.":[186],"compare":[188],"frameworks,":[194],"use":[196,253],"HiBench":[197],"benchmark":[198],"suite,":[199],"an":[202],"experimental":[203,239],"approach":[204],"measuring":[206],"effectiveness":[208],"any":[210],"computer":[211],"system.":[212],"made":[216],"based":[217,250],"three":[219],"criteria:":[220],"time,":[222],"throughput,":[223],"speedup.":[225],"test":[227],"Wordcount":[228],"workload":[229],"different":[231],"sizes":[233],"more":[235,267],"accurate":[236],"results.":[237],"Our":[238],"show":[241],"that":[242,264],"varies":[248],"significantly":[249],"case":[254],"implementation.":[255],"Furthermore,":[256],"from":[257],"our":[258],"draw":[261],"conclusion":[263],"than":[269],"deal":[272],"cases.":[281],"However,":[282],"higher":[285],"memory":[286,297,318],"allocation,":[287],"since":[288],"it":[289],"loads":[290],"be":[294],"processed":[295],"into":[296],"keeps":[299],"caches":[302],"while,":[305],"just":[306],"standard":[308],"databases.":[309],"So":[310],"choice":[312],"depends":[313],"level":[316],"constraints.":[319]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}