{"id":"https://openalex.org/W3097528317","doi":"https://doi.org/10.1109/tnsm.2020.3034824","title":"You Only Run Once: Spark Auto-Tuning From a Single Run","display_name":"You Only Run Once: Spark Auto-Tuning From a Single Run","publication_year":2020,"publication_date":"2020-10-29","ids":{"openalex":"https://openalex.org/W3097528317","doi":"https://doi.org/10.1109/tnsm.2020.3034824","mag":"3097528317"},"language":"en","primary_location":{"id":"doi:10.1109/tnsm.2020.3034824","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnsm.2020.3034824","pdf_url":null,"source":{"id":"https://openalex.org/S173527311","display_name":"IEEE Transactions on Network and Service Management","issn_l":"1932-4537","issn":["1932-4537","2373-7379"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Network and Service Management","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://upcommons.upc.edu/bitstreams/b7a9f8b7-ba56-4893-bae2-e56672ed400f/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004356594","display_name":"David Buchaca","orcid":"https://orcid.org/0000-0002-1437-6039"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"David Buchaca Prats","raw_affiliation_strings":["Data Centric Computing, Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0002-1437-6039","affiliations":[{"raw_affiliation_string":"Data Centric Computing, Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091830540","display_name":"Felipe A. Portella","orcid":"https://orcid.org/0000-0003-1245-7465"},"institutions":[{"id":"https://openalex.org/I32393484","display_name":"Petrobras (Brazil)","ror":"https://ror.org/0235kyq22","country_code":"BR","type":"company","lineage":["https://openalex.org/I32393484"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["BR","ES"],"is_corresponding":false,"raw_author_name":"Felipe Albuquerque Portella","raw_affiliation_strings":["Information Technology Department, Petr\u00f3leo Brasileiro S. A. (PETROBRAS), Rio de Janeiro, Brazil","Information Technology Department, Universitat Polit\u00e8cnica de Catalunya (UPC)\u2014BarcelonaTECH, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0003-1245-7465","affiliations":[{"raw_affiliation_string":"Information Technology Department, Petr\u00f3leo Brasileiro S. A. (PETROBRAS), Rio de Janeiro, Brazil","institution_ids":["https://openalex.org/I32393484"]},{"raw_affiliation_string":"Information Technology Department, Universitat Polit\u00e8cnica de Catalunya (UPC)\u2014BarcelonaTECH, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102349258","display_name":"Carlos H. \u00c3. Costa","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlos H. A. Costa","raw_affiliation_strings":["Department of HPC, IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of HPC, IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074281010","display_name":"Josep Ll. Berral","orcid":"https://orcid.org/0000-0003-3037-3580"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Josep Lluis Berral","raw_affiliation_strings":["Data Centric Computing, Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0003-3037-3580","affiliations":[{"raw_affiliation_string":"Data Centric Computing, Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":3.1516,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.93468123,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"17","issue":"4","first_page":"2039","last_page":"2051"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9993000030517578,"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":0.9993000030517578,"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/T12127","display_name":"Software System Performance and Reliability","score":0.998199999332428,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/spark","display_name":"SPARK (programming language)","score":0.9312872886657715},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8423779010772705},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7675108909606934},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.700289249420166},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6519086360931396},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.6051709651947021},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5783165693283081},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.4274716377258301},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.33631211519241333},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.22354719042778015},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17970648407936096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16532593965530396},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11657935380935669}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.9312872886657715},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8423779010772705},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7675108909606934},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.700289249420166},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6519086360931396},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.6051709651947021},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5783165693283081},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.4274716377258301},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33631211519241333},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.22354719042778015},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17970648407936096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16532593965530396},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11657935380935669},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnsm.2020.3034824","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnsm.2020.3034824","pdf_url":null,"source":{"id":"https://openalex.org/S173527311","display_name":"IEEE Transactions on Network and Service Management","issn_l":"1932-4537","issn":["1932-4537","2373-7379"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Network and Service Management","raw_type":"journal-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/340271","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/340271","pdf_url":"https://upcommons.upc.edu/bitstreams/b7a9f8b7-ba56-4893-bae2-e56672ed400f/download","source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:upcommons.upc.edu:2117/340271","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/340271","pdf_url":"https://upcommons.upc.edu/bitstreams/b7a9f8b7-ba56-4893-bae2-e56672ed400f/download","source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G2436365243","display_name":null,"funder_award_id":"2014-SGR-1051","funder_id":"https://openalex.org/F4320321505","funder_display_name":"Generalitat de Catalunya"},{"id":"https://openalex.org/G3222096693","display_name":null,"funder_award_id":"TIN2015-65316-P","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3324247440","display_name":null,"funder_award_id":"TIN2015-65316-P","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"},{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"HORIZON2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7096924396","display_name":null,"funder_award_id":"TIN2015-65316","funder_id":"https://openalex.org/F4320321505","funder_display_name":"Generalitat de Catalunya"},{"id":"https://openalex.org/G709866033","display_name":null,"funder_award_id":"SEV-2015-0493","funder_id":"https://openalex.org/F4320322121","funder_display_name":"Instituci\u00f3 Catalana de Recerca i Estudis Avan\u00e7ats"},{"id":"https://openalex.org/G7479456642","display_name":"Holistic Integration of Emerging Supercomputing Technologies","funder_award_id":"639595","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321505","display_name":"Generalitat de Catalunya","ror":"https://ror.org/01bg62x04"},{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320322121","display_name":"Instituci\u00f3 Catalana de Recerca i Estudis Avan\u00e7ats","ror":"https://ror.org/0371hy230"},{"id":"https://openalex.org/F4320322468","display_name":"Petrobras","ror":"https://ror.org/0235kyq22"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3097528317.pdf","grobid_xml":"https://content.openalex.org/works/W3097528317.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W136979389","https://openalex.org/W1834532152","https://openalex.org/W2048554864","https://openalex.org/W2058047606","https://openalex.org/W2100218206","https://openalex.org/W2101234009","https://openalex.org/W2155072926","https://openalex.org/W2170997892","https://openalex.org/W2192203593","https://openalex.org/W2206758307","https://openalex.org/W2318383848","https://openalex.org/W2488300951","https://openalex.org/W2582789036","https://openalex.org/W2604879234","https://openalex.org/W2613206411","https://openalex.org/W2735019080","https://openalex.org/W2735694356","https://openalex.org/W2792529086","https://openalex.org/W2889698901","https://openalex.org/W2947744938","https://openalex.org/W2963745734","https://openalex.org/W2964298054","https://openalex.org/W2970836712","https://openalex.org/W2982167413","https://openalex.org/W3002038803","https://openalex.org/W3007086929","https://openalex.org/W3022630129","https://openalex.org/W3101748252","https://openalex.org/W3104631761","https://openalex.org/W4297798504","https://openalex.org/W6639007902","https://openalex.org/W6662682235","https://openalex.org/W6675354045","https://openalex.org/W6732936052","https://openalex.org/W6740854411","https://openalex.org/W6753724254"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W4391547476","https://openalex.org/W4387225845"],"abstract_inverted_index":{"Tuning":[0],"configurations":[1,66,150],"of":[2,73,99,163,194],"Spark":[3,54,75,90,126,149,164,187],"jobs":[4],"is":[5,86],"not":[6,46],"a":[7,61,74,96,111,200],"trivial":[8],"task.":[9],"State-of-the-art":[10],"auto-tuning":[11],"systems":[12],"are":[13,29],"based":[14],"on":[15],"iteratively":[16],"running":[17],"workloads":[18],"with":[19,114,160,182,197],"different":[20],"configurations.":[21],"During":[22],"the":[23,26,38,53,83,89,102,118,169,185,195],"optimization":[24,42],"process,":[25],"relevant":[27],"features":[28,116,124],"explored":[30],"to":[31,109,120,136,179,184,191,199],"find":[32],"good":[33,79,174],"solutions.":[34],"Many":[35],"optimizers":[36],"enhance":[37,110],"time-to-solution":[39,196],"using":[40],"black-box":[41],"algorithms":[43],"that":[44,67,85,155,168],"do":[45],"take":[47],"into":[48],"account":[49],"any":[50],"information":[51,69,100,108,143],"from":[52,70,101,117],"workloads.":[55],"In":[56],"this":[57,107,142],"article,":[58],"we":[59,81],"present":[60],"new":[62],"method":[63],"for":[64,151],"tuning":[65],"uses":[68],"one":[71],"run":[72],"workload.":[76],"To":[77],"achieve":[78],"performance,":[80],"mine":[82],"SparkEventLog":[84],"generated":[87],"by":[88],"engine.":[91],"This":[92,132],"log":[93],"file":[94],"contains":[95],"large":[97],"amount":[98],"executed":[103],"application.":[104],"We":[105],"use":[106],"performance":[112],"model":[113],"low-level":[115],"workload":[119,139],"be":[121],"optimized.":[122],"These":[123],"include":[125],"Actions,":[127],"Transformations,":[128],"and":[129,189],"Task":[130],"metrics.":[131],"process":[133],"allows":[134],"us":[135],"obtain":[137],"application-specific":[138],"information.":[140],"With":[141],"our":[144],"system":[145,171],"can":[146],"predict":[147],"sensible":[148],"unseen":[152],"jobs,":[153],"given":[154],"it":[156],"has":[157],"been":[158],"trained":[159],"reasonable":[161],"coverage":[162],"applications.":[165],"Experiments":[166],"show":[167],"presented":[170],"correctly":[172],"produces":[173],"configurations,":[175],"while":[176],"achieving":[177],"up":[178,190],"80%":[180],"speedup":[181,193],"respect":[183,198],"default":[186],"configuration,":[188],"12x":[192],"standard":[201],"Bayesian":[202],"Optimization":[203],"procedure.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2020-11-09T00:00:00"}
