{"id":"https://openalex.org/W2963013210","doi":"https://doi.org/10.1145/3337821.3337909","title":"Holistic Slowdown Driven Scheduling and Resource Management for Malleable Jobs","display_name":"Holistic Slowdown Driven Scheduling and Resource Management for Malleable Jobs","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2963013210","doi":"https://doi.org/10.1145/3337821.3337909","mag":"2963013210"},"language":"en","primary_location":{"id":"doi:10.1145/3337821.3337909","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3337821.3337909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.08088","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Marco D'Amico","orcid":null},"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":"Marco D'Amico","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ana Jokanovic","orcid":null},"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":"Ana Jokanovic","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"last","author":{"id":null,"display_name":"Julita Corbalan","orcid":null},"institutions":[{"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":"Julita Corbalan","raw_affiliation_strings":["Universitat Politecnica de Catalunya, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Politecnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9998999834060669,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9998999834060669,"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":0.9995999932289124,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983999729156494,"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/malleability","display_name":"Malleability","score":0.8848000168800354},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6924999952316284},{"id":"https://openalex.org/keywords/slowdown","display_name":"Slowdown","score":0.6858000159263611},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6209999918937683},{"id":"https://openalex.org/keywords/job-scheduler","display_name":"Job scheduler","score":0.5519999861717224},{"id":"https://openalex.org/keywords/response-time","display_name":"Response time","score":0.486299991607666},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.44029998779296875}],"concepts":[{"id":"https://openalex.org/C100980136","wikidata":"https://www.wikidata.org/wiki/Q4668956","display_name":"Malleability","level":4,"score":0.8848000168800354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7652999758720398},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6924999952316284},{"id":"https://openalex.org/C2777242750","wikidata":"https://www.wikidata.org/wiki/Q31351","display_name":"Slowdown","level":2,"score":0.6858000159263611},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6209999918937683},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.5519999861717224},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5393999814987183},{"id":"https://openalex.org/C19012869","wikidata":"https://www.wikidata.org/wiki/Q578372","display_name":"Response time","level":2,"score":0.486299991607666},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.44029998779296875},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.39399999380111694},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C166235249","wikidata":"https://www.wikidata.org/wiki/Q355217","display_name":"Time management","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2736999988555908},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.2556999921798706},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.25540000200271606},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.2526000142097473}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3337821.3337909","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3337821.3337909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Conference on Parallel Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2002.08088","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.08088","pdf_url":"https://arxiv.org/pdf/2002.08088","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:upcommons.upc.edu:2117/168516","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/168516","pdf_url":"http://hdl.handle.net/2117/168516","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference report"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.08088","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.08088","pdf_url":"https://arxiv.org/pdf/2002.08088","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"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/G398560324","display_name":"Human Brain Project Specific Grant Agreement 1","funder_award_id":"720270","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4496054538","display_name":null,"funder_award_id":"SEV-2015-0493","funder_id":"https://openalex.org/F4320323737","funder_display_name":"Ministerio de Ciencia y Tecnolog\u00eda"},{"id":"https://openalex.org/G5766349579","display_name":"Human Brain Project Specific Grant Agreement 2","funder_award_id":"785907","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6456004180","display_name":null,"funder_award_id":"2017-SGR-1414","funder_id":"https://openalex.org/F4320321505","funder_display_name":"Generalitat de Catalunya"},{"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/G7291222407","display_name":null,"funder_award_id":"TIN2015-65316","funder_id":"https://openalex.org/F4320323737","funder_display_name":"Ministerio de Ciencia y Tecnolog\u00eda"},{"id":"https://openalex.org/G7441335220","display_name":null,"funder_award_id":"TIN2015-65316-P","funder_id":"https://openalex.org/F4320323737","funder_display_name":"Ministerio de Ciencia y Tecnolog\u00eda"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"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/F4320323737","display_name":"Ministerio de Ciencia y Tecnolog\u00eda","ror":"https://ror.org/034900433"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1509709811","https://openalex.org/W1539774972","https://openalex.org/W1733137719","https://openalex.org/W1836216117","https://openalex.org/W1985211757","https://openalex.org/W1994469476","https://openalex.org/W1994796314","https://openalex.org/W2042017208","https://openalex.org/W2043078530","https://openalex.org/W2127297674","https://openalex.org/W2142677441","https://openalex.org/W2256812163","https://openalex.org/W2532284696","https://openalex.org/W2887272015","https://openalex.org/W2913794485"],"related_works":[],"abstract_inverted_index":{"In":[0,76],"job":[1,61,119],"scheduling,":[2],"the":[3,32,39,46,50,56,69,88,127,132,137,175,180,213,232],"concept":[4],"of":[5,41,45,49,68,72,129,143,171,202,215],"malleability":[6,17,59,128,155],"has":[7],"been":[8],"explored":[9],"since":[10],"many":[11],"years":[12],"ago.":[13],"Research":[14],"shows":[15],"that":[16,164],"improves":[18,178],"system":[19],"performance,":[20],"but":[21,105],"its":[22],"utilization":[23,211],"in":[24,34,55,60,81,93,186,191],"HPC":[25,51,95],"never":[26],"became":[27],"widespread.":[28],"The":[29],"causes":[30],"are":[31],"difficulty":[33],"developing":[35],"malleable":[36],"applications,":[37],"and":[38,43,74,140,150,188,196,220,229],"lack":[40],"support":[42],"integration":[44],"different":[47],"layers":[48],"software":[52],"stack.":[53],"However,":[54],"last":[57],"years,":[58],"scheduling":[62,120],"is":[63,85,146],"becoming":[64],"more":[65],"critical":[66],"because":[67],"increasing":[70],"complexity":[71],"hardware":[73],"workloads.":[75,234],"this":[77],"context,":[78],"using":[79,200],"nodes":[80],"an":[82],"exclusive":[83],"mode":[84],"not":[86],"always":[87],"most":[89],"efficient":[90],"solution":[91],"as":[92,131],"traditional":[94],"jobs,":[96],"where":[97],"applications":[98,130],"were":[99],"highly":[100],"tuned":[101],"for":[102,162,231],"static":[103,181],"allocations,":[104],"offering":[106],"zero":[107],"flexibility":[108],"to":[109,135,156,159,204,224],"dynamic":[110,118],"executions.":[111],"This":[112],"paper":[113],"proposes":[114],"a":[115,168,192,198],"new":[116],"holistic,":[117],"policy,":[121],"Slowdown":[122],"Driven":[123],"(SD-Policy),":[124],"which":[125],"exploits":[126],"key":[133],"technology":[134],"reduce":[136],"average":[138],"slowdown":[139,177],"response":[141,217],"time":[142],"jobs.":[144,206],"SD-Policy":[145,185],"based":[147],"on":[148],"backfill":[149],"node":[151],"sharing.":[152],"It":[153],"applies":[154],"running":[157],"jobs":[158,163],"make":[160],"room":[161],"will":[165],"run":[166],"with":[167,197,212],"reduced":[169],"set":[170],"resources,":[172],"only":[173],"when":[174],"estimated":[176],"over":[179],"approach.":[182],"We":[183],"implemented":[184],"SLURM":[187],"evaluated":[189,233],"it":[190],"real":[193],"production":[194],"environment,":[195],"simulator":[199],"workloads":[201],"up":[203,223],"198K":[205],"Results":[207],"show":[208],"better":[209],"resource":[210],"reduction":[214],"makespan,":[216],"time,":[218],"slowdown,":[219],"energy":[221],"consumption,":[222],"respectively":[225],"7%,":[226],"50%,":[227],"70%,":[228],"6%,":[230]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2019-07-30T00:00:00"}
