{"id":"https://openalex.org/W3003942936","doi":"https://doi.org/10.1109/tpds.2020.2970013","title":"Performance-Aware Speculative Resource Oversubscription for Large-Scale Clusters","display_name":"Performance-Aware Speculative Resource Oversubscription for Large-Scale Clusters","publication_year":2020,"publication_date":"2020-01-28","ids":{"openalex":"https://openalex.org/W3003942936","doi":"https://doi.org/10.1109/tpds.2020.2970013","mag":"3003942936"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2020.2970013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2020.2970013","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.lancs.ac.uk/id/eprint/140826/2/tpds2020_rose.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050796169","display_name":"Renyu Yang","orcid":"https://orcid.org/0000-0001-6334-4925"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Renyu Yang","raw_affiliation_strings":["School of Computing, University of Leeds, Leeds, United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Leeds, Leeds, United Kingdom","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086470621","display_name":"Chunming Hu","orcid":"https://orcid.org/0000-0002-9502-3955"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunming Hu","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023692113","display_name":"Xiaoyang Sun","orcid":"https://orcid.org/0000-0001-9396-739X"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaoyang Sun","raw_affiliation_strings":["School of Computing, University of Leeds, Leeds, United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Leeds, Leeds, United Kingdom","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070708687","display_name":"Peter Garraghan","orcid":"https://orcid.org/0000-0002-7103-2515"},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Garraghan","raw_affiliation_strings":["Lancaster University, Lancaster, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Lancaster University, Lancaster, United Kingdom","institution_ids":["https://openalex.org/I67415387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066123431","display_name":"Tianyu Wo","orcid":"https://orcid.org/0000-0002-5331-3364"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyu Wo","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081043543","display_name":"Zhenyu Wen","orcid":"https://orcid.org/0000-0002-2914-912X"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhenyu Wen","raw_affiliation_strings":["Newcastle University, Newcastle upon Tyne, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Newcastle University, Newcastle upon Tyne, United Kingdom","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100740618","display_name":"Hao Peng","orcid":"https://orcid.org/0000-0001-7422-630X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Peng","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100639079","display_name":"Jie Xu","orcid":"https://orcid.org/0000-0003-4102-233X"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jie Xu","raw_affiliation_strings":["School of Computing, University of Leeds, Leeds, United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Leeds, Leeds, United Kingdom","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100323095","display_name":"Chao Li","orcid":"https://orcid.org/0000-0001-6218-4659"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Li","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5050796169"],"corresponding_institution_ids":["https://openalex.org/I130828816"],"apc_list":null,"apc_paid":null,"fwci":6.1196,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.96497834,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"31","issue":"7","first_page":"1499","last_page":"1517"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9993000030517578,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9951000213623047,"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":0.7631372213363647},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6007262468338013},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5623900890350342},{"id":"https://openalex.org/keywords/job-scheduler","display_name":"Job scheduler","score":0.5381174683570862},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4483102262020111},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3440697193145752},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3342719078063965},{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.15035757422447205},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.12524864077568054},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08232876658439636}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7631372213363647},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6007262468338013},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5623900890350342},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.5381174683570862},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4483102262020111},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3440697193145752},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3342719078063965},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.15035757422447205},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.12524864077568054},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08232876658439636},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpds.2020.2970013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2020.2970013","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:eprints.lancs.ac.uk:140826","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.lancs.ac.uk/id/eprint/140826/2/tpds2020_rose.pdf","source":{"id":"https://openalex.org/S4306401916","display_name":"Lancaster EPrints (Lancaster University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67415387","host_organization_name":"Lancaster University","host_organization_lineage":["https://openalex.org/I67415387"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"pmh:oai:eprints.lancs.ac.uk:140826","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.lancs.ac.uk/id/eprint/140826/2/tpds2020_rose.pdf","source":{"id":"https://openalex.org/S4306401916","display_name":"Lancaster EPrints (Lancaster University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67415387","host_organization_name":"Lancaster University","host_organization_lineage":["https://openalex.org/I67415387"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.550000011920929,"display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G2081710534","display_name":"Algorithmic Support for Massive Scale Distributed Systems","funder_award_id":"EP/T01461X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4537582722","display_name":null,"funder_award_id":"EP/T01461X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6408341383","display_name":null,"funder_award_id":"2016YFB1000503","funder_id":"https://openalex.org/F4320336026","funder_display_name":"National Key Research and Development Program of China Stem Cell and Translational Research"},{"id":"https://openalex.org/G6493013084","display_name":null,"funder_award_id":"EP/P031617/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8055127673","display_name":null,"funder_award_id":"61421003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320336026","display_name":"National Key Research and Development Program of China Stem Cell and Translational Research","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3003942936.pdf","grobid_xml":"https://content.openalex.org/works/W3003942936.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W110612056","https://openalex.org/W161073879","https://openalex.org/W1464363888","https://openalex.org/W1471655812","https://openalex.org/W1924159877","https://openalex.org/W2007860536","https://openalex.org/W2023214828","https://openalex.org/W2025037675","https://openalex.org/W2026543586","https://openalex.org/W2048430744","https://openalex.org/W2049717788","https://openalex.org/W2082410059","https://openalex.org/W2093941454","https://openalex.org/W2102709380","https://openalex.org/W2102849319","https://openalex.org/W2105947650","https://openalex.org/W2107894622","https://openalex.org/W2129542763","https://openalex.org/W2133569115","https://openalex.org/W2134857847","https://openalex.org/W2141992894","https://openalex.org/W2150478767","https://openalex.org/W2155178858","https://openalex.org/W2160121678","https://openalex.org/W2163961697","https://openalex.org/W2248732043","https://openalex.org/W2283208771","https://openalex.org/W2289698129","https://openalex.org/W2319794630","https://openalex.org/W2405723850","https://openalex.org/W2501172748","https://openalex.org/W2521533145","https://openalex.org/W2793098857","https://openalex.org/W2809028549","https://openalex.org/W2892785410","https://openalex.org/W2987148630","https://openalex.org/W3104065274","https://openalex.org/W3145128584","https://openalex.org/W3162118826","https://openalex.org/W4246219036","https://openalex.org/W6604455612","https://openalex.org/W6606403671","https://openalex.org/W6628558282","https://openalex.org/W6628701632","https://openalex.org/W6684084819","https://openalex.org/W6691209370","https://openalex.org/W7047381192"],"related_works":["https://openalex.org/W2418291489","https://openalex.org/W3096519538","https://openalex.org/W2744747300","https://openalex.org/W4241166160","https://openalex.org/W2068121105","https://openalex.org/W2384826897","https://openalex.org/W1973516247","https://openalex.org/W1997466117","https://openalex.org/W44553394","https://openalex.org/W3047653192"],"abstract_inverted_index":{"It":[0],"is":[1],"a":[2,7,20,61,132],"long-standing":[3],"challenge":[4],"to":[5,34,45,78,90,104,112],"achieve":[6],"high":[8],"degree":[9],"of":[10,67,85,119,131,150,153,177,191],"resource":[11,25,41,63,70,88,127,143],"utilization":[12,26,161,165],"in":[13,23,99,148,180],"cluster":[14],"scheduling.":[15],"Resource":[16],"oversubscription":[17,35,128],"has":[18],"become":[19],"common":[21],"practice":[22],"improving":[24],"and":[27,43,141,156,162,169],"cost":[28],"reduction.":[29],"However,":[30],"current":[31],"centralized":[32,95],"approaches":[33],"suffer":[36],"from":[37],"the":[38,94,159,163,174,189,193],"issue":[39],"with":[40,80],"mismatch":[42],"fail":[44],"take":[46],"into":[47],"account":[48],"other":[49],"performance":[50],"requirements,":[51],"e.g.,":[52],"tail":[53],"latency.":[54],"In":[55],"this":[56],"article":[57],"we":[58],"present":[59],"ROSE,":[60],"new":[62],"management":[64],"platform":[65],"capable":[66],"conducting":[68],"performance-aware":[69,142],"oversubscription.":[71,116],"ROSE":[72,100],"allows":[73],"latency-sensitive":[74,157],"long-running":[75],"applications":[76],"(LRAs)":[77],"co-exist":[79],"computation-intensive":[81],"batch":[82,154],"jobs.":[83],"Instead":[84],"waiting":[86],"for":[87,115,134],"allocation":[89],"be":[91],"confirmed":[92],"by":[93,129,185],"scheduler,":[96],"job":[97],"managers":[98],"can":[101,122,166],"independently":[102],"request":[103],"launch":[105],"speculative":[106],"tasks":[107],"within":[108],"specific":[109],"machines":[110,121],"according":[111],"their":[113],"suitability":[114],"Node":[117],"agents":[118],"those":[120],"however,":[123],"avoid":[124],"any":[125],"excessive":[126],"means":[130],"mechanism":[133],"admission":[135],"control":[136,140],"using":[137],"multi-resource":[138],"threshold":[139],"throttle.":[144],"Experiments":[145],"show":[146],"that":[147],"case":[149,190],"mixed":[151],"co-location":[152],"jobs":[155],"LRAs,":[158],"CPU":[160],"disk":[164],"reach":[167],"56.34":[168],"43.49":[170],"percent,":[171],"respectively,":[172],"but":[173],"95th":[175],"percentile":[176],"read":[178],"latency":[179],"YCSB":[181],"workloads":[182],"only":[183],"increases":[184],"5.4":[186],"percent":[187],"against":[188],"executing":[192],"LRAs":[194],"alone.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}