{"id":"https://openalex.org/W4403812526","doi":"https://doi.org/10.1145/3689031.3696071","title":"A House United Within Itself: SLO-Awareness for On-Premises Containerized ML Inference Clusters via Faro","display_name":"A House United Within Itself: SLO-Awareness for On-Premises Containerized ML Inference Clusters via Faro","publication_year":2025,"publication_date":"2025-03-26","ids":{"openalex":"https://openalex.org/W4403812526","doi":"https://doi.org/10.1145/3689031.3696071"},"language":"en","primary_location":{"id":"doi:10.1145/3689031.3696071","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3689031.3696071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twentieth European Conference on Computer Systems","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.19488","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028384940","display_name":"Beomyeol Jeon","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Beomyeol Jeon","raw_affiliation_strings":["University of Illinois, Urbana-Champaign, Urbana, Illinois, USA"],"raw_orcid":"https://orcid.org/0009-0002-4552-4660","affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign, Urbana, Illinois, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100337643","display_name":"Chen Wang","orcid":"https://orcid.org/0000-0003-0204-2362"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Wang","raw_affiliation_strings":["IBM Research, Yorktown Heights, New York, USA"],"raw_orcid":"https://orcid.org/0000-0003-0204-2362","affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, New York, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112353536","display_name":"Diana Arroyo","orcid":"https://orcid.org/0000-0002-2330-8986"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Diana Arroyo","raw_affiliation_strings":["IBM Research, Yorktown Heights, New York, USA"],"raw_orcid":"https://orcid.org/0000-0002-2330-8986","affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, New York, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027088517","display_name":"Alaa Youssef","orcid":"https://orcid.org/0000-0001-5346-7331"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alaa Youssef","raw_affiliation_strings":["IBM Research, Yorktown Heights, New York, USA"],"raw_orcid":"https://orcid.org/0000-0001-5346-7331","affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, New York, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027240302","display_name":"Indranil Gupta","orcid":"https://orcid.org/0000-0002-9372-5937"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Indranil Gupta","raw_affiliation_strings":["University of Illinois, Urbana-Champaign, Urbana, Illinois, USA"],"raw_orcid":"https://orcid.org/0000-0002-9372-5937","affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign, Urbana, Illinois, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028384940"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00062255,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"524","last_page":"540"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.998199999332428,"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":0.998199999332428,"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":0.9976000189781189,"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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7207509875297546},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.591506838798523},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5804739594459534},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5523177981376648},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5253952145576477},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5087090134620667},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5016610622406006},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.45592784881591797},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.44269508123397827},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.32207316160202026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23472240567207336},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1398305594921112}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7207509875297546},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.591506838798523},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5804739594459534},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5523177981376648},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5253952145576477},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5087090134620667},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5016610622406006},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.45592784881591797},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.44269508123397827},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32207316160202026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23472240567207336},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1398305594921112},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3689031.3696071","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3689031.3696071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twentieth European Conference on Computer Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2409.19488","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.19488","pdf_url":"https://arxiv.org/pdf/2409.19488","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.19488","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.19488","pdf_url":"https://arxiv.org/pdf/2409.19488","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G404909116","display_name":"CNS Core: Small: GoT -- Groups of Things Abstractions for Distributed IoT","funder_award_id":"1908888","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6393730823","display_name":null,"funder_award_id":"1909577","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403812526.pdf","grobid_xml":"https://content.openalex.org/works/W4403812526.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1451881698","https://openalex.org/W1571338238","https://openalex.org/W1595159159","https://openalex.org/W1985514943","https://openalex.org/W2019819322","https://openalex.org/W2025549137","https://openalex.org/W2034715926","https://openalex.org/W2043050457","https://openalex.org/W2075233755","https://openalex.org/W2098921651","https://openalex.org/W2102849319","https://openalex.org/W2103114915","https://openalex.org/W2122410182","https://openalex.org/W2133569115","https://openalex.org/W2141992894","https://openalex.org/W2143408306","https://openalex.org/W2157614013","https://openalex.org/W2160121678","https://openalex.org/W2194775991","https://openalex.org/W2245493112","https://openalex.org/W2319876296","https://openalex.org/W2546571074","https://openalex.org/W2751343396","https://openalex.org/W2909877301","https://openalex.org/W2912500072","https://openalex.org/W2934021599","https://openalex.org/W2934208298","https://openalex.org/W2949676527","https://openalex.org/W2963148618","https://openalex.org/W2987129946","https://openalex.org/W3003257820","https://openalex.org/W3022298203","https://openalex.org/W3023238978","https://openalex.org/W3043433718","https://openalex.org/W3043571714","https://openalex.org/W3081168214","https://openalex.org/W3102562161","https://openalex.org/W3105227206","https://openalex.org/W3130689885","https://openalex.org/W3191752327","https://openalex.org/W3202971245","https://openalex.org/W4213041519","https://openalex.org/W4221165732","https://openalex.org/W4229058446","https://openalex.org/W4253824360","https://openalex.org/W4281641923","https://openalex.org/W4286908664","https://openalex.org/W4292544546","https://openalex.org/W4382239356","https://openalex.org/W4395106452"],"related_works":["https://openalex.org/W2000785801","https://openalex.org/W986318368","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W2004734601","https://openalex.org/W2287264064","https://openalex.org/W2130149817","https://openalex.org/W2990194547","https://openalex.org/W1480123525","https://openalex.org/W2163814182"],"abstract_inverted_index":{"This":[0],"paper":[1],"tackles":[2,81],"the":[3,101],"challenge":[4,79],"of":[5,132],"running":[6,135],"multiple":[7,113],"ML":[8],"inference":[9],"jobs":[10],"(models)":[11],"under":[12],"time-varying":[13],"workloads,":[14],"on":[15],"a":[16,96,129,137],"constrained":[17],"on-premises":[18],"production":[19],"cluster.":[20,139],"Our":[21],"system":[22],"Faro":[23,80,125,145],"takes":[24],"in":[25,63,95,128],"latency":[26],"Service":[27],"Level":[28],"Objectives":[29],"(SLOs)":[30],"for":[31,100],"each":[32],"job,":[33],"auto-distills":[34],"them":[35,45],"into":[36],"utility":[37,41],"functions,":[38],"\"sloppifies\"":[39],"these":[40],"functions":[42],"to":[43,47,65,109,116,152],"make":[44],"amenable":[46],"mathematical":[48],"optimization,":[49],"automatically":[50],"predicts":[51],"workload":[52],"via":[53],"probabilistic":[54],"prediction,":[55],"and":[56,73,87],"dynamically":[57],"makes":[58],"implicit":[59],"cross-job":[60],"resource":[61],"allocations,":[62],"order":[64],"satisfy":[66],"cluster-wide":[67],"objectives,":[68],"e.g.,":[69],"total":[70],"utility,":[71],"fairness,":[72],"other":[74],"hybrid":[75],"variants.":[76],"A":[77],"major":[78],"is":[82,108,126],"that":[83,144],"using":[84],"precise":[85],"utilities":[86],"high-fidelity":[88],"predictors,":[89],"can":[90],"be":[91],"too":[92,98],"slow":[93],"(and":[94],"sense":[97],"precise!)":[99],"fast":[102,118],"adaptation":[103,119],"we":[104],"require.":[105],"Faro's":[106],"solution":[107,123],"\"sloppify\"":[110],"(relax)":[111],"its":[112],"design":[114],"components":[115],"achieve":[117],"without":[120],"overly":[121],"degrading":[122],"quality.":[124],"implemented":[127],"stack":[130],"consisting":[131],"Ray":[133],"Serve":[134],"atop":[136],"Kubernetes":[138],"Trace-driven":[140],"cluster":[141],"deployments":[142],"show":[143],"achieves":[146],"2.3\u00d7-23\u00d7":[147],"lower":[148],"SLO":[149],"violations":[150],"compared":[151],"state-of-the-art":[153],"systems.":[154]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}