{"id":"https://openalex.org/W2084587534","doi":"https://doi.org/10.1145/2802658.2802660","title":"Scalable and Fault Tolerant Failure Detection and Consensus","display_name":"Scalable and Fault Tolerant Failure Detection and Consensus","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W2084587534","doi":"https://doi.org/10.1145/2802658.2802660","mag":"2084587534"},"language":"en","primary_location":{"id":"doi:10.1145/2802658.2802660","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2802658.2802660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd European MPI Users' Group Meeting","raw_type":"proceedings-article"},"type":"conference-paper","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/A5076833325","display_name":"Amogh Katti","orcid":"https://orcid.org/0000-0001-8561-0673"},"institutions":[{"id":"https://openalex.org/I71052956","display_name":"University of Reading","ror":"https://ror.org/05v62cm79","country_code":"GB","type":"education","lineage":["https://openalex.org/I71052956"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Amogh Katti","raw_affiliation_strings":["School of Systems Engineering, University of Reading, Reading, RG6 6AY, UK","School of Systems Engineering, University of Reading, Reading RG6 6AY, UK.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Systems Engineering, University of Reading, Reading, RG6 6AY, UK","institution_ids":["https://openalex.org/I71052956"]},{"raw_affiliation_string":"School of Systems Engineering, University of Reading, Reading RG6 6AY, UK.#TAB#","institution_ids":["https://openalex.org/I71052956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007549483","display_name":"Giuseppe Di Fatta","orcid":"https://orcid.org/0000-0003-3096-2844"},"institutions":[{"id":"https://openalex.org/I71052956","display_name":"University of Reading","ror":"https://ror.org/05v62cm79","country_code":"GB","type":"education","lineage":["https://openalex.org/I71052956"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Giuseppe Di Fatta","raw_affiliation_strings":["School of Systems Engineering, University of Reading, Reading, RG6 6AY, UK","School of Systems Engineering, University of Reading, Reading RG6 6AY, UK.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Systems Engineering, University of Reading, Reading, RG6 6AY, UK","institution_ids":["https://openalex.org/I71052956"]},{"raw_affiliation_string":"School of Systems Engineering, University of Reading, Reading RG6 6AY, UK.#TAB#","institution_ids":["https://openalex.org/I71052956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065914106","display_name":"Thomas J. Naughton","orcid":"https://orcid.org/0000-0002-3546-2382"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Naughton","raw_affiliation_strings":["Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831-6173, USA","Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831-6173, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831-6173, USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831-6173, USA#TAB#","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019453159","display_name":"Christian Engelmann","orcid":"https://orcid.org/0000-0003-4365-6416"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christian Engelmann","raw_affiliation_strings":["Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831-6173, USA","Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831-6173, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831-6173, USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831-6173, USA#TAB#","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1581,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.9332832,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","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/T10772","display_name":"Distributed systems and fault tolerance","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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9902999997138977,"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/T13553","display_name":"Age of Information Optimization","score":0.9871000051498413,"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/scalability","display_name":"Scalability","score":0.860001802444458},{"id":"https://openalex.org/keywords/gossip","display_name":"Gossip","score":0.8539115190505981},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8528550863265991},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7900455594062805},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6952129602432251},{"id":"https://openalex.org/keywords/gossip-protocol","display_name":"Gossip protocol","score":0.6043152213096619},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5454992055892944},{"id":"https://openalex.org/keywords/byzantine-fault-tolerance","display_name":"Byzantine fault tolerance","score":0.4947943091392517},{"id":"https://openalex.org/keywords/consensus-algorithm","display_name":"Consensus algorithm","score":0.4875187575817108},{"id":"https://openalex.org/keywords/consensus","display_name":"Consensus","score":0.4523301422595978},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.45052438974380493},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.28679484128952026},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2688639760017395},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1124865710735321},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07728263735771179},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.07246577739715576}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.860001802444458},{"id":"https://openalex.org/C62989814","wikidata":"https://www.wikidata.org/wiki/Q854648","display_name":"Gossip","level":2,"score":0.8539115190505981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8528550863265991},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7900455594062805},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6952129602432251},{"id":"https://openalex.org/C145928361","wikidata":"https://www.wikidata.org/wiki/Q5587504","display_name":"Gossip protocol","level":3,"score":0.6043152213096619},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5454992055892944},{"id":"https://openalex.org/C168021876","wikidata":"https://www.wikidata.org/wiki/Q1353446","display_name":"Byzantine fault tolerance","level":3,"score":0.4947943091392517},{"id":"https://openalex.org/C2983222225","wikidata":"https://www.wikidata.org/wiki/Q2994424","display_name":"Consensus algorithm","level":2,"score":0.4875187575817108},{"id":"https://openalex.org/C107107730","wikidata":"https://www.wikidata.org/wiki/Q2994424","display_name":"Consensus","level":3,"score":0.4523301422595978},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.45052438974380493},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.28679484128952026},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2688639760017395},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1124865710735321},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07728263735771179},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.07246577739715576},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2802658.2802660","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2802658.2802660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd European MPI Users' Group Meeting","raw_type":"proceedings-article"},{"id":"pmh:oai:centaur.reading.ac.uk:50881","is_oa":false,"landing_page_url":"https://centaur.reading.ac.uk/view/creators/90000558.html>,","pdf_url":null,"source":{"id":"https://openalex.org/S4306402273","display_name":"CentAUR (University of Reading)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71052956","host_organization_name":"University of Reading","host_organization_lineage":["https://openalex.org/I71052956"],"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":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320323928","display_name":"Felix Scholarship","ror":"https://ror.org/04dagjw98"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W343396495","https://openalex.org/W1494600391","https://openalex.org/W1551972236","https://openalex.org/W1973269641","https://openalex.org/W1976682245","https://openalex.org/W1985006281","https://openalex.org/W1986905947","https://openalex.org/W2013860911","https://openalex.org/W2033623738","https://openalex.org/W2035362408","https://openalex.org/W2050788236","https://openalex.org/W2059701835","https://openalex.org/W2083613288","https://openalex.org/W2098499339","https://openalex.org/W2099569658","https://openalex.org/W2119283141","https://openalex.org/W2133943294","https://openalex.org/W2145734880","https://openalex.org/W2168159483","https://openalex.org/W2730779250","https://openalex.org/W3149410719"],"related_works":["https://openalex.org/W3024820515","https://openalex.org/W2131433923","https://openalex.org/W2010318438","https://openalex.org/W2020760577","https://openalex.org/W1678654634","https://openalex.org/W2120550887","https://openalex.org/W2149172033","https://openalex.org/W2108737453","https://openalex.org/W177242786","https://openalex.org/W2014496162"],"abstract_inverted_index":{"Future":[0],"extreme-scale":[1],"high-performance":[2],"computing":[3],"systems":[4],"will":[5],"be":[6],"required":[7],"to":[8,27,43,118],"work":[9],"under":[10],"frequent":[11],"component":[12],"failures.":[13],"The":[14,81,95,106,127],"MPI":[15],"Forum's":[16],"User":[17],"Level":[18],"Failure":[19],"Mitigation":[20],"proposal":[21],"has":[22],"introduced":[23],"an":[24],"operation,":[25],"MPI_Comm_shrink,":[26],"synchronize":[28],"the":[29,33,47,103,113],"alive":[30],"processes":[31],"on":[32,86],"list":[34],"of":[35,49,115,136],"failed":[36],"processes,":[37],"so":[38],"that":[39,109],"applications":[40],"can":[41],"continue":[42],"execute":[44],"even":[45],"in":[46,110,134,146],"presence":[48],"failures":[50],"by":[51],"adopting":[52],"algorithm-based":[53],"fault":[54,62],"tolerance":[55],"techniques.":[56],"This":[57,69],"MPI_Comm_shrink":[58],"operation":[59],"requires":[60],"a":[61,143],"tolerant":[63],"failure":[64,76],"detection":[65,77],"and":[66,72,78,89,93,100,138,142],"consensus":[67,79,121],"algorithm.":[68],"paper":[70],"presents":[71],"compares":[73],"two":[74],"novel":[75],"algorithms.":[80],"proposed":[82,96],"algorithms":[83,97,112],"are":[84,90],"based":[85],"Gossip":[87,116],"protocols":[88],"inherently":[91],"fault-tolerant":[92],"scalable.":[94],"were":[98],"implemented":[99],"tested":[101],"using":[102],"Extreme-scale":[104],"Simulator.":[105],"results":[107],"show":[108],"both":[111],"number":[114],"cycles":[117],"achieve":[119],"global":[120,148],"scales":[122],"logarithmically":[123],"with":[124],"system":[125],"size.":[126],"second":[128],"algorithm":[129],"also":[130],"shows":[131],"better":[132],"scalability":[133],"terms":[135],"memory":[137],"network":[139],"bandwidth":[140],"usage":[141],"perfect":[144],"synchronization":[145],"achieving":[147],"consensus.":[149]},"counts_by_year":[{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
