{"id":"https://openalex.org/W2901510811","doi":"https://doi.org/10.1109/tpds.2018.2864184","title":"Exploring Properties and Correlations of Fatal Events in a Large-Scale HPC System","display_name":"Exploring Properties and Correlations of Fatal Events in a Large-Scale HPC System","publication_year":2018,"publication_date":"2018-08-14","ids":{"openalex":"https://openalex.org/W2901510811","doi":"https://doi.org/10.1109/tpds.2018.2864184","mag":"2901510811"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2018.2864184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2864184","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://www.osti.gov/biblio/1510059","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103124363","display_name":"Sheng Di","orcid":"https://orcid.org/0000-0002-9935-5674"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sheng Di","raw_affiliation_strings":["Argonne National Laboratory, Mathematics and Computer Science (MCS), Lemont, IL, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Mathematics and Computer Science (MCS), Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054749881","display_name":"Hanqi Guo","orcid":"https://orcid.org/0000-0001-7776-1834"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanqi Guo","raw_affiliation_strings":["Argonne National Laboratory, Mathematics and Computer Science (MCS), Lemont, IL, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Mathematics and Computer Science (MCS), Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050619770","display_name":"Rinku Gupta","orcid":"https://orcid.org/0009-0002-0669-1271"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rinku Gupta","raw_affiliation_strings":["Argonne National Laboratory, Mathematics and Computer Science (MCS), Lemont, IL, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Mathematics and Computer Science (MCS), Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073478077","display_name":"Eric Pershey","orcid":"https://orcid.org/0000-0003-2613-2768"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric R. Pershey","raw_affiliation_strings":["Argonne National Laboratory, Mathematics and Computer Science (MCS), Lemont, IL, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Mathematics and Computer Science (MCS), Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041731995","display_name":"Marc Snir","orcid":"https://orcid.org/0000-0002-3504-2468"},"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":"Marc Snir","raw_affiliation_strings":["Department of Computer Science, University of Illinois Urbana-Champaign, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046613458","display_name":"Franck Cappello","orcid":"https://orcid.org/0000-0002-7890-3934"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Franck Cappello","raw_affiliation_strings":["Argonne National Laboratory, Mathematics and Computer Science (MCS), Lemont, IL, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Mathematics and Computer Science (MCS), Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103124363"],"corresponding_institution_ids":["https://openalex.org/I1282105669"],"apc_list":null,"apc_paid":null,"fwci":3.9084,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.94167975,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"30","issue":"2","first_page":"361","last_page":"374"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9944999814033508,"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":0.9944999814033508,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9894000291824341,"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":0.7088608741760254},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.57509446144104},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.520866870880127},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3924846351146698},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3312832713127136}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7088608741760254},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.57509446144104},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.520866870880127},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3924846351146698},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3312832713127136},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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:10.1109/tpds.2018.2864184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2864184","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:osti.gov:1510059","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1510059","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1510059","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1510059","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7954425250","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320309913","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17"},{"id":"https://openalex.org/F4320338284","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1533168323","https://openalex.org/W1553890549","https://openalex.org/W1558516248","https://openalex.org/W1573279165","https://openalex.org/W1578105119","https://openalex.org/W1966243865","https://openalex.org/W1978082708","https://openalex.org/W1986905947","https://openalex.org/W1999900893","https://openalex.org/W2039631162","https://openalex.org/W2054353906","https://openalex.org/W2083393867","https://openalex.org/W2094127360","https://openalex.org/W2103759606","https://openalex.org/W2115711419","https://openalex.org/W2120591095","https://openalex.org/W2131074607","https://openalex.org/W2140715562","https://openalex.org/W2142812297","https://openalex.org/W2147419311","https://openalex.org/W2158197021","https://openalex.org/W2161234420","https://openalex.org/W2250057853","https://openalex.org/W2725626595","https://openalex.org/W2767346922","https://openalex.org/W2770542984","https://openalex.org/W2782944865","https://openalex.org/W2785907813","https://openalex.org/W4232378240","https://openalex.org/W6683682350"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2384867379","https://openalex.org/W2329539859","https://openalex.org/W3191490922","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W3214280620","https://openalex.org/W2794038527","https://openalex.org/W2151092287","https://openalex.org/W1599154403"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,156],"explore":[4],"potential":[5],"correlations":[6],"of":[7,13,64,80,106,130,163,185,208,219,231,269],"fatal":[8,60,107,121,153,165,178,205,263,270,287,318],"system":[9,65,133,144,166,211,304],"events":[10,61,108,167,179,194,206,271,288,319,323],"for":[11,261],"one":[12],"the":[14,72,91,96,101,126,131,159,164,192,209,217,220,223,229,247,257,262,273,281,286],"most":[15,234],"powerful":[16],"supercomputers-IBM":[17],"Blue":[18],"Gene/Q":[19],"Mira,":[20],"which":[21,141],"is":[22,40,180,212,225,277,291],"deployed":[23],"at":[24],"Argonne":[25],"National":[26],"Laboratory,":[27],"based":[28],"on":[29,272],"its":[30],"5-year":[31,127],"reliability,":[32],"availability,":[33],"and":[34,136,146,188,191,222,254,306,308,320],"serviceability":[35],"(RAS)":[36],"log.":[37,73],"Our":[38],"contribution":[39],"two-fold.":[41],"(1)":[42],"We":[43,124,294],"design":[44],"an":[45,150],"efficient":[46],"log":[47,129,248],"analysis":[48],"tool,":[49],"namely":[50],"LogAider,":[51,135],"with":[52,82,116,238],"a":[53,76,83,169,198],"novel":[54],"filtering":[55],"method":[56],"to":[57,87,90,95,112,196,240,301,309,315],"effectively":[58],"extract":[59],"from":[62,216,228],"masses":[63],"messages":[66,187],"that":[67,158,184],"are":[68,256],"heavily":[69],"duplicated":[70,120],"in":[71,172,246],"LogAider":[74],"exhibits":[75],"very":[77],"precise":[78],"detection":[79],"temporal-correlation":[81],"high":[84],"similarity":[85],"(up":[86],"95":[88],"percent)":[89],"ground-truth":[92],"(i.e.,":[93],"compared":[94,115],"failure":[97],"records":[98],"reported":[99],"by":[100],"administrators).":[102],"The":[103,174,201,233,266],"total":[104],"number":[105],"can":[109,142],"be":[110,299],"reduced":[111],"about":[113,213],"1,255":[114],"originally":[117],"2.6":[118],"million":[119],"messages.":[122],"(2)":[123],"analyze":[125],"RAS":[128],"MIRA":[132],"using":[134],"summarize":[137],"six":[138],"important":[139],"\u201ctakeaways\u201d":[140],"help":[143],"vendors":[145,307],"administrators":[147,305],"better":[148,316],"understand":[149,317],"extreme-scale":[151],"system's":[152],"events.":[154],"Specifically,":[155],"find":[157],"distribution":[160],"or":[161],"proportion":[162],"follow":[168],"Pareto-like":[170],"principle":[171],"general.":[173],"temporal":[175],"correlation":[176,268,284],"among":[177],"much":[181],"stronger":[182],"than":[183],"warn":[186],"info":[189],"messages,":[190],"correlated":[193],"tend":[195],"constitute":[197],"few":[199],"clusters.":[200],"mean":[202],"time":[203],"between":[204],"(MTBFE)":[207],"Mira":[210],"1.3":[214],"days":[215,227],"perspective":[218,230],"system,":[221],"MTTI":[224],"2-4":[226],"users.":[232],"error-prone":[235],"item":[236],"value":[237],"respect":[239],"any":[241],"key":[242],"attribute":[243],"appears":[244],"likely":[245],"every":[249],"2-10":[250],"days.":[251],"Weibull,":[252],"Gamma,":[253],"Pearson6":[255],"three":[258],"best-fit":[259],"distributions":[260],"event":[264],"intervals.":[265],"overall":[267],"5D":[274],"torus":[275],"network":[276],"not":[278],"prominent,":[279],"whereas":[280],"small-region":[282],"locality":[283],"(e.g.,":[285],"inside":[289],"racks)":[290],"relatively":[292],"strong.":[293],"believe":[295],"our":[296],"work":[297],"will":[298],"interesting":[300],"large-scale":[302],"HPC":[303],"fault":[310],"tolerance":[311],"researchers,":[312],"enabling":[313],"them":[314],"mitigate":[321],"such":[322],"accordingly.":[324]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}