{"id":"https://openalex.org/W1998221613","doi":"https://doi.org/10.1109/dsn.2013.6575356","title":"Reading between the lines of failure logs: Understanding how HPC systems fail","display_name":"Reading between the lines of failure logs: Understanding how HPC systems fail","publication_year":2013,"publication_date":"2013-06-01","ids":{"openalex":"https://openalex.org/W1998221613","doi":"https://doi.org/10.1109/dsn.2013.6575356","mag":"1998221613"},"language":"en","primary_location":{"id":"doi:10.1109/dsn.2013.6575356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsn.2013.6575356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 43rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN)","raw_type":"proceedings-article"},"type":"article","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/A5041608911","display_name":"Nosayba El-Sayed","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Nosayba El-Sayed","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Toronto, Canada","DEPARTMENT OF COMPUTER SCIENCE, UNIVERSITY OF TORONTO, TORONTO, ON, CANADA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"DEPARTMENT OF COMPUTER SCIENCE, UNIVERSITY OF TORONTO, TORONTO, ON, CANADA","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040893798","display_name":"Bianca Schroeder","orcid":"https://orcid.org/0000-0003-3289-1824"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Bianca Schroeder","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Toronto, Canada","DEPARTMENT OF COMPUTER SCIENCE, UNIVERSITY OF TORONTO, TORONTO, ON, CANADA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"DEPARTMENT OF COMPUTER SCIENCE, UNIVERSITY OF TORONTO, TORONTO, ON, CANADA","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5041608911"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":6.9721,"has_fulltext":false,"cited_by_count":100,"citation_normalized_percentile":{"value":0.97232281,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9987999796867371,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9973000288009644,"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":0.9930999875068665,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.7566254734992981},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6726471781730652},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6661064028739929},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.6194546222686768},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5820969343185425},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4903683662414551},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.486198365688324},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4482842683792114},{"id":"https://openalex.org/keywords/mean-time-between-failures","display_name":"Mean time between failures","score":0.44824182987213135},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.3348703980445862},{"id":"https://openalex.org/keywords/failure-rate","display_name":"Failure rate","score":0.30552753806114197},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23660337924957275},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16288316249847412}],"concepts":[{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.7566254734992981},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6726471781730652},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6661064028739929},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.6194546222686768},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5820969343185425},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4903683662414551},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.486198365688324},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4482842683792114},{"id":"https://openalex.org/C44154001","wikidata":"https://www.wikidata.org/wiki/Q754940","display_name":"Mean time between failures","level":3,"score":0.44824182987213135},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.3348703980445862},{"id":"https://openalex.org/C163164238","wikidata":"https://www.wikidata.org/wiki/Q2737027","display_name":"Failure rate","level":2,"score":0.30552753806114197},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23660337924957275},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16288316249847412},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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":1,"locations":[{"id":"doi:10.1109/dsn.2013.6575356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsn.2013.6575356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 43rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.6600000262260437}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338304","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1510496002","https://openalex.org/W1558516248","https://openalex.org/W2068171717","https://openalex.org/W2081235423","https://openalex.org/W2100093247","https://openalex.org/W2101221989","https://openalex.org/W2120591095","https://openalex.org/W2120876718","https://openalex.org/W2142812297","https://openalex.org/W2148508494","https://openalex.org/W2158907675","https://openalex.org/W2164136293","https://openalex.org/W2997622231","https://openalex.org/W6630529663","https://openalex.org/W6633553838","https://openalex.org/W6670668349","https://openalex.org/W6683432465","https://openalex.org/W6683935884"],"related_works":["https://openalex.org/W2034080945","https://openalex.org/W1030923862","https://openalex.org/W2541443397","https://openalex.org/W3209466718","https://openalex.org/W2199729044","https://openalex.org/W2565733367","https://openalex.org/W184596386","https://openalex.org/W2392800390","https://openalex.org/W3022248432","https://openalex.org/W2019970137"],"abstract_inverted_index":{"As":[0],"the":[1,16,48,96,105,114,122,128],"component":[2],"count":[3],"in":[4,19,29],"supercomputing":[5],"installations":[6],"continues":[7],"to":[8,36,57,94],"increase,":[9],"system":[10,74,136,148],"reliability":[11,106],"is":[12],"becoming":[13],"one":[14],"of":[15,39,51,69,84,98,102,107,116,124],"major":[17],"issues":[18,24],"designing":[20],"HPC":[21,108],"systems.":[22,109],"These":[23],"will":[25,53,64],"become":[26],"more":[27],"challenging":[28],"future":[30],"Exascale":[31],"systems,":[32],"which":[33],"are":[34],"predicted":[35],"include":[37],"millions":[38],"CPU":[40],"cores.":[41],"Even":[42],"with":[43],"relatively":[44],"reliable":[45],"individual":[46],"components,":[47],"sheer":[49],"number":[50],"components":[52],"increase":[54],"failure":[55],"rates":[56],"unprecedented":[58],"levels.":[59],"Efficiently":[60],"running":[61],"those":[62],"systems":[63],"require":[65],"a":[66,81,99],"good":[67],"understanding":[68],"how":[70],"different":[71],"factors":[72,103],"impact":[73,97,123],"reliability.":[75,149],"In":[76],"this":[77],"paper":[78],"we":[79],"use":[80],"decade":[82],"worth":[83],"field":[85],"data":[86],"made":[87],"available":[88],"by":[89],"Los":[90],"Alamos":[91],"National":[92],"Lab":[93],"study":[95],"diverse":[100],"set":[101],"on":[104,147],"We":[110],"provide":[111],"insights":[112],"into":[113],"nature":[115],"correlations":[117],"between":[118],"failures,":[119],"and":[120,133,138,140],"investigate":[121],"factors,":[125,142],"such":[126,143],"as":[127,144],"power":[129],"quality,":[130],"temperature,":[131],"fan":[132],"chiller":[134],"reliability,":[135],"usage":[137],"utilization,":[139],"external":[141],"cosmic":[145],"radiation,":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}
