{"id":"https://openalex.org/W2767346922","doi":"https://doi.org/10.1145/3126908.3126937","title":"Failures in large scale systems","display_name":"Failures in large scale systems","publication_year":2017,"publication_date":"2017-11-08","ids":{"openalex":"https://openalex.org/W2767346922","doi":"https://doi.org/10.1145/3126908.3126937","mag":"2767346922"},"language":"en","primary_location":{"id":"doi:10.1145/3126908.3126937","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3126908.3126937","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3126937&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3126937&type=pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064269047","display_name":"Saurabh Gupta","orcid":"https://orcid.org/0000-0002-5984-852X"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Saurabh Gupta","raw_affiliation_strings":["Intel Labs"],"affiliations":[{"raw_affiliation_string":"Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007281535","display_name":"Tirthak Patel","orcid":"https://orcid.org/0000-0003-3127-5931"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Tirthak Patel","raw_affiliation_strings":["Northeastern University"],"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","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":["Oak Ridge National Laboratory"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074406596","display_name":"Devesh Tiwari","orcid":"https://orcid.org/0000-0002-7253-2458"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Devesh Tiwari","raw_affiliation_strings":["Northeastern University"],"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064269047"],"corresponding_institution_ids":["https://openalex.org/I1343180700"],"apc_list":null,"apc_paid":null,"fwci":12.499,"has_fulltext":true,"cited_by_count":121,"citation_normalized_percentile":{"value":0.98876024,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9991000294685364,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9991000294685364,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.998199999332428,"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":0.9937999844551086,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.7192644476890564},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6986805200576782},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6353932619094849},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.5998413562774658},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5378081202507019},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.47710496187210083},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.4707299470901489},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.46630609035491943},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.447922021150589},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.44369223713874817},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.3619638681411743},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.3222835063934326},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.19320106506347656},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1374243199825287},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07286453247070312},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06774857640266418}],"concepts":[{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.7192644476890564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6986805200576782},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6353932619094849},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.5998413562774658},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5378081202507019},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.47710496187210083},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4707299470901489},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.46630609035491943},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.447922021150589},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.44369223713874817},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.3619638681411743},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3222835063934326},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.19320106506347656},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1374243199825287},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07286453247070312},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06774857640266418},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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:10.1145/3126908.3126937","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3126908.3126937","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3126937&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1423066","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1423066","pdf_url":"https://www.osti.gov/servlets/purl/1423066","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":"doi:10.1145/3126908.3126937","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3126908.3126937","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3126937&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1645119126","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1719536385","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2296932962","display_name":null,"funder_award_id":"DE-AC05-00OR227","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3049477530","display_name":null,"funder_award_id":"Contract No. DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3299391273","display_name":null,"funder_award_id":"E-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G362975299","display_name":null,"funder_award_id":"DE-AC05-00OR22725.","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4423657506","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G4617282320","display_name":null,"funder_award_id":"No. DE-AC05-00OR227","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4957472368","display_name":null,"funder_award_id":". DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6486853205","display_name":null,"funder_award_id":"Contract No. DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G675320460","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G6911681599","display_name":null,"funder_award_id":"No. DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G691578896","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7114708214","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G7995982022","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8336963773","display_name":null,"funder_award_id":"DE-AC05-00OR22725.","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G8414908677","display_name":null,"funder_award_id":"DE-AC0","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8799952057","display_name":null,"funder_award_id":"DE-AC05-00OR22","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8906985441","display_name":null,"funder_award_id":"00OR22725","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/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2767346922.pdf","grobid_xml":"https://content.openalex.org/works/W2767346922.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W50065812","https://openalex.org/W1262893588","https://openalex.org/W1510692002","https://openalex.org/W1553890549","https://openalex.org/W1578105119","https://openalex.org/W1837653564","https://openalex.org/W1966243865","https://openalex.org/W1978807861","https://openalex.org/W1986905947","https://openalex.org/W1998221613","https://openalex.org/W1999900893","https://openalex.org/W2022636838","https://openalex.org/W2025024269","https://openalex.org/W2036641664","https://openalex.org/W2039631162","https://openalex.org/W2040379684","https://openalex.org/W2047394989","https://openalex.org/W2088552220","https://openalex.org/W2089536264","https://openalex.org/W2094127360","https://openalex.org/W2095157729","https://openalex.org/W2107263349","https://openalex.org/W2120591095","https://openalex.org/W2122249806","https://openalex.org/W2133046454","https://openalex.org/W2136797898","https://openalex.org/W2142812297","https://openalex.org/W2143220335","https://openalex.org/W2144569590","https://openalex.org/W2158907675","https://openalex.org/W2160821994","https://openalex.org/W2161234420","https://openalex.org/W2292040466","https://openalex.org/W2292469857","https://openalex.org/W2318507312","https://openalex.org/W2491102031","https://openalex.org/W2561164793","https://openalex.org/W2566407536","https://openalex.org/W2664249172","https://openalex.org/W2725626595","https://openalex.org/W2990714382","https://openalex.org/W3003346454","https://openalex.org/W3003432522","https://openalex.org/W3004493283"],"related_works":["https://openalex.org/W2033512842","https://openalex.org/W4322734194","https://openalex.org/W1607054433","https://openalex.org/W3005535424","https://openalex.org/W4233600955","https://openalex.org/W2913665393","https://openalex.org/W2994319598","https://openalex.org/W2369695847","https://openalex.org/W2110842462","https://openalex.org/W4233757488"],"abstract_inverted_index":{"Resilience":[0],"is":[1],"one":[2,55],"of":[3,11,44,67],"the":[4,41],"key":[5],"challenges":[6],"in":[7],"maintaining":[8],"high":[9],"efficiency":[10],"future":[12,31],"extreme":[13],"scale":[14],"supercomputers.":[15],"Researchers":[16],"and":[17,28,39,82],"system":[18],"practitioners":[19],"rely":[20],"on":[21],"field-data":[22],"studies":[23],"to":[24,76],"understand":[25],"reliability":[26,42],"characteristics":[27,43],"plan":[29],"for":[30],"HPC":[32,47],"systems.":[33,49],"In":[34],"this":[35],"work,":[36],"we":[37],"compare":[38],"contrast":[40],"multiple":[45],"large-scale":[46],"production":[48],"Our":[50],"study":[51],"covers":[52],"more":[53],"than":[54],"billion":[56],"compute":[57],"node":[58],"hours":[59],"across":[60],"five":[61],"different":[62],"systems":[63],"over":[64],"a":[65],"period":[66],"8":[68],"years.":[69],"We":[70],"confirm":[71],"previous":[72],"findings":[73],"which":[74],"continue":[75],"be":[77],"valid,":[78],"discover":[79],"new":[80],"findings,":[81],"discuss":[83],"their":[84],"implications.":[85]},"counts_by_year":[{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":20}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}
