{"id":"https://openalex.org/W2249791145","doi":"https://doi.org/10.1109/edcc.2015.19","title":"Insights into the Diagnosis of System Failures from Cluster Message Logs","display_name":"Insights into the Diagnosis of System Failures from Cluster Message Logs","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W2249791145","doi":"https://doi.org/10.1109/edcc.2015.19","mag":"2249791145"},"language":"en","primary_location":{"id":"doi:10.1109/edcc.2015.19","is_oa":false,"landing_page_url":"https://doi.org/10.1109/edcc.2015.19","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 11th European Dependable Computing Conference (EDCC)","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/A5015074167","display_name":"Edward Chuah","orcid":"https://orcid.org/0000-0002-8659-1803"},"institutions":[{"id":"https://openalex.org/I202502355","display_name":"Singapore Polytechnic","ror":"https://ror.org/05pxcn248","country_code":"SG","type":"education","lineage":["https://openalex.org/I202502355"]},{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["SG","US"],"is_corresponding":false,"raw_author_name":"Edward Chuah","raw_affiliation_strings":["Singapore Polytechnic, Singapore","University of Texas at Austin, Texas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Polytechnic, Singapore","institution_ids":["https://openalex.org/I202502355"]},{"raw_affiliation_string":"University of Texas at Austin, Texas","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005426902","display_name":"Arshad Jhumka","orcid":"https://orcid.org/0000-0003-0540-2845"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Arshad Jhumka","raw_affiliation_strings":["University of Warwick, Coventry, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Warwick, Coventry, UK","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064263297","display_name":"James C. Browne","orcid":null},"institutions":[{"id":"https://openalex.org/I202502355","display_name":"Singapore Polytechnic","ror":"https://ror.org/05pxcn248","country_code":"SG","type":"education","lineage":["https://openalex.org/I202502355"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"James C. Browne","raw_affiliation_strings":["Singapore Polytechnic, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Polytechnic, Singapore","institution_ids":["https://openalex.org/I202502355"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bill Barth","orcid":null},"institutions":[{"id":"https://openalex.org/I4388891828","display_name":"Texas Advanced Computing Center","ror":"https://ror.org/00xg4bh43","country_code":null,"type":"facility","lineage":["https://openalex.org/I4388891828","https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bill Barth","raw_affiliation_strings":["Texas Advanced Computing Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas Advanced Computing Center","institution_ids":["https://openalex.org/I4388891828"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086187734","display_name":"Sai Narasimhamurthy","orcid":"https://orcid.org/0000-0002-6448-7239"},"institutions":[{"id":"https://openalex.org/I4210142999","display_name":"Seagate (United Kingdom)","ror":"https://ror.org/04709y508","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210142999"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sai Narasimhamurthy","raw_affiliation_strings":["Seagate Technology, Havant, SA, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seagate Technology, Havant, SA, UK","institution_ids":["https://openalex.org/I4210142999"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"225","last_page":"232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9998999834060669,"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/T12127","display_name":"Software System Performance and Reliability","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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.9907000064849854,"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":0.7798658609390259},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.68845534324646},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6126430630683899},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5903175473213196},{"id":"https://openalex.org/keywords/root-cause","display_name":"Root cause","score":0.517143189907074},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4952200949192047},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.47342589497566223},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.47105690836906433},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.46481853723526},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.42736101150512695},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.4105619490146637},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3671550750732422},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.2856476306915283},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21235916018486023},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15600129961967468},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12260320782661438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7798658609390259},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.68845534324646},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6126430630683899},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5903175473213196},{"id":"https://openalex.org/C84945661","wikidata":"https://www.wikidata.org/wiki/Q7366567","display_name":"Root cause","level":2,"score":0.517143189907074},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4952200949192047},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.47342589497566223},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.47105690836906433},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46481853723526},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.42736101150512695},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.4105619490146637},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3671550750732422},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.2856476306915283},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21235916018486023},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15600129961967468},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12260320782661438},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/edcc.2015.19","is_oa":false,"landing_page_url":"https://doi.org/10.1109/edcc.2015.19","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 11th European Dependable Computing Conference (EDCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1558516248","https://openalex.org/W1962220702","https://openalex.org/W1995565928","https://openalex.org/W1998221613","https://openalex.org/W2011023286","https://openalex.org/W2025024269","https://openalex.org/W2032858539","https://openalex.org/W2044704447","https://openalex.org/W2097301968","https://openalex.org/W2115408363","https://openalex.org/W2116335710","https://openalex.org/W2121390717","https://openalex.org/W2123649031","https://openalex.org/W2126058588","https://openalex.org/W2134461696","https://openalex.org/W2145071552","https://openalex.org/W3124370832","https://openalex.org/W3173458884","https://openalex.org/W6633553838","https://openalex.org/W6641209077","https://openalex.org/W6678232197"],"related_works":["https://openalex.org/W2978729728","https://openalex.org/W2357256365","https://openalex.org/W4288966080","https://openalex.org/W2348502264","https://openalex.org/W2365486383","https://openalex.org/W2362059367","https://openalex.org/W2350084742","https://openalex.org/W2111353101","https://openalex.org/W2122963874","https://openalex.org/W2411226825"],"abstract_inverted_index":{"Large":[0],"cluster":[1,52,143],"systems":[2,144],"are":[3,43,111],"composed":[4],"of":[5,30,46,70,77,85,100,109,126,138],"complex,":[6],"interacting":[7],"hardware":[8],"and":[9,66,88,103,116,118,121],"software":[10],"components.":[11],"Components,":[12],"or":[13],"the":[14,27,44,47,68,78,83,86,133],"interactions":[15],"between":[16],"components,":[17],"may":[18],"fail":[19],"due":[20],"to":[21,26,51,82],"many":[22],"different":[23],"reasons,":[24],"leading":[25],"eventual":[28],"failure":[29,40,139],"executing":[31],"jobs.":[32],"This":[33],"paper":[34,59],"investigates":[35],"an":[36,74],"open":[37],"question":[38],"about":[39],"diagnosis:":[41],"What":[42],"characteristics":[45],"errors":[48],"that":[49],"lead":[50],"system":[53],"failures?":[54],"To":[55],"this":[56,58],"end,":[57],"gives":[60],"a":[61,98,106],"systematic":[62],"process":[63],"for":[64,136,141],"identifying":[65],"characterizing":[67],"root-causes":[69],"failures.":[71],"We":[72],"applied":[73],"extended":[75],"version":[76],"FDiagV3":[79,128],"diagnostics":[80],"toolkit":[81],"log-files":[84],"Ranger":[87,120],"Lonestar":[89,122],"supercomputers.":[90],"Our":[91],"results":[92],"show":[93],"that:":[94],"(i)":[95],"failures":[96],"were":[97],"result":[99],"recurrent":[101],"issues":[102,115],"errors,":[104,117],"(ii)":[105],"small":[107],"set":[108],"nodes":[110],"associated":[112],"with":[113],"these":[114],"(iii)":[119],"display":[123],"similar":[124],"sets":[125],"problems.":[127],"will":[129],"be":[130],"put":[131],"in":[132,145],"public":[134],"domain":[135],"support":[137],"diagnosis":[140],"large":[142],"May,":[146],"2015.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}