{"id":"https://openalex.org/W2134461696","doi":"https://doi.org/10.1109/hipc.2010.5713159","title":"Diagnosing the root-causes of failures from cluster log files","display_name":"Diagnosing the root-causes of failures from cluster log files","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W2134461696","doi":"https://doi.org/10.1109/hipc.2010.5713159","mag":"2134461696"},"language":"en","primary_location":{"id":"doi:10.1109/hipc.2010.5713159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2010.5713159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 International Conference on High Performance Computing","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/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Edward Chuah","raw_affiliation_strings":["Institute of High Performance Computing, Singapore","Institute of High Performance Computing, 1 Fusionopolis Way, 16-16 Connexis, Singapore 138632"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing, Singapore","institution_ids":["https://openalex.org/I3004594783"]},{"raw_affiliation_string":"Institute of High Performance Computing, 1 Fusionopolis Way, 16-16 Connexis, Singapore 138632","institution_ids":["https://openalex.org/I3004594783"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051958317","display_name":"Shyh-Hao Kuo","orcid":null},"institutions":[{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shyh-hao Kuo","raw_affiliation_strings":["Institute of High Performance Computing, Singapore","Institute of High Performance Computing, 1 Fusionopolis Way, 16-16 Connexis, Singapore 138632"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing, Singapore","institution_ids":["https://openalex.org/I3004594783"]},{"raw_affiliation_string":"Institute of High Performance Computing, 1 Fusionopolis Way, 16-16 Connexis, Singapore 138632","institution_ids":["https://openalex.org/I3004594783"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076999948","display_name":"Paul Hiew","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul Hiew","raw_affiliation_strings":["AStar Computational Resource Center, Singapore","TA\u2217Star Computational Resource Center, 1 Fusionopolis Way, #16-16 Connexis, Singapore 138632"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AStar Computational Resource Center, Singapore","institution_ids":[]},{"raw_affiliation_string":"TA\u2217Star Computational Resource Center, 1 Fusionopolis Way, #16-16 Connexis, Singapore 138632","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109232341","display_name":"William-Chandra Tjhi","orcid":null},"institutions":[{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"William-Chandra Tjhi","raw_affiliation_strings":["Institute of High Performance Computing, Singapore","Institute of High Performance Computing, 1 Fusionopolis Way, 16-16 Connexis, Singapore 138632"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing, Singapore","institution_ids":["https://openalex.org/I3004594783"]},{"raw_affiliation_string":"Institute of High Performance Computing, 1 Fusionopolis Way, 16-16 Connexis, Singapore 138632","institution_ids":["https://openalex.org/I3004594783"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087099593","display_name":"Gary Lee","orcid":"https://orcid.org/0000-0002-0036-511X"},"institutions":[{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Gary Lee","raw_affiliation_strings":["Institute of High Performance Computing, Singapore","Institute of High Performance Computing, 1 Fusionopolis Way, 16-16 Connexis, Singapore 138632"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing, Singapore","institution_ids":["https://openalex.org/I3004594783"]},{"raw_affiliation_string":"Institute of High Performance Computing, 1 Fusionopolis Way, 16-16 Connexis, Singapore 138632","institution_ids":["https://openalex.org/I3004594783"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019468716","display_name":"John L. Hammond","orcid":null},"institutions":[{"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":["US"],"is_corresponding":false,"raw_author_name":"John Hammond","raw_affiliation_strings":["University of Texas, Austin, TX, USA","University of Texas at Austin, Texas 78712"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas at Austin, Texas 78712","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025517625","display_name":"Marek T. Michalewicz","orcid":"https://orcid.org/0000-0002-6474-5234"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marek T. Michalewicz","raw_affiliation_strings":["AStar Computational Resource Center, Singapore","TA\u2217Star Computational Resource Center, 1 Fusionopolis Way, #16-16 Connexis, Singapore 138632"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AStar Computational Resource Center, Singapore","institution_ids":[]},{"raw_affiliation_string":"TA\u2217Star Computational Resource Center, 1 Fusionopolis Way, #16-16 Connexis, Singapore 138632","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111954797","display_name":"Terence Hung","orcid":null},"institutions":[{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Terence Hung","raw_affiliation_strings":["Institute of High Performance Computing, Singapore","Institute of High Performance Computing, 1 Fusionopolis Way, 16-16 Connexis, Singapore 138632"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing, Singapore","institution_ids":["https://openalex.org/I3004594783"]},{"raw_affiliation_string":"Institute of High Performance Computing, 1 Fusionopolis Way, 16-16 Connexis, Singapore 138632","institution_ids":["https://openalex.org/I3004594783"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064263297","display_name":"James C. Browne","orcid":null},"institutions":[{"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":["US"],"is_corresponding":false,"raw_author_name":"James C. Browne","raw_affiliation_strings":["University of Texas, Austin, TX, USA","University of Texas at Austin, Texas 78712"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas at Austin, Texas 78712","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":1.0,"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":1.0,"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":0.9868999719619751,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.9725000262260437,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.77799391746521},{"id":"https://openalex.org/keywords/troubleshooting","display_name":"Troubleshooting","score":0.73563551902771},{"id":"https://openalex.org/keywords/lustre","display_name":"Lustre (file system)","score":0.6075301170349121},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5152252316474915},{"id":"https://openalex.org/keywords/file-system","display_name":"File system","score":0.4842914938926697},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.45655953884124756},{"id":"https://openalex.org/keywords/root-cause","display_name":"Root cause","score":0.45227888226509094},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4494117498397827},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.446196585893631},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43356990814208984},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4122939705848694},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3979361355304718},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3760637640953064},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.29843786358833313},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.21494171023368835},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0970926582813263}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77799391746521},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.73563551902771},{"id":"https://openalex.org/C180699724","wikidata":"https://www.wikidata.org/wiki/Q1877782","display_name":"Lustre (file system)","level":3,"score":0.6075301170349121},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5152252316474915},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.4842914938926697},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.45655953884124756},{"id":"https://openalex.org/C84945661","wikidata":"https://www.wikidata.org/wiki/Q7366567","display_name":"Root cause","level":2,"score":0.45227888226509094},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4494117498397827},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.446196585893631},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43356990814208984},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4122939705848694},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3979361355304718},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3760637640953064},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.29843786358833313},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.21494171023368835},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0970926582813263},{"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},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hipc.2010.5713159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2010.5713159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 International Conference on High Performance Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4099999964237213}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W20722260","https://openalex.org/W31248154","https://openalex.org/W119004536","https://openalex.org/W135621451","https://openalex.org/W164902916","https://openalex.org/W179699880","https://openalex.org/W208057840","https://openalex.org/W1541620717","https://openalex.org/W1558516248","https://openalex.org/W1901980408","https://openalex.org/W1955571710","https://openalex.org/W1962220702","https://openalex.org/W2032858539","https://openalex.org/W2037019152","https://openalex.org/W2098695822","https://openalex.org/W2107263349","https://openalex.org/W2115056012","https://openalex.org/W2116335710","https://openalex.org/W2121041130","https://openalex.org/W2121122863","https://openalex.org/W2136159049","https://openalex.org/W2143220335","https://openalex.org/W2145864256","https://openalex.org/W2152671254","https://openalex.org/W2155043308","https://openalex.org/W2158907675","https://openalex.org/W2166484593","https://openalex.org/W2169411532","https://openalex.org/W2171300258","https://openalex.org/W3173458884","https://openalex.org/W6601261037","https://openalex.org/W6604746331","https://openalex.org/W6605488818","https://openalex.org/W6606699393","https://openalex.org/W6607380097","https://openalex.org/W6608443543","https://openalex.org/W6639713254","https://openalex.org/W6641209077","https://openalex.org/W6680785567"],"related_works":["https://openalex.org/W2133280212","https://openalex.org/W4311545198","https://openalex.org/W2140836923","https://openalex.org/W2113098103","https://openalex.org/W2164036813","https://openalex.org/W2994238052","https://openalex.org/W2151392458","https://openalex.org/W3097895792","https://openalex.org/W2768462553","https://openalex.org/W2786810567"],"abstract_inverted_index":{"System":[0],"event":[1,33,92],"logs":[2,34],"are":[3,39,59,175],"often":[4],"the":[5,14,25,31,52,62,69,73,101,119,139,155,163,167,182,185,190,197],"primary":[6],"source":[7],"of":[8,16,41,43,51,64,71,75,103,199],"information":[9],"for":[10,18,35,90,138],"diagnosing":[11],"(and":[12],"predicting)":[13],"causes":[15,74],"failures":[17,76,148],"cluster":[19,37],"systems.":[20],"Due":[21],"to":[22,61,117,131,146,150,180,196],"interactions":[23,153],"among":[24,97],"system":[26,32,158],"hardware":[27],"and":[28,46,80,94,126,135,159,184],"software":[29],"components,":[30],"large":[36,109],"systems":[38],"comprised":[40],"streams":[42],"interleaved":[44],"events,":[45],"only":[47],"a":[48,55,65,87,104,113],"small":[49,56],"fraction":[50],"events":[53,98,192],"over":[54],"time":[57,186],"span":[58],"relevant":[60],"diagnosis":[63],"given":[66,105],"failure.":[67],"Furthermore,":[68],"process":[70],"troubleshooting":[72],"is":[77,178],"largely":[78],"manual":[79],"ad-hoc.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85],"present":[86],"systematic":[88],"methodology":[89],"reconstructing":[91],"order":[93],"establishing":[95],"correlations":[96],"which":[99,193],"indicate":[100],"root-causes":[102],"failure":[106],"from":[107],"very":[108],"syslogs.":[110],"We":[111,143],"developed":[112],"diagnostics":[114],"tool,":[115],"FDiag,":[116],"extract":[118],"log":[120],"entries":[121],"as":[122],"structured":[123],"message":[124],"templates":[125],"uses":[127],"statistical":[128],"correlation":[129],"analysis":[130],"establish":[132],"probable":[133],"cause":[134],"effect":[136],"relationships":[137],"fault":[140],"being":[141],"analyzed.":[142],"applied":[144],"FDiag":[145,177],"analyze":[147],"due":[149],"breakdowns":[151],"in":[152],"between":[154],"Lustre":[156],"file":[157],"its":[160],"clients":[161],"on":[162],"Ranger":[164],"supercomputer":[165],"at":[166],"Texas":[168],"Advanced":[169],"Computing":[170],"Center":[171],"(TACC).":[172],"The":[173],"results":[174],"positive.":[176],"able":[179],"identify":[181],"dates":[183],"periods":[187],"that":[188],"contain":[189],"significant":[191],"eventually":[194],"led":[195],"occurrence":[198],"compute":[200],"node":[201],"soft":[202],"lockups.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
