{"id":"https://openalex.org/W1987454953","doi":"https://doi.org/10.1109/cluster.2014.6968768","title":"Digging deeper into cluster system logs for failure prediction and root cause diagnosis","display_name":"Digging deeper into cluster system logs for failure prediction and root cause diagnosis","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W1987454953","doi":"https://doi.org/10.1109/cluster.2014.6968768","mag":"1987454953"},"language":"en","primary_location":{"id":"doi:10.1109/cluster.2014.6968768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2014.6968768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Cluster Computing (CLUSTER)","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/A5015457545","display_name":"Xiaoyu Fu","orcid":"https://orcid.org/0000-0002-6405-5655"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoyu Fu","raw_affiliation_strings":["University of Chinese Academy of Sciences","State Key Laboratory Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101763273","display_name":"Rui Ren","orcid":"https://orcid.org/0009-0000-3542-2164"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Ren","raw_affiliation_strings":["State Key Laboratory Computer Architecture, Chinese Academy of Sciences","State Key Laboratory Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory Computer Architecture, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"State Key Laboratory Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022715353","display_name":"Sally A. McKee","orcid":"https://orcid.org/0000-0003-0514-3767"},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Sally A. McKee","raw_affiliation_strings":["Computer Science and Engineering, Chalmers University of Technology","[Computer Science and Engineering, Chalmers University of Technology Sweden]"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Chalmers University of Technology","institution_ids":["https://openalex.org/I66862912"]},{"raw_affiliation_string":"[Computer Science and Engineering, Chalmers University of Technology Sweden]","institution_ids":["https://openalex.org/I66862912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085963553","display_name":"Jianfeng Zhan","orcid":"https://orcid.org/0000-0002-3728-6837"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Zhan","raw_affiliation_strings":["State Key Laboratory Computer Architecture, Chinese Academy of Sciences","State Key Laboratory Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory Computer Architecture, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"State Key Laboratory Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101738013","display_name":"Ninghui Sun","orcid":"https://orcid.org/0000-0002-1953-1392"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ninghui Sun","raw_affiliation_strings":["State Key Laboratory Computer Architecture, Chinese Academy of Sciences","State Key Laboratory Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory Computer Architecture, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"State Key Laboratory Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5015457545"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":1.0752,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.79600825,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"103","last_page":"112"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9828000068664551,"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"}},{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.9782000184059143,"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":0.7889427542686462},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.763999342918396},{"id":"https://openalex.org/keywords/root-cause","display_name":"Root cause","score":0.6617696285247803},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5518548488616943},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5412980318069458},{"id":"https://openalex.org/keywords/root-cause-analysis","display_name":"Root cause analysis","score":0.5138764381408691},{"id":"https://openalex.org/keywords/root","display_name":"Root (linguistics)","score":0.5029184222221375},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.45296409726142883},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.440327525138855},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.36065220832824707},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.22356587648391724},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10891401767730713}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7889427542686462},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.763999342918396},{"id":"https://openalex.org/C84945661","wikidata":"https://www.wikidata.org/wiki/Q7366567","display_name":"Root cause","level":2,"score":0.6617696285247803},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5518548488616943},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5412980318069458},{"id":"https://openalex.org/C130963320","wikidata":"https://www.wikidata.org/wiki/Q1401207","display_name":"Root cause analysis","level":2,"score":0.5138764381408691},{"id":"https://openalex.org/C171078966","wikidata":"https://www.wikidata.org/wiki/Q111029","display_name":"Root (linguistics)","level":2,"score":0.5029184222221375},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.45296409726142883},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.440327525138855},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36065220832824707},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.22356587648391724},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10891401767730713},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cluster.2014.6968768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2014.6968768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Cluster Computing (CLUSTER)","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.lib.chalmers.se:209323","is_oa":false,"landing_page_url":"http://publications.lib.chalmers.se/publication/209323-digging-deeper-into-cluster-system-logs-for-failure-prediction-and-root-cause-diagnosis","pdf_url":null,"source":{"id":"https://openalex.org/S4377196470","display_name":"Chalmers Publication Library (Chalmers University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66862912","host_organization_name":"Chalmers University of Technology","host_organization_lineage":["https://openalex.org/I66862912"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text.Article.Conference.PeerReviewed"},{"id":"pmh:oai:research.chalmers.se:209323","is_oa":false,"landing_page_url":"https://research.chalmers.se/en/publication/209323","pdf_url":null,"source":{"id":"https://openalex.org/S4306402469","display_name":"Chalmers Research (Chalmers University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66862912","host_organization_name":"Chalmers University of Technology","host_organization_lineage":["https://openalex.org/I66862912"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W191651381","https://openalex.org/W1558516248","https://openalex.org/W1607902447","https://openalex.org/W1901980408","https://openalex.org/W1971952282","https://openalex.org/W1984578990","https://openalex.org/W1984980195","https://openalex.org/W1986510432","https://openalex.org/W1998221613","https://openalex.org/W2011023286","https://openalex.org/W2018212274","https://openalex.org/W2032858539","https://openalex.org/W2040352153","https://openalex.org/W2081497720","https://openalex.org/W2094924503","https://openalex.org/W2103759606","https://openalex.org/W2107461003","https://openalex.org/W2112090702","https://openalex.org/W2114554028","https://openalex.org/W2121041130","https://openalex.org/W2124146769","https://openalex.org/W2126058588","https://openalex.org/W2126369541","https://openalex.org/W2126908011","https://openalex.org/W2134461696","https://openalex.org/W2136797898","https://openalex.org/W2137512117","https://openalex.org/W2141676918","https://openalex.org/W2143220335","https://openalex.org/W2148508494","https://openalex.org/W2152671254","https://openalex.org/W2155043308","https://openalex.org/W2155118768","https://openalex.org/W2160100693","https://openalex.org/W2160821994","https://openalex.org/W2168716032","https://openalex.org/W6636321444","https://openalex.org/W6639713254","https://openalex.org/W6643050054","https://openalex.org/W6646175012","https://openalex.org/W6646916511","https://openalex.org/W6654806230","https://openalex.org/W6680785567","https://openalex.org/W6682562027"],"related_works":["https://openalex.org/W2030594396","https://openalex.org/W2535098331","https://openalex.org/W2202104725","https://openalex.org/W4255366506","https://openalex.org/W2056250485","https://openalex.org/W4280640835","https://openalex.org/W2885334669","https://openalex.org/W2111856191","https://openalex.org/W4230518569","https://openalex.org/W4230900947"],"abstract_inverted_index":{"As":[0],"the":[1,21,142,147,152,157,177],"sizes":[2],"of":[3,25,83,146,180],"supercomputers":[4],"and":[5,29,62,81,87,105],"data":[6],"centers":[7],"grow":[8],"towards":[9],"exascale,":[10],"failures":[11,57],"become":[12],"normal.":[13],"System":[14],"logs":[15,41],"play":[16],"a":[17,51,66,97,185],"critical":[18],"role":[19],"in":[20,131],"increasingly":[22],"complex":[23],"tasks":[24],"automatic":[26],"failure":[27,34,75,138,171,181],"prediction":[28,35],"diagnosis.":[30],"Many":[31],"methods":[32],"for":[33,42,188],"are":[36],"based":[37,58,120,140],"on":[38,59,121,141,151],"analyzing":[39],"event":[40,103,115,118,133,149],"large":[43],"scale":[44],"systems,":[45],"but":[46],"there":[47],"is":[48,93],"still":[49],"neither":[50],"widely":[52],"used":[53],"one":[54,68],"to":[55,100,106,169],"predict":[56],"both":[60],"non-fatal":[61],"fatal":[63],"events,":[64,182],"nor":[65],"precise":[67,89],"that":[69,144],"uses":[70],"fine-grained":[71],"information":[72,168],"(such":[73],"as":[74],"type,":[76],"node":[77],"location,":[78],"related":[79],"application,":[80],"time":[82],"occurrence).":[84],"A":[85],"deeper":[86],"more":[88],"log":[90],"analysis":[91],"technique":[92],"needed.":[94],"We":[95,164],"propose":[96],"three-step":[98],"approach":[99,174],"draw":[101],"out":[102],"dependencies":[104,128],"identify":[107],"failure-event":[108],"generating":[109],"processes.":[110],"First,":[111],"we":[112,125,136],"cluster":[113],"frequent":[114],"sequences":[116],"into":[117],"groups":[119],"common":[122],"events.":[123],"Then":[124],"infer":[126],"causal":[127],"between":[129],"events":[130,145],"each":[132],"group.":[134],"Finally,":[135],"extract":[137],"rules":[139],"observation":[143],"same":[148,153,158],"types,":[150],"nodes":[154],"or":[155],"from":[156],"applications":[159],"have":[160],"similar":[161],"operational":[162],"behaviors.":[163],"use":[165],"this":[166],"rich":[167],"improve":[170],"prediction.":[172],"Our":[173],"semi-automates":[175],"diagnosing":[176],"root":[178],"causes":[179],"making":[183],"it":[184],"valuable":[186],"tool":[187],"system":[189],"administrators.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
