{"id":"https://openalex.org/W2553287105","doi":"https://doi.org/10.1109/hipc.2016.035","title":"Using Message Logs and Resource Use Data for Cluster Failure Diagnosis","display_name":"Using Message Logs and Resource Use Data for Cluster Failure Diagnosis","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2553287105","doi":"https://doi.org/10.1109/hipc.2016.035","mag":"2553287105"},"language":"en","primary_location":{"id":"doi:10.1109/hipc.2016.035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2016.035","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":"2016 IEEE 23rd International Conference on High Performance Computing (HiPC)","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/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]},{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]}],"countries":["GB","SG"],"is_corresponding":false,"raw_author_name":"Edward Chuah","raw_affiliation_strings":["Singapore Polytechnic, Singapore","The Alan Turing Institute, London, UK","University of Warwick, Coventry, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Polytechnic, Singapore","institution_ids":["https://openalex.org/I202502355"]},{"raw_affiliation_string":"The Alan Turing Institute, London, UK","institution_ids":["https://openalex.org/I4210128584"]},{"raw_affiliation_string":"University of Warwick, Coventry, UK","institution_ids":["https://openalex.org/I39555362"]}]},{"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/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 at Austin, Texas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Texas","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029244502","display_name":"Nentawe Gurumdimma","orcid":null},"institutions":[{"id":"https://openalex.org/I161374704","display_name":"University of Jos","ror":"https://ror.org/009kx9832","country_code":"NG","type":"education","lineage":["https://openalex.org/I161374704"]}],"countries":["NG"],"is_corresponding":false,"raw_author_name":"Nentawe Gurumdimma","raw_affiliation_strings":["University of Jos, Jos, Plateau State, Nigeria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Jos, Jos, Plateau State, Nigeria","institution_ids":["https://openalex.org/I161374704"]}]},{"author_position":"middle","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, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seagate Technology, Havant, UK","institution_ids":["https://openalex.org/I4210142999"]}]},{"author_position":"last","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, Texas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas Advanced Computing Center, Texas","institution_ids":["https://openalex.org/I4388891828"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"232","last_page":"241"},"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":0.9441999793052673,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.770628809928894},{"id":"https://openalex.org/keywords/lustre","display_name":"Lustre (file system)","score":0.7598496675491333},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5289193391799927},{"id":"https://openalex.org/keywords/medical-diagnosis","display_name":"Medical diagnosis","score":0.5119991898536682},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44972845911979675},{"id":"https://openalex.org/keywords/hang","display_name":"Hang","score":0.4140045642852783},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3221016824245453},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.3060893416404724},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.20413807034492493},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.15165245532989502},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10888555645942688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.770628809928894},{"id":"https://openalex.org/C180699724","wikidata":"https://www.wikidata.org/wiki/Q1877782","display_name":"Lustre (file system)","level":3,"score":0.7598496675491333},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5289193391799927},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.5119991898536682},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44972845911979675},{"id":"https://openalex.org/C2781323245","wikidata":"https://www.wikidata.org/wiki/Q1363761","display_name":"Hang","level":2,"score":0.4140045642852783},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3221016824245453},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.3060893416404724},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.20413807034492493},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.15165245532989502},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10888555645942688},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hipc.2016.035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2016.035","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":"2016 IEEE 23rd International Conference on High Performance Computing (HiPC)","raw_type":"proceedings-article"},{"id":"pmh:oai:wrap.warwick.ac.uk:83539","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400665","display_name":"Warwick Research Archive Portal (University of Warwick)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39555362","host_organization_name":"University of Warwick","host_organization_lineage":["https://openalex.org/I39555362"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Item"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G1729657293","display_name":"Collaborative Research: Integrated HPC Systems Usage and Performance of Resources Monitoring and Modeling (SUPReMM)","funder_award_id":"1203604","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8659196067","display_name":"World-Class Science Through World Leadership in HPC","funder_award_id":"0622780","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310620","display_name":"University of Texas at Austin","ror":"https://ror.org/00hj54h04"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W119004536","https://openalex.org/W135621451","https://openalex.org/W164902916","https://openalex.org/W208057840","https://openalex.org/W1565377632","https://openalex.org/W1589384255","https://openalex.org/W1622035374","https://openalex.org/W1995565928","https://openalex.org/W2011023286","https://openalex.org/W2095157729","https://openalex.org/W2098695822","https://openalex.org/W2107461003","https://openalex.org/W2111410817","https://openalex.org/W2115056012","https://openalex.org/W2121390717","https://openalex.org/W2126058588","https://openalex.org/W2128825142","https://openalex.org/W2136159049","https://openalex.org/W2145224695","https://openalex.org/W2156997370","https://openalex.org/W2159311877","https://openalex.org/W2169411532","https://openalex.org/W2169710700","https://openalex.org/W2185621890","https://openalex.org/W2562383263","https://openalex.org/W2791170912","https://openalex.org/W4205774955","https://openalex.org/W4236716389","https://openalex.org/W4249923483","https://openalex.org/W6604746331","https://openalex.org/W6605488818","https://openalex.org/W6606699393","https://openalex.org/W6608443543"],"related_works":["https://openalex.org/W2402831615","https://openalex.org/W2016423940","https://openalex.org/W2002376734","https://openalex.org/W2279057839","https://openalex.org/W2356273321","https://openalex.org/W2167428716","https://openalex.org/W4253808407","https://openalex.org/W2293405763","https://openalex.org/W1519934584","https://openalex.org/W3207002378"],"abstract_inverted_index":{"Failure":[0],"diagnosis":[1,44],"for":[2,28,42,69,150],"large":[3],"compute":[4,171,183],"clusters":[5],"using":[6],"only":[7,117],"message":[8,36,63],"logs":[9,37,64],"is":[10],"known":[11],"to":[12,60,92],"be":[13,118,190],"incomplete.":[14],"Recent":[15],"availability":[16],"of":[17,26,75,90,129,143,153,159,170],"resource":[18,39,66,78,135,165],"use":[19,40,67,79,136,166],"data":[20,27,41,68,93,188],"provides":[21],"another":[22],"potentially":[23],"useful":[24],"source":[25],"failure":[29,43,70],"detection":[30,152],"and":[31,38,65,77,80,163,174],"diagnosis.":[32,71],"Early":[33],"work":[34],"combining":[35,61],"has":[45,98],"shown":[46],"promising":[47],"results.":[48],"This":[49],"paper":[50],"describes":[51],"the":[52,95,157,168,193],"CRUMEL":[53,72,91,105],"framework":[54],"which":[55,138,146],"implements":[56],"a":[57],"new":[58],"approach":[59],"rationalized":[62],"identifies":[73],"patterns":[74,83],"errors":[76],"correlates":[81],"these":[82],"by":[84,120],"time":[85],"with":[86,113,141,167,182],"system":[87,114],"failures.":[88],"Application":[89],"from":[94],"Ranger":[96],"supercomputer":[97],"yielded":[99],"improved":[100],"diagnoses":[101],"over":[102],"previous":[103],"research.":[104],"has:":[106],"(i)":[107],"showed":[108],"that":[109],"more":[110,178],"events":[111,162],"correlated":[112,140,160,164],"failures":[115],"can":[116],"identified":[119,132,176],"applying":[121],"different":[122],"correlation":[123],"algorithms,":[124],"(ii)":[125],"confirmed":[126],"six":[127],"groups":[128,180],"errors,":[130],"(iii)":[131],"Lustre":[133,144],"I/O":[134],"counters":[137],"are":[139,147],"occurrence":[142],"faults":[145],"potential":[148],"flags":[149],"online":[151],"failures,":[154],"(iv)":[155],"matched":[156],"dates":[158,169],"error":[161,179],"node":[172,184],"hang-ups":[173],"(v)":[175],"two":[177],"associated":[181],"hang-ups.":[185],"The":[186],"pre-processed":[187],"will":[189],"put":[191],"on":[192],"public":[194],"domain":[195],"in":[196],"September,":[197],"2016.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}