{"id":"https://openalex.org/W2905012370","doi":"https://doi.org/10.1109/ftxs.2018.00011","title":"SaNSA - The Supercomputer and Node State Architecture","display_name":"SaNSA - The Supercomputer and Node State Architecture","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2905012370","doi":"https://doi.org/10.1109/ftxs.2018.00011","mag":"2905012370"},"language":"en","primary_location":{"id":"doi:10.1109/ftxs.2018.00011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ftxs.2018.00011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/ACM 8th Workshop on Fault Tolerance for HPC at eXtreme Scale (FTXS)","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/A5109411373","display_name":"Neil Agarwal","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Neil Agarwal","raw_affiliation_strings":["University of California, Berkeley, California"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, California","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046869270","display_name":"Hugh Greenberg","orcid":"https://orcid.org/0000-0003-3970-9626"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hugh Greenberg","raw_affiliation_strings":["Ultrascale Systems Research Center, High Performance Computing, Los Alamos, New Mexico"],"affiliations":[{"raw_affiliation_string":"Ultrascale Systems Research Center, High Performance Computing, Los Alamos, New Mexico","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036921385","display_name":"Sean Blanchard","orcid":"https://orcid.org/0000-0002-1119-7828"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sean Blanchard","raw_affiliation_strings":["Ultrascale Systems Research Center, High Performance Computing, Los Alamos, New Mexico"],"affiliations":[{"raw_affiliation_string":"Ultrascale Systems Research Center, High Performance Computing, Los Alamos, New Mexico","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056569157","display_name":"Nathan DeBardeleben","orcid":"https://orcid.org/0000-0002-5593-9205"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nathan DeBardeleben","raw_affiliation_strings":["Ultrascale Systems Research Center, High Performance Computing, Los Alamos, New Mexico"],"affiliations":[{"raw_affiliation_string":"Ultrascale Systems Research Center, High Performance Computing, Los Alamos, New Mexico","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5109411373"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1772819,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"69","last_page":"78"},"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9970999956130981,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9900000095367432,"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/supercomputer","display_name":"Supercomputer","score":0.8937118053436279},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7939416170120239},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6369690299034119},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.6099957227706909},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.49817991256713867},{"id":"https://openalex.org/keywords/rack","display_name":"Rack","score":0.4866098165512085},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.44164666533470154},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.4140346646308899},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41222256422042847},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.41072720289230347},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3738343119621277},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.36644446849823},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2264794409275055},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08587110042572021}],"concepts":[{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.8937118053436279},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7939416170120239},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6369690299034119},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.6099957227706909},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.49817991256713867},{"id":"https://openalex.org/C2776843527","wikidata":"https://www.wikidata.org/wiki/Q1351382","display_name":"Rack","level":2,"score":0.4866098165512085},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.44164666533470154},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.4140346646308899},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41222256422042847},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.41072720289230347},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3738343119621277},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36644446849823},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2264794409275055},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08587110042572021},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ftxs.2018.00011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ftxs.2018.00011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/ACM 8th Workshop on Fault Tolerance for HPC at eXtreme Scale (FTXS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6100000143051147,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320328368","display_name":"South African National Space Agency","ror":"https://ror.org/02epph894"},{"id":"https://openalex.org/F4320338304","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1919771734","https://openalex.org/W1975705975","https://openalex.org/W1987117298","https://openalex.org/W2025024269","https://openalex.org/W2038924755","https://openalex.org/W2094127360","https://openalex.org/W2107263349","https://openalex.org/W2116580992","https://openalex.org/W2136797898","https://openalex.org/W2142812297","https://openalex.org/W2263738050","https://openalex.org/W2725626595","https://openalex.org/W2767346922","https://openalex.org/W2886481383","https://openalex.org/W6693014691","https://openalex.org/W6753359477"],"related_works":["https://openalex.org/W2377223570","https://openalex.org/W2033820166","https://openalex.org/W2360126784","https://openalex.org/W2358514374","https://openalex.org/W4399027977","https://openalex.org/W2357743194","https://openalex.org/W3149027463","https://openalex.org/W2958580061","https://openalex.org/W2354821064","https://openalex.org/W4391263626"],"abstract_inverted_index":{"In":[0],"this":[1,60,92],"work":[2],"we":[3,94,142,166],"present":[4],"SaNSA,":[5,141],"the":[6,30,70,108,156],"Supercomputer":[7],"and":[8,18,34,112,151],"Node":[9],"State":[10],"Architecture,":[11],"a":[12,85,102,144,159,179],"software":[13],"infrastructure":[14],"for":[15,50,64,76,178],"historical":[16],"analysis":[17],"anomaly":[19,148],"detection.":[20],"SaNSA":[21,68,111],"consumes":[22],"data":[23,86,162],"from":[24],"multiple":[25],"sources":[26],"including":[27],"system":[28,130],"logs,":[29],"resource":[31],"manager,":[32],"scheduler,":[33],"job":[35],"logs.":[36],"Furthermore,":[37],"additional":[38],"context":[39,157],"such":[40],"as":[41,183,185],"scheduled":[42,176],"maintenance":[43],"events":[44],"or":[45],"dedicated":[46],"application":[47],"run":[48],"times":[49],"specific":[51],"science":[52],"teams":[53],"can":[54],"be":[55],"overlaid.":[56],"We":[57,88,106,123],"discuss":[58],"how":[59,90],"contextual":[61],"information":[62,79,93],"allows":[63,69],"more":[65],"nuanced":[66],"analysis.":[67],"user":[71],"to":[72,194],"apply":[73],"arbitrary":[74],"attributes,":[75],"instance,":[77],"positional":[78],"where":[80],"nodes":[81,172],"are":[82],"located":[83],"in":[84,132,138,155],"center.":[87,163],"show":[89],"using":[91],"identify":[95],"anomalous":[96],"behavior":[97],"of":[98,101,110,129,135,146,158,170,181,187],"one":[99],"rack":[100,189],"1,500":[103],"node":[104],"cluster.":[105],"explain":[107,152],"design":[109],"then":[113],"test":[114],"it":[115],"on":[116,168],"four":[117],"open":[118],"compute":[119],"clusters":[120],"at":[121],"LANL.":[122],"ingest":[124],"over":[125],"1.1":[126],"billion":[127],"lines":[128],"logs":[131],"our":[133],"study":[134],"190":[136],"days":[137],"2018.":[139],"Using":[140],"perform":[143],"number":[145],"different":[147],"detection":[149],"methods":[150],"their":[153],"findings":[154],"production":[160],"supercomputing":[161],"For":[164],"example,":[165],"report":[167],"instances":[169],"misconfigured":[171],"which":[173,191],"receive":[174],"no":[175],"jobs":[177,193],"period":[180],"time":[182],"well":[184],"examples":[186],"correlated":[188],"failures":[190],"cause":[192],"crash.":[195]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
