{"id":"https://openalex.org/W2160821994","doi":"https://doi.org/10.1109/dsn.2004.1311948","title":"Failure data analysis of a large-scale heterogeneous server environment","display_name":"Failure data analysis of a large-scale heterogeneous server environment","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2160821994","doi":"https://doi.org/10.1109/dsn.2004.1311948","mag":"2160821994"},"language":"en","primary_location":{"id":"doi:10.1109/dsn.2004.1311948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsn.2004.1311948","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Dependable Systems and Networks, 2004","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/A5025640169","display_name":"R.K. Sahoo","orcid":"https://orcid.org/0000-0002-3270-5318"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"R.K. Sahoo","raw_affiliation_strings":["Exploratory Server Systems Department, IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"Exploratory Server Systems Department, IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013152760","display_name":"Mark S. Squillante","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M.S. Squillante","raw_affiliation_strings":["Department of Computer Science & Engineering, Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033253809","display_name":"Anand Sivasubramaniam","orcid":"https://orcid.org/0000-0001-6173-687X"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Sivasubramaniam","raw_affiliation_strings":["Mathematical Sciences Department, IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"Mathematical Sciences Department, IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053344541","display_name":"Yanyong Zhang","orcid":"https://orcid.org/0000-0001-6520-255X"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanyong Zhang","raw_affiliation_strings":["Department of Electrical & Computer Engineering, Rutgers University, Piscataway, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering, Rutgers University, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025640169"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":9.4646,"has_fulltext":false,"cited_by_count":238,"citation_normalized_percentile":{"value":0.98063234,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"772","last_page":"781"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9993000030517578,"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":0.9993000030517578,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7609925270080566},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7098477482795715},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.6917178630828857},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.6864901185035706},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6391144394874573},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.46933212876319885},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.45256781578063965},{"id":"https://openalex.org/keywords/software-fault-tolerance","display_name":"Software fault tolerance","score":0.4406147599220276},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.43304091691970825},{"id":"https://openalex.org/keywords/system-monitoring","display_name":"System monitoring","score":0.421468585729599},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.4195708632469177},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.418771892786026},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.4061627686023712},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36699771881103516},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.15418723225593567},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1128227710723877},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1126524806022644},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11141854524612427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7609925270080566},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7098477482795715},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.6917178630828857},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.6864901185035706},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6391144394874573},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46933212876319885},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.45256781578063965},{"id":"https://openalex.org/C50712370","wikidata":"https://www.wikidata.org/wiki/Q4269346","display_name":"Software fault tolerance","level":3,"score":0.4406147599220276},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.43304091691970825},{"id":"https://openalex.org/C200749887","wikidata":"https://www.wikidata.org/wiki/Q1165574","display_name":"System monitoring","level":2,"score":0.421468585729599},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.4195708632469177},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.418771892786026},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.4061627686023712},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36699771881103516},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.15418723225593567},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1128227710723877},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1126524806022644},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11141854524612427},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/dsn.2004.1311948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsn.2004.1311948","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Dependable Systems and Networks, 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.110.5829","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.110.5829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ece.rutgers.edu/~yyzhang/research/papers/dsn04.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.116.6739","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.116.6739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utexas.edu/~hestness/papers/sahoo-failuredata.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.125.3602","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.125.3602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.berkeley.edu/~randy/Courses/CS294.F07/10.3.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.88.5755","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.88.5755","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://csl.cse.psu.edu/publications/dsn04.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1527235902","https://openalex.org/W1577857692","https://openalex.org/W1965399019","https://openalex.org/W1969359541","https://openalex.org/W1980627207","https://openalex.org/W2002180307","https://openalex.org/W2006075444","https://openalex.org/W2033346530","https://openalex.org/W2056306993","https://openalex.org/W2068171717","https://openalex.org/W2120876718","https://openalex.org/W2121098551","https://openalex.org/W2124731241","https://openalex.org/W2156205360","https://openalex.org/W2158016161","https://openalex.org/W2169213530","https://openalex.org/W6678306422","https://openalex.org/W6683875599"],"related_works":["https://openalex.org/W2971479921","https://openalex.org/W2106348006","https://openalex.org/W3145923041","https://openalex.org/W2946906624","https://openalex.org/W841176518","https://openalex.org/W1978919910","https://openalex.org/W2024212764","https://openalex.org/W2157727563","https://openalex.org/W2101077206","https://openalex.org/W2470343202"],"abstract_inverted_index":{"The":[0],"growing":[1,33],"complexity":[2],"of":[3,10,39,57,80,88,110,118,143],"hardware":[4],"and":[5,16,42,44,47,77,83,127,138,158],"software":[6],"mandates":[7],"the":[8,55,75,108,119,122,135],"recognition":[9],"fault":[11],"occurrence":[12],"in":[13,64,102],"system":[14,40,62,81,103,136],"deployment":[15],"management.":[17],"While":[18,100],"there":[19,28],"are":[20,125,141],"several":[21],"techniques":[22,59],"to":[23,30,66,106,113,169],"prevent":[24],"and/or":[25],"handle":[26],"faults,":[27],"continues":[29],"be":[31,167],"a":[32,86,94,98,114],"need":[34],"for":[35,60],"an":[36],"in-depth":[37],"understanding":[38,51],"errors":[41,82],"failures":[43,84,112],"their":[45],"empirical":[46,76],"statistical":[48,78],"properties.":[49],"This":[50],"can":[52,166],"help":[53],"evaluate":[54],"effectiveness":[56],"different":[58],"improving":[61],"availability,":[63],"addition":[65],"developing":[67],"new":[68],"solutions.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73],"analyze":[74],"properties":[79],"from":[85],"network":[87],"nearly":[89],"400":[90],"heterogeneous":[91],"servers":[92],"running":[93],"diverse":[95],"workload":[96],"over":[97],"year.":[99],"improvements":[101],"robustness":[104],"continue":[105],"limit":[107],"number":[109],"actual":[111],"very":[115],"small":[116],"fraction":[117],"recorded":[120],"errors,":[121],"failure":[123,139],"rates":[124],"significant":[126],"highly":[128],"variable.":[129],"Our":[130],"results":[131],"also":[132,165],"show":[133],"that":[134],"error":[137],"patterns":[140],"comprised":[142],"time-varying":[144],"behavior":[145],"containing":[146],"long":[147],"stationary":[148,151],"intervals.":[149],"These":[150],"intervals":[152],"exhibit":[153],"various":[154],"strong":[155],"correlation":[156],"structures":[157],"periodic":[159],"patterns,":[160],"which":[161],"impact":[162],"performance":[163,172],"but":[164],"exploited":[168],"address":[170],"such":[171],"issues.":[173]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":20},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":20},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":17}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
