{"id":"https://openalex.org/W2409855605","doi":"https://doi.org/10.1109/tpds.2016.2575829","title":"Failure Diagnosis for Distributed Systems using Targeted Fault Injection","display_name":"Failure Diagnosis for Distributed Systems using Targeted Fault Injection","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2409855605","doi":"https://doi.org/10.1109/tpds.2016.2575829","mag":"2409855605"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2016.2575829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2016.2575829","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5039994265","display_name":"Cuong Pham","orcid":"https://orcid.org/0000-0001-6876-0493"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cuong Pham","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100447537","display_name":"Long Wang","orcid":"https://orcid.org/0000-0001-6073-1225"},"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":"Long Wang","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010776108","display_name":"Byungchul Tak","orcid":"https://orcid.org/0000-0002-8204-6816"},"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":"Byungchul Tak","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060996158","display_name":"Salman Baset","orcid":null},"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":"Salman Baset","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070094618","display_name":"Chunqiang Tang","orcid":"https://orcid.org/0009-0004-0133-4800"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunqiang Tang","raw_affiliation_strings":["Facebook Inc., Menlo Park, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Inc., Menlo Park, CA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043860236","display_name":"Zbigniew Kalbarczyk","orcid":"https://orcid.org/0009-0002-6040-6865"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zbigniew Kalbarczyk","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067802693","display_name":"Ravishankar K. Iyer","orcid":"https://orcid.org/0000-0003-2245-3038"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ravishankar Iyer","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1361,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.94408179,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9987000226974487,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9904000163078308,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8047301769256592},{"id":"https://openalex.org/keywords/fault-injection","display_name":"Fault injection","score":0.6712679266929626},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6487104892730713},{"id":"https://openalex.org/keywords/software-fault-tolerance","display_name":"Software fault tolerance","score":0.6408731341362},{"id":"https://openalex.org/keywords/root-cause","display_name":"Root cause","score":0.5403502583503723},{"id":"https://openalex.org/keywords/fault","display_name":"Fault (geology)","score":0.5360294580459595},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5349714756011963},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.49212855100631714},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.4334036409854889},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.39114928245544434},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3713049292564392},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.3521217107772827},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17199084162712097},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07905888557434082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047301769256592},{"id":"https://openalex.org/C2775928411","wikidata":"https://www.wikidata.org/wiki/Q2041312","display_name":"Fault injection","level":3,"score":0.6712679266929626},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6487104892730713},{"id":"https://openalex.org/C50712370","wikidata":"https://www.wikidata.org/wiki/Q4269346","display_name":"Software fault tolerance","level":3,"score":0.6408731341362},{"id":"https://openalex.org/C84945661","wikidata":"https://www.wikidata.org/wiki/Q7366567","display_name":"Root cause","level":2,"score":0.5403502583503723},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.5360294580459595},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5349714756011963},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.49212855100631714},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.4334036409854889},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.39114928245544434},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3713049292564392},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.3521217107772827},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17199084162712097},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07905888557434082},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C165205528","wikidata":"https://www.wikidata.org/wiki/Q83371","display_name":"Seismology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2016.2575829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2016.2575829","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W46959185","https://openalex.org/W192446467","https://openalex.org/W1456818137","https://openalex.org/W1524673069","https://openalex.org/W1537198022","https://openalex.org/W1575235053","https://openalex.org/W1616338336","https://openalex.org/W1683791865","https://openalex.org/W1767990287","https://openalex.org/W1967308381","https://openalex.org/W2012010763","https://openalex.org/W2033472898","https://openalex.org/W2055693471","https://openalex.org/W2067436653","https://openalex.org/W2098182691","https://openalex.org/W2107316307","https://openalex.org/W2119165870","https://openalex.org/W2121204404","https://openalex.org/W2124767313","https://openalex.org/W2126166995","https://openalex.org/W2137839528","https://openalex.org/W2139664301","https://openalex.org/W2140190241","https://openalex.org/W2141353180","https://openalex.org/W2148602057","https://openalex.org/W2153418968","https://openalex.org/W2156205360","https://openalex.org/W2156633971","https://openalex.org/W2163463765","https://openalex.org/W2164055623","https://openalex.org/W2165202235","https://openalex.org/W2171867449","https://openalex.org/W2343875716","https://openalex.org/W2434456651","https://openalex.org/W2913256667","https://openalex.org/W3149901392","https://openalex.org/W4238860748","https://openalex.org/W6601931766","https://openalex.org/W6607881844","https://openalex.org/W6628435967","https://openalex.org/W6631426539","https://openalex.org/W6632104034","https://openalex.org/W6634202960","https://openalex.org/W6637397165","https://openalex.org/W6638118107","https://openalex.org/W6664551833","https://openalex.org/W6685157726","https://openalex.org/W6696642037","https://openalex.org/W6704683568","https://openalex.org/W6718389559"],"related_works":["https://openalex.org/W2971479921","https://openalex.org/W2607474334","https://openalex.org/W2138861322","https://openalex.org/W2902466307","https://openalex.org/W3145923041","https://openalex.org/W2946906624","https://openalex.org/W841176518","https://openalex.org/W188714996","https://openalex.org/W2101077206","https://openalex.org/W2168671684"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,31,36,134],"novel":[4],"approach":[5,128,146],"to":[6,24,47,74,86,173,181],"automating":[7],"failure":[8,37],"diagnostics":[9],"in":[10,121,149,200],"distributed":[11,33,100,122],"systems":[12],"by":[13,52,194],"combining":[14],"fault":[15,22,53,115,155,170],"injection":[16,23,116],"and":[17,111,157,176,183],"data":[18],"analytics.":[19],"We":[20,124,188],"use":[21,66],"populate":[25],"the":[26,43,57,69,76,81,105,108,151],"database":[27,44],"of":[28,80,99,107,163],"failures":[29,50,71],"for":[30,93,160],"target":[32],"system.":[34,139],"When":[35],"is":[38,45,147],"reported":[39,82],"from":[40,68],"production":[41],"environment,":[42],"queried":[46],"find":[48,182],"\u201cmatched\u201d":[49],"generated":[51],"injections.":[54],"Relying":[55],"on":[56],"assumption":[58],"that":[59,144,198],"similar":[60,63],"faults":[61],"generate":[62],"failures,":[64],"we":[65,90],"information":[67],"matched":[70],"as":[72],"hints":[73],"locate":[75],"actual":[77,174,185],"root":[78,152,186],"cause":[79],"failures.":[83,165],"In":[84],"order":[85],"implement":[87],"this":[88,145,192],"approach,":[89],"introduce":[91],"techniques":[92],"(i)":[94],"reconstructing":[95],"end-to-end":[96],"execution":[97],"flows":[98],"software":[101],"components,":[102,159],"(ii)":[103],"computing":[104],"similarity":[106],"reconstructed":[109],"flows,":[110],"(iii)":[112],"performing":[113],"precise":[114],"at":[117],"pre-specified":[118],"executing":[119],"points":[120],"systems.":[123],"have":[125,189],"evaluated":[126],"our":[127],"using":[129],"an":[130],"OpenStack":[131],"cloud":[132,136],"platform,":[133],"popular":[135],"infrastructure":[137],"management":[138],"Our":[140],"experimental":[141],"results":[142],"showed":[143],"effective":[148],"determining":[150],"causes,":[153],"e.g.,":[154],"types":[156],"affected":[158],"71-100":[161],"percent":[162],"tested":[164],"Furthermore,":[166],"it":[167],"can":[168,177],"provide":[169],"locations":[171],"close":[172],"ones":[175],"easily":[178],"be":[179],"used":[180],"fix":[184],"causes.":[187],"also":[190],"validated":[191],"technique":[193],"localizing":[195],"real":[196],"bugs":[197],"occurred":[199],"OpenStack.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}