{"id":"https://openalex.org/W4308361824","doi":"https://doi.org/10.1145/3542929.3563482","title":"How to fight production incidents?","display_name":"How to fight production incidents?","publication_year":2022,"publication_date":"2022-11-07","ids":{"openalex":"https://openalex.org/W4308361824","doi":"https://doi.org/10.1145/3542929.3563482"},"language":"en","primary_location":{"id":"doi:10.1145/3542929.3563482","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3542929.3563482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th Symposium on Cloud Computing","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/A5101775931","display_name":"Supriyo Ghosh","orcid":"https://orcid.org/0000-0001-7275-3296"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Supriyo Ghosh","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088243281","display_name":"Manish Shetty","orcid":"https://orcid.org/0000-0002-8630-3998"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Manish Shetty","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101967802","display_name":"Chetan Bansal","orcid":"https://orcid.org/0000-0003-0102-8139"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chetan Bansal","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024224291","display_name":"Suman Nath","orcid":"https://orcid.org/0000-0001-7813-9756"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Suman Nath","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101775931"],"corresponding_institution_ids":["https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":5.691,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.96415922,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"126","last_page":"141"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9975000023841858,"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"}},{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.9959999918937683,"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/troubleshooting","display_name":"Troubleshooting","score":0.8305308818817139},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6518666744232178},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6323839426040649},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.6073627471923828},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.5432239174842834},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.5295905470848083},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.5052645802497864},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.48853859305381775},{"id":"https://openalex.org/keywords/root-cause-analysis","display_name":"Root cause analysis","score":0.48821523785591125},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.46863555908203125},{"id":"https://openalex.org/keywords/root-cause","display_name":"Root cause","score":0.45645803213119507},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.4268548786640167},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.22518306970596313},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20717507600784302},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.1301945447921753},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.1265621781349182}],"concepts":[{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.8305308818817139},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6518666744232178},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6323839426040649},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.6073627471923828},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5432239174842834},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.5295905470848083},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.5052645802497864},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.48853859305381775},{"id":"https://openalex.org/C130963320","wikidata":"https://www.wikidata.org/wiki/Q1401207","display_name":"Root cause analysis","level":2,"score":0.48821523785591125},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.46863555908203125},{"id":"https://openalex.org/C84945661","wikidata":"https://www.wikidata.org/wiki/Q7366567","display_name":"Root cause","level":2,"score":0.45645803213119507},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.4268548786640167},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.22518306970596313},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20717507600784302},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.1301945447921753},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.1265621781349182},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3542929.3563482","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3542929.3563482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th Symposium on Cloud Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2006307164","https://openalex.org/W2009391556","https://openalex.org/W2031513172","https://openalex.org/W2031648200","https://openalex.org/W2035264666","https://openalex.org/W2041783719","https://openalex.org/W2088512344","https://openalex.org/W2123983325","https://openalex.org/W2327265941","https://openalex.org/W2506490502","https://openalex.org/W2523146812","https://openalex.org/W2734941459","https://openalex.org/W2739169085","https://openalex.org/W2899510293","https://openalex.org/W2944436223","https://openalex.org/W2959236513","https://openalex.org/W2998839218","https://openalex.org/W3086623952","https://openalex.org/W3089515198","https://openalex.org/W3132009052","https://openalex.org/W3161874179","https://openalex.org/W3165309304","https://openalex.org/W3192479259","https://openalex.org/W3205811065","https://openalex.org/W4283071214"],"related_works":["https://openalex.org/W2030594396","https://openalex.org/W4200610016","https://openalex.org/W3045668461","https://openalex.org/W2490884653","https://openalex.org/W4255366506","https://openalex.org/W2183996497","https://openalex.org/W2056250485","https://openalex.org/W129587375","https://openalex.org/W2110363179","https://openalex.org/W167622659"],"abstract_inverted_index":{"Production":[0],"incidents":[1,32,41,72,96,152],"in":[2,11,76,108],"today's":[3],"large-scale":[4,79],"cloud":[5,27,81],"services":[6,28,123],"can":[7],"be":[8],"extremely":[9],"expensive":[10],"terms":[12],"of":[13,39,68,87,89],"customer":[14],"impacts":[15],"and":[16,50,56,73,98,115,142,144],"engineering":[17],"resources":[18],"required":[19],"to":[20,34,53,149],"mitigate":[21,57],"them.":[22,58],"Despite":[23],"continuous":[24],"reliability":[25],"efforts,":[26],"still":[29],"experience":[30],"severe":[31],"due":[33],"various":[35],"root-causes.":[36],"Worse,":[37],"many":[38],"these":[40],"last":[42],"for":[43],"a":[44,78,131],"long":[45],"period":[46],"as":[47],"existing":[48],"techniques":[49],"practices":[51],"fail":[52],"quickly":[54],"detect":[55],"To":[59],"better":[60],"understand":[61],"the":[62,95,105,122],"problems,":[63],"we":[64,126],"carefully":[65],"study":[66],"hundreds":[67,86],"recent":[69],"high":[70],"severity":[71],"their":[74],"postmortems":[75],"Microsoft-Teams,":[77],"distributed":[80],"based":[82],"service":[83],"used":[84],"by":[85,130],"millions":[88],"users.":[90],"We":[91],"answer:":[92],"(a)":[93],"why":[94],"occurred":[97],"how":[99,148],"they":[100],"were":[101,107],"resolved,":[102],"(b)":[103],"what":[104,117],"gaps":[106],"current":[109],"processes":[110],"which":[111],"caused":[112],"delayed":[113],"response,":[114],"(c)":[116],"automation":[118,154],"could":[119],"help":[120],"make":[121],"resilient.":[124],"Finally,":[125],"uncover":[127],"interesting":[128],"insights":[129],"novel":[132],"multi-dimensional":[133],"analysis":[134],"that":[135],"correlates":[136],"different":[137,158],"troubleshooting":[138],"stages":[139],"(detection,":[140],"root-causing":[141],"mitigation),":[143],"provide":[145],"guidance":[146],"on":[147],"tackle":[150],"complex":[151],"through":[153],"or":[155],"testing":[156],"at":[157],"granularity.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":5}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}
