{"id":"https://openalex.org/W3034877820","doi":"https://doi.org/10.1109/noms47738.2020.9110326","title":"Rapid Detection and Localization of Gray Failures in Data Centers via In-band Network Telemetry","display_name":"Rapid Detection and Localization of Gray Failures in Data Centers via In-band Network Telemetry","publication_year":2020,"publication_date":"2020-04-01","ids":{"openalex":"https://openalex.org/W3034877820","doi":"https://doi.org/10.1109/noms47738.2020.9110326","mag":"3034877820"},"language":"en","primary_location":{"id":"doi:10.1109/noms47738.2020.9110326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/noms47738.2020.9110326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"NOMS 2020 - 2020 IEEE/IFIP Network Operations and Management Symposium","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/A5066560659","display_name":"Chenhao Jia","orcid":"https://orcid.org/0000-0003-4616-9410"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":null,"type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenhao Jia","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014799844","display_name":"Tian Pan","orcid":"https://orcid.org/0000-0001-7718-0669"},"institutions":[{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":null,"type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]},{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian Pan","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054915610","display_name":"Zizheng Bian","orcid":null},"institutions":[{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":null,"type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]},{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zizheng Bian","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101867210","display_name":"Xingchen Lin","orcid":"https://orcid.org/0000-0003-4003-5817"},"institutions":[{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":null,"type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]},{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingchen Lin","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071045707","display_name":"Enge Song","orcid":"https://orcid.org/0000-0002-4442-2817"},"institutions":[{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":null,"type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]},{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enge Song","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052315039","display_name":"Cheng Xu","orcid":"https://orcid.org/0000-0003-4913-5371"},"institutions":[{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":null,"type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]},{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Xu","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087767046","display_name":"Tao Huang","orcid":"https://orcid.org/0000-0002-3545-1122"},"institutions":[{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":null,"type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]},{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Huang","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101690888","display_name":"Yunjie Liu","orcid":"https://orcid.org/0000-0002-9312-7523"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":null,"type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunjie Liu","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5066560659"],"corresponding_institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"],"apc_list":null,"apc_paid":null,"fwci":4.0086,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.94098493,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10714","display_name":"Software-Defined Networks and 5G","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/T10714","display_name":"Software-Defined Networks and 5G","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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.998199999332428,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9972000122070312,"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":0.8310695886611938},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.70371013879776},{"id":"https://openalex.org/keywords/troubleshooting","display_name":"Troubleshooting","score":0.6587170362472534},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.6223064661026001},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.5733963847160339},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.49614009261131287},{"id":"https://openalex.org/keywords/telemetry","display_name":"Telemetry","score":0.49246224761009216},{"id":"https://openalex.org/keywords/packet-loss","display_name":"Packet loss","score":0.44562143087387085},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.38358381390571594},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22880828380584717},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09118485450744629}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8310695886611938},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.70371013879776},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.6587170362472534},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.6223064661026001},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.5733963847160339},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.49614009261131287},{"id":"https://openalex.org/C183121708","wikidata":"https://www.wikidata.org/wiki/Q209867","display_name":"Telemetry","level":2,"score":0.49246224761009216},{"id":"https://openalex.org/C54108766","wikidata":"https://www.wikidata.org/wiki/Q391064","display_name":"Packet loss","level":3,"score":0.44562143087387085},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.38358381390571594},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22880828380584717},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09118485450744629}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/noms47738.2020.9110326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/noms47738.2020.9110326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"NOMS 2020 - 2020 IEEE/IFIP Network Operations and Management Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W14875769","https://openalex.org/W1626838828","https://openalex.org/W1969949820","https://openalex.org/W1990249073","https://openalex.org/W1994926493","https://openalex.org/W1998471240","https://openalex.org/W2014660968","https://openalex.org/W2028926203","https://openalex.org/W2114296561","https://openalex.org/W2115303222","https://openalex.org/W2126969025","https://openalex.org/W2130531694","https://openalex.org/W2136451165","https://openalex.org/W2169466806","https://openalex.org/W2465793152","https://openalex.org/W2466231594","https://openalex.org/W2495086702","https://openalex.org/W2604906639","https://openalex.org/W2623323969","https://openalex.org/W2798534715","https://openalex.org/W2900985109","https://openalex.org/W2919267195","https://openalex.org/W3147432643","https://openalex.org/W3160434771","https://openalex.org/W4206018797","https://openalex.org/W4230300228","https://openalex.org/W4232093111","https://openalex.org/W4232256169","https://openalex.org/W4235670058","https://openalex.org/W4311657430","https://openalex.org/W6600620567","https://openalex.org/W6719609709","https://openalex.org/W6736269595","https://openalex.org/W6750782330","https://openalex.org/W6756142678"],"related_works":["https://openalex.org/W3013479934","https://openalex.org/W4210597238","https://openalex.org/W4318325534","https://openalex.org/W4206476896","https://openalex.org/W4240398146","https://openalex.org/W2950310564","https://openalex.org/W4238338086","https://openalex.org/W2467308209","https://openalex.org/W2913357653","https://openalex.org/W1981753479"],"abstract_inverted_index":{"Network":[0,75],"reliability":[1],"becomes":[2],"increasingly":[3],"important":[4],"in":[5,25,56,216],"modern":[6],"data":[7],"center":[8],"networks":[9],"(DCNs).":[10],"The":[11],"DCNs":[12],"are":[13],"expected":[14],"to":[15,48,85,89,144,166],"work":[16],"sustainably":[17],"under":[18,93],"internal":[19],"failures":[20,32,210],"and":[21,66,103,119,149,196,211],"assist":[22],"network":[23,31,107,190,208],"operators":[24],"troubleshooting":[26],"them":[27],"rapidly.":[28],"However,":[29],"some":[30],"will":[33,115,163],"happen":[34],"silently":[35],"with":[36,192],"packets":[37,84],"discarded":[38],"without":[39],"producing":[40],"any":[41],"explicit":[42],"notification":[43],"before":[44],"causing":[45],"tremendous":[46],"damage":[47],"the":[49,71,91,98,110,123,156,159,181,213],"network.":[50],"To":[51,179],"troubleshoot":[52],"these":[53],"\"gray":[54],"failures\",":[55],"this":[57],"work,":[58],"we":[59,79,186],"present":[60],"a":[61,106,131,167,188,197,225],"rapid":[62],"gray":[63,209],"failure":[64,108,172,221],"detection":[65],"localization":[67,173,222],"mechanism":[68],"based":[69],"on":[70],"recently":[72],"proposed":[73],"In-band":[74],"Telemetry":[76],"(INT).":[77],"Specifically,":[78],"leverage":[80],"simplified":[81],"INT":[82],"probe":[83],"conduct":[86],"network-wide":[87],"telemetry":[88],"help":[90],"servers":[92,135],"ToR":[94],"switches":[95,195],"obtain":[96],"all":[97,158],"feasible":[99],"paths":[100,114],"between":[101],"sources":[102],"destinations.":[104],"Once":[105],"occurs,":[109],"affected":[111,214],"thus":[112],"unavailable":[113],"immediately":[116],"be":[117,164],"detected":[118],"flushed":[120],"out":[121],"of":[122,153,183],"path":[124,161,177],"information":[125],"table":[126],"at":[127],"each":[128],"server":[129],"by":[130,174],"timeout":[132],"mechanism.":[133],"Hence,":[134],"can":[136,205],"proactively":[137],"perform":[138],"source":[139],"routing-based":[140],"fast":[141],"traffic":[142,215],"reroute":[143,212],"avoid":[145],"massive":[146],"packet":[147],"loss":[148],"retain":[150],"uninterrupted":[151],"quality":[152],"experience.":[154],"At":[155],"meantime,":[157],"aged":[160],"entries":[162],"uploaded":[165],"remote":[168],"controller":[169],"for":[170],"centralized":[171],"identifying":[175],"common":[176],"elements.":[178],"verify":[180],"feasibility":[182],"our":[184,203],"design,":[185],"build":[187],"virtual":[189],"testbed":[191],"software":[193],"P4":[194],"Redis":[198],"database.":[199],"Evaluation":[200],"shows":[201],"that":[202],"system":[204],"successfully":[206],"detect":[207],"no":[217],"time":[218],"while":[219],"complete":[220],"within":[223],"only":[224],"few":[226],"seconds.":[227]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}