{"id":"https://openalex.org/W4366999533","doi":"https://doi.org/10.48550/arxiv.2304.11467","title":"Collie: Finding Performance Anomalies in RDMA Subsystems","display_name":"Collie: Finding Performance Anomalies in RDMA Subsystems","publication_year":2023,"publication_date":"2023-04-22","ids":{"openalex":"https://openalex.org/W4366999533","doi":"https://doi.org/10.48550/arxiv.2304.11467"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2304.11467","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.11467","pdf_url":"https://arxiv.org/pdf/2304.11467","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2304.11467","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087324678","display_name":"Xinhao Kong","orcid":"https://orcid.org/0009-0005-2628-7112","observed_orcids":["https://orcid.org/0009-0005-2628-7112"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]},{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Kong, Xinhao","raw_affiliation_strings":["ByteDance Inc","Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":["https://openalex.org/I4405256866"]},{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028120333","display_name":"Yibo Zhu","orcid":"https://orcid.org/0000-0002-9113-2660","observed_orcids":["https://orcid.org/0000-0002-9113-2660"]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu, Yibo","raw_affiliation_strings":["ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024833338","display_name":"Huaping Zhou","orcid":"https://orcid.org/0000-0002-4419-0825","observed_orcids":["https://orcid.org/0000-0002-4419-0825"]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou, Huaping","raw_affiliation_strings":["ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101871699","display_name":"Zhuo Jiang","orcid":"https://orcid.org/0000-0002-6144-7899","observed_orcids":["https://orcid.org/0000-0002-6144-7899"]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang, Zhuo","raw_affiliation_strings":["ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066752025","display_name":"Jianxi Ye","orcid":"https://orcid.org/0000-0002-9891-4534","observed_orcids":["https://orcid.org/0000-0002-9891-4534"]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye, Jianxi","raw_affiliation_strings":["ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054205326","display_name":"Chuanxiong Guo","orcid":"https://orcid.org/0000-0002-0730-8468","observed_orcids":["https://orcid.org/0000-0002-0730-8468"]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo, Chuanxiong","raw_affiliation_strings":["ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007943946","display_name":"Danyang Zhuo","orcid":"https://orcid.org/0000-0002-0611-3941","observed_orcids":["https://orcid.org/0000-0002-0611-3941"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuo, Danyang","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.46000000834465027,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.46000000834465027,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.4431000053882599,"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":0.02290000021457672,"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/rdma","display_name":"RDMA","score":0.9810000061988831},{"id":"https://openalex.org/keywords/performance-anomaly-detection","display_name":"performance anomaly detection","score":0.8930000066757202},{"id":"https://openalex.org/keywords/hardware-diagnostics","display_name":"hardware diagnostics","score":0.4180000126361847},{"id":"https://openalex.org/keywords/simulated-annealing","display_name":"simulated annealing","score":0.6679999828338623},{"id":"https://openalex.org/keywords/performance-counters","display_name":"performance counters","score":0.574999988079071},{"id":"https://openalex.org/keywords/network-interface-card","display_name":"network interface card","score":0.5680000185966492},{"id":"https://openalex.org/keywords/pcie","display_name":"PCI Express","score":0.39500001072883606},{"id":"https://openalex.org/keywords/processor-performance","display_name":"processor performance","score":0.5289999842643738},{"id":"https://openalex.org/keywords/distributed-learning","display_name":"distributed learning","score":0.7170000076293945}],"concepts":[{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.996924877166748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.755372166633606},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5861272811889648},{"id":"https://openalex.org/C64270927","wikidata":"https://www.wikidata.org/wiki/Q206924","display_name":"PCI Express","level":3,"score":0.4538224935531616},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.44039851427078247},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.37460994720458984},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3552170395851135},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.07126232981681824},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2304.11467","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.11467","pdf_url":"https://arxiv.org/pdf/2304.11467","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2304.11467","doi":"https://doi.org/10.48550/arxiv.2304.11467","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2304.11467","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2304.11467","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.11467","pdf_url":"https://arxiv.org/pdf/2304.11467","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320314997","display_name":"Strong","ror":"https://ror.org/041vyzr56"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4366999533.pdf","grobid_xml":"https://content.openalex.org/works/W4366999533.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4414109804","https://openalex.org/W4413756585","https://openalex.org/W2742725870","https://openalex.org/W2944524161","https://openalex.org/W2416075414","https://openalex.org/W3174469612","https://openalex.org/W7047741545","https://openalex.org/W7168044347","https://openalex.org/W6889702086","https://openalex.org/W7104256177"],"abstract_inverted_index":{"High-speed":[0],"RDMA":[1,21,67,130,176,181],"networks":[2],"are":[3,146,155],"getting":[4],"rapidly":[5],"adopted":[6],"in":[7,25,66,167],"the":[8,32,70,149],"industry":[9],"for":[10,59,96,174],"their":[11],"low":[12,46],"latency":[13],"and":[14,54,108,133,179],"reduced":[15],"CPU":[16],"overheads.":[17],"To":[18],"verify":[19],"that":[20,37,118],"can":[22,38,119],"be":[23],"used":[24],"production,":[26],"system":[27],"administrators":[28],"need":[29,71],"to":[30,61,72,104,111,115,170],"understand":[31],"set":[33],"of":[34,78,128,144,153],"application":[35,97],"workloads":[36,117],"potentially":[39],"trigger":[40,120],"abnormal":[41],"performance":[42,64,107,121,141,172],"behaviors":[43],"(e.g.,":[44,84],"unexpected":[45],"throughput,":[47],"PFC":[48],"pause":[49],"frame":[50],"storm).":[51],"We":[52,123,162],"design":[53],"implement":[55],"Collie,":[56],"a":[57,92],"tool":[58],"users":[60],"systematically":[62],"uncover":[63],"anomalies":[65,173],"subsystems":[68],"without":[69],"access":[73],"hardware":[74,82,135,150],"internal":[75],"designs.":[76],"Instead":[77],"individually":[79],"testing":[80],"each":[81],"device":[83],"NIC,":[85,131],"memory,":[86],"PCIe),":[87],"Collie":[88,99,125,137,169],"is":[89],"holistic,":[90],"constructing":[91],"comprehensive":[93],"search":[94],"space":[95],"workloads.":[98],"then":[100],"uses":[101],"simulated":[102],"annealing":[103],"drive":[105],"RDMA-related":[106],"diagnostic":[109],"counters":[110],"extreme":[112],"value":[113],"regions":[114],"find":[116],"anomalies.":[122,142],"evaluate":[124],"on":[126],"combinations":[127],"various":[129],"CPU,":[132],"other":[134],"components.":[136],"found":[138],"15":[139],"new":[140],"All":[143],"them":[145,154],"acknowledged":[147],"by":[148],"vendors.":[151],"7":[152],"already":[156],"fixed":[157],"after":[158],"we":[159],"reported":[160],"them.":[161],"also":[163],"present":[164],"our":[165],"experience":[166],"using":[168],"avoid":[171],"an":[175,180],"RPC":[177],"library":[178],"distributed":[182],"machine":[183],"learning":[184],"framework.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2023-04-27T00:00:00"}