{"id":"https://openalex.org/W7106301016","doi":"https://doi.org/10.1145/3730567.3764494","title":"Congestion Patterns in a Large-scale RDMA Datacenter","display_name":"Congestion Patterns in a Large-scale RDMA Datacenter","publication_year":2025,"publication_date":"2025-10-28","ids":{"openalex":"https://openalex.org/W7106301016","doi":"https://doi.org/10.1145/3730567.3764494"},"language":null,"primary_location":{"id":"doi:10.1145/3730567.3764494","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3730567.3764494","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Internet Measurement Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3730567.3764494","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Soudeh Ghorbani","orcid":"https://orcid.org/0000-0002-1331-1372"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Soudeh Ghorbani","raw_affiliation_strings":["Meta, New York, New York, USA and Johns Hopkins University, Baltimore, Maryland, USA"],"affiliations":[{"raw_affiliation_string":"Meta, New York, New York, USA and Johns Hopkins University, Baltimore, Maryland, USA","institution_ids":["https://openalex.org/I2799853436","https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yimeng Zhao","orcid":"https://orcid.org/0009-0002-1791-6325"},"institutions":[{"id":"https://openalex.org/I4210112286","display_name":"The Metropolitan Opera (United States)","ror":"https://ror.org/022q3vw94","country_code":"US","type":"company","lineage":["https://openalex.org/I4210112286"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yimeng Zhao","raw_affiliation_strings":["Meta, New York, New York, USA"],"affiliations":[{"raw_affiliation_string":"Meta, New York, New York, USA","institution_ids":["https://openalex.org/I4210112286"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Srikanth Sundaresan","orcid":"https://orcid.org/0009-0003-6230-9396"},"institutions":[{"id":"https://openalex.org/I55200170","display_name":"Massachusetts College of Art and Design","ror":"https://ror.org/032k6a629","country_code":"US","type":"education","lineage":["https://openalex.org/I55200170"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srikanth Sundaresan","raw_affiliation_strings":["Meta, Boston, Massachusett, USA"],"affiliations":[{"raw_affiliation_string":"Meta, Boston, Massachusett, USA","institution_ids":["https://openalex.org/I55200170"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ying Zhang","orcid":"https://orcid.org/0000-0003-2736-5694"},"institutions":[{"id":"https://openalex.org/I3197470489","display_name":"Alpha Omega Alpha Medical Honor Society","ror":"https://ror.org/057q9nn35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I3197470489"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Zhang","raw_affiliation_strings":["Meta, Menlo Park, California, USA"],"affiliations":[{"raw_affiliation_string":"Meta, Menlo Park, California, USA","institution_ids":["https://openalex.org/I3197470489","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yijing Zeng","orcid":"https://orcid.org/0000-0001-5244-5034"},"institutions":[{"id":"https://openalex.org/I4210112286","display_name":"The Metropolitan Opera (United States)","ror":"https://ror.org/022q3vw94","country_code":"US","type":"company","lineage":["https://openalex.org/I4210112286"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yijing Zeng","raw_affiliation_strings":["Meta, New York, New York, USA"],"affiliations":[{"raw_affiliation_string":"Meta, New York, New York, USA","institution_ids":["https://openalex.org/I4210112286"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Abhigyan Sharma","orcid":"https://orcid.org/0009-0006-0368-9829"},"institutions":[{"id":"https://openalex.org/I4210112286","display_name":"The Metropolitan Opera (United States)","ror":"https://ror.org/022q3vw94","country_code":"US","type":"company","lineage":["https://openalex.org/I4210112286"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhigyan Sharma","raw_affiliation_strings":["Meta, New York, New York, USA"],"affiliations":[{"raw_affiliation_string":"Meta, New York, New York, USA","institution_ids":["https://openalex.org/I4210112286"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Prashanth Kannan","orcid":"https://orcid.org/0009-0005-4794-9971"},"institutions":[{"id":"https://openalex.org/I3197470489","display_name":"Alpha Omega Alpha Medical Honor Society","ror":"https://ror.org/057q9nn35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I3197470489"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prashanth Kannan","raw_affiliation_strings":["Meta, Menlo Park, California, USA"],"affiliations":[{"raw_affiliation_string":"Meta, Menlo Park, California, USA","institution_ids":["https://openalex.org/I3197470489","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":null,"display_name":"Cristian Lumezanu","orcid":"https://orcid.org/0009-0002-8528-602X"},"institutions":[{"id":"https://openalex.org/I4210112286","display_name":"The Metropolitan Opera (United States)","ror":"https://ror.org/022q3vw94","country_code":"US","type":"company","lineage":["https://openalex.org/I4210112286"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cristian Lumezanu","raw_affiliation_strings":["Meta, New York, New York, USA"],"affiliations":[{"raw_affiliation_string":"Meta, New York, New York, USA","institution_ids":["https://openalex.org/I4210112286"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69645044,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"944","last_page":"951"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.4388999938964844,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.4388999938964844,"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"}},{"id":"https://openalex.org/T10138","display_name":"Network Traffic and Congestion Control","score":0.16820000112056732,"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/T12127","display_name":"Software System Performance and Reliability","score":0.09740000218153,"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/remote-direct-memory-access","display_name":"Remote direct memory access","score":0.9474999904632568},{"id":"https://openalex.org/keywords/network-congestion","display_name":"Network congestion","score":0.73580002784729},{"id":"https://openalex.org/keywords/nonstop","display_name":"NonStop","score":0.5974000096321106},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.5232999920845032},{"id":"https://openalex.org/keywords/infiniband","display_name":"InfiniBand","score":0.5123999714851379},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.3732999861240387},{"id":"https://openalex.org/keywords/flow-control","display_name":"Flow control (data)","score":0.3515999913215637},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.31139999628067017}],"concepts":[{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.9474999904632568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7925000190734863},{"id":"https://openalex.org/C195563490","wikidata":"https://www.wikidata.org/wiki/Q180368","display_name":"Network congestion","level":3,"score":0.73580002784729},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.6625000238418579},{"id":"https://openalex.org/C2779013668","wikidata":"https://www.wikidata.org/wiki/Q826798","display_name":"NonStop","level":2,"score":0.5974000096321106},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.5232999920845032},{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.5123999714851379},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40959998965263367},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C186766456","wikidata":"https://www.wikidata.org/wiki/Q612457","display_name":"Flow control (data)","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3490999937057495},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.31139999628067017},{"id":"https://openalex.org/C2776506862","wikidata":"https://www.wikidata.org/wiki/Q425134","display_name":"Palytoxin","level":3,"score":0.3075000047683716},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C90377713","wikidata":"https://www.wikidata.org/wiki/Q576997","display_name":"Stream Control Transmission Protocol","level":3,"score":0.29919999837875366},{"id":"https://openalex.org/C153740404","wikidata":"https://www.wikidata.org/wiki/Q671224","display_name":"Data center","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C22684755","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing theory","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.2833000123500824},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2703999876976013},{"id":"https://openalex.org/C3020431745","wikidata":"https://www.wikidata.org/wiki/Q25325220","display_name":"Many core","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C192126672","wikidata":"https://www.wikidata.org/wiki/Q1068715","display_name":"Telecommunications network","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.2572999894618988},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3730567.3764494","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3730567.3764494","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Internet Measurement Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3730567.3764494","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3730567.3764494","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 ACM Internet Measurement Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1987879194","https://openalex.org/W1988150362","https://openalex.org/W1998471240","https://openalex.org/W2050353731","https://openalex.org/W2062832101","https://openalex.org/W2102369238","https://openalex.org/W2117884704","https://openalex.org/W2149804187","https://openalex.org/W2164740236","https://openalex.org/W2168595508","https://openalex.org/W2613694343","https://openalex.org/W2743073148","https://openalex.org/W2743093301","https://openalex.org/W2744387122","https://openalex.org/W2744567246","https://openalex.org/W2769038759","https://openalex.org/W2794896506","https://openalex.org/W3046812104","https://openalex.org/W3217198056","https://openalex.org/W4290991675","https://openalex.org/W4307020348","https://openalex.org/W4386385196","https://openalex.org/W4389075802","https://openalex.org/W4401176799"],"related_works":[],"abstract_inverted_index":{"RDMA":[0,89,140,163,201],"datacenters":[1,157],"are":[2,52,74],"proliferating":[3],"to":[4,92,158,177],"meet":[5],"the":[6,31,50,53,57,109,114,132,144,152,159,166,172,204],"demand":[7],"of":[8,34,49,118,134,146,188],"emerging":[9],"workloads":[10],"such":[11],"as":[12,17,19],"AI":[13,94],"training":[14],"and":[15,68,106,116,120,179,197],"inference":[16],"well":[18],"distributed":[20,93],"storage.":[21],"This":[22,78],"trend":[23],"has":[24,142],"opened":[25],"up":[26],"a":[27,87],"critical":[28],"knowledge":[29],"gap:":[30],"traffic":[32],"characteristics":[33],"congestion":[35,65,85,102,147,181,199],"in":[36,75,86,108,139,154,162,200],"these":[37],"networks":[38,141],"remain":[39],"unknown.":[40],"We":[41,96,127],"do":[42],"not":[43],"know,":[44],"for":[45,129,194,206],"example,":[46],"which":[47],"layers":[48],"network":[51,58,160],"most":[54],"congested,":[55],"if":[56],"is":[59],"load":[60],"balanced":[61],"effectively,":[62],"how":[63,69],"long":[64],"events":[66],"last,":[67],"accurate":[70],"existing":[71,124],"telemetry":[72,125],"systems":[73],"capturing":[76],"congestion.":[77],"paper":[79],"bridges":[80],"this":[81,189],"gap":[82],"by":[83],"investigating":[84],"large-scale":[88],"datacenter":[90],"dedicated":[91],"training.":[95],"provide":[97],"insights":[98],"into":[99],"three":[100],"specific":[101],"patterns:":[103],"(a)":[104],"location":[105,145],"distribution":[107],"network,":[110],"(b)":[111],"burstiness,":[112],"e.g.,":[113],"duration":[115],"synchrony":[117],"bursts,":[119],"(c)":[121],"observability":[122],"using":[123],"methods.":[126],"show,":[128],"instance,":[130],"that":[131,171],"deployment":[133],"Priority":[135],"Flow":[136],"Control":[137],"(PFC)":[138],"shifted":[143],"one":[148],"level":[149],"up:":[150],"from":[151],"edge-host":[153],"legacy":[155],"TCP/IP":[156],"core":[161],"datacenters.":[164],"At":[165],"same":[167,173],"time,":[168],"we":[169],"show":[170],"protocol":[174],"enables":[175],"us":[176],"observe":[178],"understand":[180],"better,":[182],"even":[183],"bursty":[184],"events.":[185],"The":[186],"findings":[187],"research":[190],"reveal":[191],"open":[192],"challenges":[193],"measuring,":[195],"characterizing,":[196],"managing":[198],"networks,":[202],"paving":[203],"way":[205],"future":[207],"research.":[208]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-23T00:00:00"}