{"draft":"draft-ietf-tsvwg-aqm-dualq-coupled-25","doc_id":"RFC9332","title":"Dual-Queue Coupled Active Queue Management (AQM) for Low Latency, Low Loss, and Scalable Throughput (L4S)","authors":["K. De Schepper","B. Briscoe, Ed.","G. White"],"format":["HTML","TEXT","PDF","XML"],"page_count":"52","pub_status":"EXPERIMENTAL","status":"EXPERIMENTAL","source":"Transport and Services Working Group","abstract":"This specification defines a framework for coupling the Active Queue\r\nManagement (AQM) algorithms in two queues intended for flows with\r\ndifferent responses to congestion. This provides a way for the\r\nInternet to transition from the scaling problems of standard\r\nTCP-Reno-friendly ('Classic') congestion controls to the family of\r\n'Scalable' congestion controls. These are designed for consistently\r\nvery low queuing latency, very low congestion loss, and scaling of\r\nper-flow throughput by using Explicit Congestion Notification (ECN)\r\nin a modified way. Until the Coupled Dual Queue (DualQ), these\r\nScalable L4S congestion controls could only be deployed where a\r\nclean-slate environment could be arranged, such as in private data\r\ncentres.\r\n\r\nThis specification first explains how a Coupled DualQ works. It then\r\ngives the normative requirements that are necessary for it to work\r\nwell. All this is independent of which two AQMs are used, but\r\npseudocode examples of specific AQMs are given in appendices.","pub_date":"January 2023","keywords":["Performance","Queuing Delay","One Way Delay","Round-Trip Time","RTT","Jitter","Congestion Control","Congestion Avoidance","Quality of Service","QoS","Quality of Experience","QoE","Active Queue Management","AQM","Explicit Congestion Notification","ECN","Pacing","Burstiness"],"obsoletes":[],"obsoleted_by":[],"updates":[],"updated_by":[],"see_also":[],"doi":"10.17487\/RFC9332","errata_url":null}