L4S

L4S effectively introduces new rules for compliant endpoints and their traffic, giving L4S traffic preferential treatment in exchange for L4S endpoints cooperating by using improved congestion control algorithms. It has the remarkable property of not only improving performance for L4S traffic, but also improving performance for non-L4S traffic sharing the same infrastructure.

L4S has the advantage that it can start to provide incremental latency and throughput improvements through patchwork deployment by individual network operators without having to be adopted throughout the entire Internet, thus providing an incentive for early adopters.

Details

L4S uses Explicit Congestion Notification (ECN) to transmit information about path latency problems, and allows congested nodes to use the ECN bits to send information back to senders that will allow them to adjust their transmit rate, reducing the need for data buffering within router queues.

L4S is specified in RFC 9330. It uses the last codepoint of the Internet Protocol header's ECN field that had not previously been assigned to signal that traffic is from an L4S-capable sender. The full set of four ECN codes for packets are thus:

Routers can thus treat L4S traffic differently from non-L4S traffic, knowing that L4S endpoints can throttle back traffic in a more controlled way than would be possible using classic ECN. This is done by treating L4S traffic differently for both the cases of queuing and marking.

In an ideal world, L4S traffic would not need any network traffic policing, being entirely self-regulating. In practice. policing may be required to prevent attacks on infrastructure from mis-labeled traffic being introduced by non-compliant endpoints.