Re: [tsvwg] Neal Cardwell's rationale for supporting ECT(1) as an input/L4S signal

[Jonathan Morton <[e-mail]>]

>> - SCE is basically an extension of RFC3168 ECN: senders mark their packets
>> ECT(0), and respond to CE like RFC 3168 says they should, by halving cwnd.
>> This would not work well for large sites with a substantial installed base
>> of shallow-threshold (DCTCP-style) ECN: if these sites marked their traffic
>> with ECT(0) to try to use SCE, their local switches configured for
>> shallow-threshold ECN would make CE marks at low queue occupancies, which
>> would cause large RFC3681-style reductions in cwnd, which would cause
>> underutilization. To the best of my knowledge this applies to several large
>> Internet services.
> 
> Wait, that doesn't match my understanding.  In such an example site
> using SCE I would expect ECT(0) marking only at "large" queue
> occupancies (and resulting in cwnd halving when seen), but more
> prevalently ECT(1) marking at "small" queue occupancies - resulting
> in some smaller percentage (than 50) decrease in cwnd when seen.
> 
> What did I miss?

I think there are two points to clear up here.

1: SCE proposes keeping the existing meanings of ECT(0) (ie. ECN Capable Transport) and CE (ie. Congestion Experienced).  At an SCE AQM, CE marks would be expected at relatively deep queuing, and SCE marks - ECT(1) - would be applied at the shallower depth.  The AQM would not "introduce" ECT(0) marks; that codepoint is set at the packet's origin.

2: Neal is referring to an existing installation which signals congestion only with CE.  SCE would react to that in the same way as existing ECN transports.  In particular, SCE does not introduce any special problems with such deployments that do not already exist with RFC-3168.

The shallow queues referred to are intended for deployment in tightly controlled datacentre environments, where the typical path RTT is measured in microseconds rather than milliseconds.  It would not be surprising if a transport passing through such a queue as part of a typical Internet path of many milliseconds experienced poor utilisation.  But that, I think, should be taken as a misconfiguration of the network - one which SCE deals with identically to existing ECN transports.

 - Jonathan Morton