[Bloat] [Bug 1436945] Re: devel: consider fq_codel as the default qdisc for networking

Sebastian Moeller moeller0 at gmx.de
Wed Jun 6 04:15:49 EDT 2018



> On Jun 6, 2018, at 09:44, Bless, Roland (TM) <roland.bless at kit.edu> wrote:
> 
> Hi,
> 
> Am 05.06.2018 um 20:34 schrieb Sebastian Moeller:
>> 	The rationale for that decision still is valid, at low bandwidth every opportunity to send a packet matters and every packet being transferred will increase the queued packets delay by its serialization delay. The question IMHO is more is 4 Mbps a reasonable threshold to disable ECN or not.
> 
> ECN should be enabled irrespective of the current bottleneck bandwidth.
> I don't see any relationship between serialization delay with ECN.
> Congestion control is about determining the right amount of inflight
> data. ECN just provides an explicit congestion signal as feedback
> and helps anyway. The main problem is IMHO that most routers have
> no AQM in place in order to set the CE codepoint appropriately...

	Well, sending a packet incurs serialization delay for all queued up packets, so not sending a packet reduces the delay for all packets that are sent by exactly the serialization delay. If egress bandwidth is precious (so when it is congested and low in comparison with the amount of data that should be send) resorting to congestion signaling by dropping seems okay to me, as that immeiately frees up a "TX-slot" for another flow.
	Now, I do agree that for the affected flow itself ECN should be better as signaling is going to be faster than waiting for 3 DupACKs. But as always the proof is in the data, so I will refrain from making-up more hypothesis and rather try to look into acquiring data.


> 
> Regards,
> Roland
> 




More information about the Bloat mailing list