On 18. nov. 2013, at 13:44, Scheffenegger, Richard wrote:

> [chair hat off]
> 
> Hi Michael,
> 
>> 
>> ------------------------------------------
>>>>>>>>> RP:  Again, the tight delay control comes from narrow-band bang-bang 
>>>>>>>>> control with hard drops. The scenarios >that throughputs are good are 
>>>>>>>>> in higher congestion scenarios where there are enough packets showing 
>>>>>>>>> up to fill the >pipe. That is not the effectiveness of AQM. Tail drop 
>>>>>>>>> with shallow buffer will have high throughput in those cases >too. 
>>>>>>>>> Try a scenario when link is congested and a burst comes, see how many 
>>>>>>>>> packets of that burst can go through.
>> ------------------------------------------
>> 
>> Maybe we disagree about the goals... why would you want to allow a burst on 
>> an already congested link?
> 
> How do you define congested link?
> 
> You will want to be burst-tolerant on a link running at full capacity - but 
> is such a link already congested?

I'd say no, this is just perfectly saturated. I was thinking of a link running 
at full capacity + a non-empty queue.

BTW, there was talk about how to define congestion and how to define congestion 
control at the AQM meeting, during Fred's presentation. If we need text for 
this, it's worth looking at the ICCRG archives, I remember a long and boring 
discussion about these definitions early in the life of ICCRG.


> In any case, defining a scenario that would lead to excessive buffering delay 
> in the drop-tail case, and comparing this for various AQMs should be 
> documented.

Sure

Cheers,
Michael

_______________________________________________
aqm mailing list
[email protected]
https://www.ietf.org/mailman/listinfo/aqm

Reply via email to