One impact that come to mind is RTT fairness. A single AQM instance
results in RTT unfairness (flows with higher RTT achieve lower bandwidth
than flows with low RTT), whereas one AQM per queue results in RTT fairness.
Simon
On 7/3/2015 4:40 AM, Bless, Roland (TM) wrote:
Hi,
Am 03.07.2015 um 12:16 schrieb Toke Høiland-Jørgensen:
Polina Goltsman <[email protected]> writes:
As I understand the FQ-Codel draft, it seems to be fundamental to
FQ-Codel that each queue has separate state variables. So my question
is: is it indeed fundamental ?
I suppose that becomes a matter of semantics: What exactly do you mean
by 'fundamental'. If you mean "an integral part of the current
algorithm", then yes. If you mean "it's unthinkable to build a similar
algorithm without the separate state variables" then no. I understand
Fred's comment to take the second interpretation. :)
I guess Polina's point was:
it is a question how "similar" two realizations of PIE would be
if one applies PIE per flow like in FQ-Codel or alternatively
(as proposed by FQ-PIE) FQ first and then PIE working on the
aggregated queue.
Was it a deliberate choice for the latter and if so, why?
It would be good to document this difference to FQ-Codel explicitly.
Regards,
Roland
_______________________________________________
aqm mailing list
[email protected]
https://www.ietf.org/mailman/listinfo/aqm
_______________________________________________
aqm mailing list
[email protected]
https://www.ietf.org/mailman/listinfo/aqm
