[Codel] Wifi improvements on debloating

[Alessandro Bolletta]

Hi everybody,
I saw that you released a new version of cerowrt based on linux kernel 3.7.5 and, as I can see, cerowrt includes many fixes for debloating also at driver level, right?

Since we forked a OpenWRT svn based on kernel 3.7.5 for our communitary mesh network, we are thinking to port your debloating improvements made over cerowrt on our forked OS for our growing-up mesh network. Do you think that the effort made on your fixes is too high to made a port of these features, so it would be better to fork directly cerowrt, or do you think we shouldn't encounter big troubles in porting the features that we need?

Moreover, have you made improvements in wifi driver's queuing to fight bufferbloat at driver level? 
We are planning to use atk9k-based wireless card on our devices and we plan to build high-gain links between nodes. Don't you think that, if nodes are connected through high throughput links (as 100Mbit of real UDP flow link speed, for example), the driver-level queuing, as 802.11n packet aggregation feature, shouldn't be a source of bufferbloat? Can I ask you if you ever encountered configurations like these and what are your suggestions about that?

Thanks so much, greetings from Italy!

--
Alessandro Bolletta