> @Jonathan from your experience how tricky is it to get reliable speedtest
> endpoints and how reliable are they in practice. And do you do any
> sanitization, like take another measure immediate if the measured rate
> differs from the last by more than XX% or something like that?
It is tricky
Thanks for sharing Dave.
A good paper, but there are few gaps worthy of mentioning on this list:
Testing when there is an AQM present means the test must adapt to the challenge
of smaller cwnd existing for any one stream, therefore it will take many more
streams to saturate a line with cwnd = 3
before deploying the update, A new one should be
forthcoming.
Thanks,
Jonathan Foulkes
> On Jan 19, 2021, at 6:20 PM, Toke Høiland-Jørgensen via Bloat
> wrote:
>
> Hi everyone
>
> In case you haven't seen, there's a new OpenWrt release out[0] that
> fixes seve
.
I regressed back to .4 and all is good on the QoS front, waiting until a new
drop of dnsmasq before trying again.
- Jonathan
> On Jan 22, 2021, at 4:15 PM, Toke Høiland-Jørgensen wrote:
>
> Jonathan Foulkes writes:
>
>> I installed the updated package on a 19.07.4 box run
at the fixes dnsmasq might have some CPU spikes that simply leave not
> enough cycles for the traffic shaper?
>
> Best Regards
> Sebastian
>
>> On Jan 22, 2021, at 22:25, Jonathan Foulkes wrote:
>>
>> I figure there should be no inter-dependencies there,
al D due to bufferbloat on the
35Mps uplink, and my download is limited to 600 or so.
So it’s baked, just need to get them into more peoples hands.
Cheers,
Jonathan Foulkes
> On Jan 31, 2021, at 10:18 AM, Valdis Klētnieks
> wrote:
>
> On Thu, 28 Jan 2021 18:14:36 -0800, Dave Taht said:
ase that
ingrates new bloat-mitigation features. Since OpenWrt 21.x is about to drop,
the draft should circulate in the coming weeks.
Cheers,
Jonathan Foulkes
> On Feb 9, 2021, at 3:45 PM, David P. Reed wrote:
>
> Hmmm... good post, I guess. But aren't WiFi 6 and StarLink bein
