* [Cerowrt-devel] some sqm and cpu performance numbers for a variety of devices
@ 2020-03-28 17:39 Dave Taht
2020-03-28 22:05 ` [Cerowrt-devel] [Bloat] " Aaron Wood
0 siblings, 1 reply; 2+ messages in thread
From: Dave Taht @ 2020-03-28 17:39 UTC (permalink / raw)
To: cerowrt-devel, bloat
https://forum.openwrt.org/t/comparative-throughput-testing-including-nat-sqm-wireguard-and-openvpn/44724/44
(H/T to aaron wood)
The post persistently points out that openvpn tends to optimize for
one direction only. This is in part due to the large internal buffer
in it. I'd longed to fq it internally at one point. Similarly,
wireguard suffers, but not as bad. Fixing that is easier.
--
Make Music, Not War
Dave Täht
CTO, TekLibre, LLC
http://www.teklibre.com
Tel: 1-831-435-0729
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: [Cerowrt-devel] [Bloat] some sqm and cpu performance numbers for a variety of devices
2020-03-28 17:39 [Cerowrt-devel] some sqm and cpu performance numbers for a variety of devices Dave Taht
@ 2020-03-28 22:05 ` Aaron Wood
0 siblings, 0 replies; 2+ messages in thread
From: Aaron Wood @ 2020-03-28 22:05 UTC (permalink / raw)
To: Dave Taht; +Cc: cerowrt-devel, bloat
[-- Attachment #1: Type: text/plain, Size: 1326 bytes --]
Thanks for the H/T, Dave!
I keep seeing bufferbloat in userspace proxies and tunnels, and think that
the world would benefit greatly from aqm library for applications to use in
order to keep latency under control. Especially if work like encryption is
being done and the results thrown away due to massive tail drops and the
like (or "real-time" video streams that need to throw away a bunch of
received packets in order to catch back up the proper e2e latency.
(no I'm not volunteering at this time, nor am I obliquely asking anyone
else to...)
On Sat, Mar 28, 2020 at 10:40 AM Dave Taht <dave.taht@gmail.com> wrote:
>
> https://forum.openwrt.org/t/comparative-throughput-testing-including-nat-sqm-wireguard-and-openvpn/44724/44
>
> (H/T to aaron wood)
>
> The post persistently points out that openvpn tends to optimize for
> one direction only. This is in part due to the large internal buffer
> in it. I'd longed to fq it internally at one point. Similarly,
> wireguard suffers, but not as bad. Fixing that is easier.
>
> --
> Make Music, Not War
>
> Dave Täht
> CTO, TekLibre, LLC
> http://www.teklibre.com
> Tel: 1-831-435-0729
> _______________________________________________
> Bloat mailing list
> Bloat@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/bloat
>
[-- Attachment #2: Type: text/html, Size: 2122 bytes --]
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2020-03-28 22:05 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-03-28 17:39 [Cerowrt-devel] some sqm and cpu performance numbers for a variety of devices Dave Taht
2020-03-28 22:05 ` [Cerowrt-devel] [Bloat] " Aaron Wood
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox