It should however not lead to netifd outofmemory, load of 2.6 and the oomkiller berserking around at all... even if its not directly wg fault.

Yesterday there was no time to test fastd in such a setting,
Similar test show 5 to 15mbs depending on used crypto in the past.
But there we test laptop - 841v9(550mhz?) - broadbanduplink - backboneserver

If we are motivated, we check fastd in the next days against different cypher algos in exact the same setting, to have a realy good base for comparing software on this fairly week devices

On July 27, 2016 12:14:12 PM GMT+02:00, "Jason A. Donenfeld" <Jason@zx2c4.com> wrote:

On Wed, Jul 27, 2016 at 12:10 PM, Jens Viisauksena <jens@viisauksena.de> wrote:
 the small routers run fastd into the backbone.

Is the performance of wireguard better or worse than fastd?
Theoretically wireguard should be much faster, so if it isn't already
so in practice, I'd like to optimize a bit.

--
Sent from my Android device with K-9 Mail. Please excuse my brevity.