>From what I can see, the reason is
sysctl -w net.inet.tcp.{send|recv}space=131072
If I revert to 32768, I get back about the third of the speed.
net.inet.tcp.{send|recv}buf_auto doesn't seem to make any difference.
Thanks,
Chavdar
On Sun, 19 Jan 2020 at 18:29, Chavdar Ivanov <ci4...@gmail.com> wrote:
>
> On Sun, 19 Jan 2020 at 18:17, Jason Mitchell <jmitc...@bigjar.com> wrote:
> >
> ...
> >
> > First, Powerline adapters only get 1/7th the advertised speed. They send
> > “1Gigabit” of data, but they’re really sending ~130Mbit of the same data 7
> > times because of how noisy power cabling is.
>
> Yes, I am aware - that's around what I am getting here. I have another
> W10 machine on the same switch as the NetBSD box I did the tests with.
>
> >
> > Second, try adding -l 9000 to your iperf3 tests. The Linux distributions
> > I’ve used have this as the default and I’ve noticed big speed improvements
> > doing this, but I have no clue why it works.
>
> Yes, this appears to improve the speed a bit more - now I am getting
>
> Connecting to host ymir, port 5201
> [ 4] local 192.168.0.36 port 1236 connected to 192.168.0.29 port 5201
> [ ID] Interval Transfer Bandwidth
> [ 4] 0.00-1.00 sec 107 MBytes 901 Mbits/sec
> [ 4] 1.00-2.00 sec 111 MBytes 934 Mbits/sec
> [ 4] 2.00-3.00 sec 103 MBytes 867 Mbits/sec
> [ 4] 3.00-4.00 sec 84.7 MBytes 710 Mbits/sec
> [ 4] 4.00-5.00 sec 89.5 MBytes 751 Mbits/sec
> [ 4] 5.00-6.00 sec 86.6 MBytes 727 Mbits/sec
> [ 4] 6.00-7.00 sec 103 MBytes 864 Mbits/sec
> [ 4] 7.00-8.00 sec 110 MBytes 919 Mbits/sec
> [ 4] 8.00-9.00 sec 109 MBytes 917 Mbits/sec
> [ 4] 9.00-10.00 sec 108 MBytes 903 Mbits/sec
> - - - - - - - - - - - - - - - - - - - - - - - - -
> [ ID] Interval Transfer Bandwidth
> [ 4] 0.00-10.00 sec 1013 MBytes 849 Mbits/sec sender
> [ 4] 0.00-10.00 sec 1012 MBytes 849 Mbits/sec receiver
>
> iperf Done.
>
>
> >
> > Thanks,
> >
> > Jason M.
> >
> > Sent from my iPhone
>
>
>
> --
> ----
--
----
