Thank you @Noth.
You are right. The OpenBSD PF FAQ also says:
> PF will only use one processor, so multiple processors (or multiple cores)
WILL NOT improve PF performance.
For PC Engines APU users, I can highly recommend to update the BIOS. It improved
my networking performance quite a bit:
https
On 30/01/2020 15:43, livio wrote:
Dear all,
I am unable to achieve decent throughput with a 1 GigE interface
(Intel I210) on OpenBSD 6.6. When running iperf3 I get around 145Mbit/s.
The config/setup is: APU2c4, Win10 notebook, no switch, Cat.6a cable,
MTU 1500, 1000baseT, full-duplex, pf disa
On Thu, January 30, 2020 11:43, livio wrote:
> Dear all,
>
> I am unable to achieve decent throughput with a 1 GigE interface
> (Intel I210) on OpenBSD 6.6. When running iperf3 I get around 145Mbit/s.
>
> The config/setup is: APU2c4, Win10 notebook, no switch, Cat.6a cable,
> MTU 1500, 1000baseT
Thank you for your inputs - @Jordan, @Tom, @Christian
On 1/30/2020 9:07 PM, Tom Smyth wrote:
> Livio are you running iperf on the apu ?
> The apu doesnt have much cpu to generate packets from iperf...
> Forwarding perf should about 450m on an apu c2 with pf enabled and about
> 850m-900m with pf di
On 2020-01-30 14:29, Christian Weisgerber wrote:
On 2020-01-30, Jordan Geoghegan wrote:
All you're doing is benchmarking the speed of iperf on that machine.
I vaguely remember a thread somewhere that concluded that one of
these network benchmark tools degenerated into a benchmark of
gettim
On 2020-01-30, Jordan Geoghegan wrote:
> All you're doing is benchmarking the speed of iperf on that machine.
I vaguely remember a thread somewhere that concluded that one of
these network benchmark tools degenerated into a benchmark of
gettimeofday(2), which apparently is very cheap on Linux an
On 2020-01-30 13:14, Jordan Geoghegan wrote:
On 2020-01-30 10:06, livio wrote:
@KatolaZ and @remi
Thank you for your inputs on iperf2 vs. iperf3.
After all the tests I needed a clean setup again and reinstalled both
OpenBSD and Window 10.
With the new notebook (Dell vs Lenovo) I have diffe
On 2020-01-30 10:06, livio wrote:
@KatolaZ and @remi
Thank you for your inputs on iperf2 vs. iperf3.
After all the tests I needed a clean setup again and reinstalled both
OpenBSD and Window 10.
With the new notebook (Dell vs Lenovo) I have different results.
Dell: ~ 200Mbit/s
Lenovo: ~ 145Mbit
I ran fw_update and syspatch, which made the machine crash twice after
booting, but now it is up and running again. The iperf results are
still the same though:
apu# iperf -s
Server listening on TCP port 5001
TCP window size: 16.0 KByte
@KatolaZ and @remi
Thank you for your inputs on iperf2 vs. iperf3.
After all the tests I needed a clean setup again and reinstalled both
OpenBSD and Window 10.
With the new notebook (Dell vs Lenovo) I have different results.
Dell: ~ 200Mbit/s
Lenovo: ~ 145Mbit/s
iperf2 vs. iperf3 (I also ran th
On January 30, 2020 4:17:16 PM UTC, Ian Darwin wrote:
>Peter wrote:
>
>> chi# iperf -c beta.internal.centroid.eu
>>
>> Client connecting to beta.internal.centroid.eu, TCP port 5001
>> TCP window size: 17.0 KByte (default)
>> ---
On Thu, Jan 30, 2020 at 05:10:57PM +0100, livio wrote:
> I am happy run the tests with another cable (although the one I was
> using is brand new). I still receive 940Mbit/s with FreeBSD 12.1
> with the exact same setup.
>
> The only(!) difference is the physical mSATA SSD (one for OpenBSD, the
>
On 2020-01-30, livio wrote:
> I am unable to achieve decent throughput with a 1 GigE interface
> (Intel I210) on OpenBSD 6.6. When running iperf3 I get around 145Mbit/s.
I get more than 30 Mbytes/s over SSH (!) to an APU2.
$ scp -caes128-...@openssh.com
/usr/ports/distfiles/texlive-20190410-te
To answer your second question, I did not change any sysctls or other
settings on the OpenBSD. The only thing I ran was pfctl -d.
My installation guide was:
https://github.com/elad/openbsd-apu2
- amd/install66.fs
- stty com0 115200
- set tty com0
On 1/30/2020 5:39 PM, livio wrote:
> Yes, I tried
Yes, I tried yet another cable. I hope this gives some credibility:
https://ibb.co/m4mrWt3
I now tried with 3 different cables (and vendors). As you can see the
patch cable is brand new. I am also setting up a new Windows 10 notebook
on the right.
But again, I achieve 940Mbit/s with the exact sam
Peter wrote:
> chi# iperf -c beta.internal.centroid.eu
>
> Client connecting to beta.internal.centroid.eu, TCP port 5001
> TCP window size: 17.0 KByte (default)
>
> [ 3] loca
I am happy run the tests with another cable (although the one I was
using is brand new). I still receive 940Mbit/s with FreeBSD 12.1
with the exact same setup.
The only(!) difference is the physical mSATA SSD (one for OpenBSD, the
other for FreeBSD). They have the identical specs though.
Results
Hi Peter,
Thanks for your reply. I would already be quite happy with ~500Mbit/s.
My test do not involve a switch, just a notebook and the APU through
a Cat.6a cable. I achieve 940Mbit/s with the exact same setup but
FreeBSD 12.1 on the APU.
I am happy to change parameters, provide additional logs
On Thu, Jan 30, 2020 at 03:43:41PM +0100, livio wrote:
> Dear all,
>
> I am unable to achieve decent throughput with a 1 GigE interface
> (Intel I210) on OpenBSD 6.6. When running iperf3 I get around 145Mbit/s.
>
> The config/setup is: APU2c4, Win10 notebook, no switch, Cat.6a cable,
> MTU 1500,
Dear all,
I am unable to achieve decent throughput with a 1 GigE interface
(Intel I210) on OpenBSD 6.6. When running iperf3 I get around 145Mbit/s.
The config/setup is: APU2c4, Win10 notebook, no switch, Cat.6a cable,
MTU 1500, 1000baseT, full-duplex, pf disabled, BSD.mp, no custom Kernel
paramet
20 matches
Mail list logo
