On Tue, September 6, 2005 10:13 am, Paolo Pisati said:
On Tue, Sep 06, 2005 at 04:06:57PM +0400, Gleb Smirnoff wrote:
during your work with libalias have you found any bugs or buglets, or a
rough places, that should be considered to be merged to main FreeBSD CVS
tree as soon as possible,
Murugan wrote:
Hi
i need a sample(working) configuration files to set up a PPPoE server
in FreeBSD 4.9.
www.google.com
___
freebsd-net@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-net
To unsubscribe, send any mail to
Nikolas Britton wrote:
No I have not tired this, I didn't even know Intel made FreeBSD
drivers... I went looking on the site early but couldn't find
anything. Do you know if they are any good?... I'll check it out,
thanks.
It is essentially the same driver that FreeBSD uses, but the one
Does anyone know a good CARP howto for FreeBSD? I've googled around, but
i cant find anything specific to FreeBSD.
___
freebsd-net@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-net
To unsubscribe, send any mail to [EMAIL
Anton Yuzhaninov wrote:
Saturday, August 12, 2006, 8:30:00 PM, Mike Jakubik wrote:
MJ Does anyone know a good CARP howto for FreeBSD? I've googled around, but
MJ i cant find anything specific to FreeBSD.
You can use CARP howto for OpenBSD.
Yup, that and the FreeBSD man page gave me all
Max Laier wrote:
Have a look at: http://www.countersiege.com/doc/pfsync-carp/#big for one
idea. All requirements (carp, pf and pfsync) are available in FreeBSD as
well.
You can load balance with CARP, but AFAIK it only works on the local
network segment, i.e. it wont work past a
On Mon, January 8, 2007 2:58 pm, Steven Hartland wrote:
I've just been looking at an issue reported by some
of our users that downloads from our one of our sites
run on FreeBSD 6.1 and Apache 1.3 where strangely
slow.
After doing some digging around I found that two remote
machines on the
Hello,
It seems that the byte counters (derived from netstat -nbi) reset at
around 4 GB. Is there no way around this? It would be nice to be able to
see an accurate display of totals. It just seems pointless to even have
this, as 4 GB is just not that much anymore. I know this is a 32bit
Brooks Davis said:
Please read the archives of freebsd-net. This has been discussed
many times. There are valid reasons for this, particularly the fact
that 64-bit counters are much more expensive to update on 32-bit
architectures. API breakage is also a problem. We're aware that 2^32
is
Max Laier said:
There is now: pf comes with 64bit statistic counters. For now you can put
them on one interface only, but in future version there will be more
flexible statistics. Additionally there are many accounting programs out
there which utilize various existing (32bit) counters or the
Max Laier said:
Sure, you measure it ;) ... no, of course it is more expensive to update a
64bit counter on a 32bit arch, but the key (once again) is descision:
While
(almost) all of the pf counters are 64bit types you can configure it not
to
use the loginterface or whatsoever more. So it's
Motonori Shindo said:
Mike,
This seems like a DSL router's problem. Because PPTP encapsulates PPP
using GRE, which is neither TCP nor UDP, routers sometimes can not NAT
PPTP traffic. Some router conqurs this problem by simply passing
through GRE packets (and hence this feature is sometimes
Motonori Shindo said:
This seems like a DSL router's problem. Because PPTP encapsulates PPP
using GRE, which is neither TCP nor UDP, routers sometimes can not NAT
PPTP traffic. Some router conqurs this problem by simply passing
through GRE packets (and hence this feature is sometimes
Hello,
I have recently discovered, after long periods of trying to debug a VPN
server, that i can not establish PPTP VPN connections any more. The
culprit seems to be natd not forwarding GRE properly. I have tried adding
a 'redirect_proto gre' option to natd, but same behaviour occurs. I could
Mitch (Bitblock) said:
Short answer is Yes.
For basic failover, I've used a script which monitors link status and
function (by pinging or connecting to a remote host). Failover is
accomplished by switching the default route.
Using ipfw fwd statements, you can make both links function at
Hi,
I have recently cvsuped to a new snapshot of -current, the existing system
was about 1-2 months old. I am now seeing a lot of link state messages in
dmesg.
em0: link state changed to DOWN
em0: link state changed to UP
em0: link state changed to DOWN
em0: link state changed to UP
em0: link
On Tue, April 5, 2005 10:23 pm, Theo Schlossnagle said:
On Apr 4, 2005, at 5:05 PM, Eivind Hestnes wrote:
If you are looking for a Open Source failover solution, CARP is
probably the best choice as it stands today.
If you need assistance with the configuration, please reply to the
list, and
On Tue, April 5, 2005 10:46 pm, Theo Schlossnagle said:
It isn't unmaintained... what makes you think it is unmaintained?
wackamole version 2.1.1 was released on July 28th, 2004 (08.31.2004).
Compiles fine on my boxen. (4.11, 4-stable, 5.2.1, 5.3-RELEASE-p5)
Really? Ive never been able to
On Thu, April 7, 2005 11:12 am, Dag-Erling Smørgrav said:
You're probably using the wrong version of bison.
Yes, Theo Schlossnagle already mentioned this to me. The compile process
was using the port version of bison, removing it solved the problem.
Thanks.
On Sat, May 7, 2005 5:35 am, Marian Durkovic said:
To achieve wirespeed performance, the TX FIFO must be large enough to
accomodate 2 jumbo packets (not just 1 as the driver was assuming).
There was also a typo in the driver, causing the PBA tuning on most
cards to be non-functional.
Please
On Sat, May 7, 2005 11:20 am, Joao Barros said:
Hi all,
I recently tried ntop on FreeBSD 5.4 RC3 and RC4 and was disappointed
with the problems I bumped into. I reported this to ntop's developers
mailing list and a few coments about FreeBSD threading came up. It would
be interesting if
On Sat, May 7, 2005 12:37 am, Kris Kennaway said:
On Fri, May 06, 2005 at 08:59:50AM +0200, Marian Durkovic wrote:
Hi all,
seems we've found the problem. The performance degradation was
happening it the TX path, due to insufficient setting of TX packet
buffer FIFO on the chip.
To
On Wed, May 11, 2005 5:24 pm, Mike Jakubik said:
Any luck submitting the patch for this? I looked at Intels website, and
the latest drive for FreeBSD 4.7 is 1.7.35. Which is what is also used on
-CURRENT now. They also state Development is no longer taking place on
this driver. For the latest
On Thu, May 12, 2005 3:27 am, Marian Durkovic said:
Hi,
On Wed, May 11, 2005 at 06:38:48PM -0400, Mike Jakubik wrote:
Any luck submitting the patch for this?
Yes, it's kern/80932
Good stuff, ill test it when i get a chance.
I looked at Intels website, and the latest drive for FreeBSD
On Thu, May 12, 2005 3:27 am, Marian Durkovic said:
Seems like i am getting half the performance when sending to the fbsd
box. Also, enabling jumbo frames does not help, and sometimes even
yields slightly slower results.
Yes, that's exactly the problem my patch is addressing - for larger MTU
cific
for your use case.
Please post back to the list with your specific findings and nic/ tcp tunables,
these are very helpful for the next person!
Dave
Mike Jakubik
https://www.swiftsmsgateway.com/
Disclaimer: This e-mail and any attachments are intended only for the use of
sec 31.1 GBytes 8.91 Gbits/sec 1330 sender
[ 5] 0.00-30.00 sec 31.1 GBytes 8.91 Gbits/sec receiver
Thanks.
On Mon, 13 Jun 2022 14:41:05 -0400 Santiago Martinez
<mailto:s...@codenetworks.net> wrote
Mike Jakubik
After multiple tests and tweaks i believe the issue is not with the HW or Numa
related (Infinity fabric should do around 32GB) but rather with FreeBSD TCP/IP
stack. It's like it cant figure itself out properly for the speed that the HW
can do, i keep getting widely varying results when testing.
receiver
iperf Done.
Thank You!
On Thu, 16 Jun 2022 17:00:25 -0400 Alexander V. Chernikov
wrote
> On 16 Jun 2022, at 21:48, Mike Jakubik
> <mailto:mike.jaku...@swiftsmsgateway.com> wrote:
>
> After multiple tests and tweaks i believe the issue is not with
lem is, if it's
PCI backpressure or something else.
sysctl -a | grep diag_pci_enable
sysctl -a | grep diag_general_enable
Set these two to 1, then run some traffic and dump all mce sysctls:
sysctl -a | grep mce > dump.txt
--HPS
Mike Jakubik
https://www.swiftsmsgateway.com/
] 0.00-30.00 sec 29.4 GBytes 8.42 Gbits/sec 3863 sender
[ 5] 0.00-30.00 sec 29.4 GBytes 8.42 Gbits/sec receiver
On Tue, 14 Jun 2022 10:21:51 -0400 Mike Jakubik
wrote
Disabling rx/tx pause seems to produce higher peaks.
[root@db-02
Yes, it is the default of 1500. If I set it to 9000 I get some bizarre network
behavior.
On Tue, 14 Jun 2022 09:45:10 -0400 Andrey V. Elsukov
<mailto:bu7c...@yandex.ru> wrote
Hi,
Do you have the same MTU size on linux machine?
Mike Jakubik
.77 Gbits/sec 244 sender
[ 5] 0.00-30.00 sec 30.6 GBytes 8.77 Gbits/sec receiver
More data can be found @
https://forums.freebsd.org/threads/poor-performance-with-stable-13-and-mellanox-connectx-6-mlx5.85460/
Mike Jakubik
https://www.swiftsmsgateway.
33 matches
Mail list logo