to make it 100% clear. The problem is a ~4x
regression in RX performance. It affects stock FreeBSD, including 12.1-RELEASE.
In my 40Gbps connected lab single thread iperf receive went from 9Gbps to
2.5Gbps.
If this can't be fixed or looked at I'd heavily suggest looking at r
On Sat, Dec 9, 2017, at 02:29 PM, Eugene Grosbein wrote:
> 10.12.2017 1:29, bugzilla-nore...@freebsd.org wrote:
>
> > https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=122954
> >
> > Josh Paetzel changed:
> >
> >What
switch.
Some googling lead me to
http://unix.derkeiler.com/Mailing-Lists/FreeBSD/net/2014-02/msg00283.html
Any pointers on which direction to turn?
--
Thanks,
Josh Paetzel
___
freebsd-net@freebsd.org mailing list
https://lists.freebsd.org/mailman
g them. If they can be committed in one
go then I can just apply them all, test the end result, and commit that.
One PR with the patches attached and a note saying these can all go in in one
go is appropriate in the latter case, the former would be best ser
There's likely something wrong hardware wise. Either with that nic, the cable,
or the port you are plugging it into. The NIC is (correctly) not
autonegotiating 1000TX full duplex for some reason, and when you try to force
it it doesn't work.
Thanks,
Josh Paetzel
On Feb 7, 2013,
Vencat,
There's been a breakdown in communication. I've been working on oce with Adam
and have a bunch of oce hardware. Please cc me on any patches you have. (pr's
are fine, but they won't get my attention)
Thanks,
Josh Paetzel
On Feb 7, 2013, at 3:57 AM, "Duvv
d igb in heavy use, what would you find most
> convenient?
>
> Jack
>
The default setting is a thorn in our (with my ixsystems servers for
freebsd hat on) side. A system with a quad port igb card and two
onboard igb NICs won't boot stable/8 or 8.x-R to multius
dev em0
# ifconfig bridge0 addm vlan1 addm vlan2
Is that more in line with what you want to do?
I'm a little curious what problem set using a bridge as the parent of a vlan
solves though.
Thanks,
Josh Paetzel
___
freebsd-net@freebsd.org mailing
ink then set the default route to
192.168.1.1 and put the following rule in pf.conf
pass out route-to (em1 10.0.0.1) from 10.0.0.2 to ! 10.0.0.0/24
If you were to give more concrete examples of your config I could
probably help you out with a workable pf solution.
--
Thanks,
Josh Paetzel
pgpXxDOY8zFfw.pgp
Description: PGP signature
om 192.168.2.2 to any
This will not do load-balancing, fail-over, or round-robin NAT, but it
will make replies to incoming connections on the 'other' DSL
connection go out the same interface the incoming connection came in
on with the proper source address.
HTH
--
Thanks,
Josh Paetzel
pgpL4Cz1MZZj4.pgp
Description: PGP signature
ut it was trivial to wedge it with even moderate amounts of
UDP.
I eventually reached the conclusion (correct or not) that you can't
fix crap hardware with a driver.
--
Thanks,
Josh Paetzel
pgpKPrWej6c9c.pgp
Description: PGP signature
dly piece of advice. Dell sells an intel dual port
gig-e card for these machines. If the PCI-X riser hasn't been
populated with anything else do yourself a favor and buy it.
--
Thanks,
Josh Paetzel
pgpcXTMuqy4ZO.pgp
Description: PGP signature
s never able to solve the link up/link down problems with
the driverI was using the drivers from STABLE for a while, and
without jumbo frames everything worked somewhat ok most of the
timethe ultimate solution was to just get the intel PCI-X card
and stop using the broadcoms.
--
Thanks,
Josh Paetzel
pgp0aecUDjhLU.pgp
Description: PGP signature
cess control page that allows you to
block things by service. Not entirely sure *how* it works, but it
seems to be very effective at blocking at the application
layerincluding bt and even skype.
--
Thanks,
Josh Paetzel
___
freebsd-net@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-net
To unsubscribe, send any mail to "[EMAIL PROTECTED]"
On Wednesday 06 December 2006 10:11, Julian Elischer wrote:
> Josh Paetzel wrote:
> > On Tuesday 05 December 2006 23:52, Brett Glass wrote:
> >> Add a few IPFW "count" rules to count the bytes and packets.
> >> Then, periodically harvest and reset the count
fic other than what that
specific machine is sending/receiving.
--
Thanks,
Josh Paetzel
___
freebsd-net@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-net
To unsubscribe, send any mail to "[EMAIL PROTECTED]"
network then you are
going to need to gather info on the router itself. SNMP would be the
logical choice if the router is capable of running it. You could
then poll SNMP from a computer on the network and use any number of
tools to analyze/graph the usage. (MRTG and rrdtool being a couple o
and 4 100tx interfaces on the same PCI bus? If so
you're going to run into bus saturation long before you're able to
max out the throughput on the NICs.
Which isn't to say that 200 kBps isn't a problem, but perhaps you are
dealing with a bad cable or switchport.
--
Thank
On Tue, Dec 11, 2001 at 06:51:44PM +0300, Smirnov Konstantin wrote:
> Hi guys!
>
> We have a high-load webserver on FreeBSD 4.1.1 (~40 Apache connections at
> time with keep-alive switched off).
> Day after day we bump into following: server unexpectedly stops all
> data transfers. It responds on
On Saturday 26 May 2001 13:51, Harkirat Singh wrote:
> Hello!
>
> I want to measure UDP thruput of lossy channel, is there any tool
> which tests it? I looked at some of the tools but these do not take care
> of loss, I mean no retransmisson, just measure raw thruput of UDP (TTCP
> is one of
20 matches
Mail list logo