Jon Otterholm wrote:
This machine is going to act as access-router serving ~500
FTTH-customers.
About 500Mbit/s and 200kpps. The big issue is Dummynet, around 1000
pipes (2
pipes/customer).
That doesn't sound right, 200kpps @ 500Mbps works out to an average
packet size of 250 bytes? Am I
Matthias Gamsjager wrote:
Way over the top for simple fw and dhcpd. but how much traffic will
be involved?
Investing in a good nics will return more then a pricey cpu and
motherboard (eec mem is good idea for 24/7 tho).
Agreed.
The Supermicro Atom miniserver is more than enough CPU grunt for
rihad wrote:
The only one worth getting IMO is Intel EXPX9502CX4
(INTEL 10 GIGABIT CX4 DUAL PORT SERVER ADAPTER)
Thanks. What does DUAL PORT mean? It has two jacks? I think one such
adapter will be more than enough to replace our two 1000 mbps cards,
whether two jacks or not?
Correct, it ha
The only one worth getting IMO is Intel EXPX9502CX4
(INTEL 10 GIGABIT CX4 DUAL PORT SERVER ADAPTER)
It is low power and very fast, and works under FreeBSD. Like all Intel
NICs It supports interrupt modulation so polling support isn't really
needed.
- Andrew
___
This is a very new card which I haven't seen before on the market until
recently.
Card: E1G42ET (Intel Gigabit PCIe ET Dual Port Adapter 82576)
Server: Supermicro X7SLA-H
Operating system: FreeBSD 7.2-RELEASE and 7.2-STABLE
IGB Drivers: 1.4.1 and updated 1.7.3 from intel website
igb0: po
Matthew Grooms wrote:
I was having problems running carp on VMWare ESX 4 and did a little
investigative work to determine the cause of the problem.
If have tested CARP on ESX 3.5u4 successfully with a 32-bit FreeBSD
guest with e1000 vNICs.
As well as turning on promiscuous mode on the vSwit
The real point is that "Joe Admin" shouldn't be using controllers that have bad drivers at all. If you have to use whatever hardware you have laying around, and don't have enough flexibility to lay out $100 for a 2 port controller that works to use with your $2000 server, than you need to get you
Antonio Tommasi wrote:
Filesystem SizeUsed AvailCapacity Mounted on
/dev/aacd0s1a 64G15G 44G 26%/
In a directory (spamassassin) i've one file (auto-whitelist) with
dimension 4.0 TB and one file (bayes_learn) with dimension 1.0TB
How is it possible? How thi
Luigi Rizzo wrote:
If i am not mistaken we don't have generic support for interrupt moderation
in the kernel but that's a specific NIC feature: it works if the
hardware supports it, and it doesn't otherwise.
Of course it would be possible to modify polling to implement
generic interrupt mitigati
Yes it does!
We have deployed many 7.0-STABLE routers based on the EPIA EN12000E
motherboard, and found that vge works really well, never had any major
problems with it - don't touch it! :-)
I suspect the OP should try a newer version of FreeBSD than 7.0-RELEASE
which was so long ago.
The openvpn port tunnels IP over UDP very efficiently and with optional
compression and encryption.
- Andrew
___
freebsd-net@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-net
To unsubscribe, send any mail to "[EMAIL PROT
Jack Vogel wrote:
Hopelessly neglected and broken?? ...the driver is maintained by
me, and I am in the same organization as the developers of the
Linux driver.
Hi Jack,
Of course, most people in the community use the fruit of your labours on
a daily basis and are pleased with the results.
I think what you ask can be done by:
1. sending the packet through ng_mbuf to tag it
2. sending it to ng_ipfw to be sent through IPFW
3. use IPFW rules to operate on packets with the particular tag you
attached in #1
4. as the final IPFW rule, pass the packet back in to netgraph via a
'netgra
Are there any NIC hardware counters that FreeBSD could be taking
advantage of or displaying?
___
freebsd-net@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-net
To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Don't forget the souls who find themselves using jails. In this case it
is common to want a name server on the parent host but not on any of the
jail IPs.
___
freebsd-net@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-ne
Mike Tancsa wrote:
At 02:44 PM 7/7/2008, Paul wrote:
Also my 82571 NIC supports multiple received queues and multiple
transmit queues so why hasn't
anyone written the driver to support this? It's not a 10gb card and
it still supports it and it's widely
Intel actually maintains the driver. Not
I'm no expert, but I imagine the problem is because the net processing
of FreeBSD is not pipelined enough. We are now able to affordably throw
many gigabytes of RAM into a machine, as well 2 to 8 CPUs. So why not
allow for big buffers and multiple processing steps?
I be happy to give up a
I've just started moving a medium IPSEC+gif VPN to one based on OpenVPN.
OpenVPN solved all my problems with IPSEC:
* does not require kernel modules or recompiles
* works over UDP by default (and optionally TCP)
+ only requires a single IP port at each end
* supports compression out of the bo
The "em" driver currently only has a single worker/queue so will only
use one CPU to process packets. However I remember reading that
multi-threaded version of the driver is being worked on and is "coming
soon", but there is no known ETA yet.
I see you mentioned that you played with the rec
Firstly, tried turning off polling? Some of us have found it to be
detrimental to performance on the more modern systems. Its use was more
practical on older systems were servicing interrupts took alot of CPU
power, but the "em" driver supports delaying interrupts until more
packets have ar
Just a "me, too." Also on a Supermicro board, and it happens on some
boots, but not all.
I used to have this problem, but it went away after upgrading FreeBSD
version (7-stable)
- Andrew
___
freebsd-net@freebsd.org mailing list
http://lists.freebsd
Jack Vogel wrote:
What I would like to do is add some code into the vlan_ioctl() routine
that will make a call
to the PARENT ioctl with SETVLAN type and an argument of the tag.
By doing this both the em and igb drivers will be able to enable
hardware vlan filtering as
well, a feature we've never
In deploying 7.0 at work we were finding a persistent problem when
running "vmstat 1" on systems. The problem shows up as a 10ms "pause"
in processing, usually packet stamping and forwarding by a user level
process.
Thats interesting. I once did some quick and dirty profiling of vmtotal
an
Jack Vogel wrote:
You won't know if its still a problem if you don't take them off the
shelf and try it :)
Good point. I wasn't trying to point the finger at you, I think you are
doing a fantastic job overall :)
The card in question is a Pro/1000PT desktop adapter on PCIe 1x bus. I
had us
> I bought a new PCIe NIC a few months ago and was working with Jack Vogel
> on getting it to work but he was busy, then I got busy and things
stalled.
> Does anyone else have any idea what might be wrong here? The card is
> recognized but the em driver fails to initialize it for some reason.
Dewayne Geraghty wrote:
> Hi, I have four VIA motherboards each containing a vge0 device, three
are misbehaving.
>
> On both the 7.0R-p1 and the 6.3Rp2 motherboards, the network cable
needs to be unplugged and replugged into the motherboard, before ping
will respond in either direction. The
Robert Watson wrote:
I would generally discourage use of our current DEVICE_POLLING code
using modern network devices, as the polling rate as compared to buffer
size has changed significantly, meaning that polling rates have to be
set ridiculously high.
I agree, from my playing around ther
I can confirm that FreeBSD 7.0-RC1 can route packets at 1gbps. I used a
late-model Supermicro Xeon server which has two gigabit NICs on a
PCI-express "4x" lane.
With the new em driver improvements in 7 it uses very little CPU time, I
would recommend using Pro/1000 on 7.0 with a decent server mo
Jack Vogel wrote:
But I do not think we need more debugging at this point, when the
new code is checked in it will be great to have everyone that has seen
the issue test it though.
Will look forward to testing it, though its intermittent nature for me
means I might have trouble reproducing it.
Vladimir Ivanov wrote:
We've same issue w/Supermicro boards if IPMI daughterboard installed. A
problem looks as PHY reg reads/writes fails.
Ahh, that explains it, thanks.
The management cards seem to cause multiple problems with the FreeBSD em
driver over time. I don't want to give up the IPM
Hi,
I have a recent Supermicro board (Super X7DWT
Intel 5400 chipset) with two onboard NICs - Intel (ESB2/Gilgal) 82563EB
Dual-Port Gigabit Ethernet Controller
Usually boot up looks like this:
em0: port
0x3000-0x301f mem 0xda02-0xda03,0xda00-0xda01 irq 44 at
device 0.0
Jack Vogel wrote:
After medium-heavy traffic, the NIC locks up completely and no traffic
passes for a long time, perhaps longer than half an hour.
Then, it recovers and prints this to syslog:
em0: watchdog timeout -- resetting
em0: link state changed to DOWN
em0: link state changed to UP
If yo
Hi, I have a problem with Pro/1000 cards in Freebsd, as follows:
System: Supermicro 1RU server
CPU: Intel(R) Core(TM)2 CPU 4400 @ 2.00GHz
OS: FreeBSD 6.2-STABLE (Tue May 29 03:19:28 EST 2007)
amd64 (64 bit mode, SMP kernel)
Driver: 6.4.1 kernel module (downloaded from Intel's
33 matches
Mail list logo