* Eric K. Miller [2011-06-03 22:31]:
> > Are you running -current? There have been some massive tweaks in
> networking performance in -current. Try out and report back.
>
> We were running 4.7 amd64 version (GENERIC.MP). Also tried the single
> processor version.
>
> Intel Pro/1000 MT cards wer
On 06/03/11 20:48, Eric K. Miller wrote:
I might start a capabilities war, but we've seen OpenBSD become CPU
bound with about 150k packets per second with some pretty fast hardware.
Funny, I have more than 300kpps. With pf enabled, of course.
This is without PF running. I'm sure there are a
On Fri, Jun 03, 2011 at 10:05:21PM +, Stuart Henderson wrote:
| On 2011-06-03, Amit Kulkarni wrote:
| > If the driver is em for Intel Pro/1000 MT, that has received a serious
| > boost. People are reporting close to light speed :-)
|
| nah, close to light speed is on the MF, not MT.
Propagat
On 4-6-2011 0:04, Stuart Henderson wrote:
> On 2011-06-03, Eric K. Miller wrote:
>>> Are you running -current? There have been some massive tweaks in
>> networking performance in -current. Try out and report back.
>>
>> We were running 4.7 amd64 version (GENERIC.MP). Also tried the single
>> proc
On 2011-06-03, Amit Kulkarni wrote:
> If the driver is em for Intel Pro/1000 MT, that has received a serious
> boost. People are reporting close to light speed :-)
nah, close to light speed is on the MF, not MT.
On 2011-06-03, Eric K. Miller wrote:
>> Are you running -current? There have been some massive tweaks in
> networking performance in -current. Try out and report back.
>
> We were running 4.7 amd64 version (GENERIC.MP). Also tried the single
> processor version.
>
> Intel Pro/1000 MT cards were u
> If the driver is em for Intel Pro/1000 MT, that has received a serious
boost. People are reporting close to light speed :-)
Wow, that's pretty fast. =) I think...? ;)
> Search for the thread "Performance degradation after upgrade". The
devs have made networking for certain cards blazingly fast
>> Are you running -current? There have been some massive tweaks in
> networking performance in -current. Try out and report back.
>
> We were running 4.7 amd64 version (GENERIC.MP). Also tried the single
> processor version.
>
> Intel Pro/1000 MT cards were used.
>
> I should mention that we had
On 3 June 2011 17:25, Eric K. Miller wrote:
>> Are you running -current? There have been some massive tweaks in
> networking performance in -current. Try out and report back.
>
> We were running 4.7 amd64 version (GENERIC.MP). Also tried the single
> processor version.
>
> Intel Pro/1000 MT cards
> Are you running -current? There have been some massive tweaks in
networking performance in -current. Try out and report back.
We were running 4.7 amd64 version (GENERIC.MP). Also tried the single
processor version.
Intel Pro/1000 MT cards were used.
I should mention that we had a large number
> > I'm looking for a NAT/firewall/VPN solution with failover for a
> private enterprise TV system. While my gut reaction is PF, I'm
> wondering if anybody here has done this before.
>
> I might start a capabilities war, but we've seen OpenBSD become CPU
> bound with about 150k packets per second
Hi Michael,
> I'm looking for a NAT/firewall/VPN solution with failover for a
private enterprise TV system. While my gut reaction is PF, I'm
wondering if anybody here has done this before.
I might start a capabilities war, but we've seen OpenBSD become CPU
bound with about 150k packets per secon
Hi,
I'm looking for a NAT/firewall/VPN solution with failover for a
private enterprise TV system. While my gut reaction is PF, I'm
wondering if anybody here has done this before.
Video and voice send large numbers of small packets. I'm told that
this particular application can fill a gigabit Et
13 matches
Mail list logo
