Re: ix(intel) vs mlxen(mellanox) 10Gb performance

2015-08-21 Thread Rick Macklem
Yonghyeon PYUN wrote: > On Wed, Aug 19, 2015 at 09:00:35AM -0400, Rick Macklem wrote: > > Hans Petter Selasky wrote: > > > On 08/19/15 09:42, Yonghyeon PYUN wrote: > > > > On Wed, Aug 19, 2015 at 09:00:52AM +0200, Hans Petter Selasky wrote: > > > >> On 08/18/15 23:54, Rick Macklem wrote: > > > >>>

Re: Mellanox 40Gb support

2015-08-21 Thread aurfalien
Ah I see. Well I’m primitive and use whats in current. I had attempted this before using there standard EN driver and failed massively. So I’ll be using there OFED driver. - aurf "Janitorial Services" On Aug 21, 2015, at 8:26 AM, Julian Elischer wrote: > On 8/21/15 11:24 PM, aurfalien wrote

Re: Mellanox 40Gb support

2015-08-21 Thread Julian Elischer
On 8/21/15 11:24 PM, aurfalien wrote: Hi, Well, this is all in a test env of course, but I’m planning to use head. What are your thoughts? My curiosity was as to whether you hook this into the current NFS or whether it's so different that it's almost a new implementation..? - aurf "Janito

Re: Mellanox 40Gb support

2015-08-21 Thread aurfalien
Hi, Well, this is all in a test env of course, but I’m planning to use head. What are your thoughts? - aurf "Janitorial Services" On Aug 21, 2015, at 8:21 AM, Julian Elischer wrote: > On 8/21/15 10:29 PM, aurfalien wrote: >> Hi, >> >> Thanks very much for the response. >> >> Well, I’m imp

Re: Mellanox 40Gb support

2015-08-21 Thread Julian Elischer
On 8/21/15 10:29 PM, aurfalien wrote: Hi, Thanks very much for the response. Well, I’m implementing NFSoRDMA and as a best practices, Mellanox suggested I use the very latest drivers. really? On FreeBSD? Is this a fresh implementation of NFS or using the NFS in head? __

Re: Mellanox 40Gb support

2015-08-21 Thread aurfalien
Hi, Thanks very much for the response. Well, I’m implementing NFSoRDMA and as a best practices, Mellanox suggested I use the very latest drivers. So no bug fixes I am looking for as I haven’t implemented yet. And I was wrong about the date, its 6/11/15, not 5/11/15, sorry about that, typo. -

Re: pf and new interface

2015-08-21 Thread Andriy Gapon
On 18/08/2015 20:43, Reko Turja wrote: > Hmm does the: > > set skip on (tap) > > syntax work in this case? Basically parentheses around the alias should > tell pf that the IP is volatile and can be either activated at later > time or it can be dynamic via dhcp etc. It seems that this would be a