[gpfsug-discuss] more than one mlx connectx-4 adapter in samehost

[David D Johnson]

We're trying to get 40 gbe connection between Mellanox switches and Cisco switches down at the other end of the machine room  
The BiDi part seems to be the best given about 30m  run on multimode.  However Mellanox support says it's not supported.
Want to use this to get close to IB speeds for GPFS on nodes that aren't on the IB fabric.  
Does anyone have any luck getting 40 or 100 gig at 20-30m when the switches are different brands?

Thanks,
 -- ddj

> On Dec 20, 2017, at 4:53 PM, Sanchez, Paul <Paul.Sanchez at deshaw.com> wrote:
> 
> We have run multiple ConnectX-4 NICs in bonded MLAG (Arista) and VPC (Cisco) switch configurations on our NSD servers.  We used to see issues with firmware versions that didn’t support the optics we wanted to use (e.g. early CX3/CX4 and Cisco 40G-BiDi).  You may also want check mstflint to see whether the firmware levels match on the MLX cards, and if you upgrade firmware in some cases a power-cycle (not reboot) can be required to finish the process.
>  
> -Paul
>   <>
> From: gpfsug-discuss-bounces at spectrumscale.org [mailto:gpfsug-discuss-bounces at spectrumscale.org]On Behalf Of Andrew Beattie
> Sent: Wednesday, December 20, 2017 4:47 PM
> To: gpfsug-discuss at spectrumscale.org
> Subject: Re: [gpfsug-discuss] more than one mlx connectx-4 adapter in samehost
>  
> IBM ESS building blocks can have up to 3 dual port 10GBEth, 40GB Eth, 56GB IB, 100GB IB Mlx adapater cards, because we have 2 IO nodes this is up to a total of 12 ports per building block
> so there should not be any reason for this to fail.
>  
> I regularly see a Mix of 10GB / 40GB or 10GB / IB configurations
>  
>  
>  
> Regards
> Andrew Beattie
> Software Defined Storage  - IT Specialist
> Phone: 614-2133-7927
> E-mail: abeattie at au1.ibm.com <mailto:abeattie at au1.ibm.com>
>  
>  
> ----- Original message -----
> From: "J. Eric Wonderley" <eric.wonderley at vt.edu <mailto:eric.wonderley at vt.edu>>
> Sent by: gpfsug-discuss-bounces at spectrumscale.org <mailto:gpfsug-discuss-bounces at spectrumscale.org>
> To: gpfsug main discussion list <gpfsug-discuss at spectrumscale.org <mailto:gpfsug-discuss at spectrumscale.org>>
> Cc:
> Subject: Re: [gpfsug-discuss] more than one mlx connectx-4 adapter in same host
> Date: Thu, Dec 21, 2017 6:37 AM
>   
> Just plain tcpip.
>  
> We have dual port connectx4s in our nsd servers.  Upon adding a second connectx4 hba...no links go up or show "up".  I have one port on each hba configured for eth and ibv_devinfo looks sane.
>  
> I cannot find anything indicating that this should not work.  I have a ticket opened with mellanox.
>  
> On Wed, Dec 20, 2017 at 3:25 PM, Knister, Aaron S. (GSFC-606.2)[COMPUTER SCIENCE CORP] <aaron.s.knister at nasa.gov <mailto:aaron.s.knister at nasa.gov>> wrote: 
>  
> 
> 
> We’ve done a fair amount of VPI work but admittedly not with connectx4. Is it possible the cards are trying to talk IB rather than Eth? I figured you’re Ethernet based because of the mention of Juniper. 
>  
> Are you attempting to do RoCE or just plain TCP/IP?
>  
> On December 20, 2017 at 14:40:48 EST, J. Eric Wonderley <eric.wonderley at vt.edu <mailto:eric.wonderley at vt.edu>> wrote:
> Hello:
>  
> Does anyone have this type of config?
>  
> The host configuration looks sane but we seem to observe link-down on all mlx adapters no matter what we do.
>  
> Big picture is that we are attempting to do mc(multichassis)-lags to a core switch.  I'm somewhat fearful as to how this is implemented in the juniper switch we are about to test. 
> 
> _______________________________________________
> gpfsug-discuss mailing list
> gpfsug-discuss at spectrumscale.org <https://urldefense.proofpoint.com/v2/url?u=http-3A__spectrumscale.org&d=DwMFaQ&c=jf_iaSHvJObTbx-siA1ZOg&r=STXkGEO2XATS_s2pRCAAh2wXtuUgwVcx1XjUX7ELNdk&m=Olk0lQk7rek9IplOjJ_2Vcd7P1LgVbnrSupC7O0hJHQ&s=I5Dq2T7aYvC87Wp12fsz6CRLw4uo2-RVnrnpxRYfYuA&e=>
> http://gpfsug.org/mailman/listinfo/gpfsug-discuss <https://urldefense.proofpoint.com/v2/url?u=http-3A__gpfsug.org_mailman_listinfo_gpfsug-2Ddiscuss&d=DwMFaQ&c=jf_iaSHvJObTbx-siA1ZOg&r=STXkGEO2XATS_s2pRCAAh2wXtuUgwVcx1XjUX7ELNdk&m=Olk0lQk7rek9IplOjJ_2Vcd7P1LgVbnrSupC7O0hJHQ&s=hxNNpOkwGQ9zRmTnM3FEo5hgnPSUsPG0FNqZbK6eA6Q&e=>
>  
> _______________________________________________
> gpfsug-discuss mailing list
> gpfsug-discuss at spectrumscale.org
> https://urldefense.proofpoint.com/v2/url?u=http-3A__gpfsug.org_mailman_listinfo_gpfsug-2Ddiscuss&d=DwICAg&c=jf_iaSHvJObTbx-siA1ZOg&r=STXkGEO2XATS_s2pRCAAh2wXtuUgwVcx1XjUX7ELNdk&m=Olk0lQk7rek9IplOjJ_2Vcd7P1LgVbnrSupC7O0hJHQ&s=hxNNpOkwGQ9zRmTnM3FEo5hgnPSUsPG0FNqZbK6eA6Q&e= <https://urldefense.proofpoint.com/v2/url?u=http-3A__gpfsug.org_mailman_listinfo_gpfsug-2Ddiscuss&d=DwICAg&c=jf_iaSHvJObTbx-siA1ZOg&r=STXkGEO2XATS_s2pRCAAh2wXtuUgwVcx1XjUX7ELNdk&m=Olk0lQk7rek9IplOjJ_2Vcd7P1LgVbnrSupC7O0hJHQ&s=hxNNpOkwGQ9zRmTnM3FEo5hgnPSUsPG0FNqZbK6eA6Q&e=>
>  
>  
> _______________________________________________
> gpfsug-discuss mailing list
> gpfsug-discuss at spectrumscale.org
> http://gpfsug.org/mailman/listinfo/gpfsug-discuss

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://gpfsug.org/pipermail/gpfsug-discuss_gpfsug.org/attachments/20171220/2b7ae14b/attachment-0002.htm>