[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20200907091813.7ad7f6ef@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com>
Date: Mon, 7 Sep 2020 09:18:13 -0700
From: Jakub Kicinski <kuba@...nel.org>
To: Jiri Pirko <jiri@...nulli.us>
Cc: Parav Pandit <parav@...dia.com>, Parav Pandit <parav@...lanox.com>,
"davem@...emloft.net" <davem@...emloft.net>,
"netdev@...r.kernel.org" <netdev@...r.kernel.org>,
"roid@...lanox.com" <roid@...lanox.com>,
"saeedm@...lanox.com" <saeedm@...lanox.com>,
Jiri Pirko <jiri@...dia.com>
Subject: Re: [PATCH net-next 2/3] devlink: Consider other controller while
building phys_port_name
On Mon, 7 Sep 2020 09:21:53 +0200 Jiri Pirko wrote:
> >Putting little more realistic example for Jakub's and your suggestion below.
> >
> >Below is the output for 3 controllers. ( 2 external + 1 local )
> >Each external controller consist of 2 PCI PFs for a external host via single PCIe cable.
> >Each local controller consist of 1 PCI PF.
> >
> >$ devlink port show
> >pci/0000:00:08.0/0: type eth netdev enp0s8f0_pf0 flavour pcipf pfnum 0 cnum 0 external false
> >pci/0000:00:08.0/1: type eth netdev enp0s8f0_c1pf0 flavour pcipf pfnum 0 cnum 1 external true
> >pci/0000:00:08.1/1: type eth netdev enp0s8f1_c1pf1 flavour pcipf pfnum 1 cnum 1 external true
>
> I see cnum 0 and cnum 1, yet you talk about 3 controllers. What did I
> miss?
Heh, good point. Please make sure to put this example in docs so folks
have a reference on how we expect a 2-port smartnic to look.
Powered by blists - more mailing lists