From: Jakub Kicinski <kuba@kernel.org>
To: Danielle Ratson <danieller@nvidia.com>
Cc: Ido Schimmel <idosch@idosch.org>,
"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
"davem@davemloft.net" <davem@davemloft.net>,
"Jiri Pirko" <jiri@nvidia.com>, "andrew@lunn.ch" <andrew@lunn.ch>,
"f.fainelli@gmail.com" <f.fainelli@gmail.com>,
"mkubecek@suse.cz" <mkubecek@suse.cz>, mlxsw <mlxsw@nvidia.com>,
Ido Schimmel <idosch@nvidia.com>,
"johannes@sipsolutions.net" <johannes@sipsolutions.net>
Subject: Re: [PATCH net-next 1/6] ethtool: Extend link modes settings uAPI with lanes
Date: Tue, 13 Oct 2020 08:43:20 -0700 [thread overview]
Message-ID: <20201013084320.40283ba6@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com> (raw)
In-Reply-To: <DM6PR12MB3865E4CB3854ECF70F5864D7D8040@DM6PR12MB3865.namprd12.prod.outlook.com>
On Tue, 13 Oct 2020 14:29:29 +0000 Danielle Ratson wrote:
> > On Mon, 12 Oct 2020 15:33:45 +0000 Danielle Ratson wrote:
> > > > What's the use for this in practical terms? Isn't the lane count
> > > > basically implied by the module that gets plugged in?
> > >
> > > The use is to enable the user to decide how to achieve a certain speed.
> > > For example, if he wants to get 100G and the port has 4 lanes, the
> > > speed can be achieved it using both 2 lanes of 50G and 4 lanes of 25G,
> > > as a port with 4 lanes width can work in 2 lanes mode with double
> > > speed each. So, by specifying "lanes 2" he will achieve 100G using 2
> > > lanes of 50G.
> >
> > Can you give a concrete example of serdes capabilities of the port, what SFP
> > gets plugged in and what configuration user wants to select?
>
> Example:
> - swp1 is a 200G port with 4 lanes.
> - QSFP28 is plugged in.
> - The user wants to select configuration of 100G speed using 2 lanes, 50G each.
I mean.. sounds quite contrived to me.
But I'm not opposed if others are fine with the change.
next prev parent reply other threads:[~2020-10-13 15:43 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-10-10 15:41 [PATCH net-next 0/6] Support setting lanes via ethtool Ido Schimmel
2020-10-10 15:41 ` [PATCH net-next 1/6] ethtool: Extend link modes settings uAPI with lanes Ido Schimmel
2020-10-11 22:37 ` Jakub Kicinski
2020-10-12 15:33 ` Danielle Ratson
2020-10-12 15:58 ` Jakub Kicinski
2020-10-13 14:29 ` Danielle Ratson
2020-10-13 15:43 ` Jakub Kicinski [this message]
2020-10-16 22:15 ` Andrew Lunn
2020-10-19 7:19 ` Danielle Ratson
2020-10-19 11:04 ` Michal Kubecek
2020-10-19 12:26 ` Jiri Pirko
2020-10-19 13:24 ` Michal Kubecek
2020-10-20 7:39 ` Danielle Ratson
2020-10-21 7:08 ` Michal Kubecek
2020-10-21 7:20 ` Danielle Ratson
2020-10-21 8:47 ` Michal Kubecek
2020-10-22 6:15 ` Danielle Ratson
2020-10-22 16:27 ` Michal Kubecek
2020-11-23 9:47 ` Danielle Ratson
2020-11-24 22:12 ` Michal Kubecek
2020-11-25 10:35 ` Danielle Ratson
2020-11-26 21:07 ` Michal Kubecek
2020-12-01 17:22 ` Danielle Ratson
2020-12-02 0:52 ` Edwin Peer
2020-12-02 1:17 ` Edwin Peer
2020-10-19 12:24 ` Jiri Pirko
2020-10-19 12:38 ` Andrew Lunn
2020-10-12 16:40 ` Michal Kubecek
2020-10-12 19:10 ` Johannes Berg
2020-10-12 20:08 ` Jakub Kicinski
2020-10-12 17:03 ` Michal Kubecek
2020-11-19 20:38 ` Edwin Peer
2020-11-23 9:40 ` Jiri Pirko
2020-11-30 17:01 ` Edwin Peer
2020-11-30 17:14 ` Jiri Pirko
2020-11-30 18:00 ` Edwin Peer
2020-12-01 11:22 ` Jiri Pirko
2020-12-02 0:32 ` Edwin Peer
2020-12-02 10:09 ` Jiri Pirko
2020-12-02 17:53 ` Edwin Peer
2020-10-10 15:41 ` [PATCH net-next 2/6] ethtool: Expose the number of lanes in use Ido Schimmel
2020-10-10 15:41 ` [PATCH net-next 3/6] mlxsw: ethtool: Remove max lanes filtering Ido Schimmel
2020-10-10 15:41 ` [PATCH net-next 4/6] mlxsw: ethtool: Add support for setting lanes when autoneg is off Ido Schimmel
2020-10-10 15:41 ` [PATCH net-next 5/6] mlxsw: ethtool: Expose the number of lanes in use Ido Schimmel
2020-10-10 15:41 ` [PATCH net-next 6/6] net: selftests: Add lanes setting test Ido Schimmel
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20201013084320.40283ba6@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com \
--to=kuba@kernel.org \
--cc=andrew@lunn.ch \
--cc=danieller@nvidia.com \
--cc=davem@davemloft.net \
--cc=f.fainelli@gmail.com \
--cc=idosch@idosch.org \
--cc=idosch@nvidia.com \
--cc=jiri@nvidia.com \
--cc=johannes@sipsolutions.net \
--cc=mkubecek@suse.cz \
--cc=mlxsw@nvidia.com \
--cc=netdev@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).