[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ZixBMZLq5nPl9kU9@LQ3V64L9R2>
Date: Fri, 26 Apr 2024 17:05:05 -0700
From: Joe Damato <jdamato@...tly.com>
To: Jakub Kicinski <kuba@...nel.org>
Cc: linux-kernel@...r.kernel.org, netdev@...r.kernel.org, tariqt@...dia.com,
saeedm@...dia.com, mkarsten@...terloo.ca, gal@...dia.com,
nalramli@...tly.com, "David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>, Paolo Abeni <pabeni@...hat.com>,
"open list:MELLANOX MLX4 core VPI driver" <linux-rdma@...r.kernel.org>
Subject: Re: [PATCH net-next v2 3/3] net/mlx4: support per-queue statistics
via netlink
On Fri, Apr 26, 2024 at 01:01:16PM -0700, Jakub Kicinski wrote:
> On Fri, 26 Apr 2024 18:33:55 +0000 Joe Damato wrote:
> > Make mlx4 compatible with the newly added netlink queue stats API.
> >
> > Signed-off-by: Joe Damato <jdamato@...tly.com>
> > Tested-by: Martin Karsten <mkarsten@...terloo.ca>
>
> Not sure what the "master" and "port_up" things are :)
> but the rest looks good:
So in mlx4_en_DUMP_ETH_STATS, the driver calls mlx4_en_fold_software_stats
which does the same "port_up" / "master" check and bails out... so I figured
for these stats I should do the same.
Was hoping Mellanox would give us a hint, but glancing at the code where the
MLX4_FLAG_MASTER bit is set, it looks like sriov ? maybe "master" means pf and
"slave" means "vf" ?
Not sure why the stats code bails on is_master but not is_slave, though.
> Reviewed-by: Jakub Kicinski <kuba@...nel.org>
I'll add your reviewed-by to my v3 and wait until sometime mid next week to
send the v3. Hopefully we'll hear back from the Mellanox folks by then if they
have thoughts/opinions on the stats code.
Powered by blists - more mailing lists