[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <796881fe22cc4129b69eadad7ff37a8b@amazon.com>
Date: Tue, 11 Feb 2025 06:41:27 +0000
From: "Arinzon, David" <darinzon@...zon.com>
To: Jakub Kicinski <kuba@...nel.org>
CC: David Miller <davem@...emloft.net>, "netdev@...r.kernel.org"
<netdev@...r.kernel.org>, Eric Dumazet <edumazet@...gle.com>, Paolo Abeni
<pabeni@...hat.com>, Simon Horman <horms@...nel.org>, Richard Cochran
<richardcochran@...il.com>, "Woodhouse, David" <dwmw@...zon.co.uk>,
"Machulsky, Zorik" <zorik@...zon.com>, "Matushevsky, Alexander"
<matua@...zon.com>, "Bshara, Saeed" <saeedb@...zon.com>, "Wilson, Matt"
<msw@...zon.com>, "Liguori, Anthony" <aliguori@...zon.com>, "Bshara, Nafea"
<nafea@...zon.com>, "Schmeilin, Evgeny" <evgenys@...zon.com>, "Belgazal,
Netanel" <netanel@...zon.com>, "Saidi, Ali" <alisaidi@...zon.com>,
"Herrenschmidt, Benjamin" <benh@...zon.com>, "Kiyanovski, Arthur"
<akiyano@...zon.com>, "Dagan, Noam" <ndagan@...zon.com>, "Bernstein, Amit"
<amitbern@...zon.com>, "Agroskin, Shay" <shayagr@...zon.com>, "Abboud, Osama"
<osamaabb@...zon.com>, "Ostrovsky, Evgeny" <evostrov@...zon.com>, "Tabachnik,
Ofir" <ofirt@...zon.com>, "Machnikowski, Maciek" <maciek@...hnikowski.net>,
Rahul Rameshbabu <rrameshbabu@...dia.com>, Gal Pressman <gal@...dia.com>
Subject: RE: [PATCH v6 net-next 3/4] net: ena: Add PHC documentation
> > You are right in the regard that it is not a network specific functionality.
> > Having said that, PHC is a network card capability, making it a network-
> related component rather than purely a timekeeping feature.
> > Moreover we failed to find an existing tool which would allow users to get
> valuable feedback of the system's overall health.
> >
> > Researching its existing support in the kernel we noted that:
> > - PHC is embedded in network NIC and is supported by multiple NIC
> > vendors in the kernel
> > - PHC information is visible through ethtool -T
> > - The Linux networking stack uses PHC for timekeeping as well as for packet
> timestamping (via SO_TIMESTAMPING).
> > Packet timestamping statistics are available through ethtool
> > get_ts_stats hook
> >
> > We have found `ethtool -S` as a suitable location for exposing these
> statistics, which are unique to the ENA NIC.
> >
> > We'd appreciate your thoughts on the matter, is there an alternative tool
> you can recommend?
>
> We try to steer folks towards read-only debugfs files for stuff that's not
> strictly networking related. You also add a custom sysfs file in patch 4, I
> reckon adding stats there may also be a natural place for the user?
>
> Patch 4 FWIW is lacking slightly in the justification, would be good to clarify
> why it's disabled by default. Single sentence of "why" would be great.
Hi Jakub,
Thank you for the feedback and the recommendations, we will incorporate them in v7.
Powered by blists - more mailing lists