[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <87frwsvebh.fsf@nvidia.com>
Date: Thu, 14 Mar 2024 11:48:11 -0700
From: Rahul Rameshbabu <rrameshbabu@...dia.com>
To: "Keller, Jacob E" <jacob.e.keller@...el.com>
Cc: Jakub Kicinski <kuba@...nel.org>, "Zaki, Ahmed" <ahmed.zaki@...el.com>,
"Lobakin, Aleksander" <aleksander.lobakin@...el.com>,
"alexandre.torgue@...s.st.com" <alexandre.torgue@...s.st.com>,
"andrew@...n.ch" <andrew@...n.ch>, "corbet@....net" <corbet@....net>,
"davem@...emloft.net" <davem@...emloft.net>, "dtatulea@...dia.com"
<dtatulea@...dia.com>, "edumazet@...gle.com" <edumazet@...gle.com>,
"gal@...dia.com" <gal@...dia.com>, "hkallweit1@...il.com"
<hkallweit1@...il.com>, "jiri@...nulli.us" <jiri@...nulli.us>,
"joabreu@...opsys.com" <joabreu@...opsys.com>, "justinstitt@...gle.com"
<justinstitt@...gle.com>, "kory.maincent@...tlin.com"
<kory.maincent@...tlin.com>, "leon@...nel.org" <leon@...nel.org>,
"linux-doc@...r.kernel.org" <linux-doc@...r.kernel.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"liuhangbin@...il.com" <liuhangbin@...il.com>,
"maxime.chevallier@...tlin.com" <maxime.chevallier@...tlin.com>,
"netdev@...r.kernel.org" <netdev@...r.kernel.org>, "pabeni@...hat.com"
<pabeni@...hat.com>, "Greenwalt, Paul" <paul.greenwalt@...el.com>,
"Kitszel, Przemyslaw" <przemyslaw.kitszel@...el.com>,
"rdunlap@...radead.org" <rdunlap@...radead.org>,
"richardcochran@...il.com" <richardcochran@...il.com>, "saeed@...nel.org"
<saeed@...nel.org>, "tariqt@...dia.com" <tariqt@...dia.com>,
"vadim.fedorenko@...ux.dev" <vadim.fedorenko@...ux.dev>,
"vladimir.oltean@....com" <vladimir.oltean@....com>, "Drewek, Wojciech"
<wojciech.drewek@...el.com>
Subject: Re: [PATCH RFC v2 1/6] ethtool: add interface to read Tx hardware
timestamping statistics
On Thu, 14 Mar, 2024 17:50:10 +0000 "Keller, Jacob E" <jacob.e.keller@...el.com> wrote:
>> -----Original Message-----
>> From: Jakub Kicinski <kuba@...nel.org>
>> Sent: Wednesday, March 13, 2024 6:40 PM
>> To: Rahul Rameshbabu <rrameshbabu@...dia.com>
>> Cc: Zaki, Ahmed <ahmed.zaki@...el.com>; Lobakin, Aleksander
>> <aleksander.lobakin@...el.com>; alexandre.torgue@...s.st.com;
>> andrew@...n.ch; corbet@....net; davem@...emloft.net; dtatulea@...dia.com;
>> edumazet@...gle.com; gal@...dia.com; hkallweit1@...il.com; Keller, Jacob E
>> <jacob.e.keller@...el.com>; jiri@...nulli.us; joabreu@...opsys.com;
>> justinstitt@...gle.com; kory.maincent@...tlin.com; leon@...nel.org; linux-
>> doc@...r.kernel.org; linux-kernel@...r.kernel.org; liuhangbin@...il.com;
>> maxime.chevallier@...tlin.com; netdev@...r.kernel.org; pabeni@...hat.com;
>> Greenwalt, Paul <paul.greenwalt@...el.com>; Kitszel, Przemyslaw
>> <przemyslaw.kitszel@...el.com>; rdunlap@...radead.org;
>> richardcochran@...il.com; saeed@...nel.org; tariqt@...dia.com;
>> vadim.fedorenko@...ux.dev; vladimir.oltean@....com; Drewek, Wojciech
>> <wojciech.drewek@...el.com>
>> Subject: Re: [PATCH RFC v2 1/6] ethtool: add interface to read Tx hardware
>> timestamping statistics
>>
>> On Wed, 13 Mar 2024 17:50:39 -0700 Rahul Rameshbabu wrote:
>> > > Should we give some guidance to drivers which "ignore" time stamping
>> > > requests if they used up all the "slots"? Even if just temporary until
>> > > they are fixed? Maybe we can add after all the fields something like:
>> > >
>> > > For drivers which ignore further timestamping requests when there are
>> > > too many in flight, the ignored requests are currently not counted by
>> > > any of the statistics.
>> >
>> > I was actually thinking it would be better to merge them into the error
>> > counter temporarily. Reason being is that in the case Intel notices that
>> > their slots are full, they just drop traffic from my understanding
>> > today. If the error counters increment in that situation, it helps with
>> > the debug to a degree. EBUSY is an error in general.
>>
>> That works, too, let's recommend it (FWIW no preference whether
>> in the entry for @err or somewhere separately in the kdoc).
>
> We don't drop traffic, we send the packets just fine.. We just never report a
> timestamp for them, since we don't program the hardware to capture that
> timestamp.
My actual kdoc comments are better now, but I should have been better
with the language I used here in the email. In my head, I was thinking
more about the case of not submitting HW timestamp information when
sending out the packet rather than dropping the packet entirely (I would
say that is still a timestamping error case).
--
Thanks,
Rahul Rameshbabu
Powered by blists - more mailing lists