[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <53eb1301-fd35-4006-8eed-2d815575f196@nvidia.com>
Date: Wed, 30 Jul 2025 16:54:55 +0300
From: Gal Pressman <gal@...dia.com>
To: Andrew Lunn <andrew@...n.ch>
Cc: Jakub Kicinski <kuba@...nel.org>,
Vadim Fedorenko <vadim.fedorenko@...ux.dev>,
Michael Chan <michael.chan@...adcom.com>,
Pavan Chebbi <pavan.chebbi@...adcom.com>, Tariq Toukan <tariqt@...dia.com>,
intel-wired-lan@...ts.osuosl.org, Donald Hunter <donald.hunter@...il.com>,
Paolo Abeni <pabeni@...hat.com>, Simon Horman <horms@...nel.org>,
netdev@...r.kernel.org
Subject: Re: [RFC PATCH] ethtool: add FEC bins histogramm report
On 30/07/2025 15:59, Andrew Lunn wrote:
> On Wed, Jul 30, 2025 at 08:39:25AM +0300, Gal Pressman wrote:
>> On 30/07/2025 4:51, Jakub Kicinski wrote:
>>> On Tue, 29 Jul 2025 19:07:59 +0100 Vadim Fedorenko wrote:
>>>> On 29/07/2025 18:31, Andrew Lunn wrote:
>>>>>> The only one bin will have negative value is the one to signal the end
>>>>>> of the list of the bins, which is not actually put into netlink message.
>>>>>> It actually better to change spec to have unsigned values, I believe.
>>>>>
>>>>> Can any of these NICs send runt packets? Can any send packets without
>>>>> an ethernet header and FCS?
>>>>>
>>>>> Seems to me, the bin (0,0) is meaningless, so can could be considered
>>>>> the end marker. You then have unsigned everywhere, keeping it KISS.
>>>>
>>>> I had to revisit the 802.3df-2024, and it looks like you are right:
>>>> "FEC_codeword_error_bin_i, where i=1 to 15, are optional 32-bit
>>>> counters. While align_status is true, for each codeword received with
>>>> exactly i correctable 10-bit symbols"
>>>>
>>>> That means bin (0,0) doesn't exist according to standard, so we can use
>>>> it as a marker even though some vendors provide this bin as part of
>>>> histogram.
>>>
>>> IDK, 0,0 means all symbols were completely correct.
>>> It may be useful for calculating bit error rate?
>>
>> Exactly. mlx5 will use (0, 0) for sure.
>
> Sorry, i did not spend time to read the standard and issued this was
> related to frame length somehow, like the RMON statistics which have
> bins for packet length counts.
I'm not sure I'm using the right terminology, but the ranges are # of
symbols that had FEC errors. So (0, 0) means zero symbol errors.
Powered by blists - more mailing lists