From: Alexandra Winter <wintera@linux.ibm.com>
To: Dragos Tatulea <dtatulea@nvidia.com>, Eric Dumazet <edumazet@google.com>
Cc: Rahul Rameshbabu <rrameshbabu@nvidia.com>,
Saeed Mahameed <saeedm@nvidia.com>,
Tariq Toukan <tariqt@nvidia.com>,
Leon Romanovsky <leon@kernel.org>,
David Miller <davem@davemloft.net>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
Andrew Lunn <andrew+netdev@lunn.ch>,
Nils Hoppmann <niho@linux.ibm.com>,
netdev@vger.kernel.org, linux-s390@vger.kernel.org,
Heiko Carstens <hca@linux.ibm.com>,
Vasily Gorbik <gor@linux.ibm.com>,
Alexander Gordeev <agordeev@linux.ibm.com>,
Christian Borntraeger <borntraeger@linux.ibm.com>,
Sven Schnelle <svens@linux.ibm.com>,
Thorsten Winkler <twinkler@linux.ibm.com>,
Simon Horman <horms@kernel.org>,
Niklas Schnelle <schnelle@linux.ibm.com>
Subject: Re: [PATCH net-next] net/mlx5e: Transmit small messages in linear skb
Date: Wed, 11 Dec 2024 17:19:09 +0100 [thread overview]
Message-ID: <54945b8c-8328-4c34-982c-9a92ebab5b1c@linux.ibm.com> (raw)
In-Reply-To: <82c14009-da71-4c2a-920c-7d32fcb1ffcb@nvidia.com>
On 10.12.24 12:49, Dragos Tatulea wrote:
>
>
> On 06.12.24 16:25, Alexandra Winter wrote:
>>
>>
>> On 04.12.24 15:36, Eric Dumazet wrote:
>>> I would suggest the opposite : copy the headers (typically less than
>>> 128 bytes) on a piece of coherent memory.
>>>
>>> As a bonus, if skb->len is smaller than 256 bytes, copy the whole skb.
>>>
>>> include/net/tso.h and net/core/tso.c users do this.
>>>
>>> Sure, patch is going to be more invasive, but all arches will win.
>>
>>
>> Thank you very much for the examples, I think I understand what you are proposing.
>> I am not sure whether I'm able to map it to the mlx5 driver, but I could
>> try to come up with a RFC. It may take some time though.
>>
>> NVidia people, any suggesttions? Do you want to handle that yourselves?
>>
> Discussed with Saeed and he proposed another approach that is better for
> us: copy the whole skb payload inline into the WQE if it's size is below a
> threshold. This threshold can be configured through the
> tx-copybreak mechanism.
>
> Thanks,
> Dragos
Thank you very much Dargos and Saeed.
I am not sure I understand the details of "inline into the WQE".
The idea seems to be to use a premapped coherent array per WQ
that is indexed by queue element index and can be used to copy headers and
maybe small messages into.
I think I see something similar to your proposal in mlx4 (?).
To me the general concept seems to be similar to what Eric is proposing.
Did I get it right?
I really like the idea to use tx-copybreak for threshold configuration.
As Eric mentioned that is not a very small patch and maybe not fit for backporting
to older distro versions.
What do you think of a two-step approach as described in the other sub-thread?
A simple patch for mitigation that can be backported, and then the improvement
as a replacement?
Thanks,
Alexandra
next prev parent reply other threads:[~2024-12-11 16:19 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-12-04 14:02 [PATCH net-next] net/mlx5e: Transmit small messages in linear skb Alexandra Winter
2024-12-04 14:16 ` Eric Dumazet
2024-12-04 14:35 ` Alexandra Winter
2024-12-04 14:36 ` Eric Dumazet
2024-12-06 14:47 ` David Laight
2024-12-06 16:35 ` Eric Dumazet
2024-12-06 15:25 ` Alexandra Winter
2024-12-10 11:49 ` Dragos Tatulea
2024-12-11 16:19 ` Alexandra Winter [this message]
2024-12-11 17:36 ` Dragos Tatulea
2024-12-04 14:32 ` Alexander Lobakin
2024-12-06 15:20 ` Alexandra Winter
2024-12-09 11:36 ` Tariq Toukan
2024-12-10 11:44 ` Dragos Tatulea
2024-12-10 13:54 ` Alexander Lobakin
2024-12-10 17:10 ` Joe Damato
2024-12-11 13:35 ` Alexandra Winter
2024-12-11 17:28 ` Dragos Tatulea
2024-12-11 17:50 ` Niklas Schnelle
2024-12-13 20:41 ` Dragos Tatulea
2024-12-12 10:36 ` Christian Borntraeger
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=54945b8c-8328-4c34-982c-9a92ebab5b1c@linux.ibm.com \
--to=wintera@linux.ibm.com \
--cc=agordeev@linux.ibm.com \
--cc=andrew+netdev@lunn.ch \
--cc=borntraeger@linux.ibm.com \
--cc=davem@davemloft.net \
--cc=dtatulea@nvidia.com \
--cc=edumazet@google.com \
--cc=gor@linux.ibm.com \
--cc=hca@linux.ibm.com \
--cc=horms@kernel.org \
--cc=kuba@kernel.org \
--cc=leon@kernel.org \
--cc=linux-s390@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=niho@linux.ibm.com \
--cc=pabeni@redhat.com \
--cc=rrameshbabu@nvidia.com \
--cc=saeedm@nvidia.com \
--cc=schnelle@linux.ibm.com \
--cc=svens@linux.ibm.com \
--cc=tariqt@nvidia.com \
--cc=twinkler@linux.ibm.com \
/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