From: Carolina Jubran <cjubran@nvidia.com>
To: Samuel Dobron <sdobron@redhat.com>,
Dragos Tatulea <dtatulea@nvidia.com>,
Tariq Toukan <tariqt@nvidia.com>,
"daniel@iogearbox.net" <daniel@iogearbox.net>,
"hawk@kernel.org" <hawk@kernel.org>,
"mianosebastiano@gmail.com" <mianosebastiano@gmail.com>
Cc: "toke@redhat.com" <toke@redhat.com>,
"pabeni@redhat.com" <pabeni@redhat.com>,
"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
"edumazet@google.com" <edumazet@google.com>,
Saeed Mahameed <saeedm@nvidia.com>,
"bpf@vger.kernel.org" <bpf@vger.kernel.org>,
"kuba@kernel.org" <kuba@kernel.org>,
Benjamin Poirier <bpoirier@redhat.com>
Subject: Re: XDP Performance Regression in recent kernel versions
Date: Wed, 8 Jan 2025 11:26:39 +0200 [thread overview]
Message-ID: <733c15e7-2950-4dc7-93c0-11c4eff7ce0b@nvidia.com> (raw)
In-Reply-To: <CA+h3auPydMVmWRKPKQJ75Gg5c8uhttVik4seCtmPXduQxQSjMQ@mail.gmail.com>
Hello,
Thank you Sam for the detailed information.
I have identified the specific kernel configuration change responsible
for the degradation between kernel versions
6.4.0-0.rc6.20230614gitb6dad5178cea.49.eln126 and
6.4.0-0.rc6.20230616git40f71e7cd3c6.50.eln126. The introduction of the
CONFIG_INIT_STACK_ALL_ZERO setting in the latter version has led to a
noticeable performance impact.
I am currently investigating why this change specifically affects mlx5.
Thanks,
Carolina
On 11/12/2024 15:20, Samuel Dobron wrote:
> Hey all,
>
> We recently enabled tests for XDP TX, so I was able to test
> xdp tx as well.
>
> XDP_DROP performance regression is the same as I reported
> a while ago. There is about 20% regression in
> kernel-6.4.0-0.rc6.20230616git40f71e7cd3c6.50.eln126 (baseline)
> compared to previous kernel
> kernel-6.4.0-0.rc6.20230614gitb6dad5178cea.49.eln126 (broken).
> We don't see such regression for other drivers.
>
> The regression was partially fixed somewhere between eln126 and
> kernel-6.10.0-0.rc2.20240606git2df0193e62cf.27.eln137 (partially
> fixed) and the performance since then is -7 to -15% compared to
> baseline. So, nothing new.
>
> XDP_TX is however, more interesting.
> When comparing baseline with broken kernel there is 20 - 25%
> performance drop (cpu utilizations remains the same) on mlx driver.
> There is also 10% drop on other drivers as well. HOWEVER, it got
> fixed somewhere between broken and partially fixed kernel. On most
> recent kernels, we don't see that regressions on other drivers. But
> 2-10% (depends if using dpa/load-bytes) regression remains on mlx5.
>
> The numbers look a bit similar to regression with enabled spectre/meltdown
> mitigations but based on my experiments, there is no difference with
> enabled/disabled mitigations.
>
> Hope this will help,
> Sam.
>
> On Tue, Jul 30, 2024 at 1:04 PM Samuel Dobron <sdobron@redhat.com> wrote:
>>
>>> Could you try adding the mentioned parameters to your kernel arguments
>>> and check if you still see the degradation?
>>
>> Hey,
>> So i tried multiple kernels around v5.15 as well as couple of previous
>> v6.xx and there is no difference with spectre v2 mitigations enabled
>> or disabled.
>>
>> No difference on other drivers as well.
>>
>>
>> Sam.
>>
>
prev parent reply other threads:[~2025-01-08 9:26 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-06-18 15:28 XDP Performance Regression in recent kernel versions Sebastiano Miano
2024-06-19 6:00 ` Tariq Toukan
2024-06-19 15:17 ` Sebastiano Miano
2024-06-19 16:27 ` Jesper Dangaard Brouer
2024-06-19 19:17 ` Toke Høiland-Jørgensen
2024-06-20 9:52 ` Daniel Borkmann
2024-06-21 12:35 ` Samuel Dobron
2024-06-24 11:46 ` Toke Høiland-Jørgensen
2024-06-30 10:25 ` Tariq Toukan
2024-07-22 10:57 ` Samuel Dobron
2024-06-30 11:43 ` Tariq Toukan
2024-07-22 9:26 ` Dragos Tatulea
2024-07-23 9:52 ` Carolina Jubran
2024-07-24 15:36 ` Toke Høiland-Jørgensen
2024-07-25 12:27 ` Samuel Dobron
2024-07-26 8:09 ` Dragos Tatulea
2024-07-29 18:00 ` Samuel Dobron
2024-07-30 11:04 ` Samuel Dobron
2024-12-11 13:20 ` Samuel Dobron
2025-01-08 9:26 ` Carolina Jubran [this message]
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=733c15e7-2950-4dc7-93c0-11c4eff7ce0b@nvidia.com \
--to=cjubran@nvidia.com \
--cc=bpf@vger.kernel.org \
--cc=bpoirier@redhat.com \
--cc=daniel@iogearbox.net \
--cc=dtatulea@nvidia.com \
--cc=edumazet@google.com \
--cc=hawk@kernel.org \
--cc=kuba@kernel.org \
--cc=mianosebastiano@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=saeedm@nvidia.com \
--cc=sdobron@redhat.com \
--cc=tariqt@nvidia.com \
--cc=toke@redhat.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