From: Stephen Hemminger <stephen@networkplumber.org>
To: "Lukáš Šišmiš" <sismis@cesnet.cz>
Cc: "Morten Brørup" <mb@smartsharesystems.com>,
anatoly.burakov@intel.com, ian.stokes@intel.com, dev@dpdk.org
Subject: Re: [PATCH] net: increase the maximum of RX/TX descriptors
Date: Wed, 30 Oct 2024 08:20:20 -0700 [thread overview]
Message-ID: <20241030082020.2fe8eadb@hermes.local> (raw)
In-Reply-To: <b62a69ae-59dc-43c5-8e94-36c21d83e37f@cesnet.cz>
On Wed, 30 Oct 2024 14:58:40 +0100
Lukáš Šišmiš <sismis@cesnet.cz> wrote:
> On 29. 10. 24 15:37, Morten Brørup wrote:
> >> From: Lukas Sismis [mailto:sismis@cesnet.cz]
> >> Sent: Tuesday, 29 October 2024 13.49
> >>
> >> Intel PMDs are capped by default to only 4096 RX/TX descriptors.
> >> This can be limiting for applications requiring a bigger buffer
> >> capabilities. The cap prevented the applications to configure
> >> more descriptors. By bufferring more packets with RX/TX
> >> descriptors, the applications can better handle the processing
> >> peaks.
> >>
> >> Signed-off-by: Lukas Sismis <sismis@cesnet.cz>
> >> ---
> > Seems like a good idea.
> >
> > Have the max number of descriptors been checked with the datasheets for all the affected NIC chips?
> >
> I was hoping to get some feedback on this from the Intel folks.
>
> But it seems like I can change it only for ixgbe (82599) to 32k
> (possibly to 64k - 8), others - ice (E810) and i40e (X710) are capped at
> 8k - 32.
>
> I neither have any experience with other drivers nor I have them
> available to test so I will let it be in the follow-up version of this
> patch.
>
> Lukas
>
Having large number of descriptors especially at lower speeds will
increase buffer bloat. For real life applications, do not want increase
latency more than 1ms.
10 Gbps has 7.62Gbps of effective bandwidth due to overhead.
Rate for 1500 MTU is 7.62Gbs / (1500 * 8) = 635 K pps (i.e 1.5 us per packet)
A ring of 4096 descriptors can take 6 ms for full size packets.
Be careful, optimizing for 64 byte benchmarks can be disaster in real world.
next prev parent reply other threads:[~2024-10-30 15:20 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-29 12:48 Lukas Sismis
2024-10-29 14:37 ` Morten Brørup
2024-10-30 13:58 ` Lukáš Šišmiš
2024-10-30 15:20 ` Stephen Hemminger [this message]
2024-10-30 15:40 ` Lukáš Šišmiš
2024-10-30 15:58 ` Bruce Richardson
2024-10-30 16:06 ` Stephen Hemminger
2024-10-30 15:06 ` [PATCH v2 1/2] net/ixgbe: " Lukas Sismis
2024-10-30 15:06 ` [PATCH v2 2/2] net/ice: " Lukas Sismis
2024-10-30 15:42 ` [PATCH v3 1/1] net/bonding: make bonding functions stable Lukas Sismis
2024-10-30 15:42 ` [PATCH v3 1/2] net/ixgbe: increase the maximum of RX/TX descriptors Lukas Sismis
2024-10-30 16:26 ` Morten Brørup
2024-10-30 15:42 ` [PATCH v3 2/2] net/ice: " Lukas Sismis
2024-10-30 16:26 ` Morten Brørup
-- strict thread matches above, loose matches on Subject: below --
2024-10-29 12:46 [PATCH] net: " Lukas Sismis
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=20241030082020.2fe8eadb@hermes.local \
--to=stephen@networkplumber.org \
--cc=anatoly.burakov@intel.com \
--cc=dev@dpdk.org \
--cc=ian.stokes@intel.com \
--cc=mb@smartsharesystems.com \
--cc=sismis@cesnet.cz \
/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;
as well as URLs for NNTP newsgroup(s).