From: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
To: Martin Karsten <mkarsten@uwaterloo.ca>,
Willem de Bruijn <willemdebruijn.kernel@gmail.com>,
Samiullah Khawaja <skhawaja@google.com>,
Jakub Kicinski <kuba@kernel.org>,
"David S . Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Paolo Abeni <pabeni@redhat.com>,
almasrymina@google.com, willemb@google.com,
jdamato@fastly.com
Cc: netdev@vger.kernel.org
Subject: Re: [PATCH net-next v5 0/4] Add support to do threaded napi busy poll
Date: Mon, 28 Apr 2025 14:20:21 -0400 [thread overview]
Message-ID: <680fc6e5cc652_247f7d294a2@willemb.c.googlers.com.notmuch> (raw)
In-Reply-To: <b65404cb-cd51-40ad-a6a0-d7366391da7f@uwaterloo.ca>
Martin Karsten wrote:
> On 2025-04-28 12:52, Willem de Bruijn wrote:
> > Martin Karsten wrote:
> >> On 2025-04-24 16:02, Samiullah Khawaja wrote:
>
> [snip]
>
> > There is also a functional argument for this feature. It brings
> > parity with userspace network stacks like DPDK and Google's SNAP [1].
> > These also run packet (and L4+) network processing on dedicated cores,
> > and by default do so in polling mode. An XDP plane currently lacks
> > this well understood configuration. This brings it closer to parity.
> I believe these existing user-level stacks burn one core per queue. This
> scheme burns two.
That's specific to the AF_XDP use-case where AF_XDP also runs in
polling mode.
There are other use cases that more closely match DPDK, such as an
XDP dataplane. Conversely, DPDK with reinject into the host kernel
will also have to handle the signal or polling of the second stage.
next prev parent reply other threads:[~2025-04-28 18:20 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-04-24 20:02 [PATCH net-next v5 0/4] Add support to do threaded napi busy poll Samiullah Khawaja
2025-04-24 20:02 ` [PATCH net-next v5 1/4] net: Create separate gro_flush helper function Samiullah Khawaja
2025-04-24 23:21 ` Joe Damato
2025-04-24 20:02 ` [PATCH net-next v5 2/4] net: define an enum for the napi threaded state Samiullah Khawaja
2025-04-24 23:40 ` Joe Damato
2025-04-26 1:36 ` Jakub Kicinski
2025-04-26 3:54 ` Samiullah Khawaja
2025-04-24 20:02 ` [PATCH net-next v5 3/4] Extend napi threaded polling to allow kthread based busy polling Samiullah Khawaja
2025-04-24 23:42 ` Joe Damato
2025-04-24 20:02 ` [PATCH net-next v5 4/4] selftests: Add napi threaded busy poll test in `busy_poller` Samiullah Khawaja
2025-04-28 13:50 ` [PATCH net-next v5 0/4] Add support to do threaded napi busy poll Martin Karsten
2025-04-28 16:52 ` Willem de Bruijn
2025-04-28 17:39 ` Joe Damato
2025-04-28 17:59 ` Willem de Bruijn
2025-04-28 18:05 ` Martin Karsten
2025-04-30 12:37 ` David Laight
2025-04-30 16:47 ` Samiullah Khawaja
2025-04-28 18:05 ` Martin Karsten
2025-04-28 18:20 ` Willem de Bruijn [this message]
2025-04-30 15:23 ` Martin Karsten
2025-04-30 16:58 ` Samiullah Khawaja
2025-04-30 19:57 ` Martin Karsten
2025-04-30 20:33 ` Samiullah Khawaja
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=680fc6e5cc652_247f7d294a2@willemb.c.googlers.com.notmuch \
--to=willemdebruijn.kernel@gmail.com \
--cc=almasrymina@google.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=jdamato@fastly.com \
--cc=kuba@kernel.org \
--cc=mkarsten@uwaterloo.ca \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=skhawaja@google.com \
--cc=willemb@google.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