From: Willem de Bruijn <willemdebruijn.kernel@gmail•com>
To: Jakub Kicinski <kuba@kernel•org>,
Willem de Bruijn <willemdebruijn.kernel@gmail•com>
Cc: davem@davemloft•net, netdev@vger•kernel.org,
edumazet@google•com, pabeni@redhat•com, andrew+netdev@lunn•ch,
horms@kernel•org, shuah@kernel•org, willemb@google•com,
petrm@nvidia•com, donald.hunter@gmail•com,
michael.chan@broadcom•com, pavan.chebbi@broadcom•com,
linux-kselftest@vger•kernel.org
Subject: Re: [PATCH net-next v2 6/9] selftests: drv-net: gro: use SO_TXTIME to schedule packets together
Date: Tue, 10 Feb 2026 23:21:07 -0500 [thread overview]
Message-ID: <willemdebruijn.kernel.172899765680b@gmail.com> (raw)
In-Reply-To: <20260210194814.21a0c403@kernel.org>
Jakub Kicinski wrote:
> On Tue, 10 Feb 2026 22:15:25 -0500 Willem de Bruijn wrote:
> > > It's a bit of an opportunistic optimization.
> > >
> > > I initially intended it for for the "long sequence of packets"
> > > test. But I failed to get AF_PACKET+FQ to cooperate sufficiently
> > > to queue all of the packets in the same bucket. Otherwise FQ "sorts"
> > > the packets, and breaks what the test is trying to do :(
> >
> > I wonder what's going wrong here.
> >
> > fq_classify should pick the queue based on skb->sk also for packet
> > sockets.
> >
> > And flow_queue_add should add the packets to the tail of the linear
> > list if the delivery time is identical to that of the tail.
>
> It works but requires that we either modify the qdisc config to set
> a orphan_mask of 1, or somehow set the skb->hash on the AF_PACKET skbs.
Oh right, fq_classify does not use skb->sk for packet sockets because
they are in default sk_state TCP_CLOSE.
And this is by design, as clearly documented, as packet sockets should
not be assumed to be a single flow:
} else if (sk->sk_state == TCP_CLOSE) {
unsigned long hash = skb_get_hash(skb) & q->orphan_mask;
/*
* Sockets in TCP_CLOSE are non connected.
* Typical use case is UDP sockets, they can send packets
* with sendto() to many different destinations.
* We probably could use a generic bit advertising
* non connected sockets, instead of sk_state == TCP_CLOSE,
* if we care enough.
*/
sk = (struct sock *)((hash << 1) | 1UL);
}
An orphan_mask of 1 sounds like an effective workaround.
I don't see a way to force a specific skb_get_hash result across
flows, given hashrnd.
> The test sends out multiple flows (src ports) so if we let fq compute
> the real hash we end up in different buckets.
next prev parent reply other threads:[~2026-02-11 4:21 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-02-07 0:35 [PATCH net-next v2 0/9] net: stats, tools, driver tests for HW GRO Jakub Kicinski
2026-02-07 0:35 ` [PATCH net-next v2 1/9] eth: bnxt: gather and report HW-GRO stats Jakub Kicinski
2026-02-08 0:09 ` Michael Chan
2026-02-11 1:51 ` Jakub Kicinski
2026-02-07 0:35 ` [PATCH net-next v2 2/9] tools: ynltool: factor out qstat dumping Jakub Kicinski
2026-02-07 0:35 ` [PATCH net-next v2 3/9] tools: ynltool: add qstats analysis for HW-GRO efficiency / savings Jakub Kicinski
2026-02-09 9:43 ` Petr Machata
2026-02-07 0:35 ` [PATCH net-next v2 4/9] selftests: net: move gro to lib for HW vs SW reuse Jakub Kicinski
2026-02-09 2:36 ` Willem de Bruijn
2026-02-07 0:35 ` [PATCH net-next v2 5/9] selftests: drv-net: give HW stats sync time extra 25% of margin Jakub Kicinski
2026-02-09 2:37 ` Willem de Bruijn
2026-02-07 0:35 ` [PATCH net-next v2 6/9] selftests: drv-net: gro: use SO_TXTIME to schedule packets together Jakub Kicinski
2026-02-09 2:39 ` Willem de Bruijn
2026-02-11 1:56 ` Jakub Kicinski
2026-02-11 3:15 ` Willem de Bruijn
2026-02-11 3:48 ` Jakub Kicinski
2026-02-11 4:21 ` Willem de Bruijn [this message]
2026-02-11 17:00 ` Jakub Kicinski
2026-02-11 17:22 ` Willem de Bruijn
2026-02-07 0:35 ` [PATCH net-next v2 7/9] selftests: drv-net: gro: test GRO stats Jakub Kicinski
2026-02-07 0:35 ` [PATCH net-next v2 8/9] selftests: drv-net: gro: add test for packet ordering Jakub Kicinski
2026-02-07 0:35 ` [PATCH net-next v2 9/9] selftests: drv-net: gro: add a test for GRO depth Jakub Kicinski
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=willemdebruijn.kernel.172899765680b@gmail.com \
--to=willemdebruijn.kernel@gmail$(echo .)com \
--cc=andrew+netdev@lunn$(echo .)ch \
--cc=davem@davemloft$(echo .)net \
--cc=donald.hunter@gmail$(echo .)com \
--cc=edumazet@google$(echo .)com \
--cc=horms@kernel$(echo .)org \
--cc=kuba@kernel$(echo .)org \
--cc=linux-kselftest@vger$(echo .)kernel.org \
--cc=michael.chan@broadcom$(echo .)com \
--cc=netdev@vger$(echo .)kernel.org \
--cc=pabeni@redhat$(echo .)com \
--cc=pavan.chebbi@broadcom$(echo .)com \
--cc=petrm@nvidia$(echo .)com \
--cc=shuah@kernel$(echo .)org \
--cc=willemb@google$(echo .)com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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