Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <98b96b354ef9e0b7cafb951b12988aee727807a3.camel@redhat.com>
Subject: Re: [PATCH 0/3] softirq: uncontroversial change
From:   Paolo Abeni <pabeni@redhat.com>
To:     Eric Dumazet <edumazet@google.com>
Cc:     Jakub Kicinski <kuba@kernel.org>, peterz@infradead.org,
        tglx@linutronix.de, jstultz@google.com, netdev@vger.kernel.org,
        linux-kernel@vger.kernel.org
Date:   Thu, 20 Apr 2023 22:23:14 +0200
In-Reply-To: <CANn89iKQ2KR23Ln9FU5RCKH89KWCNcu9QWuVLB4CcEqgoH+iRQ@mail.gmail.com>
References: <20221222221244.1290833-1-kuba@kernel.org>
         <305d7742212cbe98621b16be782b0562f1012cb6.camel@redhat.com>
         <CANn89iKQ2KR23Ln9FU5RCKH89KWCNcu9QWuVLB4CcEqgoH+iRQ@mail.gmail.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
User-Agent: Evolution 3.46.4 (3.46.4-1.fc37) 
MIME-Version: 1.0
Precedence: bulk

On Thu, 2023-04-20 at 19:41 +0200, Eric Dumazet wrote:
> On Thu, Apr 20, 2023 at 7:24=E2=80=AFPM Paolo Abeni <pabeni@redhat.com> w=
rote:
> > I would like to propose a revert of:
> >=20
> > 4cd13c21b207 softirq: Let ksoftirqd do its job
> >=20
> > the its follow-ups:
> >=20
> > 3c53776e29f8 Mark HI and TASKLET softirq synchronous
> > 0f50524789fc softirq: Don't skip softirq execution when softirq thread =
is parking
> >=20
> > The problem originally addressed by 4cd13c21b207 can now be tackled
> > with the threaded napi, available since:
> >=20
> > 29863d41bb6e net: implement threaded-able napi poll loop support
> >=20
> > Reverting the mentioned commit should address the latency issues
> > mentioned by Jakub - I verified it solves a somewhat related problem in
> > my setup - and reduces the layering of heuristics in this area.
> >=20
> > A refactor introducing uniform overload detection and proper resource
> > control will be better, but I admit it's beyond me and anyway it could
> > still land afterwards.
> >=20
> > Any opinion more then welcome!
>=20
> Seems fine, but I think few things need to be fixed first in
> napi_threaded_poll()
> to enable some important features that are currently  in net_rx_action() =
only.

Thanks for the feedback.

I fear I'll miss some relevant bits.=C2=A0

On top of my head I think about RPS and  skb_defer_free. Both should
work even when napi threaded is enabled - with an additional softirq ;)
Do you think we should be able to handle both inside the napi thread?
Or do you refer to other features?

Thanks!

Paolo