Message-ID: <aaf3d11ea5b247ab03d117dadae682fe2180d38a.camel@redhat.com>
Subject: Re: [PATCH net] udp: fix memory schedule error
From:   Paolo Abeni <pabeni@redhat.com>
To:     Jason Xing <kerneljasonxing@gmail.com>
Cc:     willemdebruijn.kernel@gmail.com, davem@davemloft.net,
        dsahern@kernel.org, edumazet@google.com, kuba@kernel.org,
        netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
        bpf@vger.kernel.org, Jason Xing <kernelxing@tencent.com>
Date:   Tue, 21 Feb 2023 15:46:27 +0100
In-Reply-To: <CAL+tcoD8PzL4khHq44z27qSHHGkcC4YUa91E3h+ki7O0u3SshQ@mail.gmail.com>
References: <20230221110344.82818-1-kerneljasonxing@gmail.com>
         <48429c16fdaee59867df5ef487e73d4b1bf099af.camel@redhat.com>
         <CAL+tcoD8PzL4khHq44z27qSHHGkcC4YUa91E3h+ki7O0u3SshQ@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 Tue, 2023-02-21 at 21:39 +0800, Jason Xing wrote:
> On Tue, Feb 21, 2023 at 8:27 PM Paolo Abeni <pabeni@redhat.com> wrote:
> >=20
> > On Tue, 2023-02-21 at 19:03 +0800, Jason Xing wrote:
> > > From: Jason Xing <kernelxing@tencent.com>
> > >=20
> > > Quoting from the commit 7c80b038d23e ("net: fix sk_wmem_schedule()
> > > and sk_rmem_schedule() errors"):
> > >=20
> > > "If sk->sk_forward_alloc is 150000, and we need to schedule 150001 by=
tes,
> > > we want to allocate 1 byte more (rounded up to one page),
> > > instead of 150001"
> >=20
> > I'm wondering if this would cause measurable (even small) performance
> > regression? Specifically under high packet rate, with BH and user-space
> > processing happening on different CPUs.
> >=20
> > Could you please provide the relevant performance figures?
>=20
> Sure, I've done some basic tests on my machine as below.
>=20
> Environment: 16 cpus, 60G memory
> Server: run "iperf3 -s -p [port]" command and start 500 processes.
> Client: run "iperf3 -u -c 127.0.0.1 -p [port]" command and start 500 proc=
esses.

Just for the records, with the above command each process will send
pkts at 1mbs - not very relevant performance wise.

Instead you could do:

taskset 0x2 iperf -s &
iperf -u -c 127.0.0.1 -b 0 -l 64


> In theory, I have no clue about why it could cause some regression?
> Maybe the memory allocation is not that enough compared to the
> original code?

As Eric noted, for UDP traffic, due to the expected average packet
size, sk_forward_alloc is touched quite frequently, both with and
without this patch, so there is little chance it will have any
performance impact.

Cheers,

Paolo