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;
MIME-Version: 1.0
References: <20230713112404.2022373-1-imagedong@tencent.com>
In-Reply-To: <20230713112404.2022373-1-imagedong@tencent.com>
From:   Eric Dumazet <edumazet@google.com>
Date:   Mon, 17 Jul 2023 18:46:57 +0200
Message-ID: <CANn89iJMzChaDsB+bPAuCEDUHVApsYs8KtD3oEC+oU_Qvi1KvQ@mail.gmail.com>
Subject: Re: [PATCH net-next v2] net: tcp: support to probe tcp receiver OOM
To:     menglong8.dong@gmail.com
Cc:     ncardwell@google.com, davem@davemloft.net, kuba@kernel.org,
        pabeni@redhat.com, corbet@lwn.net, dsahern@kernel.org,
        kuniyu@amazon.com, morleyd@google.com, imagedong@tencent.com,
        mfreemon@cloudflare.com, mubashirq@google.com,
        netdev@vger.kernel.org, linux-doc@vger.kernel.org,
        linux-kernel@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

On Thu, Jul 13, 2023 at 1:24=E2=80=AFPM <menglong8.dong@gmail.com> wrote:
>
> From: Menglong Dong <imagedong@tencent.com>
>
> For now, skb will be dropped directly if rmem schedule fails, which means
> tcp_try_rmem_schedule() returns an error. This can happen on following
> cases:
>
> 1. The total memory allocated for TCP protocol is up to tcp_mem[2], and
>    the receive queue of the tcp socket is not empty.
> 2. The receive buffer of the tcp socket is full, which can happen on smal=
l
>    packet cases.
>
> If the user hangs and doesn't take away the packet in the receive queue
> with recv() or read() for a long time, the sender will keep
> retransmitting until timeout, and the tcp connection will break.
>
> In order to handle such case, we introduce the tcp protocol OOM detection
> in following steps, as Neal Cardwell suggested:
>

For the record, I dislike this patch. I am not sure what Neal had in mind.

I suggested instead to send an ACK RWIN 0, whenever we were under
extreme memory pressure,
and we only could queue one skb in the receive queue.

For details, look at the points we call sk_forced_mem_schedule().
This would be a matter of refactoring code around it, in tcp_data_queue()

The patch would be much simpler. Nothing changed at the sender side :/