Received-SPF: pass (google.com: domain of linux-kernel+bounces-155416-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
Message-ID: <7537ed21-4fc5-47c1-9c06-58982a308419@kernel.org>
Date: Tue, 23 Apr 2024 09:03:20 -0600
Precedence: bulk
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [RFC] net: add TCP fraglist GRO support
Content-Language: en-US
To: Eric Dumazet <edumazet@google.com>, Felix Fietkau <nbd@nbd.name>
Cc: netdev@vger.kernel.org, "David S. Miller" <davem@davemloft.net>,
 Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
 linux-kernel@vger.kernel.org
References: <20240423094117.93206-1-nbd@nbd.name>
 <CANn89i+6xRe4V6aDmD-9EM0uD7A87f6rzg3S7Xq6-NaB_Mb4nw@mail.gmail.com>
From: David Ahern <dsahern@kernel.org>
In-Reply-To: <CANn89i+6xRe4V6aDmD-9EM0uD7A87f6rzg3S7Xq6-NaB_Mb4nw@mail.gmail.com>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit

On 4/23/24 4:15 AM, Eric Dumazet wrote:
> I think we should push hard to not use frag_list in drivers :/

why is that? I noticed significant gains for local delivery after adding
frag_list support for H/W GRO. Fewer skbs going up the stack is
essential for high throughput and reducing CPU load.

> 
> And GRO itself could avoid building frag_list skbs
> in hosts where forwarding is enabled.

But if the egress device supports SG and the driver understands
frag_list, walking the frag_list should be cheaper than multiple skbs
traversing the forwarding path.

> 
> (Note that we also can increase MAX_SKB_FRAGS to 45 these days)

Using 45 frags has other side effects and not something that can be done
universally (hence why it is a config option).

45 frags is for Big TCP at 4kB and that is ~ 3 skbs at the default
setting of 17 which means an skb chain 2 deep. 1 skb going up the stack
vs 3 skbs - that is a big difference.

Was there a conference talk or a discussion around tests performed
comparing use of frag_list with MAX_SKB_FRAGS at 17 vs expanding
MAX_SKB_FRAGS to 45?