[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <49455AA8-0606-447E-B455-F905EA184E42@infradead.org>
Date: Sun, 07 May 2023 10:31:34 +0100
From: David Woodhouse <dwmw2@...radead.org>
To: Hao Chen <chenh@...ur.tech>, Xuan Zhuo <xuanzhuo@...ux.alibaba.com>
CC: huangml@...ur.tech, zy@...ur.tech, "Michael S. Tsirkin" <mst@...hat.com>,
Jason Wang <jasowang@...hat.com>, "David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>, Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>,
"open list:VIRTIO CORE AND NET DRIVERS" <virtualization@...ts.linux-foundation.org>,
"open list:NETWORKING DRIVERS" <netdev@...r.kernel.org>,
open list <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] virtio_net: set default mtu to 1500 when 'Device maximum MTU' bigger than 1500
On 6 May 2023 09:56:35 BST, Hao Chen <chenh@...ur.tech> wrote:
>In the current code, if the maximum MTU supported by the virtio net hardware is 9000, the default MTU of the virtio net driver will also be set to 9000. When sending packets through "ping -s 5000", if the peer router does not support negotiating a path MTU through ICMP packets, the packets will be discarded.
That router is just plain broken, and it's going to break all kinds of traffic. Hacking the virtio-net MTU is only a partial workaround.
Surely the correct fix here is to apply percussive education to whatever idiot thought it was OK to block ICMP. Not to hack the default MTU of one device to the lowest common denominator.
Powered by blists - more mailing lists