lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250527103356.GS88033@black.fi.intel.com>
Date: Tue, 27 May 2025 13:33:56 +0300
From: Mika Westerberg <mika.westerberg@...ux.intel.com>
To: Ricard Bejarano <ricard@...arano.io>
Cc: netdev@...r.kernel.org, michael.jamet@...el.com, YehezkelShB@...il.com,
	andrew+netdev@...n.ch, davem@...emloft.net, edumazet@...gle.com,
	kuba@...nel.org, pabeni@...hat.com
Subject: Re: Poor thunderbolt-net interface performance when bridged

On Mon, May 26, 2025 at 06:10:44PM +0200, Ricard Bejarano wrote:
> > Do you see that asymmetry with only single link? E.g with two (just two)
> > hosts? If yes can you provide full dmesg of the both sides?
> 
> No. You can see that in [4.6.1a] and [4.6.1a]. When red and blue talk to each
> other directly, speed is ~9Gbps both ways.

Okay that's good to know.

One thing that may or may not affect but I think is worth mentioning. The
hardware has support for end-to-end flow control to avoid packet loss and
that's enabled by default. You can turn it off by passing
"thunderbolt_net.e2e=0" in the kernel command line (or when loading the
module).

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ