netdev - Re: Poor thunderbolt-net interface performance when bridged

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] [day] [month] [year] [list]

Message-Id: <e48cc5fe-d741-4260-b561-f33c1c995cb2@app.fastmail.com>
Date: Sun, 15 Jun 2025 15:56:26 +0200
From: "Ricard Bejarano" <ricard@...arano.io>
To: "Andrew Lunn" <andrew@...n.ch>
Cc: "Mika Westerberg" <mika.westerberg@...ux.intel.com>,
 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

> Did you manage to prove it is skbuf with fragments which are the
> problem? As i said, adding the skb_linearize was just a debug tool,
> not a fix.

I did not, all my tests with skb_linearize made iperf3 fail. I did
manage, however, to prove that all UDP SKBs we transmit are linear,
thus all non-linear (if any) SKBs we see are TCP.
Thus, I could not test loss with skb_linearize vs. loss without.

Thanks,
RB