[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250526080956.7f64a5f5@hermes.local>
Date: Mon, 26 May 2025 08:09:56 -0700
From: Stephen Hemminger <stephen@...workplumber.org>
To: Andrew Lunn <andrew@...n.ch>
Cc: Ricard Bejarano <ricard@...arano.io>, 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
On Mon, 26 May 2025 16:28:23 +0200
Andrew Lunn <andrew@...n.ch> wrote:
> > > Simple peer-to-peer, no routing nothing. Anything else is making things
> > > hard to debug. Also note that this whole thing is supposed to be used as
> > > peer-to-peer not some full fledged networking solution.
> >
> > > Let's forget bridges for now and anything else than this:
> > > Host A <- Thunderbolt Cable -> Host B
> >
> > Right, but that's precisely what I'm digging into: red->blue runs at line speed,
> > and so does blue->purple. From what I understand about drivers and networking,
> > it doesn't make sense then that the red->blue->purple path drops down so much in
> > performance (9Gbps to 5Mbps)
>
> Agreed.
>
> Do the interfaces provide statistics? ethtool -S. Where is the packet
> loss happening?
>
> Is your iperf testing with TCP or UDP? A small amount of packet loss
> will cause TCP to back off a lot. Also, if the reverse direction is
> getting messed up, ACKs are getting lost, TCP will also stall.
>
> Maybe try a UDP stream, say 500Mbs. What is the packet loss? Try the
> reverse direction, what is the packet loss. Then try --bidir, so you
> get both directions at the same time.
>
> Andrew
>
What is MTU? Bridging is L2 and if MTU does not match packets are
silently dropped.
Powered by blists - more mailing lists