[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <f2ca37ef-e5d0-4f3e-9299-0f1fc541fd03@lunn.ch>
Date: Mon, 26 May 2025 16:28:23 +0200
From: Andrew Lunn <andrew@...n.ch>
To: Ricard Bejarano <ricard@...arano.io>
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
> > 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
Powered by blists - more mailing lists