RE: 3.6.10: Intel: ixgbe 0000:01:00.0 eth4: Detected Tx Unit Hang

-----Original Message-----
From: devendra.aaru [mailto:devendra.aaru@gmail.com] 
Sent: Monday, December 17, 2012 1:39 PM
To: Justin Piszcz
Cc: linux-kernel@vger.kernel.org; netdev@vger.kernel.org
Subject: Re: 3.6.10: Intel: ixgbe 0000:01:00.0 eth4: Detected Tx Unit Hang

Ccing netdev
On Sat, Dec 15, 2012 at 10:49 AM, Justin Piszcz [off-list ref]
wrote:

Hello,

Kernel 3.6.10, first time I have seen this that I can remember (on 10GbE)
anyway, is this a known issue with 3.6.10?

When the link went down is when I rebooted/etc the remote host attached on
the other end.
I've not changed anything physically with the hardware and have been on
3.6.0-3.6.9 and noticed this when I moved to 3.6.10.

--

I don't believe we have seen Tx hangs in validation. If you could narrow

down the conditions that lead to the Tx hang that would help a lot. Also 

 the output of ethtool -S eth4 after the Tx hang occurs can be useful to

get an idea of the load on the interface.

Thanks,
Emil

--

In this case I only have two servers that mount each other's NFS volumes and
that were idle at the time, I rebooted one of the systems and that is when I
saw this, if I can get something to repeat/pattern and/or the ethtool output
I will update this thread, thank you.

Justin.