Re: Looping GET to http://gnome.org, high load
- From: Owen Taylor <otaylor redhat com>
- To: gnome-infrastructure gnome org
- Subject: Re: Looping GET to http://gnome.org, high load
- Date: Sun, 03 Sep 2006 13:47:13 -0400
On Sun, 2006-09-03 at 09:21 -0400, Owen Taylor wrote:
> * At times we are getting messages like:
> Sep 3 09:04:39 window kernel: nfs: server container-back not responding, still trying
> In /var/log/messages.
> So, it seems it might be related to NFS problems
This seems to have been a red herring as far as the immediate problems
My suspicion is that what this message means is we're getting some
amount of packet loss between container and window on the backchannel.
Since they are exchanging a thousand packets a second or so, a
0.01% packet loss could create a mess in /var/log/messages.
I didn't think it was possible to get congestion packet losses between
two computers connected to ports on the same switch, but I'm no expert
in the area. If someone is interested in experimenting, they might
want to try switching the NFS mounts on window to TCP and see if that
(remount -o [...],tcp)
] [Thread Prev