I''m sure the old-timers will remember my posts awhile back about Xen 2.0.x and intermittent (but reproducible) network loss in the form of total hangs of the network paths to both dom0 and domU. It was explained away at the time as a design problem (something about queues being exhausted was one potential culprit) that would be resolved in Xen 3.0. I''m now on Xen 3.0.2 and I''m seeing similar problems -- setup a ping to dom0 and over a period of a few hours there will be occasional packet loss. It isn''t yet as bad as it was before at only about one packet in 500, but it''s still troubling, particularly given that I''m not yet running any domU''s and that the box is completely idle -- not that that should matter anyway. How can this be? What can cause dom0 to just discard packets? Thanks, John -- John Madden Sr. UNIX Systems Engineer Ivy Tech Community College of Indiana jmadden@ivytech.edu _______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users
On Thursday 20 April 2006 10:21, John Madden wrote:> I''m now on Xen 3.0.2 and I''m seeing similar problemsApologies for replying to my own post, forgot to include config details before hitting Send: This is about as vanilla Xen as it gets: Xen 3.0.2, Debian 3.1, tulip nic driver -- basically run install.sh, setup grub, do the libc tls fix, reboot, and voila, packet loss pinging dom0. John -- John Madden Sr. UNIX Systems Engineer Ivy Tech Community College of Indiana jmadden@ivytech.edu _______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users