We are sharing ocfs2 volumes to Xen domU processes on our SAN. From a stability standpoint on SLES10 (not SP1 yet) and OpenSuSE 10.2, should we keep our i/o scheduler as Deadline, or switch to CFQ? I was under the impression that CFQ was fixed and switched back to it, but I experienced a self-fence panic this morning that leads me to question how fixed it truly is. We're back to using Deadline for now, but I need to know if I should be investigating other causes instead. jeff
The default disk timeout in ocfs2 is fairly low. It just could be that that needs to be bumped up. Do you have the netconsole output of the crash? Jeff Bachtel wrote:> We are sharing ocfs2 volumes to Xen domU processes on our SAN. From a > stability standpoint on SLES10 (not SP1 yet) and OpenSuSE 10.2, should > we keep our i/o scheduler as Deadline, or switch to CFQ? I was under > the impression that CFQ was fixed and switched back to it, but I > experienced a self-fence panic this morning that leads me to question > how fixed it truly is. > > We're back to using Deadline for now, but I need to know if I should > be investigating other causes instead. > > jeff > > _______________________________________________ > Ocfs2-users mailing list > Ocfs2-users@oss.oracle.com > http://oss.oracle.com/mailman/listinfo/ocfs2-users >