[Ocfs2-users] sanity check - Xen+iSCSI+LVM+OCFS2 at dom0/domU

[Nicola Fankhauser]

hi

Alok Dhir wrote:
> However, we have now run into a more prevalent issue - at dom0, any of 
> the cluster member servers will spontaneously reboot when I start an 
> 'iozone -A' in an ocfs2 filesystem.  I am unable to check the kernel 
> panic message as the box reboots immediately, despite the setting of 
> 'kernel.panic=0' in sysctl (which is supposed to mean 'do not reboot on 
> panic').  There are also no entries in messages when this happens.

due to my very limited experience on this field (see earlier posts 
yesterday) take it with a grain of salt, but that looks to me like 
self-fencing (ie. dropping out of the cluster and immediately rebooting) 
during (probably high) I/O.

I think observing the console (like proposed) right before the reboots 
happen might prove this with a explicit message.

regards
nicola