On Thu, May 27, 2010 at 08:57:38AM +0200, Michael Monnerie wrote:
> May 27 08:32:11 zdb13 kernel: [ 738.046895] end_request: I/O error, dev
> xvdc, sector 0
> This only happens after XFS is mounted from the LVM volume. On another
> machine where active I/O is happening, I get tons of these errors every
> some seconds.
This looks like the Xen block device code is buggy and doesn't handle
the I/O pattern XFS throws at it. A sector 0 error during mount usually
is the superblock barrier test write. To verify that assumptions
try mounting the XFS filesystems with -o nobarrier and see if it goes
away. Note that this is only for testing, and I would _not_ recommend
it for production use. If it makes the error go away please file
a bug with the Xen guys to fix their barrier support by either
implementing it properly or not advertizing it.