On casual glance, it looks like a test meant to test the end of 32-bit offsets, built to test a specific ext4 case, and it happened to strafe XFS on 32-bit in the process. It is unknown to me whether a script with 64-bit version of the numbers would have a bad effect.
Michael
On Wed, Apr 10, 2013 at 10:18 AM, Rich Johnston <rjohnston@xxxxxxx> wrote:
On 04/10/2013 09:06 AM, Michael L. Semon wrote:
On 04/10/2013 09:46 AM, Michael L. Semon wrote:
The PC uses kernel 3.8-rc4 + Dave's CRC v4 patches + J. Liu's bitness
patch.
Oops, that was supposed to be "kernel 3.9-rc4." Sorry.
Michael
_______________________________________________
xfs mailing list
xfs@xxxxxxxxxxx
http://oss.sgi.com/mailman/listinfo/xfs
Runs fine on all my 64 bit machines. I quickly ran a test using 3.9.0-rc1+ on a 32 bit machine. I am seeing the same xfs_io 100% CPU usage.
Looks 32 bit specific.
--Rich
_______________________________________________ xfs mailing list xfs@xxxxxxxxxxx http://oss.sgi.com/mailman/listinfo/xfs
