On Fri, Mar 22, 2013 at 11:27:16PM -0400, Mike Snitzer wrote: > So the big difference is the thinp-test-suite uses intermediate linear > DM layers above the slower sd device (spindle/data) -- whereas in your > setup the origin device is direct to sd (8:0). I would think the difference is because DM issues (edited) copies of incoming bios to the layers underneath, so changes don't propagate back up. Darrick: if you retest with a dm linear device, does the problem go away? Alasdair -- dm-devel mailing list dm-devel@xxxxxxxxxx https://www.redhat.com/mailman/listinfo/dm-devel