I have a report from a google person who just did some basic power-it-off-during-a-write testing on 2.6.20's ext3. ordered-data is OK, but data=journal came back with crap in the file data. Is anyone doing any formal recovery stress-testing? I suspect we should resurrect and formalise my old make-the-disk-stop-accepting-writes-when-a-timer-goes-off thing. It was very useful for stress-testing recovery. - To unsubscribe from this list: send the line "unsubscribe linux-ext4" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
