On 05.12.2010, Matt wrote: > I should have made it clear that the results I get are observed when > using the kernels/checkouts *with* the dm-crypt multi-cpu patch, > without the patch I didn't see that kind of problems (hardlocks, files > missing, etc.) I have to take back my other two emails, stating that no corruption happened with the dm-crypt multi-cpu patch. Today, I encountered filesystem corruption on one, and a complete hardlock on another machine. No logfile entries, no m-sysrq, a complete deadlock. Filesystem was corrupted here too, had to reboot from CD. The machines with plain 2.6.37-rc4 are up and running... -- To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
