Please don't reply to lustre-devel. Instead, comment in Bugzilla by using the following link: https://bugzilla.lustre.org/show_bug.cgi?id=12592
Hi support team We have seen Thumper was sudden reboot with probably the H/W issue. (no system/lustre log) We are investing to find the root case for this problem, but another concern is we would like to be fast recovery after Thumper's down. Because, we were doing fsck for the MD before the staring the lustre, when Thumper was sudden reboot. But, each MD size is 2TB, so we need very long time for the fsck. In my understanding, Lustre-1.4.10 is implemented "ldiskfs2" which can be speedy fsck, right? If we can this, please inform us regarding the way to use. And sometimes, we can see to rebuild RAID5 after the booting from sudden reboot. If this case, we have to wait for the reconstruction finish? This is also very long wait time for restarting the Lustre. Thanks, -Ihara _______________________________________________ Lustre-devel mailing list [email protected] https://mail.clusterfs.com/mailman/listinfo/lustre-devel
