Lin Shen (lshen) wrote:
I did a --reformt first, and then followed by another mkfs.lustre. The
enclosed outputs are from two separate commands.
Right. The first one (with --reformat) works, the second one (without)
does not.
You can see that the first one does the formatting:
formatting backing filesystem ldiskfs on /dev/hda10
target name lustrefs-MDTffff
4k blocks 0
options -i 4096 -I 512 -q -O dir_index -F
With this command:
mkfs_cmd = mkfs.ext2 -j -b 4096 -L lustrefs-MDTffff -i 4096 -I 512 -q -O
dir_index -F /dev/hda10
The disk is now reformatted. If you try to format it again (without
--reformat), it will complain.
Writing CONFIGS/mountdata
[EMAIL PROTECTED] ~]# mkfs.lustre --fsname=lustrefs --mdt --mgs
--mkfsoptions
-i 2048 /dev/hda10
Permanent disk data:
Target: lustrefs-MDTffff
Index: unassigned
Lustre FS: lustrefs
Mount type: ldiskfs
Flags: 0x75
(MDT MGS needs_index first_time update ) Persistent
mount opts: errors=remount-ro,iopen_nopriv,user_xattr
Parameters:
checking for existing Lustre data
found Lustre data
mkfs.lustre FATAL: Device /dev/hda10 was previously formatted for
lustre. Use --reformat to reformat it, or tunefs.lustre to modify.
It's refusing to reformat what it has identified as an
already-formatted Lustre disk. This is a safety feature to
prevent you from accidentally erasing it, thus destroying
your entire filesystem. Use the --reformat flag to force it.
man mkfs.lustre:
--reformat
Reformat an existing Lustre disk
_______________________________________________
Lustre-discuss mailing list
[email protected]
https://mail.clusterfs.com/mailman/listinfo/lustre-discuss
