lfsck(8) check a Lustre distributed filesystem


lfsck [ -cdfhlnv ] --mdsdb mds_database_file --ostdb ost1_database_file [ost2_database_file ...] filesystem


lfsck is used to check and repair the distributed coherency of a Lustre filesystem.

filesystem is the mountpoint of the Lustre filesystem to be checked. e.g. /mnt/lustre).


Lfsck is used to do the distributed coherency checking of a Lustre filesystem after e2fsck has been run on each of the local MDS and OST device filesystems. Lfsck will ensure that objects are not referenced by multiple MDS files, that there are no orphan objects on the OSTs (objects that do not have any file on the MDS which references them), and that all of the objects referenced by the MDS exist. Under normal circumstances Lustre will maintain such coherency by distributed logging mechanisms, but under exceptional circumstances that may fail (e.g. disk failure, filesystem corruption leading to e2fsck repair).


Create (empty) missing OST objects referenced by MDS inodes.
Delete orphaned objects from the filesystem. Since objects on the OST are often only one of several stripes of a file it can be difficult to put multiple objects back together into a single usable file.
Print a brief help message.
Put orphaned objects into a lost+found directory in the root of the filesystem.
Do not repair the filesystem, just perform a read-only check (default).
Verbose operation - more verbosity by specifing option multiple times.
--mdsdb mds_database_file
The MDS database file created by running e2fsck --mdsdb mds_database_file device on the MDS backing device. This is required.
--ostdb ost1_database_file [ost2_database_file ...]
The OST database files created by running e2fsck --ostdb ost_database_file device on each of the OST backing devices. These are required, unless an OST is unavailable, in which case all objects thereon will be considered missing.


Bugs should be reported to Sun Microsystems, Inc. via Bugzilla: http://bugzilla.lustre.org/


This version of lfsck was originally written by Liam Kelleher <[email protected]> and maintained by Andreas Dilger <[email protected]>