WARNING: This is the _old_ Lustre wiki, and it is in the process of being retired. The information found here is all likely to be out of date. Please search the new wiki for more up to date information.
Handling File System Errors
From time to time, usually due to catastrophic disk / RAID failures, it may be necessary to repair the backing file system of an OST or MDT to correct file system errors. This is done using a special version of the e2fsck tool.
It may also be useful to run lfsck in such cases. This is a Lustre-specific tool that checks the coherency of a running Lustre filesystem as a whole.
For information on the following topics, see Fsck Support.
- Obtaining e2fsck support for Lustre
- Using e2fsck on a backing filesystem
- Running e2fsck+lfsck on a corrupted Lustre filesystem
For more information about lfsck, see Chapter 28 in the Lustre Operations Manual.