[Lustre-discuss] OST corruption?
andreas.dilger at intel.com
Fri Apr 19 00:30:31 PDT 2013
On 2013-04-16, at 10:49, "Verduzco, Benjamin P." <BENJAMIN.P.VERDUZCO at saic.com<mailto:BENJAMIN.P.VERDUZCO at saic.com>> wrote:
I’m having trouble with a filesystem after a planned outage. I’m new to Lustre, but I’ll do my best to explain what I’m seeing.
· I have a 18.104.22.168 MDS and 4 1.8.5 OSS’s.
In general, while it is possible to have mismatched client and server versions, it is never a good idea to run different Lustre versions on the servers.
When I brought the system up, it reported the used space incorrectly (df –h shows 166T total, 150T used and 7.1 T free)
· I unmounted and ran e2fsck on all of the OST’s and the MDS without error, but when I remounted everything the error persisted.
· When I ran lfsck in read-only mode, it basically showed all of the files on the two OST’s of a single OSS as “not created”.
Is there a way to save this data?
Any help or suggestions would be greatly appreciated.
Ben Verduzco | SAIC
Systems Administrator | Surveillance and Reconnaissance Group (SRG)
phone: 858-826-3884 | pager: 877-619-3140
benjamin.p.verduzco at saic.com<mailto:benjamin.p.verduzco at saic.com> | saic.com<http://www.saic.com/>
Lustre-discuss mailing list
Lustre-discuss at lists.lustre.org<mailto:Lustre-discuss at lists.lustre.org>
More information about the lustre-discuss