[Gimle-users] /nobackup/rossby14 down for checks tonight

Peter Kjellström cap at nsc.liu.se
Thu Mar 3 19:30:13 CET 2011


On Thursday, March 03, 2011 05:44:07 pm Kent Engström wrote:
> kent at nsc.liu.se (Kent Engström) writes:
> > Dear users of the /nobackup/rossby14 filesystem,
> > 
> > one of the servers serving the filesystem has been seriously confused.
> > Please read this email. You need to decide if you have to rerun
> > jobs and/or check copied data.
> 
> ...
> 
> > We will check this further, but you may assume that there is a certain
> > probability that files you have read from rossby14 during the last weeks
> > may have contained bad parts.
> 
> We have discussed this more now, and we need to run a file system check
> on the part of the filesystem that was located on the bad server.
> 
> The /nobackup/rossby14 filesystem will be down during this.
> 
> If the check completes OK, we will give you access to the filesystem
> again.
> 
> If serious problems are detected during the check, the filesystem will
> be down for some time. But then again, if we get there, the damage has
> already been done, and keeping the filesystem running will only worsen
> it.

I'm happy to report that the filesystem check completed with no errors. This 
was the best case scenario and means that the filesystem is back in normal 
use. The filesystem was unavailable for this check ~18:05-19:15 during which 
time all access would have blocked. If you have ongoing jobs with a tight wall 
time limit you may want to contact us to have it extended.

Note that this does _NOT_ change the fact that corrupted data was returned 
during the last few days (possibly weeks) so you still have to double check 
work and data done on/from rossby14.

For more information and/or help with verification/clean-up please contact us 
at smhi-support at nsc.liu.se

/Peter K

-- 
-= Peter Kjellström
-= National Supercomputer Centre
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 198 bytes
Desc: This is a digitally signed message part.
Url : https://lists.nsc.liu.se/mailman/public/gimle-users/attachments/20110303/999f5e02/attachment.bin 


More information about the Gimle-users mailing list