[premise-users] Yes another Premise Lustre update.

[Robert Anderson]

The mysql database restore appears to have been successful.  The storage system boots well past that point now.

The new issue is with one of the  MetaData storage array volumes is not coming online.

There are more rebuilds going on at the moment, but they take more than 3 hours to compete and sometime leave us in the same place without a fully redundant array.    At this point we have to be very careful with the commands used since we need to ensure we don't make it worse. It is entirely possible that we will not be able to get the old Lustre storage back online just do to drive failures and/or disk errors.  We would like to take time this weekend to explore options and see if there is a way to sort it all out.

If we have no working Old Lustre by Monday we should start working towards a plan B of coming up with out it.  And mapping a path forward for the groups with home areas on /mnt/lustre.  I was able to complete backups for most groups back in May/June, so we could get back that older data.

I really wish I had better news to distribute.


Robert E. Anderson

University of NH / Research Computing Center / Data Center Operations


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.sr.unh.edu/pipermail/premise-users/attachments/20220909/c3afda11/attachment.html>