[Lustre-discuss] Unusable ZFS backup MDT/MGS after change
Jesse Stroik
jstroik at ssec.wisc.edu
Wed May 21 08:23:20 PDT 2014
We have been a method to have a backup MDS and MDT using the
documentation here:
https://jira.hpdd.intel.com/browse/LUDOC-161
The procedure we follow is commented by Scott and was taken from our own
internal documentation. Our method is to create a ZFS file system
lustre-meta/fsmeta
lustre-meta/mgs
And then we snapshot (-r), then zfs send (-R)/receive it. To use the
backup we swap its IP addresses and name with the primary.
If the backup is swapped and used immediately after the snapshot is
taken, this method works. However, it does not work if you continue to
use the original server before migrating to the backup -- the equivalent
of migrating to a not-perfectly-up-to-date snapshot. In that case, you
can mount and read from the file system but no newly written files make
it to the OSTs.
The MDT does show files we attempt to create but their attributes are
all unknown. We are unable to manipulate the files (rm, mv, etc). The
error returned is "cannot allocate memory" (LU-4524).
We suspected the configuration logs and so we re-ran writeconf and
remounted. Same behavior.
On our primary MDT right now we have both a working MGS/MDT and also the
non-working MGS/MDT which we could switch to if testing were requested.
We are running lustre 2.4.0 on the servers and have tested with 2.4.0
and 2.1.6 clients.
Best,
Jesse Stroik
University of Wisconsin
More information about the lustre-discuss
mailing list