Well, if you read the mailing list in the past weeks you see some people who have problems with vms on gluster. http://www.gluster.org/pipermail/gluster-users/2012-July/033752.html https://bugzilla.redhat.com/show_bug.cgi?id=842254 http://www.gluster.org/pipermail/gluster-users/2012-September/034298.html My experience shows that it most of the time happens with large instances (disk file > 50gb) and under I/O load. The question is, how to debug such a scenario? 2012/11/27 Gerald Brandt <gbr at majentis.com> > > > > > Hi Whit, To be honest, I don't see any improvements since 3.2 > > concerning virtual machines (maybe under the hood?). Self-heal is > > still blocking and performance is not better. > > We've waited over 6 months for the 3.3 release and it was really > > disappointing for me personally. > > > > > > Cheers, > > Christian > > > > Hi, > > Something is seriously wrong there. I just rebuilt a RAID, with complete > loss of data. GlusterFS self healed/replicated with no stutters or > downtime to the 23 VM's I run on the Gluster mirror. > > Gerald > -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://supercolony.gluster.org/pipermail/gluster-users/attachments/20121128/ba7b2ee6/attachment-0001.html>
