[Gluster-users] Gluster with KVM - VM migration
sabose at redhat.com
Mon Apr 8 05:04:17 UTC 2019
On Thu, Apr 4, 2019 at 10:53 PM Jorge Crespo <jorge.crespo at avature.net> wrote:
> Hi everyone,
> First message in this list, hope I can help out as much as I can.
> I was wondering if someone could point out any solution already working
> or this would be a matter of scripting.
> We are using Gluster for a kind of strange infrastructure , where we
> have let's say 2 NODES , 2 bricks each , 2 volumes total. And both
> servers are mounting as clients both volumes.
> We exclusively use these volumes to run VM's. And the reason of the
> infrastructure is to be able to LiveMigrate VM's from one node to the other.
> VM's defined and running in NODE 1, MV files in /gluster_gv1 , this
> GlusterFS is also mounted in NODE2 ,but NODE2 doesn't make any real use
> of it.
> VM's defined and running in NODE 2, MV files in /gluster_gv2 , as
> before, this GlusterFS is also mounted in NODE1, but it doesn't make any
> real use of it.
> So the question comes now:
> - Let's say we come to an scenario where NODE 1 comes down. I have the
> VM's files copied to NODE2, I define them in NODE2 and start them , no
> problem with that.
> - Now the NODE 1 comes back UP , I guess the safest solution should be
> to have the VM's without Autostart so things don't go messy. But let's
> imagine I want my system to know which VM's are started in NODE 2, and
> start the ones that haven't been started in NODE 2.
> Is there any "official" way to achieve this? Basically achieve something
> like vCenter where the cluster keeps track of where the VM's are running
> at any given time, and also being able to start them in a different node
> if their node goes down.
> If there is no "official" answer, I'd like to hear your opinions.
Have you considered oVirt + Gluster hyperconverged solution
It addresses the HA problem that you are after. Let us know.
> Gluster-users mailing list
> Gluster-users at gluster.org
More information about the Gluster-users