[Openstack-operators] KVM live block migration: stability, future, docs

Blair Bethwaite blair.bethwaite at gmail.com
Tue Aug 7 23:05:19 UTC 2012

Hi Pete,

(Apologies for top posting)

Yes, we've been talking to an APAC RedHat storage solution architect. I
don't want to finger him directly on list though, so please follow up
privately if you want to make contact.

To clarify, the advice has been that this is not a recommended workload,
and that RHS is more suitable for scale out "near-line" and blob storage.
That's not to say that this workload wouldn't be supported, just that it
may result in poor random IOPS performance (which is what we've seen in
early testing with open source Gluster). Note, e.g., that currently only
RAID5/6 is supported for the underlying bricks in a RHS system, so you
start out with worst case write IOPS in your LVs.

We are still talking to RedHat about alternatives and will probably still
test Gluster or RHS at scale as time permits. The constraints of this
project (NeCTAR research cloud) make broader RedHat solutions difficult to
integrate, e.g., our hypervisors must run Ubuntu. Live block migration
looks like a reasonable option for the moment though.

-B (sent via my pocket)
On Aug 8, 2012 7:01 AM, "Pete Zaitcev" <zaitcev at redhat.com> wrote:

> On Tue, 7 Aug 2012 22:57:17 +1000
> Blair Bethwaite <blair.bethwaite at gmail.com> wrote:
> > It's interesting to note that RedHat do not recommend using RHS
> > (RedHat Storage), their RHEL-based Gluster (which they own now)
> > appliance, for live VM storage.
> Do you have a reference for this claim?
> -- Pete
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.openstack.org/pipermail/openstack-operators/attachments/20120808/30e5bbe1/attachment.html>

More information about the OpenStack-operators mailing list