Mailing List Archive: OpenStack: Operators

KVM live block migration: stability, future, docs

Index | Next | Previous | View Threaded

blair.bethwaite at gmail

Aug 6, 2012, 4:56 PM

Post #1 of 4 (459 views)
Permalink

KVM live block migration: stability, future, docs

Apologies for any duplicates, signed up to the list with the wrong
address initially...
---

Hi all,

KVM block migration support in OpenStack
(https://blueprints.launchpad.net/nova/+spec/kvm-block-migration)
seems to be somewhat of a secret - there's almost nothing in the
docs/guides (which to the contrary state that live migration is only
possible with shared storage) and only a couple of mentions on list,
yet it's been around since Diablo. Should this be taken to mean it's
considered unstable, or just that no-one interested in documenting it
understands the significance of such a feature to deployment
architects? After all, decent shared storage is an expensive prospect
with a pile of associated design and management overhead!

I'd be happy to contribute some documentation patches (starting with
the admin guide) that cover this. But first I'd like to get some
confirmation that it's here to stay, which will be significant for our
own large deployment. We've tested with Essex on Ubuntu Precise and
seen a bit of weird file-system behaviour, which we currently suspect
might be a consequence of using ext3 in the guest. But also, there
seems to be some associated lag with interactive services (e.g. active
VNC session) in the guest, not yet sure how this compares to the
non-block live migration case.

We'd really appreciate anybody actively using this feature to speak up
and comment on their mileage, especially with respect to ops.

I'm slightly concerned that KVM may drop this going forward
http://www.spinics.net/lists/kvm/msg72228.html), though that would be
unlikely to affect anybody deploying on Precise.

--
Cheers,
~Blairo

_______________________________________________
OpenStack-operators mailing list
OpenStack-operators [at] lists
http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-operators

zaitcev at redhat

Aug 7, 2012, 2:00 PM

Post #2 of 4 (438 views)
Permalink

Re: KVM live block migration: stability, future, docs [In reply to]

On Tue, 7 Aug 2012 22:57:17 +1000
Blair Bethwaite <blair.bethwaite [at] gmail> 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

_______________________________________________
OpenStack-operators mailing list
OpenStack-operators [at] lists
http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-operators

blair.bethwaite at gmail

Aug 7, 2012, 4:05 PM

Post #3 of 4 (435 views)
Permalink

Re: KVM live block migration: stability, future, docs [In reply to]

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.

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

> On Tue, 7 Aug 2012 22:57:17 +1000
> Blair Bethwaite <blair.bethwaite [at] gmail> 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
>

blair.bethwaite at gmail

Aug 8, 2012, 5:00 AM

Post #4 of 4 (432 views)
Permalink

Re: KVM live block migration: stability, future, docs [In reply to]

Regarding RHS, there is also this: http://www.tonian.com/wordpress/?p=32

On 8 August 2012 09:05, Blair Bethwaite <blair.bethwaite [at] gmail> wrote:
> 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.
>
> Cheers,
> -B (sent via my pocket)
>
> On Aug 8, 2012 7:01 AM, "Pete Zaitcev" <zaitcev [at] redhat> wrote:
>>
>> On Tue, 7 Aug 2012 22:57:17 +1000
>> Blair Bethwaite <blair.bethwaite [at] gmail> 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

--
Cheers,
~Blairo

_______________________________________________
OpenStack-operators mailing list
OpenStack-operators [at] lists
http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-operators

Index | Next | Previous | View Threaded

Interested in having your list archived? Contact Gossamer Threads