[Openstack] Hello everyone--GlusterFS performance vs CEPH

Heiko Krämer info at honeybutcher.de
Thu Jan 9 09:34:18 UTC 2014


Hi Remo,

we're using glusterFS in production env and without bigger problems
until now :).
The glusterFS 3.4 is stable and have some features for autohealing and
rebalancing. In addition the native support in qemu 1.7+ for more
performance throughput have increased the I/O for ~20%.

I need to say, we don't use it for all instance images (root or/and
ephemeral) it's only for persistent storage like databases, logs ... in
all running instances.

I think the 'improved support' which Mirantis means is the native
support of qemu.


I hope it helps.

Cheers
Heiko


On 08.01.2014 20:51, Remo Mattei wrote:
> Hello everyone, 
> while back some people were saying that the performance of GlusterFS
was not acceptable in OpenStack. I have found this article and I wonder
if anyone has had the opportunity to see if this has really improved.
>
> OpenStack Havana: GlusterFS, and what “improved support” really means
>
>
http://www.mirantis.com/blog/openstack-havana-glusterfs-and-what-improved-support-really-means/
>
> I will be happy to see what everyone has to say.
>
> Thanks
>
> Remo
>
>
> _______________________________________________
> Mailing list:
http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack
> Post to : openstack at lists.openstack.org
> Unsubscribe :
http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack






More information about the Openstack mailing list