[Openstack] Hello everyone--GlusterFS performance vs CEPH

[Remo Mattei]

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
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.openstack.org/pipermail/openstack/attachments/20140108/4e7475fc/attachment.html>

[Heiko Krämer]

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

Post by Remo Mattei
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.

Post by Remo Mattei
OpenStack Havana: GlusterFS, and what ?improved support? really means

http://www.mirantis.com/blog/openstack-havana-glusterfs-and-what-improved-support-really-means/

Post by Remo Mattei
I will be happy to see what everyone has to say.
Thanks
Remo
_______________________________________________

http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack

Post by Remo Mattei
Post to : openstack at lists.openstack.org

http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack