[Openstack] Storage Multi Tenancy

jeroen jeroen at mediacaster.nl
Mon May 19 13:51:53 UTC 2014


Where do you define the scheduler filters? I’ve found something about them in the cinder.conf config example but when I define one zone by doing this;


I don’t get to see this in Horizon after restarting the services.

Best Regards,

Sent with Airmail

On 16 May 2014 at 22:50:21, Nirlay Kundu (nirlay at hotmail.com) wrote:

This can be done the following way : Since Cinder scheduler allows you to set multiple filters, you could potentially use one of the filters, say ‘availability zone’ for this. Essentially create a different availability zone for each storage pool – one for ceph cluster, one for tenants own pool, etc. and specify it during nova boot to ensure the appropriate pool/availability zone is selected.
There are storage based options for multi-tenancy that built natively into storage arrays like HP's 3Par. You can try that.
Hope this helps.

Date: Fri, 16 May 2014 16:14:34 +0200
From: jeroen at mediacaster.nl
To: openstack at lists.openstack.org
Subject: [Openstack] Storage Multi Tenancy


Currently I am integrating my ceph cluster into Openstack by using Ceph’s RBD. I’d like to store my KVM virtual machines on pools that I have made on the ceph cluster.
I would like to achieve to have multiple storage solutions for multiple tenants. Currently when I launch an instance the instance will be set on the Ceph pool that has been defined in the cinder.conf file of my Openstack controller node. If you set up an multi storage backend for cinder then the scheduler will determine which storage backend will be used without looking at the tenant. 

What I would like to happen is that the instance/VM that’s being launched by a specific tenant should have two choices; either choose for a shared Ceph Pool or have their own pool. Another option might even be a tenant having his own ceph cluster. When the instance is being launched on either shared pool, dedicated pool or even another cluster, I would also like the extra volumes that are being created to have the same option. 

Data needs to be isolated from another tenants and users and therefore choosing other pools/clusters would be nice. 
Is this goal achievable or is it impossible. If it’s achievable could I please have some assistance in doing so. Has anyone ever done this before.

I would like thank you in advance for reading this lengthy e-mail. If there’s anything that is unclear, please feel free to ask.

Best Regards,

Jeroen van Leur

Sent with Airmail

_______________________________________________ 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
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.openstack.org/pipermail/openstack/attachments/20140519/d3289dba/attachment.html>

More information about the Openstack mailing list