[openstack-dev] Proposal for dd disk i/o performance blueprint of cinder.

Fox, Kevin M Kevin.Fox at pnnl.gov
Thu Jan 16 00:00:37 UTC 2014

What about a configuration option on the volume for delete type? I can see some possible options:

* None - Don't clear on delete. Its junk data for testing and I don't want to wait.
* Zero - Return zero's from subsequent reads either by zeroing on delete, or by faking zero reads initially.
* Random - Write random to disk.
* Multipass - Clear out the space in the most secure mode configured. Multiple passes and such.

From: CARVER, PAUL [pc2929 at att.com]
Sent: Wednesday, January 15, 2014 2:59 PM
To: OpenStack Development Mailing List (not for usage questions)
Subject: Re: [openstack-dev] Proposal for dd disk i/o performance blueprint of cinder.

Chris Friesen [mailto:chris.friesen at windriver.com] wrote:

>I read a proposal about using thinly-provisioned logical volumes as a
>way around the cost of wiping the disks, since they zero-fill on demand
>rather than incur the cost at deletion time.

I think it make a difference where the requirement for deletion is coming from.

If it's just to make sure that a tenant can't read another tenant's disk then what
you're talking about should work. It sounds similar (or perhaps identical to) how
NetApp (and I assume others) work by tracking whether the current client has
written to the volume and returning zeros rather than the actual contents of the
disk sector on a read that precedes the first write to that sector.

However, in that case the previous client's bits are still on the disk. If they were
unencrypted then they're still available if someone somehow got ahold of the
physical disk out of the storage array.

That may not be acceptable depending on the tenant's security requirements.

Though one may reasonably ask why they were writing unencrypted bits to
a disk that they didn't have physical control over.

OpenStack-dev mailing list
OpenStack-dev at lists.openstack.org

More information about the OpenStack-dev mailing list