Hi Jeff!
Make your calls!  ;-)
 
ESX does support thin-provisioned VMDKs.  They are default in NFS datastores.  You have to use vmkfstools from the command line to create thin-provisioned VMDKs in VMFS.  Either way, when you clone a thin VM in VirtualCenter, it makes a thick clone.
 
There is also thin provisioning on the NetApp side, which some customers are also using successfully (at least one that I know of for over a year).
 
Enjoy!
 
Peter


From: jeff.mery@ni.com [mailto:jeff.mery@ni.com]
Sent: Wednesday, February 13, 2008 11:48 AM
To: Glenn Walker
Cc: Daniel Keisling; Bill Holland; owner-toasters@mathworks.com; toasters@mathworks.com
Subject: RE: De-dup'ing Primary Storage


Like the others, thanks for the info.  At one point, A-SIS wasn't supported in true "production" roles, meaning in a Tier-1 use case.  Has that changed recently?  If so, I think I need to make some phone calls  =).

On the thin provisioning - ESX doesn't support thin-provisioned VMDK's yet.  Workstation does that by default, but I'm not sure about VMware Server.  Hopefully ESX is coming soon though.  I would still imagine a fair amount of reclaimed space once ESX does come through.  While you'll no longer de-dupe the white space in a VMDK, I'd imagine you'll still de-dupe all the base OS commonalities.

Jeff Mery - MCSE, MCP
National Instruments

-------------------------------------------------------------------------
"Allow me to extol the virtues of the Net Fairy, and of all the fantastic
dorks that make the nice packets go from here to there. Amen."
TB - Penny Arcade
-------------------------------------------------------------------------



From: "Glenn Walker" <ggwalker@mindspring.com>
To: "Daniel Keisling" <daniel.keisling@austin.ppdi.com>, "Bill Holland" <hollandwl@gmail.com>, <toasters@mathworks.com>
Date: 02/13/2008 12:37 PM
Subject: RE: De-dup'ing Primary Storage





Just keep in mind that we were using IOMeter to test, not actual real world workloads – we were also very much disk bound in our testing.  If you are neither using IOMeter (ie, a real-world workload) nor disk bound, I can’t foresee it being a huge problem.
 
We’ll be testing with NFS dedupe a bit later today and I’ll gladly share that info if you want.  Same number of disks, so same stipulations exist.
 
And because the question did come up, the VMWare server guy didn’t build the VMDKs with thin provisioning, so it may have also impacted the testing.
 
Glenn
 



From: Daniel Keisling [mailto:daniel.keisling@austin.ppdi.com]
Sent:
Wednesday, February 13, 2008 12:37 PM
To:
Glenn Walker; Bill Holland; toasters@mathworks.com
Subject:
RE: De-dup'ing Primary Storage

 
Thanks for the stats, I'll be de-duping VMWare data soon too.
 
My NetApp storage tech says that read cache peformance will increase since you're reducing the total number of actual blocks.  I have not heard of any performance degradations with A-SIS, other than filer overhead (CPU) when SIS is actually de-duplicating.  My A-SIS schedules are during off-peak hours so it's not a concern of mine.

Daniel

 



From: owner-toasters@mathworks.com [mailto:owner-toasters@mathworks.com] On Behalf Of Glenn Walker
Sent:
Wednesday, February 13, 2008 9:42 AM
To:
Bill Holland; toasters@mathworks.com
Subject:
RE: De-dup'ing Primary Storage

We’ve been doing some VMWare testing with FCP LUNs and A-SIS.
 
We saw a reduction from 471GB to 21GB with only about a 7% reduction in performance.  More than a fair trade-off in my opinion.
 
Our testing could have had impact on the performance more than the de-dupe, however.
 
Glenn
 



From: owner-toasters@mathworks.com [mailto:owner-toasters@mathworks.com] On Behalf Of Bill Holland
Sent:
Wednesday, February 13, 2008 6:50 AM
To:
toasters@mathworks.com
Subject:
De-dup'ing Primary Storage

 
To those of you that have implemented Nearstore and A-SIS on your primary storage:
 
1.  Have you seen any difference in overall filer performance?
2.  If you have LUNs, how are your space savings on those volumes?
 
I know that enabling Nearstore does some system tweaking in the background to increase the number of concurrent backup streams that can be running, but I don't know what else it tweaks that may adversely affect performance of a primary storage system.  Afterall, it was originally designed to run as a secondary storage platform.
 



______________________________________________________________________
This email transmission and any documents, files or previous email
messages attached to it may contain information that is confidential or
legally privileged. If you are not the intended recipient or a person
responsible for delivering this transmission to the intended recipient,
you are hereby notified that you must not read this transmission and
that any disclosure, copying, printing, distribution or use of this
transmission is strictly prohibited. If you have received this transmission
in error, please immediately notify the sender by telephone or return email
and delete the original transmission and its attachments without reading
or saving in any manner.