Thursday, October 22, 2009

Cisco UCS Requires FC To Be Stateless Today

There was a great conversation going on via Twitter yesterday that I wanted to comment on a little further. Sometimes getting things out in the open for "group think" can lead you down some interesting paths. Rod Gabriel was sharing his research regarding UCS and the idea of stateless blades. It all makes sense when you think about it but I just hadn't gone there yet.

In order for UCS to be stateless, you need to "SAN" boot the OS. Local booting of an OS prevents you from a true stateless environment. Since the primary target for UCS appears to be VMware, this means FC is the only way to boot and remain stateless. As Scott Lowe and Paul Richards pointed out, you can PXE boot ESXi but it is still in experimental support. UCS will not iSCSI boot VMware.

As I stated on Twitter, this really disappoints me from a design perspective. The big advantage I see to UCS is the statelessness of the blades but the current requirement for FC to boot ruins much of that value for me. For me personally and my customers, this limits the value of UCS into new clients dramatically.

I haven't installed FC into a new environment in over a year. Most of my new customers choose a server platform local booting and then use an IP based solution to go to storage. In my opinion, UCS will not make much traction into the SMB (Small & Medium Business) market until this changes.

Yes, the market will change and the problem will be solved but until it does, the loss of statelessness decreases a lot of value in my opinion.

I would love to hear your opinion on the subject!

4 comments:

Fridge said...

Aaron,
Thanks for the mention and the summary of our conversation. Been tied up and unable to particpate since last night but it looks like there has been plenty of followup discussion in "Twitterland".

I think your comment about the effect of this on the SMB market is debatable. My thought is that the concept of statelessness is less important to the SMB market as the environment is typically much smaller and more static.

If I buy 2 chassis w/ 10 blades now planning on 18+ months of capacity from that, how important is statelessness? (vSphere deployment by the way). I am thinking that in reality statelessness is nice but not all that important and I can live w/o it for now.

That's my thoughts at the moment, subject to change as I debate this more and continue to noodle on it.

Rod

Brad Hedlund said...

Aaron,
Im a big fan, allow me to raise a few points :)

1) UCS brings a lot more value to the table for SMB other than stateless, escpecially for VMWare. Extended memory, virtualization aware adapters, simplified management & provisioning, to name a few.

2) Support for PXE booting ESX(i) via NFS is a VMware limitation, not UCS which is capable of stateless NFS booting.

3) iSCSI booting in UCS is just a matter of adapters. SMB customers can immediately take advantage of capabilities in point #1, and then move to the environment to stateless when more adapters choices become available.

I'm glad to see you have raised the bar to stateless capabilities in a blade deployment. UCS has made it a more affordable and easier to implement capability than any other system out there.

Cheers,
Brad

Aaron Delp said...

Brad and Rod - Thank you both for your comments!

virtualcloud said...

Aaron and Brad,

I couldn't agree more with both of you however I have a different view of statelessness.

So far today we have been able to achieve either hardware statelessness or software statelessness alone, but never together.

If your SAN has already a LUN carved up and this LUN has already some sort of configuration or OS deployed, then where is the statelessness?

If your OS is already configured with specific settings, then again were is the statelessness?

I have written a comment my blog (http://virtualcloud.wordpress.com/2009/10/26/there-is-no-true-stateless-computing-today) about this about a week ago.

Thanks,
Andre