Behind The Vblock

 One of the most interesting parts of today’s VCE announcement is the Vblock – pre-integrated infrastructure for virtualization at scale.
 
Today, I thought I’d go behind the scenes, and interview one of the primary architects behind the Vblock – Jim Dowson (EMC Distinguished Engineer & CTO, Global Services).
 
I had the pleasure of hearing Jim and Phil Harris of Cisco (CTO, Strategic Alliances) present the Vblock in detail to one of our partners, and wanted to share some of their insights with you.

Jim, what problem(s) were you trying to solve with the Vblock?
 
Customers have told us that they believe that they can reduce the cost of computing through virtualization, but they are running into obstacles that prevent them from accelerating their deployment.  We wanted to remove those obstacles so that they can fully benefit from the efficiencies that are possible, and we didn’t want them to ‘Nuke & Pave’ their environments in order to get those efficiencies.

It turns out that “Less is the new More’, because by simplifying the architecture, and constraining the solution, you can drive out a lot of the complexity and cost.

It’s interesting to note that we were taking this approach to support a lower cost delivery model for ourselves, for ‘Alpine’ (now Acadia). We needed to be able to provide a price competitive managed service in a highly competitive market – so we built Vblock for ourselves.

There were a number of partners (SPs, Sis and ISVs) that also wanted a best of breed alternative to solutions from other vendors, so we got quite a bit of support and endorsement for the idea.

So, why do you think most customers can’t do this sort of architecture work on their own?

While many can do the work, it’s costly in capital and Non Recurring Engineering (NRE) expense. There is also an ongoing cost to maintain a roadmap for the architecture. For many, the budget for this development work has been been significantly cut, or eliminated altogether.

Customers have told us that they do not see a significant opportunity to competitively differentiate themselves by spending resources experimenting with what have become ‘standard’ components: virtualized x86 systems. They want to get out of IT ‘plumbing’, because that will allow them to focus on things that do bring value to their business, like new application deployment.

It’s also important to note that it’s not just about the technology. You cannot run a virtualized Next Generation Data Center (NGDC) using the same processes that were used in a physical data center – and few customers would have the time or resources to develop those practices.

You have to address the people, process and technology issues in order to get the full benefits.

I remember a great discussion you were having about variable scaling vs. shared resources – can you replay that for us?

We were reviewing two different ways to approach a data center design (both have merits).

The first is central shared infrastructure, which follows the philosophy of “put all your eggs in one basket, and then watch that basket closely” (Andrew Carnegie). This approach requires high resiliency of shared resources, because the failure of a shared resource would lead to a loss of service for dependent consumers of that resource.

The other design option is ‘block step and repeat’. In this approach, there are more (identical) ‘baskets’, and you achieve resiliency through movement of a workload to a different ‘basket’ or ‘block’. This allows more productive assets to be made available for lower cost.

The ‘block’ approach has advantages that include
•    isolation (fault, performance and change impact)
•    re-use of common  design, with well known operating characteristics and failure modes (better supportability)
•    better differentiated service levels, while still providing increased utilization through ‘pooling’
•    better operational practices that lead to better workload balancing and recoverability
•    lower costs by deferring capital purchases to when they are required (Moore’s Law works)

Where do you typically see homegrown architecture-at-scale efforts tend to go wrong?

The challenge is to define units of architecture that are large enough to handle a cost-optimized amount of work. This means that you must design the environment so that all of the resources can be maximally used.

The next challenge is to minimize the number of variations – you need fewer kinds of blocks, with larger pools of those fewer kinds in order to maximize utilization across the whole population.

If you have an environment that is ‘an inventory of one’, you can’t do anything to improve the utilization of that environment – and you’re stuck when it comes to elasticity (workload balancing and dynamic provisioning).

By trying to over-design a single environment, you’re missing the opportunity to optimize your whole data center.

What’s the rationale behind different Vblock models?  Wouldn’t it be ideal if a small one could scale into big one?

Vblocks are primarily differentiated by the class of services that they provide (their service catalog), and the ‘step size’ is defined more by the matching of the components for a given workload at a target cost.  There’s no point to having an out-of-balance system that has too much of one resource to be useful to the system – you’ll actually make things worse.

You grow the environment by adding more identical blocks that are wired once, and migrating workload across Vblocks. This approach is less disruptive to data center operations.

Were there any aspects of the new technology that made a big difference in the results?  For example, converged Ethernet, or perhaps the UCS memory architecture?

FCoE eliminates a significant amount and cost of the components (cables, NICs, ports, fans, power supplies) used to provide connectivity from a blade to the rest of the environment, and you get better utilization of those components through oversubscription. It’s a virtuous cycle, because that also leads to less power, heat and space.

Cisco’s ability to support as much as 4x the amount of commodity SDDR3 RAM on a blade will also allow a greater number of virtual machines to run on a single blade, and virtualization environments tend to be more memory than CPU bound.

I know that there are different schools of thought around laying racks out, airflow, cooling, etc. – what design philosophy did you go with for Vblock, and why?

The nature of the UCS design (front-to- back air flow) reduces power consumption and increases component reliability.

Each Vblock had to be able to stand on its own, with well defined interfaces to the aggregation layer that minimized cabling and dependencies.

You will also see several deployment options, including ‘containerized’ Vblock configurations.

Any other thoughts you’d like to share?

Vblock isn’t a single static thing, it’s a design approach that supports different service catalogs. For example, you will see Vblocks that are optimized for file services, including automated policy-based object level tiering (e.g. EFD, low power SATA or Atmos).

By building more of our intellectual property around Vblocks, we will enable customers to deploy applications more easily without having to do extended science projects to develop infrastructures to support their applications.

There are also significant opportunities to move away from physical appliances to vApps that can be more easily deployed to Vblocks, further increasing flexibility and decreasing costs.

It’s a pretty exciting time in the industry ...

Comments

[Storage guy.com]

If This is EMC's solution to NetApp's Dynamic Data Centre Solution then it looks expensive and disjointed.

Lower costs by deferring payments almost sounds laughable when you look at the costs of VMax and its lack of integration between other EMC products.

Im sure this will create some creative discussion

[Chuck Hollis]

Hi, whoever you are.

My strong recommendation to all posters is to identify your affiliation. In particular, many consider it an ethical breach for an employee of a company, such as NetApp, to masquerade as another individual.

You know, I went through the NetApp DDC pitch in detail, and all I saw was some mid-tier filers. I mean, if that's all you've got as a vendor, that's what you've got to go with.

You're welcome to throw rocks, since that what I expect competitors to do. However, in this case, we've seen enough traction from customers and partners alike that we're pretty confident in the value proposition here.

BTW, there's more to the discussion than just storage :-)

-- Chuck

[Nicholas Orr]

"Cisco’s ability to support as much as 4x the amount of commodity SDDR3 RAM on a blade will also allow a greater number of virtual machines to run on a single blade, and virtualization environments tend to be more memory than CPU bound."

This is all airy fairy theory - when are the practical solutions that I can browse coming?

Practical like:
- has this cpu
- has this amount of ram
- has this many NICs
- has this sort of PCI/PCI-X/PCIe
- has this sort of storage
- all that costs xyz

Would like to see a page/link that shows an actual solution ("V-Block") and how it solves an actual need :)

The concept and theory sounds great - I'm sure the managerial types are excited, however these types aren't the one's that have to figure out how this actually works. It is now like they unpack boxes and plug power cords in etc.

Looking forward to actual practicalities, specifications and details.

Cheers,

Nick
(interested IT guy that enjoys playing with infrastructure)

[John Dias]

Hi Chuck - customer here. Sorry but I don't get it - Vblock is a product or a service? Am I buying infrastructure to plug into my own DC or hosted services or managed services, etc etc... thanks.

[Chuck Hollis]

Hi Nick

A healthy skepticism is always good.

You'll a healthy amount of solutions qualifications from all of us (in addition to what's already out there), but -- frankly -- you won't believe a word of it until you see it running in your own shop, using your own applications.

I'd encourage you to study the data we'll be providing going forward, and see if you want to take the next step.

-- Chuck

[Chuck Hollis]

Hi John

Vblock can be best thought of as an integrated solution stack for efficient virtualization at scale: server, storage, network, hypervisor, management, security, etc.

Whether you decide to consume it as a traditional product, or consume it as a service, is really up to you and your circumstances. Acadia (working primarily through partners) can deliver it a service, or you can buy the integrated platform (again through a partner), or you can get the reference architecture and build one yourself if you choose.

Does this help?

-- Chuck

[Nicholas Orr]

Ok thanks Chuck - so that "data we'll be providing" isn't out yet, that's cool. I trust you'll blog about it when it is. You're in my Feedly for now.

Nick

[Doug Rainbolt]

I think the real merit of this announcement is EMC’s aggressive stand on advancing the ball. Chuck, while you might disagree with my assessment, I see the Vblock designs as stakes in the ground. Speaking somewhat metaphorically, they are carefully expressed opinions about what can work. Granted while the devil is in the details and not much has been disclosed about what exactly in included in each Vblock configuration, EMC is a stickler for details; the careful attention to what works with what is legendary. While EMC assertively advances the ball, I’m sure that customer experience will influence what gets sold and how the offering evolves. Expressing an opinion accelerates conversation and ultimately decisions. Customer decisions and preferences shape vendor opinions and so the cycle continues. Just keep the ball moving.

In looking over the content, I didn’t see any reference to VDI. Perhaps it’s just assumed to be a supported workload in the data center. BTW, is the intention to eventually extend the EMC and Cisco brands to the desktop/thin client/smart phone user experience or keep this transparent?

[Storage guy]

hey Chuck,

I think screening posts around competitive arguements paints EMC in a bad light.

Like i said i am an integrator who does work with EMC, HP, IBM, SUN HDS and NetApp.

[Chuck Hollis]

Storage Guy:

WAKE UP CALL!! I don't screen competitive posts and comments, period.

Go read through the +2000 comments here if you don't believe me. All the various and sundry competitive rants are there, warts and all.

Although they're not particularly interesting.

I tend to screen (a) spam, (b) blatant product pitches, and (c) people who have decided to act in an unprofessional manner, usually with alcohol involved.

I do the latter as a professional courtesy, since they usually regret their actions later.

-- Chuck

[timetoevolve]

Customers and industry leaders want to learn about IT directions when they come to your site, not see a bunch of negative vendor bashing. The vBlock discussion is so much broader than an all in one nas/emulated block storage filer.. Netapp is really struggling to find their relevance here. From the looks of the various posts on yours and other sites, ntap is trying to tell people why vblock is bad and why their disk systems are a complete solution for the cloud. Just like SSDs and deduplication ntap has been caught completely flat footed once again. I'm sure we will see a laundry list of negative posts in the coming week from them either directly, or indirectly (them posing as customers or otherwise).

[Chuck Hollis]

Timetoevolve:

Well said!

-- Chuck

[Vincent Peeters]

What's your opinion about Liquid Computing solution ? it seems to be really close to the VBlock solution : a big blade enclosure with blades building on a high memory capacity, a unified I/O switch and a storage box (here a NetApp solution). In a future version of VBlock, will be there a dedup solution buildin in V-Max (vblock 2) or CX4 (vblock 1) boxes ?

[Chuck Hollis]

Hi Vincent

I think Liquid Computing is aiming at generically the same sort of thing that Vblock is -- a scale-out virtualization appliance. However, a quick check of the specs shows that they're going to have a harder time selling their wares going forward ...

Various forms of dedupe are available today regarding backup (all Vblocks), or specifically with the Celerra found in the Vblock 0. Can't really comment on potential future capabilities, though.

Cheers!

-- Chuck

[Mike Saavedra]

Chuck:

My company will be implementing the vblock architecture/solution soon. I will serving as the PM on the project. Can you point me to someone who has gone through an implementation that can assist in the planning and risk mitigation for the implementation?

[Chuck Hollis]

Mike

Congratulations! Anyone on the VCE team ought to be able to hook you up. I'll send someone your way.

- Chuck