Saturday, June 18, 2005

The Value of Virtualization

Quick edit to my post on virtualization - Information Week published an overview of the market and key drivers recently. It is worth reading.

Utility computing is a hot topic. Companies are spending millions of dollars on VMWare and other virtualization technologies in order to consolidate data center operations and pool IT resource demand. Utility computing and virtualization are reshaping today's data center technologies and operations. Why?

Quite simply, virtualization technologies drive significant improvements in asset utilization by pooling resources across variable demand. By pooling fluctuations in demand, one needs fewer physical resources to meet resource demand. Fewer provisioned resources reduces operating and capital expenses, a good thing:)

The technology industry is borrowing an important operational best-practice from supply chain practioners - that is the pooling of inventory. Why does this work?

It works because averages are additive, while standard deviations are not. This statistical fact drives the benefits of pooling inventory (IT assets), across variable demand for those assets.

In operations, in order to avoid lost sales, supply chain managers pad inventory levels in order to avoid expensive stock-outs. The IT equivalent is to overprovision. Supply chain experts leveraged basic statistics to realize that by pooling inventory one can greatly reduce the amount of safety stock required to adequately meet demand.

How? A simple (VERY) example shows the power of pooling.

Assume two applications, managed independently, with the following weekly demand characteristics:

Application I
Mean Demand 50 servers
Standard Deviation 4 servers

Application II
Mean Demand 50
Standard Deviation 3 servers

If we set safety stock equal to two times the standard deviation, application I needs 58 servers to adequately meet demand (ie with 95% confidence), while application II requires 56 servers. The data center responsible for both applications, in aggregate, overprovisions by 14 servers of "safety stock."

Now if we decide to pool the two applications, we would observe the following:

Consolidated Applications
Mean Demand 100 servers (averages are additive)
Standard Deviation 5 servers, or sqrt(4^2 + 3^2)

Pooling the server demand of the two applications allows the enterprise to reduce server safety stock by 4 units, or by 28%.

For a large enterprise, reduced server safety stock translates into large savings.
Theoretically, 4 servers x 1,000 applications x $5,000 per server (estimate) = $20,000,000

This is an artificial example, but I think it is illustrative of the value of virtualization. It helps me, at least!, tie supply chain management operations theory to high-tech market adoption.

By leveraging enabling technologies to pool spare capacity and statistics (averages are additive but that standard deviations grow by the square root of the sum of the standard deviations in question), IT operators can continue to strip capacity and costs out of the data center while continuing to meet demand.

12 comments:

  1. On first glance, you're missing something. You can, yes, shrink inventory i.e. reduce the number of physical boxes.

    But you seem to forget that a server, once placed in service, is not 'rack and forget' solution. A server costs money to operate; it requires a minimum number of hours a week for administration, maintennance, repairs etc. To some extent some of these costs are minimized if the box is virtual, but most do not.

    There are other factors at work as well; in order to prevent a single hardware failure from taking out x*y servers you need a failover solution of sometime; more money!

    Brian Dunbar
    Liftport

    ReplyDelete
  2. Anonymous3:27 AM

    This argument assumes that there is no correlation in the server demand. I.e. if both applications tend to require demand at the same time, then this argument breaks down. In reality, one would expect that applications have server demand that is somwhat deterministic (and cyclical). This is the main issue, and can't be assumed away. It's basically why you don't see more virtualization than you do.

    ReplyDelete
  3. Hey, I Like your blog here! I'm will bookmark you! I have a mortgage after bankruptcy site, it has alot of valuable information on it and I am considering a blog for comments . I am gathering ideas so any help would be appreciated.Come and check it out if you get time

    ReplyDelete
  4. Blog is informative . Dont't stop. No better time than now to stop poor credit home loan Bad Credit? poor credit home loan

    ReplyDelete
  5. A real enlightening blog. Don't stop now. No better time than now to stop debt consolidation refinance Bad Credit? debt consolidation refinance

    ReplyDelete
  6. A real enlightening blog. Don't stop now. You may be interested in living better without Orange County real estate Learn about purchasing Orange County real estate

    ReplyDelete
  7. This is a excellent blog. Keep it going. This may be of interest to you information about Orange County mortgage refinance Start Planning Orange County mortgage refinance

    ReplyDelete
  8. Your blog is creative Keep up the great work. No better time than now to stop estimate home value How to buy estimate home value

    ReplyDelete
  9. Your Blog. It's nice . Don't miss visiting this site about california mortgage quote New Information california mortgage quote

    ReplyDelete
  10. This is a excellent blog. Keep it going. If you have a mortgage issue, I'm sure you'd be interested in low interest mortgage rate STOP renting low interest mortgage rate

    ReplyDelete
  11. Your blog is creative Keep up the great work. Here's the secrets a lot of people are searching for; low interest mortgage rate Bad Credit? low interest mortgage rate

    ReplyDelete
  12. Blog is informative . Dont't stop. Here's the secrets a lot of people are searching for; home mortgage guide How to buy home mortgage guide

    ReplyDelete