I think he's still missing the boat.
In response to some counterarguments from Charles Zedlewski and John Clingan, Carr says:
Both argue that if servers become more efficient (through virtualization, for instance), then companies will tend to buy more of them, not fewer. If a product becomes more valuable, after all, you'll want more of it. That's a great point (for unit sales, if not for revenues), though I'm not sure it applies in this case. It's important to remember that what's really being consumed is computing cycles, not servers; through consolidation and virtualization companies may both consume a lot more cycles and buy a lot fewer boxes.
I don't think Carr gets the point at all. He makes a great realization ("what is being consumed is compute cycles"), but he doesn't really follow through with the thought.
The history of computing has shown very, very consistently: the consumption of compute cycles is on an ever-increasing path. Why? Because the faster computers get, the more uses people find for them. Carr seems to be implying that we have finally reached a point that our servers are doing everything they could possibly do: from here on out, making them faster will just diminish the number of servers we need.
He writes "companies may both consume a lot more cycles and buy a lot fewer boxes," but his argument sounds more like "if the number of cycles they need doesn't increase too much, they'll be able to buy fewer boxes." That would doom the server market indeed.
But that's not what happens with computers. Computers get faster. With each increase in speed, incredible new uses are found. They tax the machines. They need faster ones. Repeat.
Virtualization is another great use for machines--but it won't keep software developers from innovating, and it won't keep companies from inventing new, faster servers. Those things will continue to happen.
Moreover, Carr keeps blurring utility computing into his argument. Quoting Frank Sommers, he says:
And with standard application interfaces, such as J2EE, shouldn't a company's IT department be able to deploy an enterprise app into a remote data center's hosting environment?Ah, there's the rub. There is no one standard. As I pointed out earlier, computes are not all alike.
While I believe strongly that there is a market for selling computes and for data centers, there is no way that will doom the server market.
And one last point to show that, while electricity is not computes, even the electricity analogy doesn't spell doom for the server companies. There was tremendous consolidation in the electric power industry when the idea of a "power plant" came about. But did that kill the industry that manufactures generators? No--there are still companies making billions of dollars manufacturing power generation equipment (I used to work for one of them). There is still tons of research going into ways to make power better.As I said before: the server industry isn't doomed. It's evolving.
Is it the generator business you should be looking at, or the waterwheel business? Before electric utilites took over, factories had to create their own power, but a lot more were using water or steam power than electric power at that point. If you were a waterwheel maker, you were screwed.
ReplyDeleteTrue enough! As I said, the analogy fails (and then I attempted to belabor it). But the fact is: manufacturing generation equipment is a multi-billion dollar industry.
ReplyDeleteAnother fact: the more electricity we get, the more we find uses for it, and the more we need. That also reminds me of our needs for compute cycles.
I'm not arguing that things won't change (or that server mfgs that don't change won't be in serious trouble)--things will change. People will take advantage of virtualization and distributed computing. SOA, SaaS, and even computes-by-the-hour will have huge effects on how we use computers (and therefore what those computers are shaped like).
But "utility computing" will never replace server sales. Data centers will need more computes than ever. Many, many businesses will need to buy servers (and won't have the desire to put them together ala Google or buy them from a nameless manufacturer halfway around the world).
IOW--the server market isn't "doomed."
Lastly, Nick--I very much enjoy your writing, and I enjoy the debate even more.
Thanks, Dan.
ReplyDeleteRe: "But 'utility computing' will never replace server sales." I sincerely think you're wrong there. We can debate how many server sales it will replace, but it will certainly replace some. Take Salesforce.com, for example. If all the firms subscribing to its CRM service instead bought their own servers to run their own licensed on-premise CRM apps, I guarantee you the total number of servers required would be more than the number Salesforce runs in its multitenant setup. Any way you look at it, that's an example of utility computing replacing server sales. And it will become more common.
No argument there--Salesforce.com results in fewer servers running CRMs. But has it resulted in fewer server sales? Or are companies finding new things to do with servers?
ReplyDeleteMy view is this: we will always find new ways to use computers. Even SaaS can result in more server sales, if people are buying SaaS that they wouldn't have implemented themselves. But, more than that, five years from now companies will be buying servers to implement applications we haven't even thought of yet.
Am I wrong? Who knows? Only time will tell. I'll repeat what I said earlier--the market certainly will change. If server manufacturers want to avoid "doom," they'll have to change with it.
Anyway, thanks for the thoughts. I see you've got a new post up about scalability (one of my favorite subjects)--I'm off to digest that one!