Richard Sawyer, director of data center technology for West Kingston, R.I.-based American Power Conversion Corp....
By submitting your personal information, you agree that TechTarget and its partners may contact you regarding relevant content, products and special offers.
(APC), knows data center management. As a former data center manager, Sawyer saw first hand the challenges involved with the profession. And now at APC, he works with customers' IT staff to get a handle on infrastructure issues. In a recent phone interview, Sawyer detailed some of the pressures data center managers are facing.
What are the biggest issues data center managers are dealing with?
Richard Sawyer: First, it's dealing with the change in the IT infrastructure to new technologies -- trying to get new blade servers and storage devices into existing data centers. The second issue is that the expectation [from C-level executives] for IT's response time to business changes is getting more compressed. Third is trying to maintain a stable data center environment while dealing with these new technologies and business pressures. Those tend to be the first three that they talk about.
Energy efficiency in the data center has come up a lot recently. Has IT evolved to the point where it can consider energy efficiency without sacrificing uptime or performance?
Sawyer: Yes. A lot of the new equipment is getting more and more efficient. The Delta conversion products we use for our large scale [uninterruptible power supply] systems are extremely efficient. They're 95% efficient down to very low load levels. Even at a 25% load level, we're running about 94% efficient, as opposed to the old legacy style systems that were 60%-70% efficient.
With the cost of electricity increasing like it is -- a kilowatt hour going from $0.08 up to $0.13 per kilowatt hour in the Northeast-- it becomes a major factor. For a one megawatt load (1,000 kilowatts), to supply that system with electricity costs close to $1 million per year. That's a million dollars you can't spend on IT equipment. Even an efficiency difference of 10% works out to $100,000 per year. That buys a lot of IT applications or head count in your division. It's becoming a larger factor in the total cost of ownership. Obviously, the more efficiency you can put in, your ongoing expenses become more manageable.
How much of an impact does the green buildings movement have on energy efficiency in the data center?
Sawyer: Data centers tend to be the place of the highest power density in a building. It's only a matter of time before it gets on people's radar. We're pushing now to make people aware that energy efficiency in the data center has a much bigger impact on the building's overall efficiency than efficiency in the lighting system or the cooling system.
Is this an IT issue or something that's being handed down by C-level executives?
Sawyer: The C-level executives are being put under more pressure to be part of the business operation. The C-level people are putting pressure on technology to get more efficient, process more data cheaply. You have to cut your costs.
That drives initiatives like consolidation. If you have 10,000 servers that are only 20% utilized, can't you get by with 2,000? The answer is probably no. But you might be able to get by with 4,000 and cut your cost in half on the equipment side. And then you start to look at not only the capital investment, but also the expense investment. How many servers can one technician service? If they're consolidated, he can service a lot more than if they're spread out all over the place. The second thing you look at is your infrastructure costs, and electricity is a large part of that.
So it is coming from the top down. The average IT guy is worrying about his standard set of servers, and he isn't paying much attention to the electricity. But when the bill hits the top-of-the-line desk, if you can save 10% off that, that's an awful lot of money.
Is there anyone else in IT doing something particularly interesting to you?
Sawyer: I was just down at a Linux cluster computing convention at the University of North Carolina. [Clustering] allows a company to utilize their processing capacity at a much higher utilization rate. That's going to be big, because it cuts down not only on the amount of equipment you need to buy, but also the amount of applications you're going to be running.
What we're seeing is that arrays of blade servers are doing the work of mainframes. I read an article a little while ago that said the fourth fastest computer in the world is an array of eServers from IBM in Barcelona, Spain. The idea of getting the maximum amount of value out of your IT investment is not only driving consolidation, but it's driving the way the applications are being run on the computers themselves.
Let us know what you think about the story; e-mail: Matt Stansberry, News Editor