Bladewatch.com

http://www.cio.com/archive/030107/col_zapped.html

Rising energy costs are short-circuiting performance gains from faster, cheaper servers. Fortunately, there are steps you can take to keep your costs in line.

Server prices are dropping, performance is increasing, and IT is consuming less space. So why is total cost of ownership headed through the roof?

The problem lies deep within the data center, far beneath the radar of most CIOs. While everyone has been focused on smaller, faster and cheaper servers (and their fulfillment of Moore’s Law), almost no one has been watching the expenses associated with powering and cooling them. If this line item isn’t already screaming for your attention, it soon will be. And unless you address the problem head on, no manner of outsourcing, staffing cuts or freezing of capital spending will save your budget.

As the energy costs rise, the need to inform your staff, from the server engineer to the person buying the boxes, that the energy efficiency of the platform matters. There will always be exceptions to the model, but choosing energy efficient models infrastructure doesn’t mean buying slower less effective servers, it means gaining a server that will provide you with performance but not have that offset by high hosting costs.

Energy costs coupled with a lack of investment are both to blame, the energy costs in the typical large corporate are paid for by facilities, as an IT guy, I don’t care, that’s a facility thingy, I just need to know what the capacity is, so that unix box that requires 2500w will eat up the space and power of 8 dl360s, I have to appreciate that. 

In the past though, I think a lot of banks, didn’t realize how much growth in the server estate they were going to see, whether it was the year 2000 project, the windows 2000/2003 migration project, all those legacy servers were supposed to be decommissioned and some were, but a lot were just good enough to get re-allocated, rebuilt and reused. That coupled with ‘normal’ server procurement, new projects/applications or business requirements, meant the datacenter that could hold a few thousand servers looked big but was getting smaller. Add a few applications that need grid computing with racks of blade servers and you can soon see how the datacenter got full, power requirements rose and the game was over, 1watt in for every watt you remove.

Also, I can imagine the response from the CFO/business sponsors:

“Hi, we need more money for the datacenter otherwise we’ll reach capacity in a year or two, can we have some invesment, some capex?” Said the CIO.

“Who’s budget is it coming from?  Not mine right? You’re not asking for more money are you?

Yeah, yeah, I’ll get back to you, a year you say, cool on the phone, will call you right back.. “

No related posts.

Related posts brought to you by Yet Another Related Posts Plugin.