First off today is reading about SSDs (solid state drives) and where they fit into the network, servers, storage, etc. These things are “quite inexpensive”? $6900 for 320GB, $11000 for 146GB (minimum of 3 required for $33000!), or the bargain basement price of $2000 for just 64GB? Are you kidding? At less than $100 for 1TB hard drives, these things have maybe a use as strategically positioned accelerators for critical services or where cost is no issue. Otherwise, I don’t think the mechanical hard drive has much to worry about.
Next is this little piece about data center retrofit strategies. Doing something different with the data center UPS is a no-brainer, but changing the PDUs? A PDU doesn’t consume any power. Don’t change your data center PDUs expecting your electrical usage to go down from it.
Email or call me or visit the SwiftWater Telecom web site for truly green data center services and data center engineering that makes sense!
Since giving my thoughts on the container data center on 11/01, I was interested to see these Microsoft container data center pictures today. The interesting thing to me is that the second floor of the facility is all traditional rackmount servers in cabinets on raised floor and that only 2/3 of the servers in the facility will be containerized. Kind of puts a crimp in the idea that anyone who runs anything except container is hopelessly old fashioned (I don’t suspect Microsoft would do the raised floor area if there wasn’t a darned good reason).
Next up is running biodiesel in your backup generator. Not the best idea to risk your reliability by doing this without extensive testing to characterize the behavior of the fuel under all environmental conditions, as well as the potential it might eat your generator.
Last on the list is reading about considerations for deploying SSD disks. At 10X the price of traditional hard drives, it’s not that hard to work these into a server refresh schedule and see a reasonable ROI for them. This is a sharp contrast to the 320GB $7000 PCIe units that I wrote about some time back, which have zero chance of showing a payback before the server is ready for refresh.
Vern, SwiftWater Telecom
There’s been a lot of talk lately about using SSD (solid state drive) for data center servers. After reading this article, I have to question how practical some of this is.
There’s no denying that SSDs consume far less power than conventional HDDs, can provide better performance, and can consume less space too. Consuming less power results in less waste heat to remove from the data center and that’s not a bad thing either. The problem is, do the economics work?
In the example given, MySpace switched to PCIe based SSD drives. This effectively allowed them to recover 50% of the physical space in their congested data center by reducing the size of their rackmount servers from 2U to 1U. It sounds good, but does it all add up?
First, the article states that they only required 2 380GB drives per machine. The DL380 servers they replaced are 2U with 6 drive bays. This shows that they were wasting the capacity of the DL380s in the first place. It’s always good to use your space more efficiently, but this isn’t attributable to the change to SSD, just correcting sloppy engineering.
Second, they replaced standard drives retailing for under $100 each with proprietary hardware of the same size for ***$7000*** each. That’s ***$14,000*** per server, plus the price tag for the new DL160 server. Figure that as $15,000 + per server. They spent 70x the cost to gain a 50% energy saving on a relatively small part of the server.
There are far more productive ways to green a data center. Leave the “gold plated” SSDs to those with more money than sense.
Vern, SwiftWater Telecom
data center facility engineering