As soon as solid-state storage hit the scene in a big way a few years ago, some people immediately began to contemplate the potential demise of mechanical storage as we knew it. That argument has once again been brought to the table by storage-tracking site Enterprise Storage Forum. Does mechanical storage have anything to worry about, or will SSD’s some day take over?
The article for the most part claims that SSD’s won’t replace mechanical storage, with the main argument being that we’re going to reach a breaking-point where build processes are going to become too small, and too troublesome to deal with. Voltage leakage could affect data stored on a nearby chip, for example, and that’s something that’s obviously going to kill the idea of owning solid-state storage.
That’s true, but that’s not thinking too far out of the box, and assumes that technologies will never improve. When Intel launched its Penryn processors, it introduced the High-k metal gate transistor, which helped to drastically decrease voltage leakage and deliver smooth power delivery, and of course, smooth performance, and a lack of concern for overheating.
I’m not quite sure what it will take to have SSD’s take over mechanical storage, but the fact of the matter is, mechanical storage has been around for ages, while SSD’s as we know them today have been on the marketplace for a mere couple of years. I think we’re way too early in the scheme of things to start predicting what’s going to happen over the next couple of years… the technology simply seems to be accelerating at this point.
I still don’t think mechanical storage is going to go away anytime soon, because let’s face it… $100 for 2,000GB or $100 for 50GB or so is a far stretch, but as SSD’s continue to decrease in price and actually become affordable, everyone is going to want one in their PC. It seems to me like mechanical storage will reach a point where they’re found only in NAS boxes or server PCs for mass storage purposes, maybe not even someone’s own PC.
There are significant challenges to making things ever smaller, which I am not going to address here, but here are a couple of links for further reading: Producing Integrated Circuits With X-ray Lithography and Wikipedia on Electron Beam Lithography. The bottom line is that there are limits to how small things can get with current technology. Flash densities are going to have data density growth problems, just as other storage technologies have had over the last 30 years. This should surprise no one.