I was reading Heather Clancy’s blog over on ZDNet, where she asks “Will 2011 bring an enterprise SSD adoption breakthrough?” http://www.zdnet.com/blog/green/will-2011-bring-an-enterprise-ssd-adoption-breakthrough/15955?tag=zd-left
I hope so. It would be one step closer to my personal Holy Grail (insert gratuitous Monty Python reference here).
I yearn for the day when all storage, temporary (ie: RAM) and persistent (ie: disk), are merged into a single entity and a single technology. It would increase scale and lower costs.
It would be wicked fast. There would be no need to read data from disk and write to memory… it would already be there, effectively reducing persistent storage I/O to zero.
Not only could persistent storage be virtualized and dynamically re-provisioned among different systems, RAM could be virtualized and dynamically re-provisioned among different systems. Think of it as a RAM SAN instead of a DISK SAN.
Oh, yeah… the only way I can see to have truly “instant on”. The operating system, device drivers, applications, et cetera won’t need to be loaded into RAM. Forget about the magic of 30 second boot times. Think 30 nanoseconds.
Add a dash of Moore’s Law (twice as much, half the price, every 18 months until you hit the limits of physics) and this technology has a very, very bright future.
But the technology isn’t there yet. SSDs cost 10x as much. Even with 400% better storage efficiency (see reference in Ms. Clancy’s post) through data de-duplication and compression (technologies that are also available for traditional “spinning disk”), the cost is approximately $8000 per effective terabyte or about $8 per effective gigabyte.
You can read an SSD roughly forever, but you can only write to a particular segment of data so many times before that segment becomes read-only.
SSDs are too new to have any factual, usage-based data to back up their MTBF – Mean Time Between Failures numbers. We have an idea of how long they are going to last, but no hard facts. I’d like the technology to have a little history before I’m going to bat to spend 10x as much as competing technology.
What happens when an SSD fails? For example, with a standard RAID5, RAID6 or RAID10 array, I switch to a hot-swap drive (and deal with some performance degradation as a mirror is rebuilt or parity calculations occur) or swap out the bad drive with a cheap replacement.
How much is it going to cost when an SSD fails? Come to think of it, what does an SSD failure look like? Not only do you have to worry about an SSD transforming itself to a read-only device, you have to worry about an SSD becoming completely unresponsive (like a traditional hard drive head-crash or stepper motor failure). How will industry deal with the first, and what are the circumstances under which the second can happen?
Lots of questions, not a lot of answers yet. But very exciting all the same.