SSD Latency, Error Rates May Spell Bleak Future

Lucas123 writes "A new study by the University of California and Microsoft shows that NAND flash memory experiences significant performance degradation as die sizes shrink in size. Over the next dozen years latency will double as the circuitry size shrinks from 25 nanometers today, to 6.5nm, the research showed. Speaking at the Usenix Conference on File and Storage Technologies in San Jose this week, Laura Grupp, a graduate student at the University of California, said tests of 45 different types of NAND flash chips from six vendors using 72nm to 25nm lithography techniques showed performance degraded across the board and error rates increased as die sizes shrunk. Triple-Level NAND performed the worst, followed by Multi-Level Cell NAND and Single-Level Cell. The researchers said MLC NAND-based SSDs won't be able to go beyond 4TB and TLC-based SSDs won't be able to scale past 16TB because of the performance degradation, so it appears the end of the road for SSDs will be 2024."

Comments

SSD =/= NAND Flash

[MischaNix]

There will be other solid-state storage solutions. The only reason NAND is currently used is its relative cheapness and reliability.

In other news...

[Troyusrex]

An old study (well, executive) showed that there was a world wide demand for "maybe 6" computers. This might all be true at current technology levels but technology will have changed an awful lot by 2024.

Re:In other news...

[Kjella]

Yeah, on the other hand a lot of people seem to have heard Moore's law so many times they're starting to think there's an actually law that computers will improve at some crazy rate. That we can just go infinitely small, infinitely fast, infinitely everything. Not simply that there might be a way around it, but that there must be a way around it. It's one thing to use it estimate that 128 bit encryption should at least be good for another X years, quite another to blindly assume that in X years then we will as a matter of fact be able to do it.

My first computer, a Commodore 64 ran at 985 kHz (PAL version) and for a while it just went up, up and away until we hit 1 GHz. Extrapolating we should be at 100+ GHz by now and closing in on THz processors. That's not going to happen, the way it looks now we'd be lucky to see a 10GHz processor if at all that. Of course we've done more cores and higher IPC and all that, but they all reflect that we can't just bump clock speed anymore. We're starting to see the same with graphics cards, they can give you more shaders but each shader is running into the same wall single threaded CPUs did.

Process die shrinks will start hitting atom size issues in the 2020s, where it's just not physically possible to go smaller. There are exotic theories but they're of the "flying car" variety, they certainly have very little to do with conventional processors that we've used for the last 30 years. So if we can't go faster and we can't go smaller, well we might be stuck. Another issue is power, how far down can you bring performance/watt? You battle leakage with SOI and 3D transistors and whatnot, but fundamentally process improvements don't give nearly the amount of "free" power drop it used to.

On the other hand, people have been saying Moore's "law" is coming to an end now for ages, and I'll be happy for every round of improvements we manage to squeeze out of it. But I'm not going to be surprised when the end comes.

Not bleak at all

[Anonymous Coward]

From the article, "This will reduce the write latency advantage that SSDs offer relative to disk from 8.3x (vs. a 7 ms disk access) to just 3.2x.". Yeah, doom and gloom.

Re:Not bleak at all

[Joehonkie]

Exactly, this quote at the end says it all: "However, even with TLC flash at 6.5nm, Grupp calculates that SSDs will continue to outperform hard disk drives on throughput, 32,000 IOPS to 200 IOPS, respectively."

Re:Sounds legit

[maxwell demon]

We already have the breakthrough, but it's not Flash, it's PRAM.

And MRAM. And FeRAM.

Re:Just add more

[Surt]

It costs money to stack. At a much higher rate than it does to scale. Or at least that has been the case. It will be a significant hit to the industry when they can no longer count on device scaling to help bring up density, and get forced to wire multiple chips in ever expanding arrays.

Re:Sounds legit

[parlancex]

Well, to start with you can make an SSD as big as you want by taking smaller SSD's and chaining them together with an intelligent front-end.

I could do the same thing with a bunch of 80 GB hard disks, but I'd rather just buy a 2 TB one and run that instead.

Did you know that your hard disk is actually already made out of multiple platters with smaller capacities that make up the whole transparently? Your RAM is made up of dozens of individual smaller chips that make up the total capacity, and so are existing SSDs and USB flash memory sticks.

Kids these days.

Re:NAND Successor

[WuphonsReach]

Prices haven't dropped in a couple years.

Prices are now down to about $1.50/GB for standard 2.5" SSDs. And you can sometimes find them for $1.25/GB. That's lower then the $2.50-$3.00 of 18-24 months ago.

Sure, it's expensive compared to the $0.10/GB of bulk storage like 1/2/4TB drives, but when you compare it to things like 10k RPM SATA/SAS and 15k SAS (about $1/GB) it starts to not look so expensive. The only things that make me nervous about them is that SSDs still have some controller issues and it's a younger technology compared to traditional hard drives.

At $1.50/GB, that means you can purchase a 120GB SSD for about $180. For a lot of people, that's big enough and cheap enough in exchange for vastly improved performance. And if you can keep the users from storing stuff locally, you could go with one of the 64/80GB units which are in the $100-$125 range.

I've converted a few users over to SSD over the past 2 years. It's been worth the money every time. The machines are far more responsive to user input, they don't sit there and spin, and it generally means that the CPU starts being the bottleneck again. Not all of these are power users, either.

I paid about $1.75/GB for my 250GB SSD. Do I wish it was bigger? Sometimes. But it turned a 4-year old laptop from something that I hated using due to the slowness of the old 500GB 5400 RPM hard drive into something that is fast and responsive. For work it made me much more productive.

Re:Sounds legit

[AK Marc]

The ironic thing about aluminum is that it was named aluminum by an Englishman who named it in the US, then, when the information was sent across the ocean, the other Englishmen figured it had to be an error. He wanted the base to be "alum" and making that metallic from the standard becomes alumium, not aluminium. So either way, the British spelling/pronunciation is wrong on all counts. The rule was clear at the time, the discoverer gets to name it, and the British refused to honor that tradition and re-named it (incorrectly at that). Not that I know what he was thinking, but perhaps he thought of alumium first and didn't like the sound, so he added in another "n" to "improve" it. If the British pedants wanted to "fix" it, it would seem to me to be simpler (and closer to the rightful namer's intentions) to have re-named it alumium instead.