Why SSDs Won't Replace Hard Drives 315
storagedude writes "Flash drive capacities have been expanding dramatically in recent years, but this article says that's about to change, in part because of the limits of current lithography technology. Meanwhile, disk drive densities will continue to grow, which the author says will mean many years before solid state drives replace hard drives — if they ever do. From the article: '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. And the lithography problem for flash doesn't end there. Jeff Layton, Enterprise Technologist for HPC at Dell, notes that as lithography gets smaller, NAND has more and more troubles — the voltages don't decrease, so the probability of causing an accidental data corruption of a neighboring NAND goes up. "So at some point, you just can't reduce the size and hope to not have data corruption," notes Layton.'"
Selective evolution (Score:4, Insightful)
Yeah, there's NO way that SSD technology will somehow evolve further than it has till now. It's after all SEVERAL years old by now!
Lets wait and see (Score:5, Insightful)
While the reasoning is interesting, and valid for all I know, why are we trying to say some bit of technology isn't going to work out ever? What's the point? Either it won't work out and that will be something the market will handle independent of whether you foresaw it or not, or a solution will be found and you'll just be wrong.
I'm reminded of an Arthur C. Clarke quote: "When a distinguished but elderly scientist states that something is possible, he is almost certainly right. When he states that something is impossible, he is very probably wrong."
Re:There are always more axes of improvement... (Score:3, Insightful)
Newer solid state memory technologies. If you can get something more durable and faster than NAND at the lithographies we're headed towards, you'll be able to expand capacity without having to jam tons of extra chips in for bad block swapouts and having to pack killer levels of ECC.
Do we always need more space ? (Score:1, Insightful)
Sure classical HDD will soon reach 5TB but do we need always more space ? With online storage, online music and videos maybe we will not need that big disks and just enjoy fast silent SSDs.
Re:There are always more axes of improvement... (Score:3, Insightful)
Correct. (Score:5, Insightful)
The bottom line is that there are limits to how small things can get with current technology.
They're right, SSDs won't replace hard drives with the current technology. If only we had a way to improve technology over time!
Expanding drives (Score:3, Insightful)
Like I said, the only place where I can see the large capacities being needed is behind the scenes on a server or similar device, in which case hard disks aren't much of a problem. On consumer computers, I'm pretty sure they're going to catch on.
Re:Who cares about replacing ALL hard drives? (Score:2, Insightful)
Not just density (Score:3, Insightful)
It's economic feasability, too. Rotating media is roughly $100/terabyte, it's gonna take more than one breakthrough for SSD to come close to that.
Nifty new technology doesn't get bought because it's nifty-new, it gets bought because it fills the need better than its predecessor for the price.
And YES there are plenty of applications where multiple terabytes are necessary, maybe not on your home system.
In case you're wondering, I have both on my system: / is SSD, /home is multi-terabyte RAID. Rotating mechanical media is sticking around at least for now.
Solid state densities (Score:5, Insightful)
I know, someone's gonna lecture me on how this isn't at all a fair comparison...
Limitations aren't the tech of the NAND chips... (Score:4, Insightful)
To wit, who honestly has a larger than 1TB disk inside their machine right now? I'd imagine not terribly many, as a percentage of all computer owners. Indeed at home I have twin 700-ish GB Caviar Blacks in a RAID 1 configuration, of which I'm using maybe 30% of their capacity.
TFA doesn't actually make any arguments about price directly. It indirectly suggests price of the drives is related to lithography resolution, but provides nothing to back that up.
It seems to me that over time as yields on current technology increase and fab costs are recouped, the price of current technology will go down.
So if we can make a 1TB disk today, it'll be the same 1TB disk in a year or two, except less expensive, probably faster, and probably more reliable.
replace hardrives WHERE (Score:3, Insightful)
Some context would be nice. It may be that SSDs end up replacing conventional hard drives on, say, all laptops. Or all personal desktops that don't also double as servers. Or we may see a two-tier situation develop where SSDs are used for day-to-day operations in the enterprise and hard drives used for storing backups, or storing infrequently accessed archival data.
Re:There are always more axes of improvement... (Score:3, Insightful)
Storage Space isn't always the limiting factor...
Storage Size has been growing faster then our ability to fill it.
I Remember back in them good old days where I filled up Hard Drives quite easily. My old 80 Meg drive when it was new, could be filled up rather quickly.
Now that we have terabytes drives it is getting less of a factor to fill it up. Combined with the fact that network speeds are getting faster our need for storage is being limited. Sure RMS Followers thing that Cloud SaaS solutions will doom us all and that rest of that nonsense... However If it is faster to download a file then get it off your drive then you will just download and run the program off the network.
So the issue isn't about the size of the drive but the speed of the drive that counts.
I predict (Score:3, Insightful)
Re:Do we always need more space ? (Score:5, Insightful)
Re:Expanding drives (Score:4, Insightful)
Sure, but you already can't store significant scientific datasets on consumer-grade equipment. Nobody's saying that hard drives will cease to exist, but it's quite possible that SSDs will displace them in consumer-grade machines, the kind normal people buy.
Re:Expanding drives (Score:4, Insightful)
You sound like me when I got my first 250MB drive. Shit! This will last me forever!
And it would have if I had kept running DOS.
Re:Lets wait and see (Score:2, Insightful)
So its future technology that will enable this to happen - but on HDD, because they are currently cheaper. How can that be valid reasoning?
Re:Do we always need more space ? (Score:5, Insightful)
The problem with "online" storage is that you can end up offline.
When that happens, the fact that my phone can hold my entire music collection is a handy thing.
It always amazes me when people talk about the cloud as if all of the necessary network infastructure was already there. It's not. Mobile networking is CRAP and mobile networking providers seem intent on also making it EXPENSIVE too.
It's the cloud that sucks. SSDs have potential. Their main problem is that they're terribly expensive. They are not likely to overtake spinny disks any time soon because of this.
Re:Expanding drives (Score:2, Insightful)
Re:Who cares about replacing ALL hard drives? (Score:1, Insightful)
Re:There are always more axes of improvement... (Score:3, Insightful)
Or we reach good enough.
How much storage do we really need on device?
I agree with your overall premise, but I have to disagree with one of your points.
If you are storing video 32 GBs is a huge amount of storage.
1 hour of analog TV on Tivo's medium quality setting is 1.2g. An average DVD (not HD) movie runs about 5.5g. Throw in OS, software, and miscellaneous other things and 32g can be pretty small when video storage is required.
But on that same note, do we really need every device to have the capacity of carrying everything that we own? We have homes so that we don't have to carry all our possessions everywhere we go. I expect to see NAS products to be more common and a central point where people share data between the variety of personal data devices that we are collecting. (smart phone, netbook/tablet, book reader, media player, etc) Servers and some desktops will need big harddrives, everything else will move to SSD.
BTW, cloud storage will always have one problem, it's out of your control. If it's something you HAVE to have access to at anytime, or security sensitive, you won't be putting it on a cloud. If people trusted other people to manage services that were critical for their business, SOAP servers would be everywhere.
HD limit soon, now SSD limit soon? Chips are tiny (Score:2, Insightful)
Not every PC is a traditional tower (Score:3, Insightful)
if you're building a new one, it shouldn't be much of a bother to fit a physically bigger drive inside your case.
Unless I'm building a laptop, or an all-in-one, or a slim PC to put next to the TV, etc. Not every PC is a traditional tower.
Compare not next year's SSDs to today's HDDs (Score:3, Insightful)
If only we had a way to improve technology over time!
Compare not next year's SSDs to today's HDDs; instead compare next year's SSDs to next year's HDDs. If both SSDs and HDDs improve at the same rate over time, HDDs will keep their lead compared to SSDs for any application that isn't handheld, vibration-sensitive, or seek-heavy.
Re:Selective evolution (Score:3, Insightful)
Cost is huge. What other issues do you see? The capacity limitations are more a function of cost than technology. They seem to crush magnetics in every performance benchmark imaginable. They last longer, use less power, and seem have very high data integrity.
I know you can only flip each bit so many times, effectively guaranteeing that an SSD won't last forever, but even with frequent reading/writing they still last for 5+ years which is more than can be said of your typical magnetic drive. In my experience, your typical hard drive lasts anywhere from 2-5 years before failing -- and if you have one older than that its probably making grinding noises reminiscent of a 2400 baud modem connecting. Moving parts suck. They are the #1 point of failure for any computer system. When a computer has a hardware issue, it's almost always that a hard drive dies, a cd/dvd drive dies, or a fan dies and something overheats.
Hard drives are not only one of the least reliable components in any given system, they're also the biggest bottleneck in a wide-array of computing operations. The only thing keeping these dinosaurs from going extinct is the high cost of the alternatives -- not technological limitations.
Re:Compare not next year's SSDs to today's HDDs (Score:3, Insightful)
The thing is, general computing seems to be seek-heavy. My HD is by far the worst performing component of my system, always laggy and grinding, unresponsive when busy. The memory sits their with huge chunks unused and processor idle. Storage needs to improve speed drastically, and SSDs give us that now, and seem to have more headroom in the future.
It Doesn't Add Up (Score:2, Insightful)
The author finds "some good data on Wikipedia" (respect!) showing that the "lithography size" will be reduced from 32nm in 2010 to 11nm in 2022. He calculates this to be a "volumetric improvement" of 50%. There I was thinking that it was an 846% improvement, but I hadn't taken the third dimension into account.
Nevertheless, I think the author has a point, but he is missing part of the picture: NAND flash SSDs may not replace HDDs any time soon, but other types of non-volatile memory may well do so.
HDD densities will probably increase, but the slow access and transfer times and the static unrecoverable error rate will probably relegate them to use for back-ups or as cheap mass-storage devices for non-critical data. SSDs, however, are not restricted by the limits of NAND flash. Non-volatile memory technologies such spin transfer torque RAM and phase-change RAM have a good chance of replacing NAND flash memory in SSDs. These technologies are available today. Memristors are probably the most exciting development, as they promise a breakthrough in memory density. HP have a memristor-based design that could make petabyte SSDs possible, but we'll probably have to wait a few more years to see if that pans out. There are also major advances being made in fabrication technology, with cheap "printable" electronics already in consumer devices.
Real random-access memory that is cheap, reliable and fast is probably only a few years away from the mass market. There is so much money to be made by such an advance that R&D spending will not be lacking. So, the author is wrong; SSDs will dominate in the near future, just not NAND flash SSDs.
P.S. I don't have any SSDs because they are too small and expensive compared to my 1TB HDDs!
Re:Not just density (Score:3, Insightful)
Really? Where can I buy a 1.4TB hard drive that can read/write at 140MB/s for under $100?
You are asking the wrong question.
Instead, how about "Summing up all of the worlds digital data, is more stored on platters, or tape?"
Or maybe, "In 2010-converted dollars, how much money has been spent on platters vs tape?"
Or how about "Will Google ever use tape?"
Re:There are always more axes of improvement... (Score:3, Insightful)
A quick calculation, comparing the volume of the highest capacity flash memory I could easily find (16 Gb microSDHC) vs the volume of the highest capacity hard drive (2 TB) shows that the microSDHC has a Gb/volume ratio 18 times higher than the hard drive. Of course you couldn't just pack a case with a few hundred microSDHC chips and have it work, but even assuming half the space could be filled with flash memory, leaving space for controller card, data/power connections, cooling, etc. you would still have 9x the storage capacity. This is ignoring some details, but it should be in the ballpark. Even accounting for other differences (i.e. density of flash vs SSD, etc), they should be able to make SSD drives with at least comparable volumes, maybe the relatively high price is the only drawback.
Re:Expanding drives (Score:3, Insightful)
Something tells me by your post that you don't really need to worry about eliminating women from your sex life, I'm pretty sure they do that naturally do to instinct when you get too close.
Creepy is just as effective at eliminating women from your sex life as anything science can produce.
Re:There are always more axes of improvement... (Score:3, Insightful)
What I see happening is the HSM idea brought back, but done by a drive's firmware.
The first level would be either fast DRAM and used purely as a cache.
The second level would be SLC flash with TRIM done in hardware so the translation table doesn't get full over time, or the drive has 2-3 times as much flash so it can move data to another space, zero out the old space and have a translation table ready to go. This is where a VM swap file would live, as well as /boot or the kernel.
The third level would be MLC flash. Here is where ideally everything the computer needs to function will reside, the OS, the application, often used data, and home directories.
The fourth level would be holographic storage/spinning platters/optical or other media where access time is slow (measured in microseconds as opposed to nanoseconds), but can hold a lot of data. Here is where archive data goes, backups of the upper tiers, and files which are not often accessed, such as system logs about to be rotated out.
The fifth level would be tape, optical, or WORM holographic storage. This is an extremely slow medium compared to upper tiers, but has high capacity and long archival life. This would be used for backups. Perhaps the media would have a small amount of flash on it to support booting or storing encryption keys and other metadata. It would be ideal to have the ability to boot from this media for a fast bare metal restore.
Of course, the issue will be having an intelligent controller that can move data around in tiers. Additionally, data can be mirrored across tiers for redundancy, so if the SLC layer loses cells and ECC can't fix it, the files can be repaired from items stored on the MLC layer, or even prompt for a backup volume. Perhaps a ZFS-like filesystem would be ideal for this.