Slashdot Mirror
Why SSDs Won't Replace Hard Drives
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.'"
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!
With SSDs, I'm sure there is always another axis of improvement, similar to with CPUs, when you hit a wall with them, go SMP. When SMP doesn't scale, crank up the clock speed, etc.
What I wonder is what can be focused on to make SSDs be able to store more. We can always stick more chips in an enclosure, and the cooling needs for SSDs are far less than the cooling needed for CPUs.
they're so damn fast. I love mine.
Error reading device 'Signature'. (A)bort, (R)etry, (F)ail?
Was plenty for my needs and boots Ubuntu in 20 seconds. Barely uses power when not in use. I'm a believer.
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."
SSDs will continue to creep up the size scale, becoming "big enough" for many. LOTS of hard drives will be replaced. All of them? No. Who mentioned that? Only this article.
If will be a long time before development of the horseless carriage will overtake the technology of my steam-powered ornithopter!
Give a man a fish and you have fed him for today. Teach a man to fish, and he'll say "WHERE'S MY FISH, YOU IDIOT?"
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.
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!
I weep for our future.
...except for the people who already HAVE replaced their hard drives with SSDs. Not those people. We're not counting them.
To my knowledge no one has implemented trim for ssd's across a hardware raid array. Trim would seem to be essential to keep up your read/write speeds with a ssd.
The reason we don't see many 1tb SSD drives is cost, not data density. We could easily have 1tb to 4tb and beyond SSD drives, but it's highly cost prohibitive. There are 1tb SSD drives (OCZ makes one, I believe), but they are in excess of somewhere around $4k, more expensive than most people are willing to spend on the computer as a whole.
Sure, they won't "replace" them because when it comes to raw storage magnetic media is king, but things are going portable and reliable. No one wants to have moving parts in something like a phone. But really how many people actually fill up their current HDD? I know, theres some people out there with 1 TB worth of pictures, movies, music, etc. there are other people there who have the entire PS1 library on their HDD just to say they can, but on the whole how much HDD is actually -used-? On an 80 GB partition, Ubuntu plus all my music plus photos (I really don't keep much video on there, I just stream stuff) and all other files total only 40 GB, and that is just half my entire HDD (I just did a 50% Windows 50% Linux setup, my Windows partition is 80 GB and only has about 12 GB of actual stuff on there) and this all was on a $300 laptop bought 2 years ago!
When it comes down to it, speed it much more important than having 2 TB of stuff on there because the average person could use a speed/durability boost but doesn't need lots and lots of space.
Taxation is legalized theft, no more, no less.
Optronics. Positronics. Cybertronics. Moleculartronics.
We need to build more Research Labs.
Years later, a doctor will tell me that I have an I.Q. of 48, and am what some people call "mentally retarded".
How far does the storage capacity really need to expand? Hard drives are in the terabyte range now, but not many people really use that much. On media servers or something, maybe, but on your average computer? I've got 50GB in my laptop once you account for my windows partition, and I'm fine with that. A 320GB SSD would last me a lifetime, especially considering the btrfs is supposed to support on-the-fly compression.
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.
Funny may not give karma, but +5 Informative never made anyone snort coffee out their nose.
"Science reporting organizations have been expanding dramatically in recent years, but this article says that's about to change, in part because of the limits of current literacy education. Meanwhile, tabloid reporting will continue to grow, which the author says will mean many years before solid science reporting replaces sensationalism -- if they ever do. From the article: 'The bottom line is that there are limits to how smart things can get with current society. Universities are going to have student density growth problems, just as other societies have had over the last 30 years. This should surprise no one. And the literacy problem for journalism doesn't end there. Buff Clayton, Editor in chief for The Onion at Delaware, notes that as literacy gets smaller, science reporting has more and more troubles -- the bullshit PR releases don't decrease, so the probability of causing accidental sensationalism goes up. "So at some point, you just can't reduce the literacy and hope to not have reader confusion," notes Clayton.'"
It takes a man to suffer ignorance and smile
Be yourself no matter what they say
It's time not only for 3D in TV but in lithography as well. ... (more chips stakced)
(2.5D we have
I don't quite get this whole argument about replacing hard drives with SSDs. I have a 64GB SSD for my OS. I have a 1.5TB HDD for my music, movies and data. The expensive, small SSD boots my OS much faster than a traditional HDD and reduces the lag on system operations. The high-capacity and cheap HDD stores my media just fine and there's no lag playing some music or a movie because they just don't need to be read at that kind of speed when they're being used.
Why do we need to replace traditional HDDs with an SSD when you can just use each to their strengths? If SSD capacities won't ever hit the size or price of a HDD who cares. Graphics cards and CPUs both perform different calculations in a way that compliments each other to build a better machine overall. I don't really get why people see HDDs and SSDs as the same kind of component for the same job.
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.
I would think that hard drives would have a scaling problem at lower capacities than SSDs. How small can that bit of iron get?
How many of these could you fit in the space of a standard HD case?
I know, someone's gonna lecture me on how this isn't at all a fair comparison...
Correct me if I'm wrong here - and I usually am wrong - but aren't we "limited" now only by controllers and the *price* of the NAND chips? I've read anandtech's last few SSD manifestos and it seems the controllers' speeds and the price of the NAND - not really anything else - is limiting their absolute capacity. I recall engadget doing several reviews of SATA and PCI-E SSDs with capacities up to 1TB. Granted the 1TB Z-drive was between $1,500 to $2,000 back in March of 2009, but you get the idea. We can make a very large SSD today. It's just not affordable.
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.
I agree, but I feel like with enough time, the technology to enhance SSDs would be visible. I know that as of right now, if you increase the storage space AND the single-file-size limit, you are going to run into voltage and data corruption issues... but I think disk based drives are possible to be replaced by this technology. It won't be a fast transfer though, but I don't believe in being "exact" by saying that it will never happen, because with technology, you never know.
"Instant gratification takes too long." - Carrie Fisher
......yeah about that...SSDs have already replaced HDDs in my computer in the role they are spectacularly suited for, my primary drive (C:)
Sure they won't hold TBs of space, but in the current reality where 1Gb wired networks are the norm, and 10Gb versions are on the way, (wireless still blows goats though is usefull for light applications) most machines will never need a big drive in them again. Other than the server that I have in my garage all my future computer builds will be with SSDs.
Once you breath the fresh air that is a computer with a RAID 0 setup composed of SSDs you'll never go back.
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.
As HDDs continue to fail before their expected lifetimes due to sensitivity to movement and the general worse state of moving parts vs unmoving parts, people may start to flock towards SSDs as replacements, especially as people start to notice the many benefits of SSDs over HDDs. They'd have to realize though that extraordinary wear could shorten the length of an average MLC and that SSDs even on normal usage are not meant to last forever, but with the improvement to wear leveling this may be less of a problem in the future.
Obvious, I know, but can't they just make the chips cheaper then use more of them?
No sig today...
Better tell that to the one I just migrated my Windows installation onto...
I am scientifically inaccurate.
SD cards go up to 32GB. They're only 2.1mm thick. Just piling them up you could fit 200 or so in the volume of a typical hard disk, and it's not like an SD card is the most space efficient means of storage since a lot of the volume is taken up with the plastic case. Micro-SD can go to a quarter of the capacity in a tenth of the size. So we can squeeze at least 16TB into the same volume. That's probably adequate for a typical home user. The price is the issue here.
They always say this, and we always find something.
Check out this article about hard drive density i just found from 2001:
http://www.post-gazette.com/healthscience/20011029disk1029p2.asp
"...within two or three years, advances in storage capacity will begin to taper off, he predicted."
Drives were about $300 for 80GB back then... Last weekend i bought a 2TB drive for $125.
Yeah, we will always find something. These articles about "zomg technology is going to END!" need to stop.
-Taylor
Worldwide Military budgets: $2100 billion. Worldwide Space Exploration budgets: $38 billion. Really, world? Really?
http://www.maximumpc.com/article/news/breakthrough_nand_flash_memory_could_lead_10gbs_ssd_writes We have had a breakthrough in solving the voltage problem. I think the authoer is nothing but idiotic to believe that SSD isn't going to replace hdds for the average consumer. Later this year intel is going to release its G3 SSDs, with the lArgest at 600GB. G2 drives were 60% cheaper than G1 drives. Let's hope we see a similar drop.
I think maybe this writer totally missed the point of SSDs. SSDs are not about space but are about speed. If you've ever had a chance to use a high performance SSD, the experience is awesome. Everything loads and unloads smoothly. You have none of the delays related to standard hard drives that do affect your experience with an operating system. Also in a laptop SSDs bring silence and a physical reliability that you just can't get in a standard hard drive. I suspect SSDs will fill their own space in the market with mechanical HDs being reduced to storage or backup drives.
Is anyone really listening to what anyone at Dell has to say???
"There ought to be limits to freedom." -George W. Bush
Flash will never have the price/density advantage of hard drives, however.
A MicroSD card has a volume of less than 0,115cm^3, with 32GB capacity currently availlable. A 3 1/2 " HD is 300cm^3. Filling the HD volume with MicroSD cards you will get a capacity of 83TB. HDs are 2TB maximum, so flash memory already has a clear density advantage.
Correct me if I'm wrong here - and I usually am wrong -
I'm usually right... but that statement might be one of the exceptions. :)
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.
It's a basic maxim of the silicon industry that cost is directly proportional to die area. To simplify, you can consider the silicon fab to have a fixed cost per wafer. Therefore the more die fit on a wafer, the cheaper each chip becomes. The two main ways to do this are by reducing the amount of functionality on each chip (undesirable when the goal is to increase capacity), or to move to a smaller lithography so you can fit many more die on a wafer. While new lithography generations have frequently allowed greater performance, even if they don't they are deployed anyway because it reduces cost for the manufacturer.
Yield improvements and paying off R&D both will help cost, but only to a limited extent. Yields for a production lithography should already be quite high and will asymptotically approach 1. Once R&D is payed off the cost will drop, but there still remains a very large fixed cost per wafer. Neither is going to come close to the cost benefit of being able to, say, go from a 45nm to 32nm process and get roughly 40% more die per wafer.
So yeah price will come down for other reasons, but in the long term price reductions in flash memory devices are going to depend on using smaller lithographies just like it does for other semiconductor devices. The author probably just didn't think to explain this aspect of it, since it's such a well-known aspect of the silicon industry.
On the other hand, people were saying that CMOS processes used in CPUs were going to reach fundamental limits 20 years ago. And 15. And 10. And 5. And oh sure, some of those limits were reached, but then clever people worked around them. The statement in the article amounts to "We can't just blindly reduce lithography size without changing anything else indefinitely", which is true but also kinda pointless since the people working on smaller lithographies for flash are probably aware. In the end exponential progressions like this can't last for ever, but I'm not about to tell the process engineers that they aren't going to be able to find enough tricks to keep it going long enough.
The enemies of Democracy are
(See Subject) Excluding notebooks and netbooks, can't the increase in volume be taken advantage of for more flash capacity.
May I please have my frontal lobotomy if I bring back the ashtrays?
This is what annoys me is that it seems like Flash is idea as a cache for magnetic HDDs. The same principle is already at work in our CPUs:
So a modern CPU is way faster than modern RAM. The access times are much lower. How then, can we have a system not hamstrung by RAM? The answer is cache. With a good system of high speed L1/L2 (and sometimes L3 cache) we can have our cake and eat it too. You have a few megabytes of expensive high clock SRAM right on the core. You have a few gigabytes of cheap DRAM clocked much slower. With proper caching, you then get 90-95% of the expected speed of the SRAM. Nearly all of the speed, a fraction of the cost.
Why not HDDs then? Have the RAM on there (L1) and a couple gigabytes of flash (L2) pared with the disk. Use an intelligent caching algorithm (as in not just the first part of the drive) to cache reads and writes. This should again offer most of the expected speed of the flash, while still offering a low price.
I'd pay for that. Say a full magnetic drive is $100 for 1TB. A full SSD is $3000 for 1TB. A Hybrid 1TB drive, which features 4GB of flash, is $200 but performs 50% faster than the magnetic drive and deals with simultaneous reads and writes much better. I'd buy that.
Unfortunately all the hybrids are for laptops and use it to save power, not to speed things up.
As I can attest to while I read it on my CRT monitor.
Welcome back 5½ drives. We all have missed you!
I have never understanded the idea to make smaller HD's when there have been need to bigger storage space. Not in the normal cases. HTC's and laptops the 1.8" or littlebit bigger can be natural. But full or half tower case, the 5½ is enough. And if with that we can make more secure (less errors) drives, I welcome it right now. Just yesterday Windows 7 destroyed my third HD..... Why it always happend to HD's where I install Windows, but never to HD's where I install Linux or other Unix OS?
It may be quite a few years down the read but there are other solid state technologies that don't use NAND chips.
Ferroelectric, holographic, phase-change, nanotube, ....
I think the point is more like why you didn't need your 48x CD player to listen to music. I have my software on an SSD and my audio and video on HDDs. It's OK if a single SSD can be both the fastest thing I can get my software on per dollar and the largest thing I can get my data on per dollar. It's just not necessary.
Right now, my gaming PC's slowest point is the hard drive, and this is one of the newest hard drives on the market. The Windows 7 spec is 5.9, which is the fastest that a hard drive can reach from what I've read, and I can easily get 60-70 MB/sec throughput from it (continuous, not burst). But quite frankly unless SSD can reach the price/GB ratio that make it comparable to hard drives, my time really isn't valuable enough to warrant paying for the much, much higher price/GB ratio of SSD. Maybe in another 5 or 10 years it will be comparable or at least to a point where decision making will end up more like "I really don't need the space on that new 10 TB hard drive, so I'll get the 2 TB SSD drive instead for about the same price."
The Overrated mod is for reversing inappropriate, positive mods, not for voicing disagreement with a post.
At Intel, IT has already decided that all laptops will use SSDs. IT also reports money saved in terms of increased uptime. Also, it is noteworthy that Dell is behind IBM, HP and Oracle in terms of incorporating SSDs into their server platforms.
Hello? IBM? Anyone?
In Liberty, Rene
As network bandwidth continues to grow, mass storage in central servers or clouds becomes more feasible. A netbook with even 8-16GB of SSD space not only gets more life out of its battery; it can also take more of a beating and access its data faster.
Different media fulfill different purposes: SSD is more expensive and less dense, but it's also faster - that's how the pyramid of storage media is arranged.
And flash memory, with its nice regular arrays of identical cells, lends itself much more to extreme lithography tricks (such as double exposure) than, say, a CPU. And those tricks are exactly what made possible to keep on shrinking the feature size the last years while still using those good ol' 193 nm excimer photolithography steppers.
Let's see, you can fit 32 GB on a memory stick Duo. They are abut 3/4" x 3/4" inch x 1/16 inch. That's about 40 of them in a box the size of a laptop HDD. 1.2 TB on my laptop is PLENTY for my forseeable future. (I have a 40 GB spinner now and I use about 25 of it)
Flash based SSDs won't be able to out compete conventional hard drives at large storage, but what about others? HP is working on memristor based storage, devices which need to be nanoscale to function.
http://en.wikipedia.org/wiki/Memristor
Awesome furniture, accessories and cabinetry in Santa Rosa, CA: http://humanity-home.com/
Smaller lithography necessarily results in less write endurance. It's important to intelligently handle writing to SSDs, and that is not something that any operating system currently does. Until OSes and filesystems are written specifically to handle the write endurance and amplification problems, SSDs will not replace HDDs in applications requiring high reliability.
That said, they're awesome if you do an image backup every day and just want your machine to scream...
Seems obvious to me that a hybrid drive is optimal. Flash supports faster writes, so use it as a buffer before the slow spinning platters, so even in the event of catastrophic crash, whatever writes are in the buffer are already to permanent storage. This will make fynsc() calls much faster, since we don't have to wait for platter rotations, just for the flash write to succeed. The bytes are then migrated to the platter in the background as the disc spins, so less seeking.
Finally, this flash buffer only needs a small fraction of the size of the full disc, thus keeping costs down.
Higher Logics: where programming meets science.
It's a basic maxim of the silicon industry that cost is directly proportional to die area. To simplify, you can consider the silicon fab to have a fixed cost per wafer.
You are of course correct, but there's also been a push towards larger and larger wafers, last from 200 mm to 300 mm. Currently they are experimenting with 450 mm wafers, which would increase surface area per wafer by 125%. Additionally they get less cutoff at the edges and less "edge" which usually has the highest defect rate. Undoubtedly effort in this area would go up if reducing the lithography process proves difficult. Just like CPU manufacturers have gone sideways with more cores instead of higher GHz.
As for hard disks, I see the cheapest laptop HDD I can buy is now 160GB and costs about half of the cheapest SSD. Reducing the process from 34nm to 25nm should bring those much, much closer and is due already in Q4 this year. A lot of people will value a snappy computer more than a bigger HDD, if the price starts getting equal. Also perhaps a new life for dual-bay laptops, one SSD + one HDD. Having gotten used to a SSD, I can tell you that going back to work with a HDD as main drive is frustrating...
Live today, because you never know what tomorrow brings
Could someone please dig up an old slashdot article talking about HDD's hitting their theoretical capacity peak? I'm sure there's been a few, before innovations like http://en.wikipedia.org/wiki/Perpendicular_recording came along.
So, won't the real future be a combo/hybrid drive that has both technologies in the same unit? Seems to be the SSD is good to run the apps, and the spinning stuff is good-and cheaper- for long term bulk storage. So why not combine the two, with some sort of intelligent control, so the combo drive knows which to use and when?
..for me. not everyone needs terabytes of storage.
bite my glorious golden ass.
I kinda get the point, then again SSD sure as hell replaced the HDD in my EEE PC. I wish he had told me a year ago!
It's only slightly more expensive to keep all the disks online and use virtual tapes on them. You can even raid them and test them occasionally in order to find flaws. Depending on your scale, the cost for the disk bays and disk controllers may be less than the cost of a tape library.
"So at some point, you just can't reduce the size and hope to not have data corruption,"
Fire up the Heisenberg compensators!
Chips can be super tiny, spinning platters aren't so much. It wasn't that long ago that people were predicting hard drives couldn't get much more dense due to neighboring bits flipping each other too frequently, then they had a breakthrough with perpendicular recording. Look at what a 4 gig microSD card looks like. Then imagine how many of those could fit in a 3.5" drive chassis if carefully stacked them in there. I bet you'd be able to stack more than 1000 easily. Aside from that, even if each format may not be able to scale down significantly further, I can only collect so many TB of "linux isos" before I can't find a damn thing.
I bought an expensive one, and everytime they system was accessing it the whole system froze. Pathetic.
If Google really cared they would fix Android Chrome to reflow text, instead of discriminating
The hot new solid state non-volatile memory technologies are phase-change memory (PRAM), memristors, ferroelectric RAM, resistive RAM.
Some of these technologies are much more area-efficient than Flash, and will stack in pseudo-3D chips reasonably well (memristors in particular should stack in full 3-D arrays very efficiently...).
The general observation that disks have the lead right now is true, but the other technologies close a lot of the gap, and the growth curves look very similar after that. Who knows if it ever gets cheap enough to completely replace disks in our lifetimes, but there is hope of seeing that.
That does entirely change the game on system architecture. Disks are slow and far away from the CPU. Solid state memory can be as close or nearly as close as DRAM, and if it doesn't require a lot of handholding on lifecycle management (wear rates etc - Flash is horrible here) then can be used and managed as a simple byte or block array rather than the whole "filesystem" crap we now use. We still may want POSIX like abstractions for parts of storage management, but life is so much easier if the back end store is just a block array we read/write than if it's really a spinning disk, behind a cache, behind a controller, behind a SATA/SAS bus, behind a controller, behind a PCI bus, behind a southbridge, ....
Yes, like that, thanks for the link. The SSD part needs to be larger though, that's it. All your OS and apps would go on it. I guess you can do that now with just two different drives, put /home on the spinning disk, but that combo drive is interesting, I'll bookmark/retain the info and follow that model. Eventually soon here I need a new drive, that might be it.
A 3.5" drive has dimensions of 26.1mm x 101.6mm x 146.99mm, a microSD card has dimensions of 15mm x 11mm x 1mm. So you could fit 2362 microSD cards into a HDD. I can buy a 32GB microSDHC right now. So that's 75TB.
I'm sure you'd have some serious heat issues, and of course need some electronics, so just fill 1/4 of it with them for 18TB and the rest with space for heat dissipation and the electronics.
Of course the price isn't worth thinking about.
The idea that SSDs should totally replace such a time tested storage system at this point is not even really an issue imo. SSDs are doing what they are designed to do and do it pretty well: be damn fast.
I in good /. tradition did not RTFA but I can only assume the author is not trying to predict too far into the future. And in the near future I can see SSDs hitting a sweet spot where they can become the only drive in people machines. But then for large storage, even within the same household, there will be a hard drive(s).
Really, I know what I'm doing...Ohhhh, look at the shiny buttons!
laptops are aruldy making the move to ssd drives. being they simply work better on a laptop where tons of storage in most setups is not needed. the ssd inside a laptop will last much longer then spinning moving meda. laptop hdd die often due to people moving there laptop a problem that does not happen with a ssd, in the non moving desktop systems hdd drives will be domment for a long time. grater storage lower price and there fast enough. only speed freaks will want a ssd inside there desktop.
They just need to resurrect the 5-1/4" Full height drive form factor. They can probably get 10-20TB in one those. Problem solved. Now.. what did I do with that old tower that had 4 5-1/4" full height drive bays? Laptop owners? - We don't need no stinking laptops!
You are of course correct, but there's also been a push towards larger and larger wafers, last from 200 mm to 300 mm. Currently they are experimenting with 450 mm wafers, which would increase surface area per wafer by 125%.
That's a very good point. I thought to mention how that affects the situation, but figured it doesn't happen often enough to dominate in the long term. But I may be underestimating this factor as just another way to get around the cost problem.
Having gotten used to a SSD, I can tell you that going back to work with a HDD as main drive is frustrating...
I don't have an SSD, but I think they're ready to replace or augment many HDDs, especially in consumer computers. Though speaking of work, I'm pretty sure my work place's data center is going to be placing value on storage/price for quite some time, and frankly I'm glad to have them do so (since it's networked anyway).
The enemies of Democracy are
It's called journalistic malpractice. Mod headline down.
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.
We have homes so that we don't have to carry all our possessions everywhere we go.
Unless you're a child whose parents have divorced. Then you need to pretty much move from your mother's house to your father's house or vice versa every 7 days.
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.
So you suggest a big RAID of 32 GB microSDHC cards. I've made the same suggestion before in comments to a different Slashdot story, but someone replied that the PCB and the controller would still take up a lot of space in the case.
Neither is going to come close to the cost benefit of being able to, say, go from a 45nm to 32nm process and get roughly 40% more die per wafer.
But how many percent more live?
The first few generations of iPod used hard disks. Then the low end started using Flash. Then higher and higher - the iPod Touch is all flash; so is the iPad. The largest capacity iPod is still based on hard disk, but I suspect that will change soon.
There are a few laptops using SSD now, but I expect the proportion to increase steadily. SSD is well suited to laptops - it uses less power than hard disk, it resists dropping better (especially when in operation), and it's faster - most of us boot a laptop more often than we boot our desktop machine, so a drive that lets the machine boot faster is a GOOD THING (tm).
I have SSDs in both the desktop PCs I've built this year - an SSD is an awesome boot drive, and the boot drive doesn't have to be large (40GB is plenty). One of these machines has no large drives in it - I keep the large space on NAS. The other one has a largeish hard drive, but it has nothing on it - I built it first, and thought I'd need the hard drive - my mistake :-)
I won't claim that SSDs will replace all hard drives - I'm sure Google will continue have vast numbers of hard drives, for example, but I see SSDs replacing hard drives in an increasing range of devices.
SSDs (or at least hybrid SSHDDs) will replace HDDs. How many of you tolerate the slows speeds of a tape drive despite the fact it is more cost efficient than a disk drive? Eventually people said, "Its not the most space, but I'd rather have the speed". There is simply going to be a point when:
The price is not cheap but not expensive either. Less than 20% of the total cost of the computer is probably the key price point here.
The density is enough that most people can live with it comfortably. Based on typical usage, this seems to be 128 - 256 GB, which is already met by SSDs at decent price points and it is only a matter of time before this is cheap to the average consumer.
The reliability and ease-of-use becomes mainstream. While people are still having to do firmware updates, this isn't mainstream yet. Same goes with using the SSD as a boot drive and as the page file drive. Consumers don't like the complexity of dealing with multiple drives, where one is superior to the other it confuses and inconveniences them.
Size doesn't matter... one can have more chips to increase the capacity
500 GB: $520 SSD instead of a $80 HD - around 6x the price. When the price drops to 2x to 3x, the game is over for the consumer market.
- SSDs in laptops are a no-brainer. No moving parts, no crashed HD heads, faster speeds, less power needed. Apps are faster, OS is faster, life is better.
- SSDs in desktops also make sense, but is a little less compelling.
- SSDs in servers also make sense depending on the use-case, the application and the network.
- SAN and NAS already have SSD capability as a "top level" non-volitile memory in the storage hierarchy, and it will continue to grow.
- And finally, mobile devices will eat up SSD storage, how many smart-phones are going to have a spinning disk in them?
Spinning disk will never be 100% replaced (just as with tape) but the market will swing from 80-20 spinning disk to 80-20 flash. The question is when.
Two decades ago a whole system would fit on a 1.2" floppy. A game as complex as Elite (8 galaxies) would fit in 48K of memory and would have mesh graphics. Nowadays, after what they believe is propper training and colege education every moron needs eye candy and sound themes that should change with the mood making a system able to fit on a DVD after making some of the multimedia content available online for free. We need Tb for what? For having duplicate copies of the google databases? A game supporting a number of hardware devices itself (and not through some other layer) designed to work on a 386 needs to be slowed down in order to make it playable, yet a Linux desktop with all the bells and wistles needs almost a minute till you enter some comands. On the current storage units you can do video processing, yet for a regular user "that's not enough". Oh, really?
http://www.accountkiller.com/removal-requested
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!
That's illegal.
In america.
I've just replaced my HDD with SSD and was so happy about it. Does it mean I need to go to the shop and ask to get it back??
There are many reasons to buy (or not to buy) an SSD. For me, it was simple: Noise. When my laptop hard disk failed a few months back I replaced it with an equivalent sized SSD (64 Gb HD -> 64Gb SSD) and boy am I happy - it runs absolutely silently now. Not. A. Whisper. I can't say I've noticed any difference in performance or battery life, but that could be because the laptop is old and running fedora + OSS radeon drivers. Speed certainly wasn't an objective (it was ample fast enough before for my needs), though longer battery life would be nice. I expect that with the forthcoming radeon power manager advances things will improve even more :-)
I can see one of the big drive makers at some point creating a drive that effectively is 2 drives in one case. Maybe 1/5 of it would be SSD, containing the OS and regularly used files, games the user is currently playing etc with the other 4/5 being a standard HDD used for "slow" storage. I know it's completely possible to set this up right now but as with everything, a plug and play solution is needed for the non-enthusiasts to adopt.
If processors had enough cache, we would not need DRAM.
If systems had enough DRAM, we would not need drives, whether they be SSD or spinning rust (see, I can be trendy too!)
If systems had enough hard drive capacity, tape storage would no longer be necessary. (If I were to put my money somewhere, I'd probably bet that tape could become obsolete as HD capacities increase, but I would probably be wrong * )
There has always been hierarchy of storage that trades off the parameters of speed vs. capacity (and factors in convenience, physical size and cost.) Anything that falls in line or fills a need (e.g. portability of CD/DVD/BD, size of micro-SD) will remain in use if it doesn't cost too much. If something becomes slower and yet holds less or remains expensive, it will fall out of use.
New technologies that stake out an advantageous point somewhere in this trade off will grow and prosper. That's the situatoin for SSD which provides increased speed but at higher cost. Some new technologies will likely make older technology obsolete. It will be fun to see what comes along and what falls by the wayside. However I don't see the price/performance/capacity proposition for SSDs making spinning drives obsolete any time soon, so I guess I agree with the author.
(*) Years ago I visited the computer center at Fermi National Accelerator Lab. They had petabytes of tape on which they stored data collected during experiments. I wonder if they're still using tape. I would be surprised if not.
I can understand the points being made about density and scale, but I believe that between the disk drives and CPU we have a big difference: the cooling needs for flash are very different from a "classic" hard drive, or a CPU for that matter, and with flash, we are not exactly racing for the smallest form-factor.
Yes, I can understand that it would be cool to carry a SSD the size of a toenail, with at least some 500 TB of storage. However, I would be very happy to buy an SSD with tons of space, even if it takes the size of a 3,5" disk (correct me if I'm wrong, but usually SSDs are 2,5" in size, right?). The difference is that, while I don't expect my CPU to suddenly grow up to the size of a shoe-box, I already know that 3,5" is the "normal" form-factor for storage (yes, I'm only considering desktops).
My point is that in storage, we don't need to "race" to the infinitesimally big/fast, on the infinitesimally small form factor. We started with a pretty decent form-factor (3,5"), in terms of space and efficiency. I guess that it will take quite some time to drain that completely.
I know it's good to have lot's of storage, and I certainly don't want to pull a "bill gates" and say that "1 TB is enough for everyone", but how many of you have memory cards bigger than 16 GB on your mobile phones / smartphones and what not? And if you do, do you actually use all that space? And if you do, don't you, at some point, synchronize it with some other storage somewhere (a computer, the cloud, network)? If you don't, you should, it's called "backup", and you'll only miss it when it's too late :)
So, in my personal case, I'll welcome our SSD overlords with joy, when they get a bit cheaper, of course :) And yeah, I don't mind having a 3,5" SSD inside my computer.
"A sysadmin is a cross between a detective, a police officer, a gardener, a doctor and a fireman"
I agree (I realize that you're being ironic). Overall I think it was an interesting article but his arguments aren't really strong enough for example: Bit Density Comparisons vs. Cell Density Comparisons: Or that's what I'm going to call the part where he's talking about lithography. I get that when vendors are showing you growth curves they are showing you bit density not cell density. That is the growth we are seeing aligns much more with products being shifted to pre-existing higher density technology - instead of the growth of flash lithography. However for that to be unfair we have to assume that the growth we see in the HD market aligns well with advances in their underlying technology. Fair enough. However that doesn't actually support his argument of "it won't happen soon" unless we look at the current bit densities of both products and the growth rates of their underlying technology. This year we saw the release of a 3TB 3.5" drive - if we use Mr. Newmans argument we can assume this is following reasonably closely with the capacity of the underlying technology (not necessarily limited to theoretical capacity but also production etc...) . Sadly for comparison there isn't a flash drive that pushes the capacity of the 3.5" form factor. However if we assume that the logic for managing multiple drives is small compared to that of the storage itself we might be able to make the following comparison. A 3.5" drive is 147mm x 101mm x 46mm a micro sd flash card is 15mm x 11mm x 1. Which means we could fit at least a 9 x 9 array on a plane the same size as a 3.5" drive. Again I'm going to assume that whatever spacing is required it isn't going to require more than the same thickness above and below each "card". If true we can layer fifteen of these "sheets" of sd cards in the same volume as the 3.5" drive. That gives us about 1200 cards and given that the highest density card is 32GB which means we could fit about 37TB of this kind of flash memory in the 3.5" space. Now I'm not going to try to estimate what the growth rates of each underlying technology is but from my analysis here I'd say it's HD's that need to catch up.
What a fucking tool. SSDs have *already* replaced HDDs, in all desktops and notebooks, for every single person I know who isn't retarded or in some weird financial hardship situation. It has *ALREADY* happened. Even fucking TELEGRAMS have not been TOTALLY replaced. Henry Newman, you are a cunt and a retard. Please hang yourself.
especially since 'solid state drive' is about the most nebulous possible term, and, taken unambiguously, only means 'not some fucking retarded mechanical contraption'
That's it.
SSDs are too expensive. Retarded even, have you priced one yet? When the cost difference is that great, between the same HDD of the same data capacity, then the performance issues are irrelevant (yes, even if they could transfer information twice as fast as they do now, they are worthless due to scant storage space and price.) Actually, when it comes to HDs, I doubt performance is the most important factor over storage, cost and reliability. Oh, and let's not ignore the reliability either. SSDs will eventually die, and predictions are rather accurate making them less desirable, considering the fact I have 25 year old hard drives from database servers that still work fine today.
SSDs have to drop in cost, a lot. They should be cheaper than SATA drives largely because they always have less storage space. The justification for their price is the read performance, as many of the current SSDs don't even have comparable write advantages over say UltraSCSI 320 or SATA II. What they seem to be banking on, is public acceptance that the drives are "fast" because their computer boots up faster, or maybe a game loads faster, fair enough... but does that justify the cost? I don't think so.
There is a price threshold, at least for me. Right now HDD's cost say 5-6 cents per GB. Once Flash starts to hit the 3-4 cents per GB level (assuming HDD have gone below 1 cent/GB), it starts to make up for itself for many applications because of the performance/reliability factor. Right now I have say 200 'videos' per drive on a single 1.5TB drive (2TB just recently became more cost effective if you wait for the $99.99 sales at newegg). However, if that drive goes, it will tend to go in a catastrophic way, and I would lose all or a large portion of that drive. The hope/expectation is that a Flash drive sitting around without moving parts, would be much less likely to have a catastrophic failure like that. More likely for Flash is you would lose a single file or two. When you realize it might take two to three months to recover a completely lost HDD (redownload the 'videos'), at a reasonable download rate, it makes a lot more sense to make that switch as soon as you can.
A naive analysis of my Comcast Business Class service: $59.99 per month, bandwidth usage 1 TB, but lets say 1TB. A naive analysis already values a GB at 5-6 cents per GB just on ISP costs alone. You could say knock this down to 2-3 cents if you assume that even if you stopped downloading, you would need to spend $30 a month for decent internet if you didn't want good bandwidth.
Plus the labor involved in organizing your 'video' downloads, etc. might run into 4-10 hours per drive.
Once that threshold is met, and the perceived reliability of SSD versus extra cost becomes negligible in the overall cost, a lot of people will be jumping on SSDs, which should ultimately drive the costs even lower.
http://blog.slaingod.com
To see why SSD won't make disk obsolete, look at the history of bubble memory. It was (is) fast, and highly resistant to vibration, and doesn't have the limited lifetime of flash memory. The killer problem seems to have been lack of need for the greater reliability or disk and flash, which would justify the cost and size. I hear rumors that a small quantity is still made and used for space environments, because of radiation resistance, but unless wikileaks documents this it's just rumor. In any case, disk kept getting bigger and faster, flash ate the rest of the market, and bubble... well, burst.
My thought is that before SSD becomes a real competitor with disk that one of the emerging technologies will overtake it, providing better lifetime, faster write (ie. rewrite without an erase operation), and all flash will either vanish, or remain in the 4-32GB thumb drive niche, where it now rules.
Ok I'm going to give a more realistic example...
Take a look at the OCZ Colossus it's a pure flash 3.5" drive which was produced last year which has a capacity of 1TB. Now mind you this was engineered by tacking together a bunch of flash on a SATA controller, then plugging two of these into another SATA controller to produce a RAID of these two cards. IMHO this this design was not made to create the highest capacity drive possible.
However it might be a better benchmark for figuring out where our limits are for example..
This drive puts about 5mm between each Flash package. Given that Toshiba has a 128 GB Flash chip/controller launching this fall. Considering that the carrier measures 17mm x 22mm x 1.4mm we can probably put a 4 x 5 Array of these on a card like the ones in the Colossus. Either by double-siding the board or adding more boards (but not necessarily by using bulky SATA connectors). Let's say we can put four of these hypothetical boards into a 3.5" chassis. That still clocks us in at 10TB. Which is still 3x what we have going on with spinning disks. So even if we assume that the density increases for Disk vs. Flash are the same. I'd argue that economies of scale will soon make this cost effective.
Maybe if they squeeze and XOR between each NAND? :)
ad astra per alia porci
I have tried larger hard drives (> 100G) and found that I actually don't like them. I prefer my primary drive to be about 80G, which seems to have been the sweet spot for me for at least the past 5 years. At any given time, I have between 40 and 70G worth of bloatware, games, and audio projects, and if I'm going to exceed that, it's time to remove an old app or game or back up some .wav files. So, what the author claims to be the reason why SSDs won't replace spinning pieces of metal is not relevant in my case.
I declare bullshit on this whole story. Obviously the writer has not done his research and is blowing hard on stuff he knows little about:
http://gizmodo.com/5125341/new-sdxc-memory-card-spec-supports-2tb-capacities
http://www.computerworld.com/s/article/9125622/Memory_card_standard_could_provide_up_to_2TB_on_an_SD_card
http://www.wired.com/gadgetlab/2009/01/two-terabyte-sd/
I know the technology is different, but if they can fit 2 TB's on a stamp sized piece of silicon there is no reason why SSD flash cannot scale far greater. Take the size of a typical 2.5" SSD and then cram enough SD cards to fill it, you are already far exceeding the storage capacity of any HDD is capable of for the next decade. The new SDXC standard will support 300 MB/s transfer which is better then current SSD on the market. Take 4 2TB SDXC, stripe the fuckers in RAID and you easily have 8 TB of storage with a transfer rate of up to 1.2 GB/s in something about the size of a stick of gum. And I get the target price of SDXC will be under $500.
Obviously the SD guys realize they can scale SD storage technology to fit up to 2 TB of storage and have speeds match that of a desktop hard drive. Its why they defined the SDXC standard. So why on earth is it not possible for SSD to suddenly leapfrog HDD technology in the next few years?
Offtopic? I was only claiming that a desktop PC is not practical for someone who doesn't have one place to live. Such nomads would have to use a laptop as a desktop replacement, which at current cost per GB would mean that someone who keeps a lot of video or games would need either an internal HDD or an internal SSD plus an external HDD.
It's not about a billion writes, but about being able to take an impact as a portable device is moved around. Most people need that reliability more than capacity. Most people need the additional speed of solid state, better instant on, more than more capacity. Most people need mobility, small size, more than capacity.
An example of this is iPad. Lower capacities than a typical notebook, but mobile, rugged, small, instant on. The lack of a hard drive is one of the things people love about iPad even if they aren't conscious of it. They love the benefits.
Yeah, there will be hard disks for a while yet, but they are going to become minority real fast.