Solid state revolution: in-depth on how SSDs really work

SSDs use a huge grab bag of techniques to make a computer feel "snappy."

Read the whole story

 

[hairyfeet]

Now contrast this with SSDs where the rule and not the exception is to have no warning at all, just flip the switch and its dead. often even BIOS no longer detects it, its just gone.

Sounds to me more like a controller failure than a catastrophic nand failure. Something similar can happen on HDDs. Hell, the impression i get is that it may well be the most common HDD failure these days rather than out and out mechanical failure.

At the little shop i run I find that just isn't the case, most HDDs give you a LOT of warning before they die unless you do something REALLY bad like drop it off a table while running. Here is what I have found to be the usual course of events..1.-First the heat level rises, this may be noticed in a laptop, not on a desktop, 2.- Then comes the most telling error, the "Delayed write fail" error, you get this one that is your early warning to get that drive outta there! this is finally followed by 3.-Whine and or clicks, although new Seagate tend to chirp like a cricket and then finally 4.-Dead drive. Now while these events CAN progress rapidly, especially if you continue to really push the machine, most folks when they see delayed write fail shut it down and bring it to me and I don't fire it back up until its time to transfer the data to the new drive so there is no problem.

Contrast this with an SSD fail which I've seen several times and consists of 1.-Flip the switch and nothing happens. That's it, no warning, no tell tale signs, its just over. And I had a customer that wanted his data back bad enough to buy an identical for me to try the old controller swap trick like we used to do on dead HDDs and I never could get it to work again. Maybe when the controller goes it takes something with it, I couldn't see anything burnt on the surface but I wasn't gonna strip the whole thing down to check so who knows.

So until they can give us some sort of self check for SSDs that give us SOMETHING, anything, some warning there is trouble, my advice is that unless the customer is in a niche where they have to carry around a running unit its better to max out the RAM and use Readyboost for faster small I/Os, SSDs are still just too buggy to be trusted.

 

[ashylarry]

I'm curious about why RAM disk adoption is so slow in the industry. The last page of the article mentions DRAM caching for enterprise systems, but I'm pretty sure that end users would also benefit from a huge speed bump.

Ramdisks are really a desktop/home user tool because they have to be general purpose.

With systems and services architecture memory is turned into an effective 'ramdisk' with caching services as their use cases are a lot more specific.

Many major sites have physical systems dedicated to acting as a big ramdisk: i.e., arrays of 16GB servers with Varnish or NGINX using 99% of the memory to cache the webdata which effectively means the entire site is in memory.

 

[JimmiG]

I think the graphic on the first page should be updated to include where SSDs would fall into that hierarchy. Once that's done, the obvious question would arise: why not have SSDs as Level 5 cache and spinning disks as Level 6? If we could somehow tell the OS and controllers that this is sequential or user-level data (movies, music, documents) then it seems like we'd get the best of both worlds.

I agree. SSD's are essentially a cache that has to managed manually by the user. You have to decide which applications to "cache" (by installing them to the SSD). Also, it's not lilely that the *whole* game or application needs to be available at low-latency. For example, a game might contain several gigabytes of movies, speech and background music that doesn't require the performance of a SSD.

Also, user patterns change over time. You might be using Application A a lot for 2 weeks, before switching entirely to Application B for a month, then Application C and then back to Application A etc. With an intelligent caching system, the controller could make sure the data you use most frequently is always availble, even with a smaller SSD.

I think SSD caching is a logical evolution that mirrors the evolution of CPUs (from just registers to Level 1 cache to L1+L2 cache to L1+L2+L3 cache).

 

[Devin]

I've been deeply missing Jon Stokes level of depth in hardware articles here at Ars, but I think Lee has picked up the torch in a fine way. Keep it up!

++ Good article

 

[jonhern]

i just ordered a new computer, should come in this week. Instead of going ssd I got a 32GB mSSD that is on the motherboard, hp called it Hard Drive Acceleration Cache, along with a 1TB hard drive, and it still has a free second HDD bay. Will this cache drive be comparable to an SSD drive in terms of speeding up the computer? It was only a $34 upgrade and I felt it would be better than the 750gb hybrid drive that only has 8GB SDD cache on it.

 

[ol1bit]

Nice write up! My gen 1 80GB Intel SSD with Win7 64bit on it is still going strong after about 3 years.

I have a 120GB CorsAir GT drive I use for MP games, so primary read, always first person in each round for COD. Love it!

SSD is super fast, and have had no problems with it. I have all my junk data stored on a 1.5TB WD green drive. Slow, but has the mass.

 

[g.leech]

Really great article! I was surprised at how in-depth it went, and exactly how this technology worked. Thanks for the hard work!

 

[infusednz]

Long live the Voodoo2.

Love the article.

 

[hairyfeet]

I'm curious about why RAM disk adoption is so slow in the industry. The last page of the article mentions DRAM caching for enterprise systems, but I'm pretty sure that end users would also benefit from a huge speed bump.

Ramdisks are really a desktop/home user tool because they have to be general purpose.

With systems and services architecture memory is turned into an effective 'ramdisk' with caching services as their use cases are a lot more specific.

Many major sites have physical systems dedicated to acting as a big ramdisk: i.e., arrays of 16GB servers with Varnish or NGINX using 99% of the memory to cache the webdata which effectively means the entire site is in memory.

Actually if they are using Windows Vista or Windows 7 especially they are already using RAMDisks, they just don't know it. Readycache is I believe the term though I may be wrong, but i'm sure a lot of former XP users have noted that the "free memory" is much lower in Vista and 7 and that's because when not in use by other programs its used as a cache for most used programs. I find that with 8Gb of RAM in both my desktop and netbook that all of my most used applications launch instantly and that is due to be preloaded into RAM and ready to go. I've also found that contrary to the early Vista reports Readyboost DOES give a pretty decent speed boost, as well as extends the battery life on my netbook, by leaving small I/Os to the faster NAND while sequential is done by the HDD. So many are already using RAM caching similar to RAMDisks, its just done automatically by the OS now.

 

[Wheels Of Confusion]

Actually if they are using Windows Vista or Windows 7 especially they are already using RAMDisks, they just don't know it. Readycache is I believe the term though I may be wrong, but i'm sure a lot of former XP users have noted that the "free memory" is much lower in Vista and 7 and that's because when not in use by other programs its used as a cache for most used programs.

Superfetch, loading commonly-accessed things into RAM instead of letting the RAM sit empty. W7 does this automatically when there's "free" memory enough to hold the applications/data.
ReadyBoost is using a small flash drive (thumb drive, memory card, etc.) as a non-volatile cache. Need to have some kind of flash device plugged in to a USB port.

 

[baldolino]

Excellent article, thanks!

 

[AnonymousRich]

Actually if they are using Windows Vista or Windows 7 especially they are already using RAMDisks, they just don't know it. Readycache is I believe the term though I may be wrong, but i'm sure a lot of former XP users have noted that the "free memory" is much lower in Vista and 7 and that's because when not in use by other programs its used as a cache for most used programs.

Superfetch, loading commonly-accessed things into RAM instead of letting the RAM sit empty. W7 does this automatically when there's "free" memory enough to hold the applications/data.

Perhaps it's because I don't have any standard workload and spread things across several computers, but I've not seen any of the instant app starts that Superfetch is supposed to give.

ReadyBoost is using a small flash drive (thumb drive, memory card, etc.) as a non-volatile cache. Need to have some kind of flash device plugged in to a USB port.

I tried this with my Daughter's old Toshiba Laptop using my fastest USB, a 2GB Sandisk Titanium (you're supposed to be able to run over it with a car). It did make a noticeable difference, but even here it was slight. They have much faster USB drives today, but I don't know if the benefit would be be worth the cost. Probably you'd be better off just getting an SSD.

Overall I'd say that these features may or may not work for you, for reason that are not clear. Even hardware tweaks like Hyperthreading may or may not help. As I recall SETI@home (the original) users claimed that running two instance of SETI@home would yield maybe 10%-15% more work units than the same processor without hyperthreading, and if you're chasing work units this will help some, but for most users the difference will probably not be noticeable.

 

[lolski]

It's a good idea if we could have a way to program the caching of web browser to write on these SDRAM of the SSD, or other drives that you have mounted in your computer (instead of your SSD, as to reduce the amount of write to it). Doesn't have to be all cached content, e.g. just a selective small files such as the html pages or javascripts. Because it turns out, these small files are those that hurts our priced SSD the most.

As people browses online practically the whole day I reckon it could relieve the SSD from alot of writing duty. I bet noone could feel the difference of browsing a cached page on an ssd or your magnetic drives

 

[AphidSoda]

This is a great article. I believe I'm having the issue of my SSD locking my system and "zeroing" the disk pages with 1's. It has been filled several times, so it makes since that I have used most of the free pages.

Does anyone know if you can do something to "force" the zeroing of the pages"? I read a suggestion about zeroing the disk with the linux tool 'dd', but that is a logical zero. I'd like the SSD to do that page-level "one-ing" where it clears the pages. That way, I'll regain the full speed of the drive.

Thanks again for a great article! -AphidSoda

 

[wawjohn]

I was looking how to zero out an SSD drive, and I found this: http://www.overclock.net/t/1227597/how- ... rted-magic

Apparently, there's a built-in command in the SSD which allows you to perform a "secure erase". The drive firmware handles the details, and it zeros out all the cells (sets them to 1).

An interesting, detailed paper from UCSD is available here: http://www.usenix.org/events/fast11/tec ... rs/Wei.pdf Reliably Erasing Data From Flash-Based Solid State Drives

Quoting the article: "It's also possible to emulate the beneficial effects of over-provisioning by simply using less than the stated capacity of an SSD—for example, by purchasing a 90GB SSD, creating a 30GB partition, and leaving the rest unallocated. The controller itself doesn't care about the logical constructs built by the operating system—it will happily continue to write to new fresh pages as long as they're available."

So I could just zero a used drive, partition 1/3 and leave the other 2/3 unpartioned, and I'd have a 200% over provisioned drive? That would be incredibly useful for server root disks.

 

[malor]

Not really. What actually matters is how many pages of data you write to the drive, how many times each cell has to be erased. It doesn't matter how you partition it, it matters how much you data you write and rewrite onto the drive. Partitioned at 90 gigs, it will still take almost exactly the same amount of total blocks erased before failing.

You can think about it like a massively overprovisioned 30 gig drive, but you can think that way independently of what partitioning scheme you use.

If you think, for some reason, that you will write less total data to the drive if you partition it smaller, then do so. But loading the drive once is no big deal, it's the constant rewriting that eats the cells. And you can rewrite data just as easily and just as quickly on a 30 gig partition as on a 90.

 

[Fritzr]

Aside from grating on your insistence of 'inexpensive' being correct ('independent' makes much more logical sense, regardless of the history of the thing - RAID0 is an argument against 'redundant' more than it is against 'independent'), very nice article. I too am glad to see Ars coming back to the long form, technical articles. It's really a surprisingly simple system, just with a lot of moving parts, aside from the SandForce stuff it's all rather straightforward.

More like this!

Useful reading: http://www.technick.net/public/code/cp_ ... uide_raid/

In RAID 0 the disks are NOT independent. The data is striped across the volumes in the set. There is no redundancy in this configuration.
In a 2 disk set (the minimum) half of each word of data is written to disk 1 & the other half of each word is written to disk 2. Because of this, removal of either disk destroys the entire volume. These disks are definitely not independent.

A collection of independent disks that are not tied together into a file system volume is a JBOD (Just a Bunch Of Disks) and is often confused with RAID 0 (striping without recovery data)
"Higher" RAID levels add error correction and data recovery information to the data. Some configurations do not stripe, but they still write data as part of a collective volume. Removing a disk generates an error condition. Data recovery is possible due to the error correction data written to the other disks in the set, but some of the resiliency to damage is lost until the disk is replaced and the volume rebuilt.

The Microsoft solution introduced in WHS 1 and available in Win8 is a Redundant Array of Independent Disks. The disks in the Microsoft file system can be removed from the set and read independently of the volume they are a part of. Trying this with a disk from a RAID volume usually results in garbage with the exception of Disk Mirroring without spanning or striping. Add disk device spanning to achieve larger logical capacities or data striping to achieve higher read write speeds with a larger logical capacity and you have eliminated independence. Even in Disk Mirroring mode, they are not truly independent. Identical data is written to each drive volume.

The I in RAID refers to the cheap commodity disks that could be used to build large volumes instead of very expensive disks with large capacities. Because of the the way RAID functions at the disk level, they are very definitely not independent file system volumes no matter how modern usage has corrupted the meaning.

 

[Fritzr]

Hmm, and there I would think the Lee would have problems with the word "redundant", not independent. If you put two disks in a RAID 0 array, they are still independent disks, but they are not redundant. (Perhaps that's why it was named 0) Strangely, Lee doesn't have any problem with the manufacturers using the word independent in their naming conventions - though, I don't think any of them are sticking them in a RAID 0 class configuration, so perhaps that is why.

RAID has always stood for "Redundant Array of Inexpensive Disks." The "I" has been bastardized of late and most folks say "Independent", but they're wrong. I can call a duck a cow, but that doesn't make it so.

RAID's opposite, which we don't hear much these days, is SLED--"Single Large Expensive Disk". When it first appeared in the late 80s, RAID was originally a cost-saving measure as much as anything else, since large hard disk drives at the time were extremely costly.

I'm not going to argue the history, because that is true that it began life as inexpensive. It would have been fine if you wanted to argue that, but instead you chose to say that it didn't make sense because of the independent part, which is simply untrue. Following that logic, it wouldn't make sense to use inexpensive for referring to a large array because the total cost of said large array would no longer fall into the inexpensive category.

The fact is that RAID is commonly defined both ways and personally, independent makes more sense in this day and age where a disks inclusion in an array doesn't preclude relatively expensive drives from finding a home there. The English language evolves and I see no reason why acronyms should not evolve with usage either.

RAID ties the disk together so that the Volume is dependent on the elements of the Array. The elements of an array are not independent. "Independent array elements" is a nonsense phrase.

The ability to use Inexpensive disks is built in to keep costs down. If you want to use $50,000 disks in a RAID volume you can, but it is not necessary.

The fact that the I in RAID is commonly defined as Independent is indicative of a major failure to understand what RAID is and how it functions. When part of a RAID volume, the disks are not independent. The data written to each disk in the array is extremely dependent on the other disks in the array. At the file system level it is a single volume that is stored on multiple physical surfaces. This is like saying that having 4 sticks of RAM in the computer means that you have 4 independent RAM areas that can be addressed independently. Contrary to that thought, the OS treats them as a RAIM (Redundant Array of Inexpensive Memory) volume.

 

[malor]

('independent' makes much more logical sense, regardless of the history of the thing - RAID0 is an argument against 'redundant' more than it is against 'independent')

The original meaning of the term is absolutely 'Redundant Array of Inexpensive Disks' -- it was invented in an era when permanent digital storage was extremely expensive. The whole point of the technology was using a bunch of small and cheap drives, instead of the big, expensive ones.

RAID changed the game so much that really large, expensive drives have almost completely gone away. The total price delta between the cheapest per-byte volumes and the physically largest volumes isn't tens of thousands of dollars, anymore, it's typically hundreds. And this is because of RAID, as it's really hard to sell a $10,000 drive, when ten $250 drives will be both larger and faster. FusionIO is sort of in that space, but they're selling a completely different technology that can be abstracted similarly to a hard drive.

In a sense, you're wanting to redefine what RAID means, because the original definition has been so wildly successful, has so dominated the market, that it seems kind of silly and pointless to say 'inexpensive'. RAID works so well that it's hard to imagine a world where RAID doesn't exist. Drives are cheap, but they're cheap because of RAID, so leaving that as part of the definition is important. If, somehow, RAID as a technology disappeared tomorrow, you'd see ridiculously huge single drives come back into the market, priced, once again, at nosebleed levels. The Inexpensive part of the acronym is directly responsible for why drives are inexpensive.

RAID-0 is a weak argument for redefining 'redundant', as it's kind of a butchered variation. There are many many flavors of RAID, and all of them but RAID-0 have at least some redundancy. In fact, I would argue that RAID-0 itself is a misnomer -- it's just striping two disks together. RAID-0 not being redundant doesn't make the definition wrong, it makes its inclusion in the term wrong.

 

[error404]

The fact that the disks are inexpensive is completely irrelevant to the technology, which is why I prefer the 'independent' variant. What do you call a RAID of expensive disks? I will grant that the initial impetus for the development and research of RAID was the increasing cost of high-capacity disks, however I don't agree that it's why the technology has stuck around. Today's RAID is typically used with expensive, low-capacity and high performance disks to achieve performance and redundancy. Some users do use the cheap, PC-oriented disks spoken of the original literature, but I think this is the exception, not the rule, and certainly hasn't been the primary selling point in most settings for at least a decade.

If RAID0's inclusion in the term RAID is wrong (which I'd agree with), then RAID0 can't be an argument against 'independent' as it was used in the article. Anyway, in the context of a 'Redundant Array of Independent Disks' I don't see the problem anyway. The disks are independent; they fail independently and have independent interfaces and storage, and they are what we have an array of.

Anyway, I think either term is acceptable, just didn't think the forcefulness was appropriate given that both are generally accepted and 'inexpensive' in the context of modern RAID doesn't make sense.

The initial paper seems to have been the 1988 paper by Patterson, Gibson and Katz, using the inexpensive term. Independent appeared in the literature only a few years later in the early 1990s.

 

[malor]

The fact that the disks are inexpensive is completely irrelevant to the technology, which is why I prefer the 'independent' variant.

Only RAID1 is (somewhat) independent; all the other types are clusters of disks that all rely on one another. The disks are meaningless on their own.

What do you call a RAID of expensive disks?

A RAID. At higher capacities, it will always be cheaper to gang together N devices of X capacity than to buy a single device of N*X capacity and speed. RAID devices are almost always far cheaper than an equivalent single-drive alternative.

Down in the super low end of the market, the mechanisms cost so much that the price stops moving downward. You just can't get it below a certain point, so if you were to buy a bunch of the absolute cheapest disks you could find, you might be able to do better in terms of bytes/dollar by buying a single midrange drive instead. So RAID doesn't make sense there in terms of storage size for money spent. But even this slightly odd case, the array is going to be a lot faster than the single mechanism. You'd have to spend a LOT more money to match the transfer rate you'd get off an array of the slowest and cheapest IDE drives you could find. Even in that segment, RAID remains inexpensive in terms of price/performance, even though price/storage kind of breaks down due to the physical minimum price for hard drives.

And, in the much more normal case, that of ganging up a bunch of midrange or high-end drives, the resulting RAID volume is vastly cheaper and faster than any single unit. This is such a powerful effect that they don't even make super high-end magnetic drives anymore, because nobody would buy them.

RAID has been so successful, in other words, that there are really only Inexpensive disks left. You just don't see $50,000 drives anymore. If you buy a $50K storage unit, it will have a bunch of inexpensive disks in it -- inexpensive, again, compared to the alternative. Even if they cost $1K each, that's still a tiny fraction of what it would cost to buy a single drive that was as fast and large as the whole array.

I will grant that the initial impetus for the development and research of RAID was the increasing cost of high-capacity disks, however I don't agree that it's why the technology has stuck around. Today's RAID is typically used with expensive, low-capacity and high performance disks to achieve performance and redundancy.

Again, unless you're at the absolute bottom of the market, ganging together N drives, even pricey ones, is a bargain compared to what a single unit of similar performance and capacity would cost you. RAID lets you take advantage of the miracle of mass production, using the same drives that smaller outfits are using, instead of needing bespoke storage solutions.

Some users do use the cheap, PC-oriented disks spoken of the original literature, but I think this is the exception, not the rule, and certainly hasn't been the primary selling point in most settings for at least a decade.

Dude, RAID is everywhere with cheap IDE-class disks. Again, that's the whole point to having it -- you can use inexpensive, relatively unreliable storage, and avoid downtime from your penury. These aren't big-dollar installations, that being the entire point, and because of that, they don't command very much attention, but they are freaking ubiquitous, especially on Linux.

Yes, they do also use RAID with pricey drives, but they do this because it brings high performance and high capacity into financial reach.... ie, it makes ridiculous amounts of storage at ridiculous speeds very Inexpensive, compared to any other alternative. Being able to buy 5 300-gig SSDs is vastly cheaper than a custom 1500-gig SSD would be, because you can buy the same hardware that everyone else is using. You just gang them up together to make the storage size you need; other people or companies buy fewer (or even singles) and make smaller volumes. But you're all buying similar drives, so the drive manufacturers can scale. It's the miracle of mass production of Inexpensive Disks.

If RAID0's inclusion in the term RAID is wrong (which I'd agree with), then RAID0 can't be an argument against 'independent' as it was used in the article.

True, but of all the forms of RAID, only RAID1 could actually be considered independent. You cannot take a single disk out of any other RAID type and get any kind of useful data off it... pull a singleton drive, and it's garbage. For the great majority of installations, you will need a large fraction of the total number of disks to extract usable data -- all-but-one for RAID5, all-but-two for RAID 6, and at least half for RAID 10.

Anyway, in the context of a 'Redundant Array of Independent Disks' I don't see the problem anyway. The disks are independent; they fail independently and have independent interfaces and storage, and they are what we have an array of.

They aren't independent, they're interdependent. You can only recover when Disk 1 fails if enough other disks survive. And arrays don't usually don't have truly independent interfaces, unless it's a very expensive setup -- the vast majority of RAIDs run through one hardware controller or motherboard. And, as discussed, for everything but RAID1, they're not independent storage either, because the disks are garbage data by themselves.

Anyway, I think either term is acceptable, just didn't think the forcefulness was appropriate given that both are generally accepted and 'inexpensive' in the context of modern RAID doesn't make sense.

In my view, it's only because RAID has had such a gigantic impact on the upper echelons of the drive market, making it so Inexpensive, that you can really seriously think that Independent is a better word choice. And it's had an equally large impact in the cheaper seats, too, if only because the technologies trickle down from the enterprise to the common folks.

The initial paper seems to have been the 1988 paper by Patterson, Gibson and Katz, using the inexpensive term. Independent appeared in the literature only a few years later in the early 1990s.

Well, they were wrong too. I didn't realize that the misnomer went back that far, though. I thought you were just backing up a misunderstanding, rather than echoing things people had actually been saying for real. So I owe you an apology for that much... I was a little more aggressive than I should have been, because I thought the idea originated with you. I'm sorry for being too harsh. I spoke more strongly than I should have. I seem to have come down with a case of Someone Is Wrong On The Internet, which I suppose is worthy of a scolding.

That said, even back in the beginning, the disks were not independent in the great, great majority of installations. Only RAID1 qualifies in that sense, and that's far too narrow a slice of the overall market to be the definition of the term.

Inexpensive always works, anywhere from the bleeding edge down to the cheap seats, because it's usually cheap compared to any possible alternative storage solution. Midrange or higher, I think it's probably ALWAYS cheaper, but the absolute bottom of the market kind of screws that up a little.

Independent, however, only applies to a very limited subset of the solution space.

 

[malor]

I mean, from another angle, realize that the world we came from was where IBM did your storage. I dunno if you saw that picture of an early 5MB drive getting loaded on an airplane, but it was the size of a washing machine, and probably a lot heavier.

In a world without RAID, maybe where it was locked up forever under patent or something, if you wanted big storage, you'd have to call a big company like IBM, and they'd quote you some obscene figure, and then show up a few days later with the forklifts. You'd end up with a huge wall of hardware that would hold, say, 2TB, and set you back a million bucks or so.

In a world with RAID, basically all disks are inexpensive. Even the scariest, nosebleediest prices you can think of for drives are a tiny fraction of what custom solutions would cost, and without RAID or something like it, custom solutions would be the only option. The very fact that you think about large drives as an assembly of units, costing a few hundred to maybe a thousand dollars each, as opposed to million-dollar monolithic units, is because of RAID.

In the RAID world, all drives are Inexpensive, even the pricey ones.

 

[error404]

Only RAID1 is (somewhat) independent; all the other types are clusters of disks that all rely on one another. The disks are meaningless on their own.

I still don't agree with this assessment. It is the 'array' part that couples them; the disks themselves are absolutely independent. Accessing the data stored on them is dependent on the RAID arrangement, but the disks themselves are completely independent of one another, sometimes all the way to the operating system.

RAID has been so successful, in other words, that there are really only Inexpensive disks left. You just don't see $50,000 drives anymore. If you buy a $50K storage unit, it will have a bunch of inexpensive disks in it -- inexpensive, again, compared to the alternative. Even if they cost $1K each, that's still a tiny fraction of what it would cost to buy a single drive that was as fast and large as the whole array.

Okay, I'll buy that. This evolution of storage argument is reasonably compelling. It strikes me as a rather inevitable and necessary engineering solution to the problem, not something that gives literal merit to a redefinition of 'inexpensive', but I'll buy it all the same.

They're not independent storage either, because the disks are garbage data by themselves.

I was never suggesting that the storage was independent, just that the disks themselves are. One disk does not depend on any others in any way. It will operate, and work normally, outside of the array. Its interface is independent, it's physically independent, and in software RAID it is even logically independent. It's the RAID that makes them depend on one another by making an array of them. I take the term to have a meaning something like: "We've taken a bunch of independent disks. We've organized an array of them with some redundancy built in."

 

[Rageset]

This article has enlighten me on SSD technology but it also has increased my hesitation on diving in. I know disk-based HD's have issues, but I still have IDE hard drives from over 10 years ago that are operational. Five years isn't good enough for me, I need them to potentially last longer than that. The key is potential. I've had some disk-based HD's last a couple of months, one with no warning of failure but my experience with these kinds of drives have given me some peace of mind.

Eventually, I will take the plunge into SSD, but only when I'm sure that a quality drive can deliver more than five years of normal use.

 

[atuxer]

I registered just to thank the author for an excellent article. One of the best pieces of technology-related writing I've read in recent years (maybe I don't read Ars enough ;-) )

 

[Dhj1980]

because no modern operating systems really delete files. When Windows or OS X or your Linux distro of choice "deletes" a file, it simply adds a note in the file system saying that the clusters that make up that file are free for use again.

This is still a shock to many people - people who may consider themselves "Tech-aware".