Slashdot Mirror
Intel 34nm SSDs Lower Prices, Raise Performance
Vigile writes "When Intel's consumer line of solid state drives were first introduced late in 2008, they impressed reviewers with their performance and reliability. Intel gained a lot of community respect by addressing some performance degradation issues found at PC Perspective by quickly releasing an updated firmware that solved those problems and then some. Now Intel has its second generation of X25-M drives available, designated by a "G2" in the model name. The SSDs are technically very similar though they use 34nm flash rather than the 50nm flash used in the originals and reduced latency times. What is really going to set these new drives apart though, both from the previous Intel offerings and their competition, are the much lower prices allowed by the increased memory density. PC Perspective has posted a full review and breakdown of the new product line that should be available next week."
Fortunately I got it for only about ~$300 so I only "lost" $100 with the new ones coming out. That having been said, I don't regret the purchase at all, it is insanely faster than any other laptop drive out there, while being completely silent and power-friendly. As for TRIM support, I've heard that Intel is not going to add it for the older drives, but I'm not sure if that is just speculation or if it's been officially confirmed by Intel (Intel not expressly say the old drives are getting TRIM support is not the same as expressly denying the support). Fortunately, the drives with the newer firmware don't seem to suffer from much performance degradation, so I'm not really obsessed with TRIM anyway.
Oh and yes, it does run Linux (Arch 64-bit to be precise) just fine.
I can't wait for next year with the ONFI 2.1 FLASH chips (the new drives are not using the new ONFI standard yet) as well as 6Gbit SATA support. At that point I'll put together a new desktop that only uses SSDs, and turn my existing desktop into a 4TB RAID 1+0 file server to handle all the big files... the perfect balance of SATA & spinning media.
AntiFA: An abbreviation for Anti First Amendment.
Getting the prices lower is definitely a move in the right direction. I'm looking forward to moving to SSD in the near future, and not having to worry about hard drive crashes anymore.
You see? You see? Your stupid minds! Stupid! Stupid!
While hard drives will continue to live on for a good while yet where $/GB considerations are paramount (especially archival type applications), the performance advantages of flash drives will soon trump the decreasing cost advantage both for workstation (x25-m) and server (x25-e) environments. The case for flash in servers is even more compelling, where we measure drives in terms of IOPS and a single Intel flash drive performs 10 or 20 times better than the best hard drives on the market for a fraction of the power consumption. Understandably, many IT managers are cautious about adopting new technologies, especially when the failure characteristics are not completely known, but I suspect the advantages are so great that minds are going to start changing, quickly.
Having gotten 2 out of 3, does Intel make a trifecta here, or is there some lurking downside (e.g. limited write cycles etc.)?
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
The last page of the review states that these should cost you roughly $3 per GB. Whether that's "laughably expensive" depends on what you want to do with the drive.
AnandTech has a nice writeup too. If the price curve drops like the first-gen X-25M we should all be happy pretty soon.
While SSD may be the new kid on the block and show signs of superiority. Hard drives retain a bit of advantage over their non-moving, solid state counter parts. Hard drives can take more write overs than SSD. Flushing the cache to the actual media is still faster on HDD than SSD. SSDs are still very susceptible to static discharge versus HDD due to more surface area having sensitive parts.
I do agree with the parent. SSD are a big thing and they have some important advantages. However, let's not go putting the cart in front of the horse and say that the era of SSD is here upon us. Cost, durability, performance, and longevity are some important areas where SSD needs improvements. In some departments of each of those categories SSD wins hands down. But SSD doesn't win enough in those areas to justify the incredibly high price of the drive. So it is a bit premature to start waving the banners right now.
..and it is fantastic. This was the largest performance increase i've seen on computers in over a decade. I was going to go with a Velociraptor because I knew how important drive access latency was but then Intel patched the fragmentation issue that was worrying me.
I got mounting rails to fit the drive into my desktop case so i'm using it as my primary desktop drive for OS, some applications (Adobe Design Premium Suite runs great on it! Photoshop CS4 loads in 3-4 seconds!), and my main games. I then have a 1.5 TB secondary drive to store my data and music collection etc. I paid around $430 for my 80GB Intel X25-M so being able to get the 160GB for that same price is a fantastic improvement. I will definitely only be going SSD in my machines from now on. Everything loads faster, I get consistently fast boot times even after months of usage.
It is amazing to see Windows XP load up and then all of the system tray apps pop up in a few seconds. You can immediately start loading things like e-mail and Firefox as soon as the desktop appears and there is no discernible lag on first load like you will get with SATA drives since they are still trying to load system tray applications.
"To strive, to seek, to find, and not to yield." - Tennyson
I'm excited about the end of the tiny-primary-memory era. One of these days, maybe the line between primary and secondary storage will shrink.
"Sorrow is better than laughter, for by sadness of face the heart is made glad." [Ecclesiastes 7:3]
Last year when the x25-m first came out the 80 gig version cost $595, or just a little less than $7.50/gig. Now the same 1st gen drive costs $314 with a -10 dollar discount and free shipping on newegg, or about $3.92/gig.
The new 2nd generation drive 80 gig drive sells for $225, or $2.81/gig. If it follows the same price trend as the 1st gen model around this time next year it should cost ~125 dollars, or about $1.53/gig.
Here are the quick results of the xbench of my 5400rpm 160gig drive in my two year old macbook pro:
Compare those to the results of the new drive here: http://www.anandtech.com/cpuchipsets/showdoc.aspx?i=3607&p=4
Sequential read on the SSD is over 6x faster, and sequential write is 2x faster, but for the performance where it matters the difference is much more noticeable. Random read on the SSD is nearly 140x faster, and random write is over 40x faster.
Couple that performance difference with the lower power consumption, lower noise, and higher threshold for damage, and its a no brainer as to what is the single most price-efficient possible upgrade you can make to a laptop to boost overall performance, responsiveness, and battery life.
I wish I could justify buying one now, but I can't. However, 12 to 18 months from now I will probably be shopping around for a new laptop, and when I do I won't be settling for anything but a SSD. The benefits are just to great to ignore.
How can reviewers be impressed by reliability when they've only had the units for, at most, a year? When these things hit the five-year mark running perfectly well with no data loss in the home/work environment, then I'll be interested.
Ok, they may have been stress tested in factories by the manufacturers, but reviewers don't do that sort of work.
If he's the Walrus then can I be a penguin please?
All you'd need to do to demonstrate to me the greater reliability of an SSD is drop it and a regular hard drive onto the table a couple of times while they're running and see which one keeps running. That would be enough to get me impressed by increased reliability. Regular hard drives are delicate beasts.
You may not be extremely lucky to get a regular HDD to the 5 year mark, but you are moderately lucky. Lucky enough that I would recommend regular backups rather than depend on your luck with the hard drive.
Wouldn't you?
As long as they don't wear out in months, instead of years. I'm still leery of just how quickly you can start killing one of these when it's hosting the swap file. And I have yet to hear data on just how many R/W cycles 34nm cells are good for yet.
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
Would you run DeFrag on an SSD like you do on an HD? After all, sequential reads are still sequential reads.
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
They have wear leveling algorithms. Enterprises wouldn't be buying these if they didn't work.
If you're really that worried about it just throw a velociraptor or something in your machine and put your swap file on that and use the SSD for everything else.
You are using English. Please learn the difference between loose and lose; they're, there, and their; your and you're.
marketing. WTF?
This has been covered many times. It's a good number. I can't recall the article, but basically if you write 20GB per day, you'll get more than 5 years out of it thanks to wear leveling and extra space (SSDs actually have more capacity than they make available to you). Now, you might scoff at that but:
1) 20GB/day is a lot for the typical user.
2) People who routinely do more than 20GB/day probably need a lot more storage than SSDs currently provide (you are talking about filling the drive in 4 days) so you probably won't be using an SSD for those purposes anyway
3) People who buy into SSDs at this point in time are typically more on the cutting edge, and are likely no have moved on before the drive wears out.
4) When the drive finally does start having problems, my understanding is that it won't just fail and you'll have lost data. The failure should happen on write, and if it fails to write that will be detectable. If it writes successfully, then it should be readable. If it does fail, I believe that part will just be marked inaccessible and the data will be written somewhere else. The drive should (again, as far as I know) provide details of the failure to SMART and other disk utilities, so the problem can be detected before it progresses to a critical stage. This is much better than magnetic media, where the typical failure is that you go to read data and it is suddenly inaccessible.
Of course, this is all just what I've read about previous generations. I have no data about the 34nm, but I have no reason to suspect it's any worse.
PS. If you want to know how much you currently write to disk and you run a linux system, check out /proc/diskstats. The 10th column should be number of sectors written. Each sector is 512 bytes, so take value*512/1024/1024/1024 and you'll get the number of GB each device has written since bootup.
For me, the biggest problem from SSD is the price (on Brazil, you pay two to three times the US price) and off course, the write cicles limit too. But, if they can be cheaper, maybe now I can consider a SSD to "system" partition.
Religion: The greatest weapon of mass destruction of all time
Intel rated the first generation X25-M's at 100GB/day for 5 years, I'd be surprised if these were significantly worse.
Let's make some wild predictions based on recent price trends. (Trends found here). Over the last few years, flash memory has been increasing in GB/$ at a rate of 185% per year. Meanwhile, hard drives have slowed to only 42% improvement per year.
Based on these trends, here is the estimated cost of 10 TB using either technology:
July 2009: Platter = $750, Flash = $28,125
July 2010: Platter = $528, Flash = $9,868
July 2014: Platter= $130, Flash = $150
July 2019: Platter= $23, Flash = $0.80
July 2024: Platter= $4, Flash = $0.004
In July 2024, a 10 PB flash drive would cost $42! Of course, we can't assume these trends will continue, but it seems a good bet that we won't be worrying about the size of our mp3 collections. The traditional hard drive may only have five years of competitive life remaining.
There is a huge market segment that doesn't care about much more space than 500 GB, so when the cheapest hard disk available is only $75 cheaper than a 500 GB SSD that runs circles around it, lots of people are going to go with the SSD.
So the actual crossing of the price / GB ratios isn't real important to the people marketing the SSDs.
Hell, I would jump at a 320 GB SSD for $200, which is nearly 7 times the price ratio you quote.
Nerd rage is the funniest rage.
"boost overall performance, responsiveness, and battery life"
That's the crux: SSDs boost performance pretty much only when doing random reads. Not random writes, not sequential reads, and not anything not HD-related. Basically, you're boosting boot times, app launch, game level load... and anything else that has to do with disk access, exclusively.
$200-400 is a lot to pay for a boost, even sizeable, in those rare occasions. They don't help with anything CPU-, RAM- or I/O-intensive. And cost pretty much the price of a second computer, or a netbook.
The Cloud - because you don't care if your apps and data are up in the air.
These SSDs contain a RAM cache that's powered by the host PC IO bus. Why don't they have a battery in the SSD? The OS thinks that everything ACKed as sent to the storage unit is written, but a power failure kills the cache before it's flushed. A little battery charged off the host PC IO bus would make these drives even more reliable than spinning discs.
--
make install -not war
understand when you put them all.
In the right place.
(Yes, I know the new parts are 34 nm)
I thought the progression of feature size went: 90 nm, 65 nm, 45 nm, 34 nm.
But the graphics processors seem to be using 55, and these SSDs are being reduced from 50.
I thought they had to pour gazillions into standardizing fab construction, steppers, and all the equipment. So is some plant manager stumbling in with a hangover one morning and accidentally setting the big dial for 50 or 55 or something? What's the deal here?
My other car is a 1984 Nark Avenger.
Let's make a few predictions based on recent trends:
July 2007: number of wives = 0
July 2009: number of wives = 1
July 2011: number of wives = 2
July 2013: number of wives = 3
July 2015: number of wives = 4
July 2017: number of wives = 5
July 2019: number of wives = 6
July 2021: number of wives = 7
Gosh, I'll need to implement wear levelling soon, too.
Extrapolation: almost as good as copulation.
The Cloud - because you don't care if your apps and data are up in the air.
One assumes they are MLC which are still good for about 10,000 write cycles. SLCs for 100,000.
The controller does a very good job of cycling "sectors" used, so the whole disk gets good use, rather than the same areas being overwritten constantly. The MTBF for SSDs is much higher than for conventional drives as a result, although the figure is less relevant as it's much more down to usage than anything else.
Keep enough free space on the drive for the controller to do its cycling, don't use it for constant writes (torrents are a good example of what not to use it for - as for swap file, I don't know), and the drive will last longer than you'll use it for.
Intel's SSD (and OCZ's Vertex) boost random read AND write speed, as well as sequential read AND write speed.
So what the hell are you talking about? Did we catch you talking about something you havent research at all, again?
"His name was James Damore."
The interesting difference between SSDs and platter based drive, is a write failure is not a warning sign that your heads are about to crash and you're going to lose the whole drive, it's just a failure of that one sector. Given extreme use over an extended period, the sectors would start to fail one by one, but no data should be lost, the drive capacity would start to shrink but the rest of the drive would be fine. Head crashes will be a thing of the past, thank god.
Even when the entire device's writes are used up, one should still be able to read all the data from it! :)
That's what Anandtech found out during "desktop" testing.
(And, I assume, OS, Apps and Documents loads)
That's it. 25% faster during the, what, 1% of the time your PC spends actually loading stuff off the disk ?
The rest of the time, you get nothing.
That's not worth $200 to me.
On the Enterprise front, I wouldn't know how compelling that is (or not). But on the consumer front ...
The Cloud - because you don't care if your apps and data are up in the air.
Its not only that, but the commodity platters that currently cost so little are not anywhere near the high end of regular HD performance. Time and again people compare the best HD performance against SSD's while only considering the lowest HD prices.
A high performance 10K RPM drive is going to cost $0.66/GB at best, while the 15K RPM drive will easily cost $1.00/GB or even a lot more. SSD's are considerably faster than these things, and look even better compared to the commodity drives.
"His name was James Damore."
I've had to build more than one server from consumer-class components when money was tight. Once these are down to 70 cents or so a gigabyte with 500GB+ capacities - let's say in two years, if prices keep dropping as they have been - I'll be putting them in servers at first opportunity. With their random read performance, they blow away even the best server-class rotating hard drives.
I can hardly wait. Really. Rotating media is the bane of my existence.
>Sequential read on the SSD is over 6x faster, and sequential write is 2x faster,
>but for the performance where it matters the difference is much more noticeable.
>Random read on the SSD is nearly 140x faster, and random write is over 40x faster.
So
>Not random writes, not sequential reads, and not anything not HD-related.
is wrong.
It also seems to me that you don't really need to say
>[no performance increases on] anything not HD-related.
or
>They don't help with anything CPU-, RAM-...-intensive
when you are talking about hard drive upgrades.
And of course it does help with I/O intensive stuff if that I/O is to the HD.
My RAM and CPU speed are fine, but my second upgrade (when I can afford it) will be an SSD (my first upgrade will be a video card - I currently have an Intel x3100, good for bleeding edge Xorg stuff, but low-powered, and Radeon[HD] will be catching up before I can afford it).
P.S. I wish slashdot would quote like a mail client (or a *chan), Also, the preview should not leave out blank lines if they will be present in the final post
Climate Progress - Hell and High Water
TFA says next week. Try reading it some time.
I bought a 4GB Gigabyte iRAM box specifically for the swap file on an SSD system.
Define laughably. The first SSD I bought, around '94-95ish was 128KB. At the same time, my laptop had a 60MB hard disk. The hard disk was worth about £80, the SSD cost £30, so the SSD cost around 180 times as much per unit storage. The SSD had a few serious limitations. The transfer speed very slow, but most importantly it was a single cell so the only way of reclaiming space after deleting / modifying a file was to copy everything off, format it, and copy everything back.
This generation costs around $3/GB, while a 2.5" HDD costs around $0.25/GB, meaning the SSD has gone from being 180 times as expensive to being 12 times as expensive over the past 15 years. The SSD can now handle orders of magnitude more seeks per second than the HD (which it couldn't) and a much faster linear transfer rate (which it couldn't), so it's now giving better performance than the HDD, in exchange for lower capacity and a higher price.
I am TheRaven on Soylent News
the new product line that should be available next week.
I am fighting the urge to head down to Puget Systems in Auburn, WA and see if they really have the SSDSA2MH160G2 for sale for $490.55. My guess is it isn't quite ready to be sold yet and was merely indexed by Google.
Must. Control. Checkbook.
"Giving money and power to governments is like giving whiskey and car keys to teenage boys." - P.J. O'Rourke
Part HDD, part SSD?
During operation, the SSD data is mirrored onto the HDD in the background, or, better yet, the HDD is larger and the most frequently used data is kept on the SSD but you get the whole capacity of the HDD.
Cool, thanks for the tip!
cat /proc/diskstats | grep "[sh]d[a-z] " | awk '{print $10 "*512/1024/1024/1024"}' | bc -l
http://images.anandtech.com/graphs/intelx25mg2perfpreview_072209165207/19505.png
tests say sequential write = 50% faster than HD, not twice as fast. Maybe 2x faster than older SSDs, but not than HDs. Again, that's 50% when you're doing disk writes, which really is not that often. Plus those disk writes need to be "blocking", not done in the background.
My point is that SSDs boost performance in the very rare cases where
1- you're doing "blocking" disk IO
2- SSD are significantly faster than HDs
That's not a lot.
Four your second upgrade, I'd sell my old PC, and use that + the SSD money to buy a whole new PC, sans SSD. That's what I'm doing right now.
The Cloud - because you don't care if your apps and data are up in the air.
Try and put things in perspective. On a desktop computer, what % of the time is spent doing disk access ? Actually, what % of the time is spent doing blocking disk access, because background ones are not really noticable, fast or slow.
Anandtech found sequential writes to be 50% faster than an HD (192 vs 120 MB/s). That's good, but not incredible, especially if your OS or HD does any kind of write caching.
Same remark for random writes, though SSD's advantage is much larger then: small % of time spent doing that, mostly cached anyway... the low-level tests are pretty much worthless.
Higher level tests show really negligible performance gains.
The Cloud - because you don't care if your apps and data are up in the air.
Laughably was probably a poor word choice on my part, sorry. Impractical is a little better.
I find most SSDs price-to-space ratio to need a little improving. Speed is nice but I much prefer space, and from what I've seen with SSD, it's way too much to get an SSD of equivalent size to, say, a 500 GiB hard disk and not break the bank. I might be wrong, but I'm sure I could buy another 500 GiB HDD for only around $90... whereas I'd be hard put to find an SSD of equal size for less than a whopping $600, which is way more than I even payed for my computer.
I am beginning to think that maybe Darl McBride was attacked viciously by a penguin as a child.
Unless you system is maxed out on ram, I don't see the point. 4GB of extra ram will give you the same ability as a 4GB swap file. I've never had any problems running either windows or linux with no swap as long as you have sufficient ram (under windows, the only downside is that I think it won't be able to give you any debug info if the entire OS crashes, because the swap file is where it dumps the crash log)
HotHardware has taken a crack at these new drives also today.
of doubling production costs and increasing complexity.
Boffoonery - downloadable Comedy Benefit for Bletchley Park
Try and put things in perspective. On a desktop computer, what % of the time is spent doing disk access ? Actually, what % of the time is spent doing blocking disk access, because background ones are not really noticable, fast or slow.
It isnt what % of the time is spent doing disk i/o .. On my system a low % of time is also spent rendering 3D graphics.. just the same I have a good 3D graphics card (8800GT.)
Anandtech found sequential writes to be 50% faster than an HD (192 vs 120 MB/s).
The only HD's that push that much write speed are also expensive. We arent talking about those $100/TB drives here, which are going to struggle with 60MB/sec sequential write. Drives like the velocirapter approach $1/GB. If you are in the market now for a high performance HD, the jump to SSD isnt as much as people make it out to be.
Higher level tests show really negligible performance gains.
Lets go even higher. People who actualy use their computer with these new SSD's rave about the performance. Thats real world.
"His name was James Damore."
Yes, I'm aware of what is in that document (that's how I figured out what the columns were to begin with). That document skips over the first 3 columns of the output for it's numbering (major device number, minor device number, and device name). It considers column 4 to be field 1. Not sure why they wrote the document that way, but PsychiKiller's command above uses awk to print out the 10th column, and that does indeed give you the number of bytes written.
When the drive finally does start having problems, my understanding is that it won't just fail and you'll have lost data. The failure should happen on write, and if it fails to write that will be detectable. If it writes successfully, then it should be readable. If it does fail, I believe that part will just be marked inaccessible and the data will be written somewhere else. The drive should (again, as far as I know) provide details of the failure to SMART and other disk utilities, so the problem can be detected before it progresses to a critical stage.
That's what I've read too, but my experience has been different. I had two of the first affordable SSDs, made by OCZ and with the infamous JMicron controller. I was having serious issues with data corruption quite soon after OS installation and I wasn't sure if it was something with the controller and Linux. I ended up using some *nix utility designed to fill the drive with a byte combination and then read it back and see if it was correct. There was apparently a multi-megabyte section of the drive that would fail writing every other bit. (Writing 1111 would read back as 1010.) Because of the wear leveling, the location of the failure on the drive would change constantly, and the drive/OS never notified of a write failure. Silent data corruption.
The drive was eventually replaced by OCZ, and neither replacement nor the other original showed similar issues so it may have just been a fluke. But it's very possible that the possibility of write failures is very much being glazed over by manufacturers. I have also seen flash devices like USB thumb drives and flash cards fail catastrophically to read written data, so I am pretty skeptical of these claims.
Still, it's not any worse than my experience with hard disk drives.
I might be in the market for an SSD soon, so I put some note together based on my reading of the articles in the topic and elsewhere. I thought I'd share them here so I can just Google them later.
Conclusions:
Also note that Kingston sells licensed clones of the X25 disks, although currently they are actually a bit more expensive than the Intel-branded ones on newegg.
If they'd use OUM for their memory modules they'd not have to worry about r/w cycles for a drive that is used for swap.
Still waiting on Serviscope_minor to wake up to fucking reality and realize that Jessica Price isn't going to fuck him.
I've never had any problems running either windows or linux with no swap as long as you have sufficient ram (under windows, the only downside is that I think it won't be able to give you any debug info if the entire OS crashes, because the swap file is where it dumps the crash log)
Unless you have the system set to share one file between swap and hibernation, and your combined swap-and-hibernation file is smaller than RAM. I've read comments in other articles telling how someone had to close programs before the computer could hibernate properly; otherwise, it would just suspend.
You made me think up a good question: exactly how hard is it to do a secure wipe on one of these things with a standard NTFS or EXT3 OS on it? Because I often get businesses to donate to me their older machine when they are gonna upgrade because I refurb them and give them to the poor. They don't worry about their data because they know that all they have to do is ask and I'll perfom a DoD-7 onsite, and I have a good enough rep that they'll just hand the boxes over knowing that my SOP is to DoD-7 without even booting up one time. After all, I want the hardware, not what is on it.
But if these things become standard for businesses and they can't be reliably wiped? Good luck with refurbing. It is bad enough that so many have bought into that wives tales about needing hardware destroyed (I say show me a single site that has recovered a DoD-7. Hell show me one that has recovered from even a single random wipe. You can't because it can't be done) but if these SSDs can't be wiped thanks to the wear leveling algorithm it is gonna be another piece of e-waste filling up our landfills when they could have been refurbed like HDDs. After all, a single mom doesn't care if a PC has a 40Gb HDD as long as her kid can do his schoolwork on it.
So has anybody tried to do recovery on one of these? Or tried a DoD-7 or other secure wipe? How does the level wearing affect the possibility of data recovery? I have seen a lot of articles on this tech but I can't remember ever reading anybody testing these for questions like this. And considering these are being marketed to business as well as gamers these questions should be answered.
ACs don't waste your time replying, your posts are never seen by me.
The DoD wipe criteria are based on magnetic drives. For SSD, I believe a delete + TRIM would be equivalent to a DoD wipe, and much faster.
Don't quote me on that though.
It's not that the data can't be completely removed, in fact once data is overwritten on an SSD as far as I know there is no way to recover what was previously there. Again, don't quote me on that, but if you are re-formating a drive, filling it up with a full pass of 0's should do the trick, because unlike magnetic media it isn't "mostly 0" or "mostly 1", it's either switched one way or the other. It's a completely different technology and the drawbacks that created the need for DoD multi-pass writes to elimate the ability to read back data should not be necessary.
Once the write gates have worn out and all you can do is read it, though, physical destruction is probably the only way to eliminate the data. Even then, it would be easier and less expensive than magnetic disc destruction (not that that's all that expensive).
BTW, regarding the effectiveness of HDD recovery from random writes and the DoD wipe spec, hard drive data extraction that made the extreme measures of the DoD wipe spec necessary is very very difficult today because the drives are laid out differently than they used to be 10 years ago. In particular, standing the magnetic bits on end made the surface area for each bit an order of magnitude smaller. This is what caused the explosion of hard drive sizes (500gb drives were seen very shortly after this happened), it also required much finer equipment to read and write to the drives in the hard drive. The techniques for recovering data on drives that had been over-written relied on the fact that the small read/write mechanism inside the drives was not very precise. It did not write the perfect magnetic equivalent of a 1 or a 0, the best it could manage was a .98 or .99. Well, upon writing a "0" over a .99 (which read as a 1 to the imprecise hard drive)it became a .02 or maybe .03. Because of this the writes and re-writes were effectively trackable three or four writes deep, and with sharp equipment and a good algorithm you could reliably trace and recover the original data. Hence the multiple passes of 0's, then 1's, then random, then more 0's, etc. all designed to fool data recovery algorithms. Fast forward to modern drives, however, and the read/write heads are writing .999's and .001's instead of .99's and .01's. It is significantly more difficult to measure and recover the data these days
None of it applies to SSDs though, they are different in every way and the DoD spec is meaningless when applied to them. Seriously though, if you want to be truly secure, a delete + TRIM should be enough, but there are also already programs that will fill the disk with useless data, after which a delete + TRIM would be as secure as you can get.
Security is mostly a superstition... Avoiding danger is no safer in the long run than outright exposure. - Helen Keller
That and I don't believe the data itself is lost is it? Only the capacity to erase the data and re-write it is lost? In other words, it would essentially turn that it into a read-only device in those 'bad' blocks?
Extrapolation: almost as good as copulation.
Almost.
Security is mostly a superstition... Avoiding danger is no safer in the long run than outright exposure. - Helen Keller
Hold on a sec, have you looked at the benchmarks? At all?
The fastest hard discs on the market can only keep up on the sequential reads and writes. These are drives like the 300gb velociraptor, which is loud and costs nearly $300. Granted, it's still about 1/3 the cost of the X-25m G2, but there simply is not a faster consumer grade hard drive that you can buy if you wanted to, so capacity is not relevant if you only want to talk speed.
Random reads and writes, which is what normally happens when you are using a computer for anything but mass data transfer, the fastest hard drives on the market are significantly slower than the slowest SSD's on the market.
Seek times? Hello? That's the single biggest failing of HDDs, and it's the reason drive manufactureres put massive amounts of cache on the drive - to mitigate that. Even with that SSDs are in the single-digit NANOSECOND range, while HDDs are in the millisecond range.
For the stuff that HDDs are very, very good at (large amounts of sequential reads and writes) they are close to what an SSD can do. Most people very rarely do bulk transfers of data. A few people do large data reads on a regular basis, but the HDD is not even on the same level for every-day usage.
So, what you end up with is SSDs are quickly approaching high-end hard drives in price and capacity, and they are faster in every way. In the ways that are generally most noticeable - random reads and writes, they are currently 40-160x faster. That's a crapton, and they are only getting faster, cheaper, and bigger.
Security is mostly a superstition... Avoiding danger is no safer in the long run than outright exposure. - Helen Keller
While that is true ATM, I doubt seriously it will be true in the future. Hell in the 90s I was just sure I would never use up the 40Gb HDD I had (still works and is sitting in a drawer BTW) while now, thanks to huge MultiGB game installs and videos I have moved up to 750Gb, and honestly would be surprised if I go past the TB barrier next year when TB drives are ultra cheap.
We are just now getting to where 10+ MP cameras, HD videocams, and other such devices are getting so cheap that everybody and their dog has one. All of these thing require huge amount of space.While I agree completely for the mobile space, where you just don't need to carry that much with you, or in certain servers situations where I/O is king that SSD will be the standard. But I think the HDDs have gotten cheap enough, reliable enough, and more importantly huge enough to handle incredible amounts of data for pennies that they will continue to be the standard for home computing, maybe with a hybrid SSD/HDD for the best of both worlds.
And let us be honest here-computers have gotten "super fast" for Joe and Jane user anyway. My biggest sellers right now are the bottom of the line AMD and Intel dual cores, and my customers can't quit talking about how crazy fast their machines are. The simple fact is for the kind of stuff Joe and Jane are doing both CPUs and HDDs, especially when it is backed up with a big fat pile of RAM( I build with 4Gb as minimum now) and the difference in price simply isn't worth it to them. And don't forget to Joe and Jane "more is more" and if you give them a choice of a 320Gb SSD that is fast or 2TB of HDD they are gonna go "Ohhh Big!" and go for the bigger nearly every time.
ACs don't waste your time replying, your posts are never seen by me.
If you want to carry a huge load and you don't mind driving day and night for a week, you need a Semi.
If you want to get to the end of the track as fast as possible, turn around and come back as fast as possible, what you need is a sub 7 second hot-rod.
Who in their right mind would buy a sub 7 second Semi? That's insane! It'd also cost millions of dollars, if you could even do it. Better to just fly.
I think my analogy went awry there somewhere. Anyway, slow, steady, big semi is the cheap HDD, great for long trips with a big load, while lighting fast hot-rod is the SSD. It can't haul as much, but man oh man is it fast! High-end HDDs are like the 15-second dodge van. Ya kinda go "Huh?".
Security is mostly a superstition... Avoiding danger is no safer in the long run than outright exposure. - Helen Keller
oblig
Sewage Treatment Facilities - "Our duty is clear."
Why does everyone insist on using cat where grep alone will suffice?
Everyone likes cats!
But mostly, it's just what they're used to. There's nothing wrong with it, it's roughly the same efficiency either way, so do it the way that makes sense to you, and for the problem you're solving.
Your sig is quite apt right now... :D
But that IS extending the life. Without wear leveling, if I've got an 80GB drive and I store 50GB of data on it which I frequently modify, then after X years that 50GB will be worn out and I'll be left with 30GB. That isn't enough for me to use, so essentially the drive is dead as far as I'm concerned. Now consider a drive with wear leveling. After X years, I will only have used up 5/8 of the write cycles across the entire drive. I can still use the drive for another 0.6X years. Wear leveling has extended the useful life of the drive by 60%.
But even for more typical usage, it's possible for wear leveling to actually extend the number of writes that can be done if the wear leveling works in certain ways. For this to make sense, you have to understand how SSD storage is organized. Much like a HDD, which is organized into sectors, clusters, platters, etc, we have a similar organization with SSDs. You have bytes grouped into pages, and multiple pages are grouped into blocks (and it goes on from there).
The smallest group of data which you can write on an SSD is a page. However, the smallest group you can erase is a block.
SSDs don't allow you to overwrite a page with your new data. Instead, you must first erase it and then write the new data to it. The problem here is that you have to erase a block at a time, but the rest of the pages in the block could already contain other data. So what happens is that the controller copies all of the pages that you don't want to modify from that block into cache, erases the block, writes back all of the page that are staying the same, and then writes your new block. Now surely you can see the problem here...you've only intended to write to one single page, but you've also used up a write cycle for every single page that you DIDN'T modify.
So how can wear leveling help this? Well, lets say that block consists of 10 pages, and only 9 of those pages are filled. You now want to modify one of those 9 pages. Well, instead of doing an erase, which uses up a write cycle on 9 of the 10 pages, the wear leveling can simply say "OK, I won't erase page 4...instead I'll just remember that I don't care about the data stored there. I'll also write this new data for page 4 into page 10 and remember that the data is now stored there". Thus to make that modification, we only use up a write cycle on a single page instead of 9 of the pages. Now, the next time we go to make a write, we'll have to erase the entire block and write to 9 of those pages. However, we'll once again have an empty page, so on the 3rd write we can do the same thing we did the first time. As a result, instead of a single modification writing to 9 pages each time, it averages 5 page writes each time (alternates between 1 and 9 pages).
Of course the wear leveling can be extended to perform the same type of thing across multiple block. The advantage here would be that, as lots of data gets modified, each page may eventually be migrated out of that block without the block having to be erased. Eventually, we could end up with the block being empty and then we can erase it without rewriting pointlessly to any of the page (or if it's almost empty, we'll only rewrite a few pages).
Other things wear leveling could do is recognize that some blocks never seem to get modified, and then shuffle that data to a different spot on the drive so that you don't end up with certain blocks that suffer almost no write-wear while other blocks are reaching their limit.
I don't know which specific techniques current SSD drives implement, but these are a few possibilities. I'm sure there are others.
It should be longer than that actually -- using the 10k write lifepsan and a 80gb drive, your life span would be:
(10k * (80gb/20gb)) * Q
where Q is the efficiency of wear leveling and defending against write amplification (as Intel calls it).
using Q of 0.5, we get 20000 days, or 54.8 years.
I think it will be less than that though...10k writes makes a lot of assumptions, and I think is only guaranteed for a particular period of time....the flash cells 'age', and the age interacts with write lifespan.
I can't find the website where I originally read the numbers I quoted, but that website showed the calculations similar to yours, and they came up with the 5 year, 20GB figure. However I did find the numbers I quoted straight from Intel:
http://www.intel.com/cd/channel/reseller/asmo-na/eng/products/nand/feature/index.htm
Expand the "Comparison chart" link a few paragraphs from the top. You will see an additional table. Last row in the table:
"5 years - 35TB written, up to 20GB/day for 5 years"
I'm still leery of just how quickly you can start killing one of these when it's hosting the swap file.
Then you should probably buy more RAM.
I bought a 4GB Gigabyte iRAM box specifically for the swap file on an SSD system.
That's a damn expensive way to fix problem(s) that likely didn't exist in the first place...
I could make a similar extrapolation based upon my life :
July 1999 : number of wives = 0.5 (fiancee)
July 2000 : number of wives = 0
July 2003 : number of wives = 0.5 (another fiancee)
July 2005 : number of wives = 0.75 (common-law marriage)
July 2007 : number of wives = 1
July 2008 : number of wives = 0 (thank God!)
July 2009 : number of wives = 0
July 2024 : number of wives = 0 (bet your ass on that)
On the plus side, I think the trends for SSDs will show consistent growth. Actually, on the plus side as well, the number of chicks I've been with has shown consistent yearly growth at a fixed rate of 8-24 since 1992, and based upon factors (a) I'm not monogamous nor have ever been or ever will be and (b) if it's female and has a hole and a heartbeat, it's getting nailed like cheap siding, I don't see this trend changing in the least. So let's hear it for SSDs (both Solid State Disks and Sluts Summarily Dicked)!
PC moderators can suck my White pierced, tattooed dick. If you think pride == hate, s/dick/Aryan meat mallet/g.
Interesting...I wonder what accounts for the difference in the numbers...aging, or just being conservative? Or maybe the 10k figure is not accurate...using it, an 80gb drive should be in theory able to write 800tb, not 35. Probably, all of the above.
Truecrypt has a handy feature where it can tell you how much data has been read and written to an encrypted system drive.
My system has been on for about 45 minutes, doing some email, web browsing and RDP. Total read data is ~550MB and total written is ~179MB.
Besides, by the time the SSD fails (which is more likely to be down to some kind of electrical fault or failing on-board flash/RAM) you will be able to get a new one for a fraction of the cost.
const int one = 65536; (Silvermoon, Texture.cs)
SJW, n: "Someone I don't like, and by the way I'm a fuckwit" - AC
Well, your 800tb figure would be based on a perfect distribution of writes...essentially like treating the entire 80GB as a gigantic ring buffer. Factors that could modify that figure:
1) First, your very basic figure should be slightly higher, because these 80GB drives actually contain something like 6GB additional capacity that is unavailable for use. It's there so that the wear leveling has some extra room to work with.
2) You have to write in pages at a time, but there are going to be many times when you don't need to write a full page, so that's the first thing to cut into the theoretical amount.
3) Wear leveling isn't going to be perfect. There are going to be pages that are written to "unnecessarily" as part of the erase process. With SSDs, you can write in pages but you have to erase in blocks, so to modify a used page, you copy the entire block to cache, modify the page in cache, erase the entire block, and write back the modified block. How many writes are "wasted" like this depends on both how you write data and how intelligent the wear leveling algorithms are.
"That's a damn expensive way to fix problem(s) that likely didn't exist in the first place..."
Not really. I got a good deal on the chassis, and pulled the RAM out of my box of junk.
Plus, half the reason I did it this way was just to see how well it would work.
But damn, is it fast! Paging basically incurs no performance penalty at all.
I ordered one yesterday. Guess you and the article got it wrong.
I got nothing wrong. The article claims that the estimated date is next week, but it also did say that there were a couple of places selling them now.
In any case, it only goes to show that you are a trolling fuckwad. Honestly, why would you ask a question when you would actually be able to buy one if you go to order one on the same day? Seems to me you could have answered your own question without asking it, and without the fucking snide remark that you gave in return.
They became available after I asked my question. They also sold out very quickly when they did become available. But I do have to ask was it really necessary to be such a complete and total jerk?
Does anyone know a store that sells this?
Well I have to ask, was it really necessary for you to act like a trolling fuckwad?