Slashdot Mirror
SSD Won't Make Sense In Laptops For Two Years
kgagne writes "While solid state disk drives can vastly improve random read performance and are perfectly suited to most mobile devices, many operations are sequential in laptops and desktops and involve writes where SSDs most often lose to magnetic hard disk drives in performance. While introducing multi-channel flash memory controllers and interleaving the NAND flash chips increases performance, it will still be about two years before the cost versus benefit ratio will make sense to install SSD in your laptop or desktop PC, according to a Computerworld story. '"I think you need to get to 128GB for around $200, and that's going to happen around 2010. Also, the industry needs to effectively communicate why consumers or enterprise users should pay more for less storage," says Joseph Unsworth, an analyst at Gartner Inc.'"
Try 16GB SDHC, available now for $50, delivered.
One for the OS and apps, one for the data. Need more? Put the other ones in your pocket.
Help stamp out iliturcy.
The small increase in performance isn't worth the several hundred in cost it would add to my laptops. I bought my laptop for $650, and a better HD just isn't worth increasing that to nearly $1000. YMMV.
craptops I don't see going SSD for a long time.
ordinary decent laptops I see offering SSD as an option but I don't see it being popular in the near future.
Ultraportables on the other hand are already going ssd in many cases. Tiny hard drives tend to have terrible performance and a 2.5 inch 9.5mm high drive is pretty big for an ultraportable (though some ultraportables do use them).
note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
Complexity, power, heat, and failure from kinetic shock. These are either reduced or zero with a flash device.
If you're looking for non-mobile, or a large storage application, then the disk makes sense.
The comment about sequential reads causing the SSD to lose on performance compared with magnetic drives caught my attention. Isn't this highly dependent on the filesystem you use and its strategy for block allocation ?
Wouldn't it be possible to design the block allocation algorithm to favour SSDs the same way previous generations of filesystems tried to put the next block on the disk to be the one under the head at the current moment (or whatever it was they did) ?
Servlet v2.4 container in a single 161KB jar file ? Try Winstone
Well, I use Linux/Windows as my servers, and use a Mac mini/G5 as my development environment, and even though I do now own an SSD laptop I know it makes sense.
Uses less power and can be dropped. My laptop is a macbook (not pro) and I know it is overkill with what I do with it, so a macbook AIR would be just the right thing to do if it had the correct pricing with SSD. But it doesn't, at least not for me.
No optical drive, limited HDD? I do not really care. For my visits to clients (of web projects) could be done on a 5 year old crap (if it wasn't windows and had a battery live of 10 minutes) so for me an AIR would be just fine.
Ohh... does it makes sense on WINTEL? Do not know how Vista runs on an SSD and if you have any space on a 64GIG drive after installing VISTA. Not flaming, I really do not know.
I know, that if I had to travel more I would get an AIR with SSD, and it would perfectly satisfy my multimedia needs (just grab those 4-5 movies to HDD for the flight and you are set).
Just my 2c, but I am a (mostly web) developer, so all you sales people and myltimedia freaks might have a different viewpoint about the whole fuss.......
I think people are willing to pay a premium for extended battery life. If I can use my device more, it has more utility.
-Dave
It will be easy to sell the concept of SSD to pretty much anyone, particularly for a laptop. Here is the short list:
- Faster Reads
- Potentially faster to wake up from sleep
- More durable
- Less chance of sudden and complete data loss (e.g. A smaller portion of the drive would fail instead of a complete drive failure as with a magnetic disk)
- Consumes less power
- Quieter
- Cooler (also a power saving feature due to less fan running time)
SSD drives are very cool pieces of technology and I for one can't wait to be able to buy a superthin laptop with no magnetic disk.
I can verify that Openoffice starts much faster on my little eee PC than on my Desktop machine with 75 MB/S 7200 RPM WD7500AACS. Or any other desktop I have used for that matter.
It is not just Openoffice of course, but Openoffice being a big pig of an application makes a nice example.
Have you got your LWN subscription yet?
SSD HAS made sense in laptops for two years already. Things like the eeepc have brought it to the attention of the mainstream, but there were other things before it (expensive Toshiba machines etc). When you think about it the majority of tasks a laptop is used for involved changing mere Megabytes of information - it's usually a combination of a typewriter and an address book.
Sure. If speed, durability, power, and acoustics are valueless to you.
For the rest of us, SSDs are worth a premium. The amount of that premium depends on the user and workload.
However, given the success of WD's Raptor line of drives, I would suggest that there's certainly a segment of the population who needs or thinks it needs faster rather than larger disk. And further that this segment is sufficiently large to support a business.
It's not just database users who are buying fast SSDs (which can hit 200MB/sec read and >100MB/sec write these days), and prices are plunging as a result.
High-speed Road Trip (18.000KPH)
Maybe its just me, but I fully expect 128GB SSD to go for much less than $200 by the end of 2010.
How much HDD space will you be able to buy by that time for $200? I'd say easily 10-15x capacity.
I feel like TFA is trying to set you up to accept higher prices on the hardware for a longer period of time.
SSD is merging onto the superhighway that is Moore's Law for HDD and I can't see settling for lower capacity and higher prices for more than another year or so.
Cube On! (http://stores.ebay.com/PuzzleProz)
Also, the industry needs to effectively communicate why consumers or enterprise users should pay more for less storage," says Joseph Unsworth, an analyst at Gartner Inc.
MAGIC
Seriously, solid state electronics, even after years and years of being around them as an early 80's baby, still just seems like magic to me. I can't wait to get rid of every little motor whine in my computing world, even if it's another 10 years, that will be a happy day to have a powerful computer without any moving parts.
I read the script, and I think it would help my character's motivation if he was on fire. -Bender
Time to burn some Karma...
On a "News for Nerds" site, moderators should understand the sources of disk latency. Rotating Hard Drives have latency from the time it takes to move the head across the platter, and for the platter to rotate under the head. SSDs do not have these sources of latency.
One of the big problems is that current flash is just slow on writes. Some of them don't do DMA properly. If there are problems with block sizes, this can be adjusted easily. But the underlying technology has to improve, or manufacturers need to build SSDs with more parallelism and better features. Perhaps very parallel SSD architectures might need filesystems optimized for large block sizes.
One of the big potential benefits of flash is reliability. Imagine highly modular flash drives for servers with hardware RAID 5? Instead of a disk failure, you get a notification that a module needs replacing. In fact, you could build versions with an extra slot for a failover spare in-place!
Also, with wear leveling, there's the potential for hard drives that can warn you several days before they fail!
My familys three eeepc and the one i have at work would be utter pain if they had spinning disks and not SSD. Cheap laptop drives is terrible when it comes to sequential reads but even worse at access times.
Ubuntu runs faster in some areas on the eee than on my brand spanking new desktop.
What i long for is faster speeds and more write cycles. Servers is what i think would benefit the most from SSD and thats where i suspect it will take off soon.
HTTP/1.1 400
Also, the industry needs to effectively communicate why consumers or enterprise users should pay more for less storage
For the consumers, or average Joe, there is no reason to pay more for less storage.
//.
The trade off is reliability. For 99%, if not more of the people using pc's today, a generic 120gb hd does the job just fine. On my desktop, I've never had any of the 3 hard drives fail in the last 12 years that I've been using them, or any time before that for that matter.
From a fundamental electronics standpoint, SSD is amazing. It's what I dreamed of making in the early 80's when I was first turned on to electronics by ham radio and Apple
As TFA states, it's not practical for now other than USB drives, which is fine. I just hope the development of these devices continue to recieve funding, because in the long run, it will be a boon to the PC industry.
How many write cycles are your SSDs good for?
With wear leveling? More than a hard drive. Time to put that myth to rest. And no, I am not trolling.
One good reason for SSD would be the negative effects on
using hard drives at high altitudes.
They are not well documented either.
http://forums.cnet.com/5208-6035_102-0.html?forumID=59&threadID=243684&messageID=2625001&tag=forums06;posts#2625001
google "32 trillion offshore needs IRS attention"
It is good to see that the typical computer is closer to getting rid of moving parts. Currently we have HDDs, CD/DVD/BR/HDDVD players and fans. We know that the SSDs are replacing the HDDs and that the players will be wiped out by the internet, wireless and memory sticks. Now we just need something feasible to replace the damn fans to get the first true consumer notebook with no moving parts.
Full Tilt
Not true. SSDs are already faster in every aspect than magnetic drives. And the new intel ssd drive will totally offset this in favor of ssds. Even the price is no longer a big issue, 64GB SSD drives can be gotten for $270.
120mb/s sustained and sequential read and write. WD Velociraptor (the new 10k rpm drive) has that value much lower at 85mb/s sustained and 68mb/s sequential.
http://benchmarkreviews.com/index.php?option=com_content&task=view&id=149&Itemid=1&limit=1&limitstart=4
There's no good reason for your SSD to come perfectly honest about that either.
Is there a reason for it not to?
How about providing a consistent interface to the software driver? Do you *really* want solid state disks that all require a different driver? Sort of like current video hardware, which is plagued by buggy drivers, missing specs of the chip, missing open source drivers...
I'd much rather have a standard interface, so that when I buy a disk, I know it'll work.
The Intel drive uses MLC and while its write speed might appear competitive, the relatively large block erase that happens with MLC will make this drive impractical for typical "system drive" usage. Small writes will bring this drive to its knees.
this sig was brought to you by the letter
Turned out it didn't fully support DMA...??? Like they didn't complete all the traces properly...
This problem is rampant in many flash card models and brands - even ones that claim to support DMA or UDMA. Search around on the interweb using your Napster machine and you'll see many others with the same issues.
:)
After trying a Transcend 4GB 133x that would only work in PIO mode, I got my hands on a Ridata 4GB 266x that *does* work in DMA. So if anyone is considering that card, maybe that's a good sign.
Mechanical challenges turned out to be not the only ones waiting for me when I worked on connecting the CF cards to the camera. These cards were hanging when the CPU tried to read them using DMA mode (and the card identified itself as supporting DMA mode). I tried to find the problem, and used all the tools I had. I added a bunch of printk's to the driver source, tried different speed settings for the DMA, and finally used an oscilloscope to spy on the signals between the CF card and the CPU. What I found was that the card did actually send the data using DMA mode, but always only for two "sectors" (1024 bytes total), regardless of the number of blocks to transfer written to the corresponding register. Then it silently hung, without activating an IRQ line, even if it was asked to transfer just a single block. And the CPU was relying on that interrupt to continue with the processing of the data read from the CF card. Careful examination of the data on the IDE bus did not reveal any problems (I was expecting something specific to the ETRAX). The same CF card with the DMA mode disabled in the driver worked fine (but slower, of course), as did the IDE hard drive (or SATA through the bridge) with DMA enabled. Googling the issue showed that I'm not the first to have problems with CF cards and DMA. The driver itself had a blacklist for some of the devices that caused problems. -- http://linuxdevices.com/articles/AT5102023409.html
Fact: Everything I say is fiction.
I hope it's not something important in that outlook PST. Because PST files are a really ugly data format, that are horrifically prone to corruption and just generally 'not working'. If it's important to have archives, the tool for the job is archiving it. Not keeping it in massive piles of 'maybe I will need it' junk on your HDD.
Reliability and data protection may be more important.
What I'd love in a portable device where performance wasn't the overriding factor:
1) Temporary files stored on a media that doesn't wear out, e.g. RAM or HD
2) Permanent files that are not confidential stored on a media that's resistant to shock. Accelerometers help but silicon generally wins here.
3) Confidential files that are in a "2-part" format. This could mean an encryption key on a dongle, or it could mean encrypted files with some of the bytes on a removable media.
A two-bank silicon "drive" in a RAID-0-like format with one of the memory devices removable greatly increases security even if the data is not encrypted. If it is encrypted or even compressed using certain algorithms, it won't even be partially recoverable without both pieces. This is also provides "two-key" or even "3-key" access for sensitive operations: One person has the laptop, one person has the external half of the data, and a 3rd person has the encryption keys.
This also gets around the "search your laptop at ports of entry" problem - if one person carries the laptop, and the other half of the data is sent by courier or electronically, there's not much to search. Of course, this doesn't have to be a 50/50 proposition, with encrypted data it could be 90/10 or even 99.99/0.01, with the small part shipped over the wire and downloaded to a hotel courtesy computer and put on a USB key.
Knowledge is how to play a game, intelligence is how to win, wisdom is knowing what game to play.
As a ff/paramedic the laptops we use (both truck-mounted and toughbooks) get quite a bit of abuse... though the Solid state drives are smaller, we store all patient information on a server as the report is finished, so we really don't need that much space anyway. most failures are from HDDs.
solid state gets the rating of 'firefighter proof'