Slashdot Mirror
Alienware Puts 64GB Solid-State Drives In Desktops
Lucas123 writes "In the face of Seagate's announcement this week of a new hybrid drive, Dell subsidiary Alienware just upped the ante by doubling the capacity of its desktop solid-state disk drives to 64 GB. Dell has remained silent on the solid-state disk front since announcing a 32-GB solid-state option for its Latitude D420 and D629 ATG notebook computers earlier this year. Now, Alienware seems to be telling users to bypass hybrid drives altogether. 'Hybrid we consider to be a Band-Aid approach to solid state,' said Marc Diana, Alienware's product marketing manager 'Solid state pretty much puts hybrid in an obsolete class right now.'"
Maybe hybrid?
can s/o comment on the durability of these (presumabily flash-based) devices? What if the OS decides to write stuff to certain sectors all the time?
how long are solid state drives suppose to last? Compared to the hard drive?
I would pay the extra price for solid state disks on my computer tomorrow, but I can't help but be a bit nervous about the limits of flash memory in terms of the number of times a cell can be written to. On a well exercised machine, how do they pro-actively monitor this and/or avoid corrupting data when one of those cells can't reliably flip bits anymore? I'm not too stressed about it if I get a corrupt picture on my digital camera because of that, but I use my computer for real work.
Best,
Damn this is going to make crash recovery a nightmare. When my hard drive crashed I was able to read the data off by opening it up and using a magnifying glass, pen and paper. Using my notes and a typewriter I soon had my old drive data mirrored onto my new drive.
Is it possible to do this with a solid state drive?
Open source, flash charts
Comment removed based on user account deletion
'Solid state pretty much puts hybrid in an obsolete class right now.'
Yes, well, as a graduate of Solid State, I'm really getting a kick out of his reply.
The theory of relativity doesn't work right in Arkansas.
No idea who modded this 'underrated,' but those buses have nothing to do with this. The AGP bus never had any effect on storage performance (isolated), the PCIe bus is much faster than storage, etc. The IDE controller is on the Southbridge, and it's not bottlenecking. Storage is the bottleneck more often than not (seek times and raw speed). Will this cut down on seek times? Yes. Solid-state storage has nigh-instantaneous seek times, since there aren't any heads seeking.
"The more corrupt a society, the more numerous are its laws." -Tacticus
Yeah, but as the first adopters and the die hard gamers looking for every advantage they can get buy more of these, we'll see the price drop eventually.
It also means that the extra speed and reliability really isn't worth the high price for most business folks who would be, I guess, the ones to really drive the market in the beginning stages after the first adopters.
I prefer Flambe as apposed flamebait.
Now there's a misleading quote if I ever heard one. Magnetic drives currently allow for storage of 250GB and up for a cost of $0.50/GB or less. In comparison, Flash Drives are are still measured in dollars per GB. The hybrid drive allows a bit of a tradeoff. A fast storage cache combined with massive space in exchange for a slight increase in price. Thus it's possible to have 1TB or more of storage, but with the performance characteristics of Flash memory under most circumstances.
Javascript + Nintendo DSi = DSiCade
Ever notice you never get any read errors on SSD? That's because they don't spend any bits on ECC or RS codes for error correction! So it may be fast but how would you know you are reading what was written?
SSD won't be acceptable until the native capacity will be ~1.4x the accepted storage capacity.
The PCI bus isn't a bottleneck until you start getting over 120 megs a second down from a hard disk. Basic parallel PCI transfers up to 133 megs per second, theoretical, and even a single lane of PCI-e is quicker than that.
Well, from what I know, the write speeds are abysmal, but the read speeds are actually quite fast, especially when you're accessing lots of little files, because you cut down on seek times. So a flash drive would be optimal for putting static data like the OS, and Programs, which change very rarely, and contain lots of little files that need to be read very quickly. Your computer would boot a lot faster, and programs would start much quicker. I don't think these would operate well as a swap partition, but then again, the best solution to swap is just buy more RAM, so you don't have to use it.
Anthropic principle: We see the universe the way it is because if it were different we would not be here to see it.
As soon as they ramp up production, and cut down on "bad drives" in the production process, the price will come down. Anyone remember buying a 250 megabyte drive back in the mid 90's and paying more for that, than you do for a 250 gigabyte drive today? As with anything "new" (ie: iPhone) the early adopters are going to be paying a price for the "wow" factor. I suspect in less than 24 months, these will become more mainstream.
Okay, for some $1,700+ you get two 64GB SSD drives.
...and:
And what do you get for that ridiculous amount of cash? According to Alienware's best PR spin:
"speed up operating system boot and application launch/runtime by up to 2 times."
"consume up to 50 percent less power than rotating HDDs."
Those specs aren't exactly thrilling, particularly since "up to" tends to mean you'll never get close to either spec.
Seems like a complete joke to me, which oddly fits in quite well with the rest of the Alienware line-up.
Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant
- Quieter.
- Can be shaken about more.
Cons:- Lower capacity.
- More expensive.
- Not suitable for swap.
- Dies after n thousand reads to a particular block.
Misleading claims:A quick look at Alien's desktop systems shows hard drives with a minimum capacity of 160G. They are announcing 64G for mid 2008. How will a small, expensive store obsolete a large, cheap hard drive?
seek time hasn't been a issue for a LONG time now. transfer speed is what is king. my 3 year old U320 Scsi drives still kick the ever living crap out of anything IDE or SATA and I bet will kick the crap out of these oversized flash drives.
What nobody is pointing out is that a standard windows install will thrash the hell out of a Solid state drive. There is a reason you need to balance your writes and not treat a SS disk like a hard drive. I destroyed a Solid state IDE drive back 6 years ago (you have been able to buy them for over 15 years now) by installing windows on it. the swap space died within weeks. Yes I knew what I was doing, I was proving a point to a manager that refused to listen to his engineers. you need a special filesystem to even out writes to the SS disk to make sure your drive life is maximized. that means that you really should run the Filesystem in ram for apps that like to write to the disk all the time. Your favorite webbrowser in default config write a crapload of junk to disk. that all needs to be disabled.
Yes newer SS disks are better. Yes you can get SRAM based ones that have a battery backup. but the cheapest are the flash based and they have a limited lifetime of writes.
Do not look at laser with remaining good eye.
Flash costs seem to be halving each year at the moment, while hard drive capacity is going up by a smaller amount.
Flash may eventually max out, still more expensive than hard drive space, or it may eventually overtake it. I'm not convinced that there's anything inherently more expensive about flash construction techniques in the long term.
My Journal
Do you read slashdot at all? We have this exact same question asked many times every single time an article about flash memory is posted. No, it's not a problem for the average user thanks to wear leveling. End of story.
Last I checked, while solid state drives had excellent random performance, their transfer rate was way below that of normal drives. Now random access is all well and good, I'm glad we are improving on it, hard disks are really weak at that, but it isn't the only concern, and maybe not even the primary concern in most setups. If you have a well maintained system with a defragmented drive, and that system is a single user desktop, it's a good bet that your disk access is often fairly sequential. You go and launch a game, the drive seeks to the game executable, loads that, then seeks to the game data (which is often in a couple large pack files) and starts loading that. There's not a whole lot of jumping around. You aren't waiting on the drive because it is having to seek, you are just waiting for it to read from the platters.
As such if solid state drives aren't faster (or at least as fast) in BOTH regards, I'm not sure I see them as a better performance choice. Sure, there may be a reason to use them in servers or other multi-user situations where the majority of the disk penalty is because of seek time, but I don't think that holds true at home.
Seems to me that until it gets faster, hybrids are the way to go. That's how MS's ReadyBoost thing works. You add a flash stick to a computer and use it for ReadyBoost. It's maximum transfer rate is much slower than the disk, but its seek rate is faster. So what Vista does is cache the first part of things you frequently access there. Then, when you run it, it starts loading from flash while the disk seeks, then switches to the disk as soon as it is ready. It only works as a supplement to a drive, it isn't a replacement, it won't fully cache programs on there because, size aside, it'd actually be slower. It's just designed to try and fill the access gap, not as a real replacement.
I have a Latitude D430 for work with a 32GB SSD, and while it isn't noticeably faster than the guy next to me that has a standard HDD in the same machine, my battery life is WAY better. I'm getting 10+ hours with the extended battery out of the thing. And, I'm not as scared about losing data due to a dropped laptop. (Networking = frequently dropped laptops!)
Me fail English? That's unpossible!
"Hybrid we consider to be a Band-Aid approach to solid state."
Coming from a company that has positioned itself as the rice boys of computer hardware, that remark sounds rather appropriate.
Those who can, do. Those who can't, write technology blogs.
Flash drives seem tailor made for music samplers which can stream off the hard disk, such as Kontakt, Gigastudio, and LinuxSampler.
Samples can contain hundreds or thousands of small files. A good piano sample may contain samples for 88 notes, each note having sample files for 8 to 16 different volume levels, release samples, close and far miking samples, etc. Reading these samples in real time puts a lot of demands on a hard drive. Plus, with most samplers, you can have multiple instruments loaded, and you can overlay instruments. So having an instrument bank of full of piano, horns, drums, violin, and guitar samples can bring a hard drive to its knees.
Once you've written your samples to the flash drive, there will be only a limited need to rewrite. So the write speeds and rewrite limitations won't be a problem.
Flash drive should give a huge boost to the performance of music samplers.
This ad space for rent.
and what are you trying to prove now ? That the ss drive built 6 years ago were crap ? I agree, but in 6 years, the industry has changed. So did the ss drives. It would be interesting that you redo this experiment and post your results in 3 months.
funny, I was checking out the Dell choices the other day since finding out my company has a discount.
They offer a 128GB solid state drive option on their XPS M1730 notebook.
I don't know how long they've offered that but it seems that Dell does have that option.
Is "solid state" really a good way to refer to flash drives? Sounds like a terrible mis-nomer to me.
Earth to Lumpy:
:-D
Flash drives have had wear-leveling as standard for several years.
Now, back to your utra-scuzzy crap kickers.
A lot of flash-based drives I have taken a look at have very poor write performance. Why anyone would choose to use this in a high-performance desktop is strange.
Single lane PCIe is 1.25Gbps.
After you move to bytes and remove overhead you get 150 MBps.
whois gawk date unzip strip find touch finger mount join nice man top fsck grep eject more yes exit umount sleep dump
First companies will try to milk as much money out of people as they can, hybrid drives. Second, it is possible that there is not enough world capacity to produce enough flash HDD. However, the market will correctly price these drives based on demand, as supply ramps costs will drop. Third, the manufacturers are testing the water for flash HDD. The switch would be a fairly large changeover from existing HDD. Thus, production equipment would have to be scrapped before its end of life.
I don't get it. Modern flash has 1M+ write cycles, and we might presume that there is some rudimentary write balancing in these drives. If you work 1GB of cache (not unlikely, and probably on the low side for Vista), I get 8Gb x 1M writes = 8x10^15 write operations before your 1GB area fails completely. Using load balancing, and dynamic reallocation of a 64GB disc, but taking the "limit" of useability at 50% of the write cycles before you are might start to worry, how long does it take to write 256x10^15 bits (8x10^15 x 64GB x 50%)? Well, TFA didn't give write speeds, so I'm going to presume a ludicrous write speed of 50MB/s (I'm not aware of any consumer-grade flash that writes that fast). 50x8=400Mb/s or 4x10^8 b/s. So if I've got my exponents correct, that put the 50% threshold at an even 64x10^7 seconds, or about 177,777 hours of continuous writes, or only about 20 years. That presumes you actually have your machine (a) never reading the cache, and (b) never writing anything else to the disk, since the entire bandwidth taken up by the cache writing and (c) it's doing this 24/7 (as I presume Vista attempts to do).
And at this point, your drive will be through 50% of it's theoretical write-cycle life. And about 1/1000 the capacity of the drive you would be able to buy for $100 to replace it.
Is it just my observation, or are there way too many stupid people in the world?
A couple years ago (Fall 2005) I did my senior engineering project in college using embedded Linux devices which utilized 512MB flash drives (CF) as the only storage mechanism. The devices were basically Soekris boards with Debian and some highly custom WiFi drivers/software designed for mesh networking research. After my project, I was hired on by the research institute which funded the project, so I got to play with these things for a while. Nearly every mesh node that used flash ran into "hard drive" issues within a year (we suspected the failure frequency was directly related to how often we used the devices). Most of the time it was simply the MBR becoming corrupt which you could fix by mounting the card on a Linux computer, chroot'ing and re-running LILO; but in a few cases we had to replace the entire card due to corruption. These devices had fairly typical usage patterns of a normal desktop/laptop (booted daily), and we were no where near the 3-5 year estimates most people give flash drives.
Sadly, PS/2 was yet another victim of USB, which doesn't care what you plug into it, the electrical slut.
How much space do these samples take up? It it too much to be loaded into memory? Seems to me that if you're re-reading the sample every time you need it, then there's something wrong with the way the program accesses the samples.
Anthropic principle: We see the universe the way it is because if it were different we would not be here to see it.
These days (well, since YEARS ago now) we have this thing called Wear Leveling which means you can't wear out NAND flash by simply writing over the same portion over and over again. The writes get spread around other areas instead.
It hasn't been possible to kill a (decent) solid state drive like this in a very long time now. Please don't misinform people.
Software raid (using RAID 0) 4 Sandisk firewire readers. Now take 4 40MB/sec read time, 8 GB flash disks from same company. RAID is fun if you don't have big seek times, and you'll have 32 GB of storage for far less money than you are trying to spend. Use RAID 5 for less performance, but bigger reliability. Actually, I'm still waiting on someone to perform this experiment, it's still too costly for me. Anyway, I just had to wait for my drive to spinup in my fanless computer, so I'll probably but a single 8 GB card and firewire reader just to see how much it can speed up my VIA EPIA system. I'll just backup to the HDD now and then, and use it for music storage as well.
Are these packed with a Adtron A25FB-20 ? Last time I checked a solid state disc was more then $1000,00
I recently switched my home servers to using a sandisk 4G flash for / (with variable directories moved to disk; /home, /opt, and parts of /var such as /var/logs). The system now loads in about a 1/3 of the time. I have also seen that it is quieter (the regular disks sleep when not in use and the fan that ran all the time now runs infrequently ), and the temp dropped 5 degrees. I would expect that my electricity usage has dropped (as evidenced by lower heat).
All in all, I have no doubt that within a year, flash will be the rage.
I prefer the "u" in honour as it seems to be missing these days.
You could run Windows well on flash without too much trouble, use a ramdrive and redirect TMP and TEMP to that and disable swap, set your browser to use TMP for cache or disable it altogether. Turn off timestamping on file access and it's even better. By that point if your flash has 500K writes before average failure then you have a drive that will last many years, probably longer than your average HDD.
There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
what about using raid10 to improve both ?
:) ), that would be a killer laptop. well, maybe a killer because of the price, but we all hope the prices will drop...
let's say, 6x32GB ssd, with three raid1 used in one raid0.
both read and write speeds should improve quite noticeably, total space would be ~90GB.
i don't know how large these things are, how much power 6 of those would consume and how much heat would they produce, so any of these could kill the solution.
if all three stay at the normal hdd range (single hdd
Rich
Who modded this clown +4 Interesting? The only thing I can imagine from your completely incorrect post is that you are trolling, in which case I got sucked in. But I can't stand by and let the +4 make other people think that what you say is even close to the truth. Please people, read up on this tech before you believe his completely idiotic statements.
Interesting datapoint --- however, how full were the 512 MB cards?
Did you compare their lifetime w/ 1 GB cards w/ the same data (but much more empty space)?
William
Sphinx of black quartz, judge my vow.
A positive attitude may not solve all your problems, but it will annoy enough people to make it worth the effort.
I too have seen this. But what we found was diff cards (even the 'same type') card would give different performace. You look a bit closer at the specs and they say things like 1 million in big bold letters. But down under it says 100k-1M (some as low as 30k) depending on usage, temp, voltage levels. What we found was boot cycle would cause the most strain on the devices due to power levels. Reformat and the device was fine again for awhile.
Flash is all over the place in quality of product. Some you can run over with a truck and they will keep on truckin, others you look at them wrong and they self corrupt. Even cards that are supposedly the 'same' have been all over the place. In other words they changed something from rev a to rev b, and it didnt help the drive.
And do not get me started about hibernation/power off and writing while the cpu is 'going away'.
http://www.sandisk.com/Products/Catalog(1353)-SanDisk_Extreme_Ducati_Edition_CompactFlash.aspx
I haven't benchmarked it myself, so I can't say anything to back up the marketing claims. But if true, that's in the neighborhood of the 50 MBs that you used in your calculations.
Stack 8 of the 8 GB versions together, and you've got the 64 GB that Alienware is using.
This is really cool. I'd love to replace a lot of platter-based hard drives with some of these, and it's looking like a new opportunity is starting to open up here.
The best way to predict the future is to create it. - Peter Drucker.
Unfortunately I didn't have the opportunity to investigate it much further (and I no longer work for that research institute). From what I recall, we partition the cards into two volumes. The first volume was set to read-only and contained static OS files (eg. /etc, /lib, /[s]bin...) and we had a second partition for logging (which obviously could and did fill up). I believe the read-only volume was larger than the space actually used so we never filled the cards completely; it's probably fair to estimate we hovered around 60-85% most of the time. All the CF cards were off-the-shelf components bought in one big purchase (so it may have been related to that batch); they were typical cards you'd throw into a camera and I'm unsure what speed they were.
When I was hired on, I was actually developing embedded devices which would work over the mesh network provided by the mesh nodes mentioned above, so I didn't get to try larger cards, etc. (but that's an interesting theory and would have been good to test). I would also have been curious to just leave one node on for the whole time (not rebooted like the other nodes) and see if it failed around the same time.
Sadly, PS/2 was yet another victim of USB, which doesn't care what you plug into it, the electrical slut.
How often were you writing the MBR? That's a very strange place to get a failure like this.
We at slashdot are scientists, specialists and kernel hackers. Your FUD will be found out.
100 comments so far and no one has commented on the built-in pun "Dell has remained silent on the solid-state disk front..."? :-) One of the things I love about my Mac mini is how quiet it is. Bring on the silent drives!
In other news, I still want a small laptop (preferably Mac) with a 10" screen, no optical or hard drive, and ~10 GB of solid-state storage. Maybe a low-power wireless card that only does 802.11b. Should weigh 2-3 pounds and run for 12-16 hours on a charge.
Dear Slashdot: next time you want to mess with the site, add a rich-text editor for comments.
My favorite print magazine Custom PC (recommended for those PC hardware fetishes, although not sure if they cover the USA?) had a round up of these solid-state devices in the summer:
http://www.custompc.co.uk/labs/601070/solid-state-drives/products.html
Still looks like the market needs more baking by the 1.0 cash-gullible crowd...
Not to mention the real problem lies with the RAM. We really need to get MRAM on the way to enable faster reboot and faster transfer of information through the motherboard. Sure increasing HDD efficiency will help run a system faster but as far as productivity RAM needs some serious advances.
OK, don't kill this BEFORE you read it....
Since it's so easy to get "old" data off of a hard drive once it's written, have the ultra-security experts looked at RAM based drives for storing data that should never be recovered at a later time? If you just used a regular disk to boot your OS fully configured into a RAM-based drive, then run the machine from there you could theoretically have a non-recoverable data storage unit. Long-term files would be written to a USB FLASH drive. No "ghost image" to be read back off a magnetic device and looked at, just pull the plug and BAM, your "history" IS really history (inside the computer, anyway).
Does flash technology leave a phantom image after it's erased like magnetic storage does?
That may be true with a homebrew SSD, but when you are controlling each chip directly without having to go through a RAID or USB interface, you can simply multiplex the reads and writes over 10s or 100s of memory chips, increasing throughput speeds to whatever you want, 1MB/s to 1GB/s, you name it.
Yes, but on my laptop, I would gladly get a solid state disk of 64 or even 32 GB, and then supplement it with an external 500GB harddisk, which i won't normally carry around. It's true that the price per GB is a lot higher, but do I really need
This way:
-my laptop will be lighter
-my battery will last longer, because solid state uses less power
-my laptop will last longer because i am less likely to break the hard disk (ever tried dropping a hard disk while it is spinning? or even when it isn't actually.. I broke my ipod that way twice and then decided that --for me-- spinning hard disks are not portable.)
will my laptop also be faster? maybe, but i don't really care that much.
also, my laptop will be more silent, with no spinning disk. Of course there are fans, but with some sacrifices in the performance area it would be possible to build a laptop with NO MOVING PARTS . Totally silent. How cool is that? ( In fact, The XO does that already, but is a bit too underpowered for most people)
This would be my suspicion as well.
Wear levelling can only occur when there are free blocks to utilise.
In my Amiga days I had a 245mb Quantum fireball drive (first one I was mega proud..) and I had a 20mb partition for my code.
This was the only portion of the disk which ever crapped out on me.
After a deep reorganisation I took the 20mb block out of use and left it with one single partition (~220mb).
I continued using this drive and computer in a similar way for another couple of years without issue from the drive which I attributed solely to there being spare blocks to use instead of cramping everything up.
liqbase
Our company manufactures embedded devices that run off CF cards (typically the cheapest 512M we can source). In five years the only failures have been attributed to bad CF cards themselves. Now, each time we receive a difference batch of cards, we scrutinize them under many days of stress testing.
http://laptop.org/
I hold very few opinions. I hold information based on observation and fact. If you wish to disagree, please use facts.
It is this random access low latency performance that really improves the experience for the users.
Now think about this. You saved some electricity by switching to flash, as well as heat output. What happens when Google does a cost benefit and sees how much power they could save across their entire cluster farm in both energy usage and heat, and swaps everything out. It's going to be a great energy conservation benefit, as well as help bring down the cost of flash (economy of scale).
I find myself wanting a computer to be powerful in 2 main ways: performance and capacity (especially in the age of MP3's and digital pictures). So what this device does for me is allow me to load my intense applications and the files they access onto the solids state drive, and leave pictures of my Cat and MP3's on a standard HDD, where they're accessed infrequently. Solid state drives entering the market will drop in price and cause 'regular' hdd's to drop in price as well, I WIN.
Hybrid drives sound like a much easier solution for most people. Let's say we had a hybrid drive with 4GB of solid-state storage (can't be that far off, can it?), the benefit here is that the drivers or hardware handles the tiering of your storage/data for you. If you're looking for performance and you have much more than 64GB of data, for example, the hybrid drive I think will do better than the solid-state/separate hard drive combo in the long run. I know I'd much rather have an LRU cache handled for me rather than me trying to create something similar by trying to manually place data on the correct storage tier.
The other option, of course, is to have a filesystem that does this for you. Give it your fast storage and your slow storage with costs assigned to each and have it manage your storage like a cache. This is what would make the 64GB storage+large hard drive a superior option in my mind mind. There are filesystems that already do this (Sun has one, for example), but I think it may be time for Microsoft and/or Apple to implement something like that for the home user as well.
60-85% Full would leave 15%-40% free. If you take into consideration wear leveling by dividing the MTF of 3-5 years by the change of available overwrite space, you get MTF 0.5-2 years so that seems to equate with your experience of died within a year.
Would you mind running and sharing a few quick benchmarks like hdparm -Tt?
are you aware of how they do their set-up? All of their work system have ramdisk that are loaded from elsewhere. As long as the system does not go down, the ramdisk is valid. Somehow I doubt that they will change their ram disks.
enable faster reboot
you must be running windows...
The guy next to me at work did this, albeit with modest 1 GB drives on a USB hub. He made a RAID-5 of 4 of them, and activated ReadyBoost on his Vista laptop, and Excel would load *instantly*. And I do mean instantly... as if by magic. It was the coolest thing I saw all day. He doesn't remember what exactly his benchmarks were, but only says that "it pwned."
3. Profit!
2. ???
1. On Soviet Slashdot, a Beowulf cluster of alien Natalie Portman overlords welcomes YOU!
Interesting, simply moving heavy IO parts of the filesystem to a flash disk, and you've got a poor man's hybrid drive...
Gamingmuseum.com: Give your 3D accelerator a rest.
As I see it, the real issue isn't the longevity of the modules so much as how Windows does a half-baked(another terms comes to mind that's less than G rated implementation of memory and swapfile management.
Fix this and it's a done deal. Myself, I swear by it. My very first laptop had the OS in Rom and a CMOS battery backed ramdisk. Not exactly the same thing, but booting up in two seconds fifteen years ago, having zero issues with failures, and no noise or heat to speak of(plus 5-6 hours battery life back them) was worlds better than a hard drive.
I suspect that my turning off the swap file/virtual memory entirely, reliability issues would become moot. Of course, that would force you to have 2-4 times the physical memory that you now have if you are running Windows, but ram is cheap enough now.
Another method might be to just make a ramdisk and put the swap file on that. That's not an impossible bit of programming, either. CMOS changes could probably set aside one bank of memory(say, color it white vs the other 4's black or purple/green(which seems common))that is always the ramdisk. CMOS battery of course - and Windows tosses the swap file onto that virtual drive.
usage of the solid state drive would drop to only when you actually are moving files around. MTBF wold be measured in decades.
Yeah... try running any programs on Windows without swap, though. I know Photoshop used to get really pissed, even if you had plenty of RAM. I've never had good experiences with Windows and turning off the swap file, and very rarely hear of anyone who does it successfully.
My blog. Good stuff (when I remember to update it). Read it.
Or a notebook. Not everyone does all their computing on a desktop machine. In fact, more people use laptops than desktops any more (more laptops than desktops are being sold since 2005 or so). I'd love for my Linux laptop to be able to shut down to a completely off state and power back up more quickly.
My blog. Good stuff (when I remember to update it). Read it.
Keep in mind, that CF is actually IDE specs. I used this to hook the IDE cable to a CF card. This is what I will use next time. Combine that with a GOOD card (i.e. skip the cheap chinese crap). I used this card, but will switch to a different san disk next time as well.
/. I chose to use ext2, and put the bulk of / on it. Be sure to move the dirs that are changing on disk (as mount points). I put /home, /opt (due to size), parts of /var on disk. It works great.
I assume that you are using Linux. You have several choices. Format with JFFS and use that at
I prefer the "u" in honour as it seems to be missing these days.
I think both windows and Mac have technology to "optimize" the placement on disk of your static programs and data so that it is all sequentially read from disk when it is used. This negates a large portion of flash drives' benefit.
Yes, Windows memory requirements basically quadruple with virtual memory turned off(which is rally what it is - no different than using system ram for video, for instance, and just as much of a speed killer).
Windows is a frighteningly bloated beast. But I'm pretty much preaching to the choir here I suspect.
The way to deal with the swap file is a ramdisk. 3 gigs for Windows(assuming you're NOT stupid enough to be running Vista) and the remaining 1 gig windows doesn't usually access is the swap file. Problem solved. You just tricked Windows into using real ram instead of the hard drive.(as it should have been)
It nearly quadruples speed in XP, btw.
Newegg is selling a 128 GB Solid State Drive as a single unit. It's pretty expensive though. (Note: this link may go out of date really fast.)
Since wear leveling has been addressed (repeatedly) in reply i'll skip it.
Instead let's talk about how your 3 year old U320 drive will kick the crap out of bla bla bla.
In raw transfer speed probably. SSDD do fall behind by varying degrees in raw transfer. However, raw transfer is rarely the most important aspect of a hard drive.
Far more important is seek time. That's why your fancy SCSI drives spin at 10k or 15k RPM. The 4mS average seek gives them a bid advantage over the 7-10mS in standard desktop hard drives. What's the seek time on SSDDs? Generally around 100uS or 0.1mS. So if you sacrifice 2/3 of your drive capacity (1TB vs 150-300GB for 15k) to halve your seek time what would you sacrifice to improve it by at least an order of magnitude?
Random seek is critically important for most servers and also for many home uses. In testing with SSDDs windows boot time improved by about 20-30% depending on the situation. App load times also showed substantial improvements. Try throwing a sizable DB on a SSDD and you'll be amazed at the performance even without caching.
So yes. For raw backup, very high data rate streaming, etc. Your SCSI drives might win out. For the majority of applications SSDD > U320 15K SCSI.
You can get rich if you own a politician, but you have to be rich to buy one in the first place.
That is incorrect. If the drive notices that a certain block has been written a lot (say a bit of the swap partition) and another block has been written much less (say a bit of
HAND.
You're a dinosaur. Get a new outlook.
Disk on chip IDE drive. dead with lots of bad locations. if I was to have used it correctly instead of how the manager wanted it would have survived.
forgot to mention what type it was.
Do not look at laser with remaining good eye.
Huh?
A quick look at newegg: http://www.newegg.com/Product/Product.aspx?Item=N82E16820609245
"Sequential Access - Read 60MB/s (min)
Sequential Access - Write 45MB/s (min)"
That is just barely slower than a 7200 rpm hard disk, and with less than 1 ms access times the SSD will blow away a 7200 rpm drive in real world performance.
...do they only power the chips being used?
I think parent was talking about a laptop with an off the shelf SSD thrown into it not a homebrew SSD.
-*The above statement is printed entirely on recycled electrons*-
Tape drives are very much still in use as backup solutions. It again boils down to economics. Tape drives have better data integrity so they work better for data backups. Thus thats what they are used for. SS drives work better than hard drives for portable memory thus thats what they are used for.
and with quad core processors, dual SLI. And from a company that isn't Alienware.
Well, a good piano library can be 1 to 2 gigs. I have several that size. I have a guitar library that spans several DVDs. This library samples every string at every fret, with samples for different velocity levels, different styles of picking, pull ons and pull offs, bends, harmonics, muted, thousands of chords, etc. Sample libraries for the major PC samplers, Kontakt and Gigastudio, can be huge. They are several magnitudes larger the the samples built into even pro keyboards, unless the keyboard has its own hard disk.
Horns - French, trumpet, trombone, and stings - violin, viola, cellos can also have large libraries. Some libaries are fairly small, like electric piano, or an electric organ. Sample libraries for a good pipe organ, though, can again be several gigs.
Of course, for all these instruments, their are smaller libraries available, with less velocity levels, less articulations, etc.
I play sample libraries with a Kawai MP 9500 keyboard hooked up to my PC. It has four programmable zones I can divide the keyboard into, and set an instrument to each zone. Thus, bass, piano, guitar, horn. I can also overlap the instruments, so I can have a violin on top of a piano. If I have to many large libraries loaded, and play too fast, the hard disk won't be able to keep up, and the sampler will stutter. Of course, a 10,000 rpm hard disk would help, or a raid array. Or a solid state drive.
This ad space for rent.
and low power means low heat.
what i really want to see is lots of cheap, high-speed (read *AND* write), high-capacity (in the many-hundreds-of-GB or terabyte ranges) solid-state disks so i can completely replace all my drives in all my machines.
disk drives use a fair amount of power, they run HOT (and the faster they are, the hotter they run), and they're prone to failure.
SSDs have no moving parts, are low power, and low heat.
unfortunately, they're also currently only in small sizes and cost way too much. both of those factors will change over the next few years....then it's goodbye to disk drives forever.
Flash based memory has been in mass production for a long time. More flash memory is produced then hard drives. It's just really expensive to produce flash chip based memory (in comparison to magnetic drives) per gig. You could be waiting a very long time for it get to 64 gigs at $100.
Hmmm... Pie...
Actually, 64gig is too small a drive, with todays video and audio files being sent and stored. The laptops will require external drives for storage. If load times go from 9 milliseconds to 0.09 milliseconds, what is the deal, my keyboarding and reading speed has not changed. I still read at 250 words a minute and type at 30.
Leslie Satenstein Montreal Quebec Canada