Slashdot Mirror


TB-Sized Solid State Drives Announced

prostoalex writes "Several companies have announced solid state hard drives in excess of one terrabyte in size. ComputerWorld describes one from BitMicro that's just 3.5". Their flash drive will support up to 4 Gbps data transfer rate. From the article: 'SSDs access data in microseconds, instead of the millliseconds that traditional hard drives use to retrieve data. The BitMicro E-Disk Altima 4Gb FC delivers more than 55,000 I/O operations per second (IOPS) and has a sustained data transfer rate over 230MB/sec. By comparison, a fast hard drive for example will run at around 300 IOPS.'" Ah, the speed of tech. Seems like only last month we were talking about 500GB drives.

130 comments

  1. Don't Forget Fusion IO's PCIe Card Drive by eldavojohn · · Score: 4, Informative

    Ah, the speed of tech. Seems like only last month we were talking about 500GB drives. We also discussed 640GB PCIe cards with sustained data rates of 800Mb/sec for reading, 600Mb/sec for writing and 1,000,000 operations per second.

    The Texas Memory Systems datasheet claims 24 GB/second of random sustainable data bandwidth which is much higher than the Fusion IO card but it looks like they are serializing this possibly across multiple drives. They also claim higher (3.2 million) operations per second.

    The BitMicro drive is groin grabbingly amazing in size but claims only 55k operations per second & sustained data transfer rate over 230MB/sec.

    So what I would wager is that PCIe might provide more throughput than SATA but don't quote me on that. I'm interested to see where this goes & also curious to see whether we continue dumping drives on channels like the Texas Memory solution or if it just goes back to a server with a ton of PCIe slots on it and hot pluggable card swapping for 'drives.'

    Worth revisiting is the fact that Fusion IO claims to be releasing the cards for sale next month. As we all know, sometimes it's just a case of who gets to market first that wins in the technology world.
    --
    My work here is dung.
    1. Re:Don't Forget Fusion IO's PCIe Card Drive by Jeff+DeMaagd · · Score: 1

      The BitMicro drive is groin grabbingly amazing...

      Ouch!

    2. Re:Don't Forget Fusion IO's PCIe Card Drive by Gr8Apes · · Score: 4, Informative


      The Texas Memory Systems RAMSan requires 2500W of power.

      For the BitMicro SSD: 230MB/s >> 800 Mb/s card, and 55K IOPS >> 300 IOPS for todays hard drives.

      It sounds to me like the BitMicro is a clear winner, especially considering that today's fastest HDs deliver about 300 IOPS and a max of about 40MB/s sustained data transfer. You can RAID the drives to increase performance, but I imagine the same will hold true of the SSDs. The only issue is price. The Texas Memory System is out of the question - it makes an Intel P4 Extreme look like a power miser.

      --
      The cesspool just got a check and balance.
    3. Re:Don't Forget Fusion IO's PCIe Card Drive by had3l · · Score: 1

      "As we all know, sometimes it's just a case of who gets to market first that wins in the technology world."

      As long as your product doesn't suck, that is.

    4. Re:Don't Forget Fusion IO's PCIe Card Drive by Junta · · Score: 4, Insightful

      The Texas Memory Systems datasheet claims 24 GB/second of random sustainable data bandwidth which is much higher than the Fusion IO card but it looks like they are serializing this possibly across multiple drives. They also claim higher (3.2 million) operations per second. The Texas memory product is cramming a bunch of ram in 24U and putting a whopping 25 minutes of battery backup. If you disconnect power for more thon 25 minutes, the only thing left is whatever was committed to 'real' peristant storage. They provide Infiniband and FC ports, so it's more akin to an EMC or Engenio storage controller than a hard drive. 1 TB/24U is actually kind of sad when hard drives can easily yield 3 TB/U nowadays. There is a place for this (ramdisk performance is pretty nifty), but it's not even remotely relevant to anything a normal person would think of when they hear SSD (they picture a drive intended to connect directly to a system some how, not participate in a SAN directly.

      The BitMicro drive is groin grabbingly amazing in size but claims only 55k operations per second & sustained data transfer rate over 230MB/sec. And it *actually* is flash based storage, meaning it can fairly be called persistant storage. Of course, the clear hint is there when they talk IOps and only mention FC connection that they are targetting only deep pockets with the product as of this press release or whatever. 55k operations and 230 MB/s is ludicrously insane performance for a single drive relative to current spinning disks. You can fit 144 of these into a 24U space and have a theoretical aggregation that exceeds the ram based system specs. Of course, RAM should be able to trounce it so the limiting factor is a controller setup to push the IOPs and throughput, so both solutions would probably perform comprably.

      So what I would wager is that PCIe might provide more throughput than SATA but don't quote me on that. I'm interested to see where this goes & also curious to see whether we continue dumping drives on channels like the Texas Memory solution or if it just goes back to a server with a ton of PCIe slots on it and hot pluggable card swapping for 'drives.' Well, considering that SATA controllers at best currently use PCI-e as the method to communicate with the chipset, PCI-e slots better be capable of better than SATA... Ok, it's over-simplyfying, a 1x PCIe first gen slot yields about 2.5 Gb/s or so, and a SATA II port is 3.0 Gb/s, so a single lane PCI-e slot would be slower than a SATA port. However commonly PCIe appears in 4/8/16 lane configurations, I assume you meant 880 MB/s, which would point to PCIe 4x slot sort of throughput, which makes sense, it's not unreasonable to expect at least a 4x lane slot to be free, requiring anything more could waste limited hardware resources.
      --
      XML is like violence. If it doesn't solve the problem, use more.
    5. Re:Don't Forget Fusion IO's PCIe Card Drive by Znork · · Score: 1

      "55k operations and 230 MB/s is ludicrously insane performance for a single drive relative to current spinning disks."

      Yep. Still, in the pricerange they're in it's hardly single disks they're competing against, so comparing to those is about as useful as comparing with the performance of 5 1/4 inch floppys. Perhaps they want to have a market position as an SAN accelerator, but SAN cabinets in that range are pretty generous with RAM caches anyway and stripe storage over many spindles.

      I tend to be sceptical about these storage techs, as they seem to aim at either very small niches of the market space or very defective applications. I'm not at all sure there is any useful market (yet, and apart from the low-space applications like laptops) between the curve points of todays GB price for hard disks and todays pricepoint for merely throwing more RAM into the servers. It doesnt come close to comparing on price with disks, and it doesnt come close to comparing on speed with RAM.

      Perhaps there is some exploitable niche between, but frankly, this isnt the first time I've seen tech aimed at filling that niche (conceptually it goes back to various extended BIOSes and before that) but it didn't become a big hit back then, nor do I expect it to now.

    6. Re:Don't Forget Fusion IO's PCIe Card Drive by arminw · · Score: 3, Funny

      .....The Texas Memory Systems RAMSan requires 2500W of power........

      It appears that one of these is NOT ready to be used in your next laptop in the near future!

      --
      All theory is gray
    7. Re:Don't Forget Fusion IO's PCIe Card Drive by Gr8Apes · · Score: 2, Funny

      .....The Texas Memory Systems RAMSan requires 2500W of power........

      It appears that one of these is NOT ready to be used in your next laptop in the near future! Well, if you're looking for the quick and easy cure to procreation....
      --
      The cesspool just got a check and balance.
    8. Re:Don't Forget Fusion IO's PCIe Card Drive by RzUpAnmsCwrds · · Score: 1

      a max of about 40MB/s sustained data


      Modern 7200 RPM SATA drives can deliver 70-100MB/s in sequential reads, depending on where the data is stored on the platters.

      Most people don't know it, but hard drives have been getting steadily faster. Not crazy-insane-faster like semiconductors, but they have been making some sizable gains.
    9. Re:Don't Forget Fusion IO's PCIe Card Drive by Gr8Apes · · Score: 2, Informative

      Just took a look at a few sites reviews on drives. It appears that the current crop of drives in more realistic tests approach 40-60 MB/s. So I'll up my statement to 60MB/s. Still well short of 100MB/s. (Don't believe drive manufacturers or their ad-driven reviewers).

      Just FYI: the 60 MB/s surprises me for non SCSI hardware, that's a pretty darn good number.

      --
      The cesspool just got a check and balance.
    10. Re:Don't Forget Fusion IO's PCIe Card Drive by booch · · Score: 1

      What gets me is that they have the nerve to call it non-volatile memory. If that's non-volatile memory, then what memory ISN'T non-volatile?

      "You keep using that word. I do not think it means, what you think it means."

      --
      Software sucks. Open Source sucks less.
    11. Re:Don't Forget Fusion IO's PCIe Card Drive by Anonymous Coward · · Score: 0

      Just FYI: the 60 MB/s surprises me for non SCSI hardware, that's a pretty darn good number.

      Why would that surprise you? The limiting factor for sustained transfer rate has not been interface performance for a very long time. It's a direct consequence of the linear information density and rotational velocity of the disk. Some of the modern 1 TB disks can sustain over 100 MB/s in their outer zones (where there are more sectors per track). The SATA interface is more than adequate for such speeds, especially the second generation version (which runs the data link at somewhere around 300 MB/s).

      However, sustained transfer rate is a fairly meaningless figure for a lot of workloads. It's certainly nice to have, but any disk's throughput goes down a great deal when it has to actually seek around instead of stream data from consecutive sectors. This is where the notion that disk performance has improved significantly falls down; seek performance has not markedly improved for a decade or more.

      It's actually seek performance which has traditionally been the real differentiator for SCSI disks. At one time the interface even played a role in it, when SCSI had support for tagged command queueing and command reordering while ATA did not. However, SATA now has a decent implementation of command queueing. At this point the main difference is that the highest seek performance drives are available only with SCSI family interfaces primarily because of market inertia rather than any technical limitation.

      By the way, it also turns out to be the case that even no-seek STR isn't improving as quickly as disk capacity. Of the two methods available for increasing disk capacity, only one (increased linear density) improves STR while the other (decreased track-to-track spacing) does not. As a result, it now takes longer than ever before to read or write every sector on a disk.

    12. Re:Don't Forget Fusion IO's PCIe Card Drive by Emetophobe · · Score: 1
      From the FusionIO website:

      The ioDrive(TM) is designed to deliver 87,500 IOPS (input/output per second @ 8K packets) per PCIe x4 card, while achieving sustained data rates of 700MB/sec (Read) and 600MB/sec (Write) -- making the ioDrive(TM) almost a thousand times faster than any existing disk drive.

      The OP apparently confused you when he incorrectly used Mb instead of MB.

    13. Re:Don't Forget Fusion IO's PCIe Card Drive by Gr8Apes · · Score: 1

      I read the referenced articles which also had them listed in Mb.

      BTW, current HDs can do 60 MB/s (105 MB/s theoretical), so that would be only 1 order of magnitude faster, not 3. Let's not correct a bit of misinformation with an injection of more misinformation, even if quoted. (On a side note, they may be only looking at IOPS, but even then it's less than 2 orders of magnitude - looks like standard marketese: round up to 2 orders plus 1 order = 3 orders... 1000 times faster?)

      --
      The cesspool just got a check and balance.
    14. Re:Don't Forget Fusion IO's PCIe Card Drive by proudfoot · · Score: 1

      Well, if you're looking for the quick and easy cure to procreation...

      What, reading slashdot?
    15. Re:Don't Forget Fusion IO's PCIe Card Drive by Emetophobe · · Score: 1

      I'm sure the "1000 times faster" figure is is just marketing, but the device does seem to have huge potential. Check out the two videos with the CTO doing a demonstration of the ioDrive: http://www.tgdaily.com/content/view/34065/135/

      In the first video, at one point the CTO claims that a "regular hard drive can do around 100 IOPS" and that their device can do 100,000 IOPS. So that's probably where they get the 1000 times faster figure from.

    16. Re:Don't Forget Fusion IO's PCIe Card Drive by Gr8Apes · · Score: 1

      Actually, that's not 100% correct, as transfer rates are also dependent upon the number of platters, not just rotational speed. 4 platters @ 7200 rpm will perform better overall than a single 10K platter drive.

      The earlier SATA drives were single and double platter drives that were competing with multi-platter SCSI drives, hence the much higher numbers for SCSI. Now that SATA drives are coming in at 4 platters (sides?), that seems to be about the limiting factor for both in the 1" configuration.

      It's why those full height 50GB old SCSI drives were so good for data transfer and had seek times in the sub 3ms - there were 9 platters in that beast (IIRC).

      --
      The cesspool just got a check and balance.
  2. Clarification to the Summary required. by AmIAnAi · · Score: 4, Informative

    The TMS link is for a 9U rack of non-volatile DDRRAM, consuming 2.5KW and weighing up to 720lbs, so not quite suitable for the desktop.

    The BitMicro article goes on to say that the maximum capacity in a standard 3.5"x1" format is 640GB, so requiring around 2.5" for the full 1TB.

    This is Slashdot, so we don't expect facts in the summary to be correct. However, this is still amazing progress.

    --
    Any sufficiently advanced bug is indistinguishable from a feature.
    1. Re:Clarification to the Summary required. by Jeff+DeMaagd · · Score: 1

      I don't see any factual errors, maybe too much is left for the reader to assume. That first item is still solid state drive, even if it's not flash.

    2. Re:Clarification to the Summary required. by dpaton.net · · Score: 4, Informative

      The TMS link is for a 9U rack of non-volatile DDRRAM, consuming 2.5KW and weighing up to 720lbs, so not quite suitable for the desktop.

      It's actually 24U, and it consists of (what appear to be) 8 3U racked computers that each manage 128GB of RAM storage for the network, and have a 4 drive hot-swap array for backup.

      Source: http://www.texmemsys.com/files/f000225.pdf

      --
      This is not a sig. this is a duck. quack.
  3. In other news by moogied · · Score: 5, Funny

    Wells Fargo, Bank of America, Washington Mutual, and Chase all annouced there new "PC Home Equity Loans". Averaging at 5.8% APR(OAC) you can take out a home equity loan for the purpose of purchasing a 1TB SSD.

    --
    So basically, -1 troll/offtopic is really slashdots way of saying "I hate that you thought of something before me."
    1. Re:In other news by EvanED · · Score: 1

      What I want to know is whether I can get something that's the equivalent of a mortgage for this. In other words, use the drive itself for collateral. Do they offer this service?

    2. Re:In other news by dosguru · · Score: 1

      Here in Wells' IT, we'd like to encourge you to take out the new loan so we can afford to buy a disk array of these things to keep track of your loans.

    3. Re:In other news by lsllll · · Score: 0, Offtopic

      Yeah, but what they don't tell you is if it's compatible with MS-DOS 3.3. It might as well be a paperweight if I can't get my DOS games to load faster.

      --
      Is that a roll of dimes in your pocket or are you happy to see me?
    4. Re:In other news by SatanicPuppy · · Score: 4, Funny

      Well, at 2500W you could probably buy it as a space heater with a home improvement loan, and snip it off your taxes for the year as well.

      --
      ad logicam Claiming a proposition is false because it was presented as the conclusion of a fallacious argument.
    5. Re:In other news by corbettw · · Score: 0, Troll

      You can always talk to a hardware leasing company. Check out TimePayment Corp, I met one of their salesmen at a conference recently and he said they do a lot of work setting up lease agreements for high end hardware.

      --
      God invented whiskey so the Irish would not rule the world.
  4. This is not a drive... its an array by segfaultcoredump · · Score: 3, Informative

    The linked to press release for TMS systems are not a single drive. They are a half rack sized array. Dont try and put one in your desktop anytime soon.
    Their systems have been in use for years by folks who need speed at any cost.

    Now, the BitMicro drives... those look interesting. I wonder if I can slot them into my StorageTek 6140 :-)

    1. Re:This is not a drive... its an array by vidarh · · Score: 2, Interesting

      The key being "any cost". I talked to them at one point, and was quoted a price for one of their devices that was about as much as my company pays in hardware lease, bandwidth and power for hosting 4 racks worth of high end servers for a year...

    2. Re:This is not a drive... its an array by hedwards · · Score: 1

      That doesn't surprise me, a few companies with a need for this kind of speed and deep, deep pockets will buy them. And in time the cost of producing them will come down in price to the point where I'll have one.

      I must admit that I'm drooling over this, there are times when having a drive that ridiculously fast would really come in handy. Of course I can't afford one of those just so that I can compile my software with the bottle neck being largely elsewhere.

  5. Hick by Jeppe+Utzon · · Score: 0, Offtopic

    One terrabyte is a heck of a lot brown stuff. I wonder if I risk data loss if it gets infected by earth worms? I hear they are nasty little fuckers...

    1. Re:Hick by Anonymous Coward · · Score: 0

      Does anyone know where I can buy powder for my itchy asshole? (I call it Jeppe)

    2. Re:Hick by Anonymous Coward · · Score: 0

      How is this offtopic? The idiot who posted the article is the one who called it a terrabyte - you know, terra as in earth? Brown stuff? Pretty funny, actually. He meant tera as in trillion...

      Too intellectual, I guess...

    3. Re:Hick by Anonymous Coward · · Score: 0

      Too intellectual, I guess... too nerdy, and beanbag-jewish. - please stop guessing for the eternal future, ktnx

      - next?

  6. And again... by SharpFang · · Score: 3, Interesting

    ...how does it compare to capacity equivalent in SD cards plus RAID/reader glue logic piece of hardware?

    --
    45 5F E1 04 22 CA 29 C4 93 3F 95 05 2B 79 2A B2
  7. the bus will be the bottleneck by petes_PoV · · Score: 2, Insightful
    To get the best performance out of these things we need to move away from IDE/SATA architectures and have the storage directly on the PCI or PCI-E bus.

    Once that happens, PCs will really start to get useful!

    --
    politicians are like babies' nappies: they should both be changed regularly and for the same reasons
    1. Re:the bus will be the bottleneck by not+already+in+use · · Score: 1

      Yes, because until then, PC's are just a commodity. :)

      --
      Similes are like metaphors
    2. Re:the bus will be the bottleneck by Kjella · · Score: 2, Insightful

      Right now, even the best prosumer SSDs aren't close to matching the SATA2 interface speed of 300MB/s. Their access time is already minimal (I saw 0.2ms in a test for one disk). Remember that there's a lot of headroom in the SATA interface that isn't used except for buffer bursts today. So I don't really see the point. Having an standard connector and making them drop-in replacements for HDDs sounds to me like the logical way to go...

      --
      Live today, because you never know what tomorrow brings
    3. Re:the bus will be the bottleneck by Junta · · Score: 1

      The performance of the BitMicro SSD isn't even up to a SATA-II 3.0 Gb/s speed. And to top it off, they only seem to support FC, which is currently commonly 4.0 Gb/s and moving toward 8.0 Gb/s. If you have more than one drive, yes, you'll exceed 3.0, but you'll also be using more SATA ports, so in the aggregate, still staying below the SATA standard limits. Maybe a different standard will come, but for now, SATA is perfectly capable. The likes of PCI-e has not been extended in a standardized way to allow for significant trace (I guess in this situiation cable) length. Unless PCI-e is extended in such a way *and* drives can cheaply implement the hardware/firmware necessary to speak the more generalized protocol, it will not be feasible and the current state of the technology is also meaning it is pointless to bother. By the time the SSDs get above 3.0 Gb/s per port making sense, I'd wager an iteration of the SATA architecture will be available that would suit the speed and permit reasonable backward and forward compatibility with SATA devices.

      The other thing is just a bunch of servers with lots of DIMM slots and a 25 minute UPS marketed as a SAN solution, so no need to sweat that detail with respect to this. (You'd only buy such a thing to hook up to your infiniband or fibre channel fabric, not direct-attached to a single system).

      --
      XML is like violence. If it doesn't solve the problem, use more.
    4. Re:the bus will be the bottleneck by afidel · · Score: 1

      An interesting concept for a really fast SSD is to use the SATA/SAS software presentation layer on a card that plugs directly into PCIe. That way you have the standards support from the OS level and are not restricted by SATA physical signaling limitations.

      --
      There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
    5. Re:the bus will be the bottleneck by aaronvegh · · Score: 1

      Once that happens, PCs will really start to get useful!
      Sure! Because right now these damn PCs are nothing but expensive paperweights!
      --
      You can have my one-button mouse when you pry it from my cold, dead fingers.
    6. Re:the bus will be the bottleneck by drinkypoo · · Score: 1

      That way you have the standards support from the OS level and are not restricted by SATA physical signaling limitations.

      Except that you're still subject to driver limitations, and the driver probably makes assumptions about the maximum performance of the device that will limit you anyway :P

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    7. Re:the bus will be the bottleneck by Junta · · Score: 1

      Except they *can't* make such assumptions at a higher layer. For example, the generic layer has to anticipate that a single presented block device could represent a RAID-0 of devices. The specific driver, would, of course, be written for that card or else it would probably emulate a controller with hardware raid-0 capability.

      --
      XML is like violence. If it doesn't solve the problem, use more.
  8. Very nice by Bullfish · · Score: 3, Insightful

    But for now the cost isn't worth the performance differential. With enough ram, generally you aren't hitting the hard drive too often except for a few tasks. With 64 bit computing, you get to have even more useful ram. When the price of solid state drives is competitive with hard disks, I'll pay attention.

    1. Re:Very nice by itsdapead · · Score: 2, Insightful

      When the price of solid state drives is competitive with hard disks, I'll pay attention.

      Hah. When I were a lad you could get a 7 MEGABYTE Winchester Hard Disk for a mere £3500 (what, about $5000?). (Source, 1981 copy of Personal Computer World).

      That's about £10k in modern money (according to this calculator - a.k.a. $20k dollars (or $10k at Microsoft/Adobe screw-the-Brits rates).

      Now, if you think that 1981 was, like, ancient history then GET OFF MY LAWN! If the usual growth rate applies, 1TB solid state drives will be cheap and plentiful by the time you get round to repainting your house.

      --
      In a survey of 100 programmers, 111111 thought that duck-typing was a good idea.
    2. Re:Very nice by PitaBred · · Score: 1

      Just as an FYI, a lot of people get annoyed at the "screw the Brits" rates, and quite fairly most of the time. But realize that prices in the US are quoted WITHOUT tax. The British prices include VAT charges, because you have sensible price advertising rules :P So, in reality, when you see a US price of $1000, add 8.235% (or so) to get the actual price we'd pay. That $1000 price is actually $1082.35 (on average) in the US. Just some food for thought :)

    3. Re:Very nice by Poromenos1 · · Score: 1

      I'd rather pay $1082.35 (on average) than $2000...

      --
      Send email from the afterlife! Write your e-will at Dead Man's Switch.
    4. Re:Very nice by KrackHouse · · Score: 1

      If your apps only read data then yeah, but if you have a bulletin board or log a bunch of data the RAM doesn't really help for write caching.

      --
      What if Digg added local news and a Slashdot inspired comment karma system? ---
      http://houndwire.com
    5. Re:Very nice by SanityInAnarchy · · Score: 1

      Hah. When I were a lad you could get a 7 MEGABYTE Winchester Hard Disk for a mere £3500 (what, about $5000?). (Source, 1981 copy of Personal Computer World).

      What I'm sure was meant was when they become competitive with their current hard drives.

      In other words, right now, going to any solid-state storage system only makes sense in various specialized places. For example: You need performance at any cost, so you buy some battery-backed RAM with hard-disk backups. Or, you need something smaller and more durable than you can conceivably make a hard drive, so you buy a USB flash drive. Or, you want your notebook to be as power-efficient as possible, and to be durable -- no moving parts -- so you get some 15-20 gigs of flash to run your notebook off of.

      But hard drives seem to be the happy medium between that performance/convenience and the opposite extreme of burning 4.7 gig DVDs -- arguably cheaper than a hard drive, but it takes awhile.

      But, the performance still sucks. Seek times alone are a problem. And I sort of agree -- while it's exciting to hear what might be just around the corner, it's really not going to matter until these things start to be remotely competitive with modern hard drives.

      --
      Don't thank God, thank a doctor!
  9. ReadyBoost, et al by inKubus · · Score: 4, Interesting

    These could be used with some sort of intelligent prefetch (ala ReadyBoost) with good results. I know they use them currently in high-performance systems to swap out table indexes and the like. Since the indexes are relatively small files--but there are many of them--seek time becomes the bottleneck, rather than throughput.

    I've heard about doing this in Linux by mounting a USB key and using it as extra swap. Here's how in Ubuntu (from http://ubuntuforums.org/showthread.php?t=395435:

    1) Plug the USB drive in your USB connector;
    2) If Ubuntu automount the device (usually in /media/usbdisk), umount the device (ie., sudo umount /media/usbdisk);
    3) sudo mkswap /dev/sda1 (assuming /dev/sda1 is the correct device for the connected usb device)
    4) sudo swapon -p 32767 /dev/sda1

    "cat /proc/swaps" to check if everything is ok; on my laptop I get the following output:

    Filename Type Size Used Priority /dev/hda4 partition 2353512 116 -1 (standard HD swap partition) /dev/sda1 partition 1981928 123900 32767 ("ReadyBoost"-style pen drive)

    Quite obviously, performance is not the same as with real additional ram; however, I feel REAL gain in speed while using eclipse+tomcat+mysql for development on my laptop (which is equipped with just 512MB ram).

    To turn it off, type:

    "swapoff /dev/sda1", assuming /dev/sda1 is the correct device.

    Obviously you are going to be write limited due to the physical limitations of the flash disk, but reads will be very fast. ReadyBoost will keep a table of files that get read a lot, but written infrequently and then cache them on the flash device. It would probably be possible to do this at the disk driver level in linux with a fast database like BDB, keep a table of the last 1000 files read, if there's a write, remove them from the table. Then move those files up to the flash drive as a disk cache... there may be something like this already, like the Google Prefetch project that's in the works.

    --
    Cool! Amazing Toys.
    1. Re:ReadyBoost, et al by mikiN · · Score: 2, Insightful

      Interesting idea, but somehow I can't escape thinking this is like mashing up an iPod in a blender because the resulting grey powder looks nice in the mock-up fireplace for your Christmas stall.

      Unless there have been some really important changes in the performance of Flash memory, using it as swap would be like the second worst possible scenario in terms of it's life expectancy (using it for main memory would be the worst). Just how long is a typical Flash chip with a guaranteed average of 1 million write cycles going to last in this kind of environment? Hours? Days? Perhaps even...weeks?

      --
      The Hacker's Guide To The Kernel: Don't panic()!
    2. Re:ReadyBoost, et al by inKubus · · Score: 1

      Don't know til you try ;)

      Since they are only a few dollars now, it's worth a shot. However, as I said, it would be better if it only used frequently READ files.

      --
      Cool! Amazing Toys.
  10. One terrabyte! by ArAgost · · Score: 4, Funny

    Finally! One terrabyte! I was hoping to get more than mere giggabytes (or, even worse, meggabytes) for SSD. I still remember the epic moment when SSD reached killobytes, after years struggling with just some bbytes.

    1. Re:One terrabyte! by K.+S.+Kyosuke · · Score: 0

      Isn't a terrabyte some ten times more than a lunabyte or so?

      --
      Ezekiel 23:20
    2. Re:One terrabyte! by Clueless+Moron · · Score: 1

      I'm eagerly awaiting the unit "arrhabyte". I propose that it should stand for the amount of software you can pirate in a 24 hour period.

      "Dude", I've got a whopping sixteen arrhabytes of warez here in my backpack!"

    3. Re:One terrabyte! by ArAgost · · Score: 1

      I don't think it would work: given the definition, it would be a non-standard, ever-changing measure. But then, if we look at declared vs. real size of today's storage devices...

  11. Just amazing. by had3l · · Score: 1

    A big improvement from the predicted "State-Sized Solid TB Drives".

  12. Drive Life? by JCSoRocks · · Score: 0, Troll

    AFAIK all of these SSDs have a limited number of writes that can be performed before they start having bad "sectors" (dunno the flash memory name equivalent of a sector off the top of my head). I don't see any information on those sites, but I'd be interested in knowing - how long until they start to fail? At what rate will it fail (in other words, how long to go from say, 500GB to 0GB)? These drives are great, but if you drop that kind of coin and then they fail in a year... that would suck.

    --
    You are using English. Please learn the difference between loose and lose; they're, there, and their; your and you're.
    1. Re:Drive Life? by Yetihehe · · Score: 1

      This is not funny anymore.

      --
      Extreme Programming - Redundant Array of Inexpensive Developers
    2. Re:Drive Life? by LighterShadeOfBlack · · Score: 2, Informative

      This comes up every single time flash drives get mentioned on Slashdot. Go search around and you'll dozens of posts in every article asking and answering this question. The short answer is that with the wear levelling used on all modern flash drives they work out at at least an order of magnitude more reliable than current HDDs despite the write limit.

      --
      Spelling mistakes, grammatical errors, and stupid comments are intentional.
    3. Re:Drive Life? by DeadChobi · · Score: 1

      These are RAM drives with a battery backup. They aren't flash drives. RTFA.

      --
      SRSLY.
    4. Re:Drive Life? by CastrTroy · · Score: 1

      Yes, it would suck, because we all know that standard hard drives with spinning platters, and magnetic read/write heads, almost never break down. :)

      My point is, is that if solid state drives had better known failure times, they could be better than the spinning platter types. Spinning platter drives tend to die whenever, for unknown reasons, and they also die if they just get too old. If using solid state drives could solve the first problem, and only have drives die at a known point in the future, when they get too old, then it would probably work out better for most people. If the drive has a lifetime of 5 years, but you know with 99.99% certainty that it won't start to die before that, you can plan to replace it. However, with the spinning platter hard drives, we know they are probably going to die in 5 years, but also that they could die at any point, for no reason at all.

      --

      Anthropic principle: We see the universe the way it is because if it were different we would not be here to see it.
    5. Re:Drive Life? by yakumo.unr · · Score: 1

      from the the article : "Competing products include Texas Memory Systems Inc.'s RamSan 500, a flash SSD with a dynamic RAM cache. That drive achieves up to 400,000 IOPS. Dutch company Attorn's HyperDrive 4 is a DRAM-based SSD that runs at 44,000 IOPS. Theoretically, DRAM should be faster than flash, but BitMicro's ASICS have made their flash faster."

      The TMS RamSan is flash ssd with dynamic cache.
      Attorns Hyperdrive is DRAM.
      Bitmicros system is flash.

    6. Re:Drive Life? by Khyber · · Score: 1

      If the people in charge of making SSDs would quit using NAND Flash and move to OUM you wouldn't even need to worry about wear leveling. 10^8 is much better than 10^5 that we generally get now.

      --
      Still waiting on Serviscope_minor to wake up to fucking reality and realize that Jessica Price isn't going to fuck him.
    7. Re:Drive Life? by Anonymous Coward · · Score: 0

      Much longer than a hard drive with moving parts.

    8. Re:Drive Life? by JCSoRocks · · Score: 1

      Soooo I'm asking a serious question and I get troll? Ok... Anyway, thanks to those of you that gave intelligent responses. I learned somethin'.

      --
      You are using English. Please learn the difference between loose and lose; they're, there, and their; your and you're.
    9. Re:Drive Life? by pal3f · · Score: 1
      Per TF bitmicro website:

      MTBF: 2 million hours.

      Doesn't exactly address your concern, but should give us some idea.

    10. Re:Drive Life? by cthulhu11 · · Score: 1

      Lots of supposed answers, for sure, but they tend to be riddled with assumptions, eg. that data is written sequentially, and in large blocks. Filesystems tend to not work that way. I've yet to see an analysis of flash drive lifetime with a real-world UFS (or whatever) filesytem on it.

  13. Infiniband by NetJunkie · · Score: 2, Informative

    The big feature here is the included Infiniband support. Without digging real far in to the specs if this array supports RDMA it would make a very nice shared memory array for a grid type implementation.

    1. Re:Infiniband by Anonymous Coward · · Score: 0

      http://www.systemfabricworks.com/news1.html System Fabric Works and Violin has 1/2TB of DRAM in 2U running at 350 watts.

  14. Planetary bytes! by Anonymous Coward · · Score: 0

    Dude, one terrabyte! I must not be paying attention... when did they pass one lunabyte and one venerabyte?

  15. TB-sized? by peacefinder · · Score: 5, Funny

    Is it really a good idea to make a hard drive the size of mycobacterium tuberculosis? I'm just sure I'd lose it before I figured out how to plug it in.

    --
    With reasonable men I will reason; with humane men I will plead; but to tyrants I will give no quarter. -- William Lloyd
    1. Re:TB-sized? by QRDeNameland · · Score: 1

      Reminds of the reason why I'll never own an AM radio...what good is a radio that won't work after noon?

      --
      Momentarily, the need for the construction of new light will no longer exist.
    2. Re:TB-sized? by smoker2 · · Score: 1

      Oh dear,
      First it was sneakernet, then the internet.
      What are the ?iaa going to do now you can transfer a couple of movies just by sneezing !
      Pretty soon, all information exchange is gonna be viral.

  16. About time too by mollymoo · · Score: 1

    I'm glad news of solid-state drives is getting more common. Disk seek times have been the number one cause of annoying delays on my desktop systems for several years now, and I certainly don't have exotic hardware. Perhaps I can ditch my plan for a Solaris box in the garage and diskless clients and just wait a year or two for >100GB $400 solid-state disks.

    --
    Chernobyl 'not a wildlife haven' - BBC News
    1. Re:About time too by glop · · Score: 1

      You might not wait long: Newegg is selling 16GB of Flash for less than 130$ (in CF,USB and SD).
      This means you could build a little >100G RAID of those for 800$ or so.
      And I believe the prices go down really fast (I paid 70$ for 2G in May 2006 and thought it was a good deal. Now I could get 8G for that price).
      I guess you will get your 100GB flash before September 2008 :-)
      Enjoy!

    2. Re:About time too by Tom+Womack · · Score: 2, Informative

      It'll take only about a year or so; Samsung 8Gbit Flash chips are $9 on the spot market at the moment.

      Though the interface for connecting eighty of them onto a single SATA channel wouldn't be completely straightforward just from the point of view of I/O pins; each chip presents eight data pins and nine control pins, so you need a total of about 1500 pins on the disc-controller ICs.

      For the early market you'd probably use FPGAs, you'd need six XC3S400A in one of the larger packages to get enough I/Os, which would be another couple of hundred dollars; the master one can speak SATA directly and do a bit of buffering, and using this baroque configuration means you get the full data rate from each chip so reads are very fast. Say $1000 for 80G SATA-attached - but that's making mass-manufacturing assumptions, which are clearly false if what you're manufacturing are 80G disc drives for $1000.

      Five hundred dollars for 80G SATA-attached sounds a reasonable sort of pricing once Samsung have got one more generation of Flash factory online, and once the devices are more plausibly consumer items.

  17. Quick Erase? by Jah-Wren+Ryel · · Score: 3, Interesting

    Many of the predecessors to these models were aimed at military applications and contained a really cool feature - instant erase. They could erase themselves very quickly (seconds) to a level believed to be reasonably secure from recovery.

    I would like to see that feature incorporated into these consumer level drives. You never know when you might need to ditch that terabyte of pr0n in a hurry...

    --
    When information is power, privacy is freedom.
    1. Re:Quick Erase? by LighterShadeOfBlack · · Score: 5, Funny

      Right, because when your house gets raided and the police see you erased your hard drive they just turn around and say "well played". 'Obstruction of justice' ringing any bells?

      Not to mention the British police will assume it's just encrypted and you'll get 5 years jail-time for not providing the key.

      --
      Spelling mistakes, grammatical errors, and stupid comments are intentional.
    2. Re:Quick Erase? by Jherek+Carnelian · · Score: 1

      Right, because when your house gets raided and the police see you erased your hard drive they just turn around and say "well played". 'Obstruction of justice' ringing any bells? Since when is pr0n illegal? However, since you want to go down that path...

      If whatever your drive contained was 'illegal' or sufficiently incriminating, it may very well be that an "obstruction of justice" charge is preferable to whatever charges would have come about from confiscation of the actual drive contents.
    3. Re:Quick Erase? by LighterShadeOfBlack · · Score: 1

      Since when is pr0n illegal? Well, why would you need to erase your entire drive for anyone besides the police? You'd have to have a serious lack of crisis management skills to erase your hard drive every time you heard your wife coming. It wouldn't exactly avert suspicion either...

      'What are you doing in here honey? Why is the screen black?'
      'Oh I'm just err.. reformatting it. Damn thing got corrupted'
      'That new "solid state" thingie is useless, this is the third time this week you've had to do that!'

      And yes, I know what you're thinking: With convincing dialogue writing skills like that I could make millions as a script writer in Hollywood.
      --
      Spelling mistakes, grammatical errors, and stupid comments are intentional.
    4. Re:Quick Erase? by noidentity · · Score: 4, Funny

      Not to mention the British police will assume it's just encrypted and you'll get 5 years jail-time for not providing the key.

      All those zeroes... there must be something hidden in them. Produce the key at once!

    5. Re:Quick Erase? by Lost+Engineer · · Score: 1

      Yeah, and the government is the only entity that can afford these things. Your tax dollars at work, covering their asses.

    6. Re:Quick Erase? by kylemonger · · Score: 1

      Plenty of open positions at the moment.

    7. Re:Quick Erase? by Jherek+Carnelian · · Score: 2, Insightful

      Well, why would you need to erase your entire drive for anyone besides the police? Well, why would you need to encrypt your entire drive for anyone besides the police?

      A laptop with a "quick erase" button would be useful to many businesses with people who travel in less than the safe regions. Same goes for people in less than free countries who are working for change. Full disk encryption doesn't stand up to rubber-hose cryptography very well.

      I'm sure with more than 30 seconds to think about I could come up with any number of 'legitimate' uses.
    8. Re:Quick Erase? by PitaBred · · Score: 2, Funny

      I don't think you mean rubber-hose cryptography. Torturing someone to get them to... encrypt information? Maybe rubber-hose decryption...

    9. Re:Quick Erase? by dossen · · Score: 2, Insightful

      Just to pick nits - the commonly used term is rubber-hose cryptanalysis (http://en.wikipedia.org/wiki/Rubber-hose_cryptanalysis).

    10. Re:Quick Erase? by Jherek+Carnelian · · Score: 0
  18. WANT!!!!!!! by billcopc · · Score: 1

    How much?

    This would be a whole lot nicer than my current stack of SCSI 15k drives, and I'll bet they put out a lot less heat too!

    --
    -Billco, Fnarg.com
  19. EVE Online uses the TMS RamSan by LakeSolon · · Score: 4, Interesting

    As has been mentioned already, TMS sells a solution that fills a rack. The article is about something to fill a drive bay.

    We've had a few EVE-Online stories lately, so I thought it might be interesting to some to point out that one of the users of the TMS setup is CCP Games, the makers of EVE Online. In fact if you click on 'success stories' in right sidebar of the first link in the summary you'll see a short article about CCP's first install of the TMS RamSan a while back.

  20. When? by rice_burners_suck · · Score: 1

    When can I drop one of these into my laptop?

  21. getoffmylawn by ronadams · · Score: 3, Funny

    Yeah, these look pretty nice, but you can't beat those old tube drives for that warm, acoustic sound.

    --
    Appended to the end of comments you post. 120 chars.
    1. Re:getoffmylawn by rubycodez · · Score: 1

      but they're prone to getting all clogged up with electric mails, and those technicolor Flash moving pictures don't help any either. and they never should have got rid of those nice operator ladies with rolls of wire under their desks of blinky lights and plugholes to route calls, replacing them with those tabulator contraptions with only four or five plugholes to move packages has got the tubes so backed up

    2. Re:getoffmylawn by Anonymous Coward · · Score: 1, Funny

      I prefer non-acoustic sound, thanks very much.

    3. Re:getoffmylawn by Anonymous Coward · · Score: 0

      I'm using mercury relay memory and it really makes my FLAC more dancable.

  22. If you have to ask by sammyo · · Score: 1

    You really can't afford it.

    1. Re:If you have to ask by billcopc · · Score: 1

      And there lies the problem.

      Technological evolution is yet again foiled by financial obsession. I can think of many applications where this technology could help stimulate a dramatic growth in performance/efficiency... just the benefit of not having a platter die every few weeks means a lot less downtime/recovery/junior staff!

      --
      -Billco, Fnarg.com
  23. It's a Ram Disk. by camperdave · · Score: 4, Informative
    a 9U rack of non-volatile DDRRAM

    So, it's a giant ram disk with either flash or hard drive backup.

    Will I lose data if I lose power to a RamSan?

    No. The RamSan-300 and RamSan-400 systems are equipped with redundant batteries and four internal hard disk drives. When external power is lost, the batteries will power the system under full operation for five minutes (this is just in case the power outage is temporary). After five minutes, the system will turn off Input/Output for the system and complete backing up all data that is in memory to the internal hard disk drives. Even if the system is fully loaded with memory, backing up to the internal disks will take no more than 12 minutes to back up. The batteries in the system are N+1 redundant, which means that there is enough battery capacity with just two of the three batteries to power the unit and complete backup after external power fails. The hard disk drives in the system are RAID protected which means that even if a hard disk drive fails, the other disk drives will be able to backup the system in the event of power outage.

    No. The RamSan-500 systems are equipped with redundant batteries to power the DDR cache long enough to flush the DDR cache to the Flash memory RAID. Flash memory is inherently non-volatile and does not require power to save data.
    http://www.superssd.com/faq.htm
    --
    When our name is on the back of your car, we're behind you all the way!
    1. Re:It's a Ram Disk. by TimothyDavis · · Score: 1

      So what happens two years down the road when the batteries can no longer hold out for the needed time?

      Does this mean that the OPS team needs to proactively change the batteries before disaster?

    2. Re:It's a Ram Disk. by camperdave · · Score: 1

      So what happens two years down the road when the batteries can no longer hold out for the needed time?

      By that time they'll upgrade to the ten terabyte version which comes with fresh batteries.

      --
      When our name is on the back of your car, we're behind you all the way!
    3. Re:It's a Ram Disk. by Mattsson · · Score: 1

      So what happens two years down the road when the batteries can no longer hold out for the needed time? If someone hasn't horribly neglected his/her job, the batteries will not reach such a state.
      All UPS-systems have specifications on how long the batteries will last and any UPS that's in professional use should be services properly.
      So should those in private use too actually, but it isn't part of anyones job-description to actually keep it serviced so most probably isn't.
      --
      /.Mattsson - My native language is not English, so please don't whine over linguistic errors. (That's lame anyway...)
    4. Re:It's a Ram Disk. by camperdave · · Score: 1

      Not only that, on a rig like this, there's probably a monitoring system that will call for help if the batteries start failing.

      --
      When our name is on the back of your car, we're behind you all the way!
  24. New! Improved! by JohnnyBigodes · · Score: 2, Interesting

    Now available with a terabyte-sized pricetag!

  25. The marketing slogan should be... by StressGuy · · Score: 1

    A Tera-Byte and a Tera-ble price

    {feel free to groan}

    --
    A goal is a dream with a deadline
  26. Windows XP by edxwelch · · Score: 2, Informative

    Apparently this works on Windows XP too: http://www.windowsxlive.net/?p=1337

  27. All This For the Modest Price Of.. by nimr0d · · Score: 4, Informative

    RamSan-400

    The starting capacity of a RamSan-400 (32GB) is $35,000. It includes:
    -32GB DDRRAM storage
    -one dual-ported 4Gb Fibre Channel controller
    -hot swappable RAID 3 hard disk drives
    -hot swappable and redundant power supplies
    -redundant battery and fans
    -IBM Chipkill in memory (redundant RAM)
    -1 year return to factory warranty

    Each additional 4Gb FC controller is $3,000 (up to 4 in each chassis).

    The RamSan-400 can upgrade in 32GB increments for $18,000 (up to 128GB).

    RamSan-400 (64GB) - $50,400
    RamSan-400 (96GB) - $65,800
    RamSan-400 (128GB) - $81,200

    RamSan-500

    The 1TB base-level system of a RamSan-500 (1TB SLC NAND Flash, 16GB DDR) is $200,000. It includes:
    -one dual-ported 4Gb Fibre Channel controller
    -hot swappable and redundant power supplies
    -redundant battery and fans
    -1 year return to factory warranty

    The 2TB base-level system of a RamSan-500 (2TB SLC NAND Flash, 32GB DDR) is $300,000. It includes:
    -two dual-ported 4Gb Fibre Channel controllers
    -hot swappable and redundant power supplies
    -redundant battery and fans
    -1 year return to factory warranty

    The RamSan-500 can upgrade DDR Cache.
    -16GB to 32GB is $10,000
    -32GB to 64GB is $20,000

    Each additional 4Gb FC controller is $3,000 (up to 4 in each chassis).

  28. In 24U? wow by JustNiz · · Score: 1

    This only gets interesting when I can get a 1TB SD drive the same physical size and approximate price as a 1TB mechanical (conventional) drive.

  29. How about this hack: by Anonymous Coward · · Score: 0

    Given that the usb sticks' innards nowadays get smaller and smaller it should be possible to take apart two sticks (or more) and solder both into one housing. That way you'd have a single usb stick in one slot, but you could run the contained units as a RAID-0 to increase transfer rate and writing speed.

  30. Black book by ROMRIX · · Score: 1

    I want one so I can load it up with all my girl friends phone numbers cause I have so many!
    Ya, and I'm rich too so I might get two, one for girls I like and one for girls I used to like! Ya!

  31. Filesystems by peterlombardo · · Score: 2, Insightful

    Since filesystems are so closely tied to cylinders, tracks, sectors and blocks...how does this play on SSDs? If I'm not mistaken, when allocating new extents, filesystems take into account physical locations to minimize future seek times...is that valid on a SSD?

  32. the best part is by Jarik+C-Bol · · Score: 1

    that if you have to ask what they cost, it means you cant afford one.

    --
    I've decided to Diversify my Holdings. I've divided my cash between my left and right pockets, instead of all in one.
  33. Woopity doo! Another announcement. by inotocracy · · Score: 1

    How about we see some of these large solid state drives actually for sale?

  34. That's so 1980's ;) by Moraelin · · Score: 2, Informative

    Since filesystems are so closely tied to cylinders, tracks, sectors and blocks...how does this play on SSDs? If I'm not mistaken, when allocating new extents, filesystems take into account physical locations to minimize future seek times...is that valid on a SSD?


    Actually,

    1. Even for low level disk access, that hasn't been so since the days of MFM hard drives. Nowadays everything uses LBA (Logical Block Addressing). Meaning that when the computer wants a certain sector it tells the hard drive, quite literally, something like "give me block #13526".

    2. As a side effect, this already allows the hard drive to remap around bad sectors. If you read blocks #13525, #13526 and #13527, you might get the middle one from a whole other position than the other two because it was remapped.

    Disk defragmenting is based on the assumption that contiguous logically _probably_ means contiguous physically too, but there is no guarantee that it's actually so. _Probably_ the HDD won't remap when there's no need, but again, it wouldn't tell you anyway.

    3. For _filesystems_ doubly so. Even the FAT in DOS 1.0 didn't work with tracks and sectors, it worked with block numbers. The translation to cylinder, head and sector was made at a whole other level to actually read or write the data. But the filesystem didn't contain any reference to those.

    E.g.: a 1.44 MB hard drive image still works flawlessly when copied to the first 1.44 MB of a CD. (That's how bootable CDs work. They have a floppy image at the start, and it's really booting that.) The FAT contained no references to cylinders and heads, so the exact same image works just as well off a CD.

    4. Well, it's not that new a problem. You know those USB memory sticks one can buy? Or connecting a Flash-based MP3 player to your PC and copying files on it? Those tend to be formatted as FAT. So there you go. They don't have to invent anything new for an internal SSD. They already did it on other devices.
    --
    A polar bear is a cartesian bear after a coordinate transform.
  35. monster by eleitl · · Score: 1, Interesting

    http://en.wikipedia.org/wiki/Tera-

    Tera- (symbol: T) is a prefix in the SI system of units denoting 1012, or 1,000,000,000,000 (1 million million).

    Confirmed in 1960, it comes from the Greek , meaning monster.[1] It also bears a resemblance to the Greek prefix - meaning four; the coincidence of it signifying the fourth power of 1000 served as a model for the higher-order prefixes peta-, exa-, zetta- and yotta-, all of which are deliberately distorted forms of the Latin or Greek roots for the corresponding powers (fifth to eighth respectively) of 1000.

    In computer science tera- can sometimes mean 1,099,511,627,776 (240) instead of 1,000,000,000,000, especially in the term terabyte. To avoid this ambiguity, the binary prefix tebi- has been introduced to signify 240, but this, in common with the other binary prefixes, is not currently in general use.

    --
    -- Eugen* Leitl leitl ICBM: 48.07100, 11.36820 http://molecu
  36. venerabyte? by Anonymous Coward · · Score: 0

    That'd be an STD rather than an SSD (but still a good place to keep your pron.)

  37. Pseudocode by Weaselmancer · · Score: 1

    Right, because when your house gets raided and the police see you erased your hard drive they just turn around and say "well played". 'Obstruction of justice' ringing any bells?

    if (time_in_jail(OBSTRUCTION_OF_JUSTICE) < time_in_jail(WHATS_ON_MY_HARD_DRIVE)) wipedrive();

    --
    Weaselmancer
    rediculous.
  38. 2500 watss of power? by NuMessiah · · Score: 2, Interesting

    From the "Tera-RamSan Details" page:

    "Requires 2,500 watts of power."

    Huh?

    bb4now,
    PMC

    --
    we-go-we-fly
  39. Not Yet Convinced by Nom+du+Keyboard · · Score: 2, Insightful
    I'm not yet convinced that paying a premium price for a hard drive using a more expensive technology with a very (compared to rotating storage) limited lifetime in terms of write cycles is a wise idea. There are parts of my hard drive (swap areas) that get beat-up pretty badly at times. Don't want to wear this thing out in a year or two.

    That's also why I don't have a plasma big screen yet. I'm using an alternative technology there as well.

    --
    "It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
  40. You mis-converted... by tempest69 · · Score: 1
    BitMicro is 230 MB/SEC + 55K iops fantastic.


    ??$/gig up to 1.5 tb, plus the cost of a 4G fiber card.



    FusionIO is 700 MB/SEC + 87K iops (3x more bandwith, Exceeds SATA 2)


    30$/gig up to a 640GB card (19k$)



    TMS, its huge and heavy, and blows the doors off either product, and expensive. They have a $150/gb

    product that is still pretty fast. 2GB/sec 100K iops (8x more than bitMicro)



    Unless the Bitmicro comes in at a price that is below fusionIO ($30/gig) I don't see the point, just buy 3 fusionIO devices in raid-0 and keep your backups recent

    Storm

    1. Re:You mis-converted... by Gr8Apes · · Score: 1

      I took the Fusion IO numbers off of the summary and the referenced articles. If it's supposed to be MB, not Mb, then blame all three sources. (OMG, I just admitted to RTF!!!:)

      That said, yes, it depends upon the $/GB and your needs as to which is better.

      --
      The cesspool just got a check and balance.
  41. About freakin' time! by Anonymous Coward · · Score: 0

    The spinning disk has been with us for a long time. Yes, they were (and are) great mass storage technology, wildly more stable and also wildly faster than tape, but as a technology, its getting a bit dated. I remember IBM 3370 disk packs which had several sets of disks in them, and also engineers who worked at companies that made platters for IBM mainframes --usually 1/8 inch thick, nickel plated copper with a very high polished surface, and usually about 20 inches in diameter. The disks spun on ball bearings, each disk (usually 8 disks in a pack) weighed about 20 pounds, and spun at 1800 RPM. The motor that turned them was usually 1/2 horsepower, and turned a pulley connected to a central shaft (through the middle of the platter). The drive between motor and shaft was a 1/2 inch wide belt (not unlike a fan belt found on late model cars). Occasionally the pack would 'crash' when a belt broke. It was a lot harder for heads to score the nickel surface (much harder than scratching the ferrous coated aluminum on todays hard disks (ok, they have 'pixie dust' on them...sorry). The slowest part of a computer for years has been disk access (even though its wildly faster than tape access ever was). Solid state storage is yet another improvement (getting rid of CRT's was another great thing to get rid of).

  42. Very large solid-state drives are easy by davidwr · · Score: 1

    Just shove BIGNUM memory cells and the necessary controller circuitry into the device. In principle you could build a single device that has a trillion trillion bytes today.

    On the other hand, making very large solid-state drives small enough to fit on your keychain is a challenge.
    --
    Mod this post +1 insightfultotheblind -2 obvioustothewise

    --
    Knowledge is how to play a game, intelligence is how to win, wisdom is knowing what game to play.
    1. Re:Very large solid-state drives are easy by Falladir · · Score: 1

      This is a 3.5 inch drive.

  43. Gimme slots by jtgd · · Score: 0

    Skip the ATA interface, and the PCIe. I predict in a few years we'll see DIMM-like slots on our motherboards for terabyte flash memory modules next to our DIMM slots for RAM.

    --
    J
  44. yuppie cocksucker by Anonymous Coward · · Score: 0

    I want one so I can load it up with all my girl friends phone numbers cause I have so many!
    Ya, and I'm rich too so I might get two, one for girls I like and one for girls I used to like! Ya! It's because of cocksuckers like you we still use conventional harddrives. -Should a drive-platter suddenly spring loose and fly across the room, you would be the shield between anything worth preserving, and it.
    1. Re:yuppie cocksucker by ROMRIX · · Score: 1
      • I want one so I can load it up with all my girl friends phone numbers cause I have so many! Ya, and I'm rich too so I might get two, one for girls I like and one for girls I used to like! Ya!

      It's because of cocksuckers like you we still use conventional harddrives. -Should a drive-platter suddenly spring loose and fly across the room, you would be the shield between anything worth preserving, and it.

      Giggidy Giggidy Giggidy!
  45. Its a bit more that VAT... by itsdapead · · Score: 1

    Correct me if I am wrong, but can't USAians avoid tax by buying from out-of-state?

    Anyway, although you may need to ignore the tax to get the full £1=$1 ripoff story, the price differences in question are often far more than the tax.

    E.g. Adobe CS 3 Design Standard Full from the Adobe online store: UK Price £895 *excluding* tax, US price $1,199 (About £600)...

    Anyway, in the past (certainly in the era of that HD drive I quoted) the "VAT inclusive" rule only applied to "retail" shops and consumer goods Anything vaguely resembling business equipment or commercial supplies was advertised without tax, with maybe a little "*excluding VAT" in the small print. The rationale for this is that most businesses can reclaim any VAT that they pay on materials or equipment.

    --
    In a survey of 100 programmers, 111111 thought that duck-typing was a good idea.
    1. Re:Its a bit more that VAT... by PitaBred · · Score: 1

      Only if that business doesn't have a presence in your state. So, the answer is "sometimes". If I buy from HP online, I still pay tax since they have plants and such in Colorado.

  46. What would OS/400's do? a huge leap into the SLS by gelfling · · Score: 1

    Or as I believe they are called now, iSeries eServer machines. OS/400 is what's called an SLS architecture. There are no devices in the system nor are there file systems. It's simply one huge 64bit address space. The hardware and software abstraction layers intercept the call from an application or a hardware interface and pipe it to the SLS which just does one reach into the address table. An SSD would be ideal for that architecture. It would be essentially one huge non volatile RAM address space at bus speeds.

    http://www-03.ibm.com/servers/enable/site/porting/iseries/overview/overview.html