Stories
Slash Boxes
Comments

News for nerds, stuff that matters

Slashdot Log In

Log In

Create Account  |  Retrieve Password

640gb PCIe Solid-State Drive Demonstrated

Posted by Zonk on Fri Sep 28, 2007 01:04 PM
from the super-fast-super-small dept.
Lisandro writes "TG Daily reports that the company Fusion io has presented a massively fast, massively large solid-state flash hard drive on a PCIe card at the Demofall 07 conference in San Diego. Fusion is promising sustained data rates of 800Mb/sec for reading and 600Mb/sec for writing. The company plans to start releasing the cards at 80 GB and will scale to 320 and 640 GB. '[Fusion io's CTO David Flynn] set the benchmark for the worst case scenario by using small 4K blocks and then streaming eight simultaneous 1 GB reads and writes. In that test, the ioDrive clocked in at 100,000 operations per second. "That would have just thrashed a regular hard drive," said Flynn. The company plans on releasing the first cards in December 2007 and will follow up with higher capacity versions later.'"
+ -
story

Related Stories

This discussion has been archived. No new comments can be posted.
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
 Full
 Abbreviated
 Hidden
More
Loading... please wait.
  • Oblig. (Score:5, Funny)

    by Anonymous Coward on Friday September 28 2007, @01:07PM (#20785353)
    640gb ought to be enough for anybody.
    • Maybe for your pr0n collection ;)
    • Re:Oblig. (Score:5, Insightful)

      by ady1 (873490) on Friday September 28 2007, @01:11PM (#20785421)
      Its not the size of the harddrive which is amazing. Its the read/write speed.
      Even if you get a 32GB model, you can install windows on it and use the regular SATA2 HDD for movies/music storage. Think of the booting time.
        • Re: (Score:3, Interesting)

          Which brings to mind an interesting point..

          Why even have swap files? Shouldn't caching decisions be done a bit more intelligently at the application level? I have 10 times more RAM in my current PC than all of the memory (including the HDD) on my first PC. At some point, can't we drop swap?
          • Re: (Score:3, Informative)

            Once you get above $500 desktop computers, it doesn't much matter. A properly tuned system will only use swap, if at all, to drop a few MB from RAM to disk because it's just never accessed. A server that swaps during use is just not set up properly.

            • Re: (Score:3, Informative)

              Not in Windows. It has a swap file by default. If you disable swap, it still swaps. If you have swap enabled and have something running in the background and come back hours later, it's so slow it's painful, since everything gets swapped to disk except the one thing running. "Tuning" may be possible, but well outside the realm of the average user, and even completely disabling swap in all settings, you still have swapping happening.
          • Re: (Score:3, Insightful)

            True, you have a lot more RAM now than you used to... BUT, you are also not running DOS anymore. Hell, MS Office alone take 256M just to load Word (I KID...) But seriously, modern apps are huge. Because memory is cheap, apps are not efficient. We also use our systems differently, working with massive files (images, movies, music) and tend to run lots of apps at the same time, including virtual machines. Yes, you can still run windows in 512M, but it seems that even 2G isn't enough at times.

            So we still need
                  • Re:Oblig. (Score:4, Informative)

                    by Eccles (932) on Friday September 28 2007, @05:03PM (#20788639) Journal
                    Oh yeah, how does a solid state drive handle fragmentation? I have heard that they don't fragment, but not from reliable sources, and I just don't see how that is possible unless there is some built in mechanism to close gaps on the fly or something.

                    Hard disks have a fragmentation issue because sequential accesses are much faster than random ones with a spinning disk. Each time the next sector to get isn't right after the previous one, the head must seek to the start of the next track. Solid state "disks" have true random access, where accessing blocks in random order costs no more than sequential accesses. So while solid state will fragment, it doesn't matter for performance or reliability.
                    • So while solid state will fragment, it doesn't matter for performance or reliability.

                      Yes, but it *needs* to be defragged because I *hate* seeing red in my disk analysis...
                    • Re: (Score:3, Informative)

                      "Solid state "disks" have true random access, where accessing blocks in random order costs no more than sequential accesses"

                      AFAIK for flash, sequential access is still faster than random access, even for NOR flash.

                      It's quite amazing how slow some flash is (esp NAND flash). Some are 1ms for random access, and others are even 7ms.

                      For comparison a 15krpm drive has a random access time of about 5-6ms. So if you have RAID10, you might get similar or faster speeds, than a flash drive 10x the total price of a RAID
          • Re:Oblig. (Score:5, Informative)

            by norton_I (64015) <hobbes@utrek.dhs.org> on Friday September 28 2007, @02:25PM (#20786553)
            You can tell if flash is bad, if worst comes to worst, by reading after writing. Or reading after erasing, and looking for stuck 1's.

            'worn out' flash doesn't spontaneously change state. Bits just get stuck and don't erase correctly.

            I don't know how flash drives actually handle this, but it isn't magic or impossible to fix.

            Also, the lifetime of modern flash is long enough that it is hardly an issue any more, even for normal desktop use. Maybe you don't want to use it for swap *IF* you swap a lot, but given the cost is in the same ballpark as RAM, you could just buy more RAM.
            • Re: (Score:3, Informative)

              by Anonymous Coward
              You can also tell if FLASH is verging toward failure on any particular block by timing the erase cycle. As the part ages out, the erase cycle takes longer. You can also use that information to enhance wear leveling.
            • Re:Oblig. (Score:5, Interesting)

              by Cantinflas (514778) on Friday September 28 2007, @05:56PM (#20789217) Homepage
              I don't know where you got your info, but 'modern' flash has horrible life-expectancy in terms or write-cycles.

              Explanation:

              Most flash vendors have moved to MLC (Multi-Level Cell) flash. It's cheaper and denser, but the bit-error rate goes up because you have more bits per cell. The typical life expectancy for MLC is somewhere in the range of 10,000 writes using single-bit error correction. This is compared to 'older' SLC flash which has a write endurance of 100,000 to 300,000 writes.

              Now, most vendors making media out of flash take varying degrees of a combination of two approaches (in addition to standard wear-leveling approaches). The first approach is to assume that the majority of the users will only ever store audio or video data so the occasional uncorrectable error won't have much impact as long as it doesn't corrupt the filesystem. The second approach is to use more advanced error correcting algorithms to compensate for the higher bit-error rate.

              Using more advanced algorithms, it's possible to get more than 300,000 writes out of a MLC flash-block before the errors become uncorrectable.

              P.S. I may be wrong, but I believe flash can have some really odd error conditions. For example, it's possible to disturb a bit in a block just by reading it. I believe it's also possible to disturb a bit in a different block on the same matrix when writing. That's why some form of error correction is always required with NAND flash.
          • Re:Oblig. (Score:4, Informative)

            by Lisandro (799651) on Friday September 28 2007, @02:55PM (#20787023)
            our childish "uh oh" introduction, your completely un-cited "a lot of issues" comment, and your vague "I recall" interruption reveal the fact that you're spouting off some crap on a subject you have no direct, real-world experience with. Find another subject with which to stroke your ego kid, because you're looking like a pompous dumbass on this one.

            The specs for a 256Mb NAND flash memory chip [alldatasheet.com] by Samsung (which is by far the biggest NAND flash manufacturer today) quotes 100k millon write/erase cycles, and this is for an IC commonly used in USB pendrives. The figure usually tends to get worse with increased memory sizes since the memory "element" (float gate) becomes smaller. For example, Modern 16Mb chips, which are the ones i have experience with, usualy quote 1 million W/E cycles endurance.

            But, it felt good stroking my ego a bit more :) Thanks!
          • Re: (Score:3, Informative)

            No you would boot directly from it. GP doesn't understand BIOS very well. This could hook into the boot process much the same as any RAID controller does.
            -nB
  • Uhh, Price? (Score:5, Interesting)

    by mosel-saar-ruwer (732341) on Friday September 28 2007, @01:08PM (#20785379)

    Who, what, when, where, why?

    Price would seem to be a pretty important detail...

    • by thegnu (557446) <thegnu@@@gmail...com> on Friday September 28 2007, @01:11PM (#20785427) Homepage Journal
      I think it's safe to assume you won't be buying one soon.
    • FTFA:

      So how much will these cards cost? Flynn told us that the company is aiming to beat $30 dollars a GB, something that should seem very cheap to large corporations, adding "You can drop ship or Fedex this card and be up and running in a few minutes... you can't do that with a storage area network."
      So, let's say they get to $29 a GB, a reasonable price for NAND flash-based memory devices. 640*30==$19,200. Sorry, but that doesn't seem to beat an inexpensive SAN in price. I recently priced out a 12TB iSCSI SAN for a little bit more than that, and even 1-2 TB fibre SAN from IBM should be around the same price.

      • This device is all about the IO/second.. a 12 TB SAN cant come close..

        If your looking to run a blast/darwin query on 50k files to find the closest match to an unknown dna sequence Either you need to recode a bunch of software to use sql, or you snag a piece of hardware that gives database level performance. 80gigs at $2400.00 is a bloody bargain.

        The device is also 10x faster in bandwidth than a normal drive which is comparable to a san, but not such a power hog.

        So really the tradeoff rocks for small

        • Re: (Score:3, Insightful)

          Um dude? He is quoting the FA. It's pretty clear that this drive will release at prices closer to $30/G. Maybe next year they can get down to $8...
    • From the article they are "aiming to beat $30 a GB". Not cheap! Figuring $30/GB, a 640GB drive would cost $19,200. So it is way out of my price range.
    • So how much will these cards cost? Flynn told us that the company is aiming to beat $30 dollars a GB

      At $30/GB, that would make an 80GB drive around $2,400. Hopefully the price will eventually come down, as "He even hinted that the company is looking into some gaming applications, but didn't want to give any further details."

      • Re: (Score:3, Insightful)

        I could buy a 10 GB drive for most of my OS and software, and just keep my media on a traditional hard drive. You don't need a super fast drive for your MP3s and Videos, but it would be nice to increase boot times as well as application start up times.
      • Re:Uhh, Price? (Score:5, Informative)

        by walt-sjc (145127) on Friday September 28 2007, @01:59PM (#20786187)
        Um, we were using large RAM disks (the kind that hooked up to SCSI, had a built in UPS and disk to dump RAM contents) many years ago (8 now?) to speed up databases. That was limited by the SCSI bus, but access time and latency were near zero (which was awesome.)
        Of course, large back then meant 4G, and the average hard disk was 9G. This is evolutionary, not revolutionary.

        • Re: (Score:3, Interesting)

          > Of course, I don't personally know if PCIe is hot swappable

          It is. But so is PCI -- it's just a matter of whether the physical and electrical connections on your hardware allow it, and whether your OS is set up to handle it. I wouldn't recommend yanking out your video card while the PC is on.
  • With small but fast flash drives appearing on the market, it would be nice to have storage systems that can automatically migrate data between disk and flash to maximize performance.
  • by AltGrendel (175092) <ag-slashdotNO@SPAMexit0.us> on Friday September 28 2007, @01:10PM (#20785413) Homepage
    What's the MTBF? [wikipedia.org]
  • Wow (Score:4, Interesting)

    by thatskinnyguy (1129515) on Friday September 28 2007, @01:12PM (#20785435)
    I could imagine using this as an OS drive. No sooner do you let your finger off the power button than the login screen appears.
    • Re:Wow (Score:5, Interesting)

      by zlogic (892404) on Friday September 28 2007, @02:05PM (#20786273) Homepage
      My PDA boots in about 30 seconds, and it doesn't have a harddrive. Booting isn't just loading stuff from a drive, it's hundreds of tests like
      - hardware changes
      - hardware initialization (e.g. loading firmware)
      - searching for drivers
      - applications acquiring and releasing resources and checking for stuff like library versions, user names etc.
      That's why BIOS initialization often takes time, and yet it works even if the system has no drives.

      The only way this would work is hibernating, but hardware would still need to be initialized.
  • I can't find any mention in the article of whether you'll be able to boot from them with current BIOSs. Surely any system they'll be in will have a decent amount of RAM for the OS, but it would be pretty cool solely for the fast boot times.
  • Will it last as long as a standard hard drive?
  • So how much will these cards cost? Flynn told us that the company is aiming to beat $30 dollars a GB
    So the initial 80GB model will hopefully cost less than $2400. I suspect these will be limited to servers demanding immense I/O with a large amount of data.
  • $30 per gb, ouch (Score:3, Insightful)

    by dnamaners (770001) on Friday September 28 2007, @01:14PM (#20785495) Journal
    Its fast, but not as fast as I would have hopped with parallel access. They better get the speed up or the cost down to hit it big. Right now I'd take either direction, as they both have decent applications. Good progress though, time will tell.
  • Seems like finally a newer reason to upgrade my hardware. I've never bothered with Vista, and I'm not big into gaming, so my P4/2.2GHz rig has been more than adequate for (surprisingly) over 5 years. Haven't needed a high end graphics card for a while, and only upgraded that for DVI output 3 yrs ago. When I built the thing in '02, I figured I'd get 3 yrs tops before it became a file server.

    But it doesn't have a PCIe slot. Something like this would finally give me a reason to build an all new PC. Anyone e
  • Misleading benchmark (Score:5, Interesting)

    by Chris_Jefferson (581445) on Friday September 28 2007, @01:29PM (#20785739) Homepage
    "'[Fusion io's CTO David Flynn] set the benchmark for the worst case scenario.."

    By which he means, set up a completely unrealistic benchmark which shows his flash drive in the best possible light, and a traditional drive in the worst possible light.

    I still want one of these, but that benchmark is nothing to be proud of.

    • Re: (Score:3, Insightful)

      "[Fusion io's CTO David Flynn] set the benchmark for the worst case scenario.."

      By which he means, set up a completely unrealistic benchmark which shows his flash drive in the best possible light, and a traditional drive in the worst possible light.

      No, the scenario he set up is a classic worst case scenario for drives, one which is well known to large disk usage corporations: near-random access by hundreds-or-thousands of concurrent users. This is what SANs are built to address, this is what parallel RAID

  • HardCard! (Score:3, Interesting)

    by jeffy210 (214759) on Friday September 28 2007, @01:56PM (#20786155)
    It's the return of the HardCard!!!! I remember having one of these with my old PC/XT. It was a 20 MB HardCard that fit into an ISA slot. The first ever hard drive i had running Windows 3.0 with DOS 3.3 on it.
  • by shdowhawk (940841) on Friday September 28 2007, @02:30PM (#20786633)
    Having talked to people at demo, what it pretty much came down to is this... is this a product we should be excited about? Definitely ... is it something that will do well right away? Not at all. The price has to drop before this becomes a really valid and useful tool for the GENERAL PUBLIC / Company. But there are a lot of companies out there willing to pay too much money to get these. Hopefully these big companies buy these up and fund this project as QUICKLY as possible. 7 of these side by side at 320/640 gigs a piece is a SCARY/powerful server.

    That being said, a few of the guys there said that they pretty much expect these (at the beginning) to do the best sales for companies that are looking to get really really fast database servers going. NOT for scsi san replacements (it's silly to spend $100,000 for something you could get for 10,000 hard drive space wise). Eventually as the price drops... i know of a handful of people who would EASILY pay 1000$ to get one of these on a gaming rig even if it was only 100 gigs. But that right there is already 1/3rd of the price of what it currently is. (assuming it's around 30$ a gig).

    Another thing to keep in mind that came up in the conversations... since these are tiny, think about the cost per server rack... and think of the cost per electricity to run. If you take those into consideration, these are actually less expensive that most people would think! A massive rack of hard drives could cost a lot of money in a co-location ... and a lot of electricity to run it all... But then again, we're talking about savings on servers, not general in home use.

    When this gets to about 1/3rd of it's current price, that's when you will see these things become TRUELY mainstream both to the average company and home users (be it rich ones who need the latest and greatest).

    Fusioni-io [fusionio.com] -- Link to their site.

    • I hope this means that laptops and large capacate media players with extremely long battery life are not too far away.

      At least as far as laptops are concerned, I thought a limited number of write cycles was a problem for solid-state drives.

    • Re:Still Expensive (Score:5, Insightful)

      by Jeff DeMaagd (2015) on Friday September 28 2007, @01:19PM (#20785579) Homepage Journal
      I hope this means that laptops and large capacate media players with extremely long battery life are not too far away.

      I think people expect too much from SSDs. The hard drive is far from the dominant power consumption component in a notebook. The CPU, chipset, GPU and display panel each consume more power than a notebook hard drive does. If you follow a modified version of Amdahl's law (not a law, but whatever), you want to fix the biggest problem first, and that is either the display or CPU. An LED backlit display can save some power, and running a lower power rating CPU saves power too. Compared to that, the savings of swapping HDD for SSD is negligible. On a standard notebook, I think you might add 15 minutes to battery life, which is still far from "extremely long battery life".

      In media players, doubling in capacity every year is a reasonable expectation.
    • According to the article, they are looking at pricing to be 30 dollars a gig. That is pretty pricey.

      That means their low-end 80GB drive will be around $2400+ or so US dollars depending on tax, shipping, retail prices etc.
    • Re: (Score:3, Funny)

      by Anonymous Coward
      should its battery fall out

      The fuck?

      by egg troll (515396)

      Oh, carry on.
      • Re:write limit? (Score:4, Insightful)

        by Lord Ender (156273) on Friday September 28 2007, @02:31PM (#20786651) Homepage
        That's a standard feature these days. I want to know how many times I can overwrite the entire disk with /dev/random. If I did a "dd if=/dev/random of=/ioMemory size=[size of ioDrive]" how many times could I execute that command before the thing goes tits up?
        • Re:write limit? (Score:5, Informative)

          by TinyManCan (580322) on Friday September 28 2007, @04:15PM (#20788115) Homepage
          Somewhere between 100k and 1 million times.

          Cosidering that this drive is 640GB, that means you would need to write somehwere in the region of 61 PETABYTES of information.

          You'd have to write to the drive at a perfect 800 MB/s for 941 days to hit that mark.

          It could last as long as 30 years, at full write speed of 800 MB/s if it can handle 1M writes per cell.

          At the end of the day, semiconductors this large and high quality are certainly better than tiny bits of rust on rapidly spinning platters.

            • Re: (Score:3, Informative)

              Certainly they are using wear leveling. They are probably (information is thin) also over allocating storage, such that 10-15% can fail before impacting the advertised free space on the device. In reality you will see your full 640GB of storage, which you could write 61PB of data to the very first sector on the disk over and over and never experience any issues. Before the last 'extra' block is used up, you'll get an alert and replace the device.