Slashdot Mirror


Hard Drive of the Future: Ram Drive

benzick writes "3d Retreat has posted a hands on look at a 2gig ram drive called the Rocket Drive. Article blurb: Overall the rocket drive is the best in I/O performance I have seen. It outperforms U160 SCSI drives by almost a factor of two. Yet there are some drawbacks to the Rocket drive, foremost is the price, although listed at the end of the review is some alternative pricing options to make it less expensive. And the rocket drive can not act as a boot drive. Also, if you have some extra money to spend, you can use multiple rocket drives in parallel."

397 comments

  1. x10^2?! by i_need_no_nick · · Score: 0, Redundant

    OMG! I want one! How much?

    1. Re:x10^2?! by biggknifeparty · · Score: 3, Informative

      Product: Rocket Drive (2 gig)
      Manufacturer: Cenatek
      Web site: Product Information
      Price (MSRP): $2,999 (as tested)
      Release Date: Available Now

    2. Re:x10^2?! by mstyne · · Score: 4, Funny

      For that price, I'll wait the extra 7 seconds for Mozilla to load, thankyouverymuch.

      --
      mstyne: real name, no gimmicks
    3. Re:x10^2?! by BigBir3d · · Score: 2, Informative
      Here are the MSRP pricing for the rocket drives.
      Rocket Drive DL (no memory)

      $399 USD RDB-000-M, 512 MB Rocket Drive
      $599 USD RDB-001-G, 1 GB Rocket Drive
      $699 USD RDB-002-G, 2 GB Rocket Drive
      $799 USD RDB-004-G, 4 GB Rocket Drive

      Rocket Drive Standard (with memory)

      $999 USD RDS-000-M, 512 MB Rocket Drive
      $1,799 USD RDS-001-G, 1 GB Rocket Drive
      $2,999 USD RDS-002-G, 2 GB Rocket Drive
      $4,999 USD RDS-004-G, 4 GB Rocket Drive


      i hope they put some sweet memory in there...
    4. Re:x10^2?! by Anonymous Coward · · Score: 1

      You would truly have to be a total idiot to buy the drive with the RAM on board. $4,200 for 4 1GB RAM sticks? Uh, no thanks, I will just get it from crucial.com for $1,100 (~$275 each) with free shipping, thank you vey much.

    5. Re:x10^2?! by bunratty · · Score: 2

      Factor of two = times two. Two orders of mangitude = times about a hundred. At least you were within two orders of magnitude of being right!

      --
      What a fool believes, he sees, no wise man has the power to reason away.
    6. Re:x10^2?! by i_need_no_nick · · Score: 1
      Eeep.

      So it's not really worth getting after all.

      /me scrambles for the "Cancel order" page...

    7. Re:x10^2?! by Feanturi · · Score: 1

      (no memory)
      $699 USD RDB-002-G, 2 GB Rocket Drive
      (with memory)
      $2,999 USD RDS-002-G, 2 GB Rocket Drive

      i hope they put some sweet memory in there...


      No doubt! The article said it takes standard SDRAM, I can get 2G of PC-133 for less than $400 (Canadian, yet!) and here they want $2300 USD to populate the slots. Either they think that 512MB of SDRAM is worth around $600/stick or that's one hell of a labor charge, isn't it?

      It looks cool, but I don't feel the urge to shell out any bucks for it until it can operate as a boot device. I can see good uses for it in its present form, but I'm going to wait till it's bootable.

    8. Re:x10^2?! by Anonymous Coward · · Score: 0

      > thank you vey much
      Perhaps you should spend your money on english classes instead?

  2. Yay by miketang16 · · Score: 0

    multiple rocket drives in parallel

    I wish I could afford one.

    --
    -------
    "In times of universal deceit, telling the truth becomes a revolutionary act."
    -- George Orwell
  3. Of the future? by Jedi+Alec · · Score: 1

    Dunno, but this Winxp machine I'm typing this on has a 700 MB Ramdrive(yes, one ISO), and I could easily upgrade that if I could be bothered to buy more memory...

    --

    People replying to my sig annoy me. That's why I change it all the time.
    1. Re:Of the future? by Anonymous Coward · · Score: 0

      People replying to my sig annoy me.

      Why?

    2. Re:Of the future? by nicuss · · Score: 3, Insightful
      Nope, it's not of the future. The HDD future belongs to something else: platter-level RAID systems. That is, you make a RAID with each head/platter being one unit. It has been tried in the past, but the problem was that the heads would get slightly misaligned in time and you'd have to reformat too often. I think that with the current technology it should be possible to decrease the data density (which is ok now) and use a stronger recording signal (fatter tracks) to allow for some head alignment change.

      Once you do this then ALL heads will be able to read or write simultaneously (in parallel) rather than one at a time as they do now.

      Only question is -- how long till they decide to go for it.

    3. Re:Of the future? by delta407 · · Score: 2

      Right; this isn't exactly "way out there" kind of technology as "Of the Future" would imply. I know of a high-performance web server that's being deployed in less than a week that uses one of these.

    4. Re:Of the future? by Anonymous Coward · · Score: 0

      Yeah, ram drives in software are quite an old and established idea, but I think you'll find quite marked differences between your WindowsXP implementation and the hardware mentioned in the article. The first that springs to mind is the total loss of data a software ramdrive experiences when the power is suddenly switched off. You're using it to serve an ISO image? That's fine... I wouldn't use a WindowsXP ramdrive to serve dynamic data unless checkpoint files were being kept on other media... which may negate some of the performance increases.

      Having said that, 2gig is just a tiny bit small for UT2003, so maybe I'll hold out for the 4 gig version.

    5. Re:Of the future? by Lux · · Score: 1

      The optimization you describe seems to target transfer rates more than latency. Latency is the real killer, and though this solution would eliminate seek time (~9ms), the platter still needs to spin around, which on a 7200RPM disk, only spinning 120x/sec, that's .0083 seconds/rev or... 8ms. Expected latency is thus 4ms. That doesn't factor in bus latency and other factors, just the latency on the platter.

      This ram drive thingy has a 6 _micro_second latency (if memory serves), roughly 1000X faster. Stick that in your RAID pipe and smoke it. :)

    6. Re:Of the future? by nicuss · · Score: 1

      Yeah it doesn't address latency, just data rate. The neat thing is that you can still make an external RAID of these.

      [zipping flame suit] Not to mention a beowulf cluster ...

    7. Re:Of the future? by poopdik · · Score: 0, Troll

      The optimization you describe seems to target transfer rates more than latency.

      Yep, that's the real problem. "Geeks" don't usually like to address any problems though unless they're trendy problems. Neon lights, and cooling solutions (for systems that don't warrant it). You can have a 500MB/Sec bus for storage, and never put more than 40MB/sec on it because of the shit drives that are connected to the other end. It's ridiculous.

      I used RAM drives in DOS about 8 years ago. Why wouldn't you just add the RAM to your mb though where your access to it isn't hampered by your shit-slow PCI bus and save yourself the couple of grand for some hookers and beer.. something everyone here could use more of.

    8. Re:Of the future? by Anonymous Coward · · Score: 0

      It wont help you.I'd whoop your ass if you had a 160gig ram drive.Maybe if you o/ced your vid card and cpu...nope,your still hit.

      Save your money,kid.You can't buy skillz.

    9. Re:Of the future? by mark-t · · Score: 2
      RAID systems? Uhmm... the problem with that is that it's still based on the spinning disk methodology, which is, I'm afraid, a very dated concept. A better long-term solution is to create a solid-state storage system that has no moving parts and does not require any power to maintain its data. Peering into my own private crystal ball on this issue, what I forsee is that we will come to a point where data is holographically stored in readily swappable crystals about the size of sugar cubes. One cube will be capable of holding on the order of many millions of gigabytes worth of data. First we will see "write-once/read-many" versions of this technology, but "write-many" technologies will probably not be far behind. Such storage technology will easily replace most every type of media and storage device that currently exists, including hard drives, CD's, DVD's, and even film!

      There's only one drawback... these beasties will have some serious copyright protection technologies built right into the hardware. No fun.

    10. Re:Of the future? by Anonymous Coward · · Score: 0

      but does the stuff stay on your RAM drive after a reboot or if you power down your computer? i think not...

      this ram drive comes with it's own powersupply that keeps the data even after reboots and when you power down the comp

    11. Re:Of the future? by Sivar · · Score: 2

      Nope, it's not of the future. The HDD future belongs to something else: platter-level RAID systems.

      I'm sorry to be blunt, but that is incorrect. If you are interested in the future of storage, follow StorageReview.com's forums. Every other week or so when someone comes into the forums complaining that nobody makes such a drive, or comes up with this "great new idea!!", they are usually referred to the website of Tannin, one of the more knowledgeable members, who keeps track of this sort of thing. Here is that website: Odd drives

      I don't mean to be rude, but you made your statement about interdrive RAID authoritatively, as if you knew this for a fact, which you do not, because it is wrong. Further, you are incorrect about the reasons for not implementing such a system. The real reasons are:

      1) Too expensive. It simply costs more to make. It requires a small processor to split and recombine data, it requires extra testing, it requires extra validation, more complex firmware, and is less reliable.

      2) Time to market. See 1

      3) There is absolutely no point. As the website linked states, you can achieve the same results with two ordinary hard drives in RAID. If you are going to spend extra on such a drive, you mas as well get better reliability/performance/capacity by just using the tried and true method of more than one drive.

      To further compound the incorrectness of the statement, the primary advantage of RAM and Flash-ROM based drives--the reason they are so good, is their access time. The world's fastest hard drive, the Seagate Cheetah 15k.3, access data in milliseconds. Even poor quality RAM can access in microseconds or nanoseconds.
      One company used as a "case study" by Platypus, a company making solid state disk drives, was able to replace their mail server drives with platypus drives and REDUCE the number of servers (which had RAID) rather than increase the number. Mail servers do not give a damn about sustained transfer rate (STR), but they certainly do care about access times, especially when dealing with tons of small files like Maildir-bases systems use.

      Again, I don't mean to be an asshole. I have certainly been dead wrong my fair share of times, but I am usually rather bluntly corrected. Make a mental note and drive on.

      --
      Computer Science is no more about computers than astronomy is about telescopes. --E. W. Dijkstra
    12. Re:Of the future? by Com2Kid · · Score: 1
      • and save yourself the couple of grand for some hookers and beer.. something everyone here could use more of.


      So that is why all the trolls are always in such a crappy mood, hung over from the beer and STDs from the hookers.
    13. Re:Of the future? by Disoculated · · Score: 1
      Not a beowulf cluster, but you could set up a PVFS cluster of these, which would be an excellent filesystem configuration to support a beowulf cluster.

    14. Re:Of the future? by Anonymous Coward · · Score: 0

      Hey pal, what program are you using to have such a big ramdrive? I have 1024Mb DDR and I can take use of that for cd writing...

  4. Huh? by Anonymous Coward · · Score: 0

    U160 SCSI drives by almost a factor of two

    Really? Is that all?

    1. Re:Huh? by Trusty+Penfold · · Score: 4, Insightful

      It's another bullshit "hardware site" test.

      The "benchmark" was a Photoshop filter on an image. It was twice as fast as with the SCSI disk.

      This tells you very little about the relative performance of the drives since image processing is typically not disk bound.

    2. Re:Huh? by Anonymous Coward · · Score: 0

      This tells you very little about the relative performance of the drives since image processing is typically not disk bound.

      That is, unless you're making a banner ad for slashdot. Man those things are huge!

    3. Re:Huh? by at_18 · · Score: 5, Informative

      This tells you very little about the relative performance of the drives since image processing is typically not disk bound.

      Actually, the author of the article made it disk bound, by forcing Photoshop to go into swap space with an image much larger than the available memory.
      And you missed the HD testing pictures, measuring high throughput (sp?) and unbelievable low latency.

    4. Re:Huh? by narkotix · · Score: 0

      so does that mean when i get ultra320 that factor of 2 means nothing??? or am i mathematically incorrect?

      --
      We played dungeons and dragons for 3 hours.....then i was slain by an elf
  5. Good for Mozilla by minus23 · · Score: 2

    I was thinking something like this... (tho even on a lesser scale) would be a good place to install Mozilla or Pheonix. I know especially Pheonix is getting really fast to launch for a browser.. but this would be great!

    1. Re:Good for Mozilla by Jedi+Alec · · Score: 3, Interesting

      The trick is not to put something on it that remains constant, but something that changes all the time. So instead of the actual browser, dump the cache on it. Tell your OS and software to use the drive for temporary storage(swapfile for example) and then you'll get the most out of it. Something the article does not specify but which my software driven Ramdrive allows me to do is to actually load a disk image into the drive on bootup, allowing you for example to permanently install an entire piece of software on it permanently which will then only have to be loaded from the harddrive once...

      --

      People replying to my sig annoy me. That's why I change it all the time.
    2. Re:Good for Mozilla by Anonymous Coward · · Score: 0

      Hardly new!! Quantum having been selling sold state drivers for nearily a decade... Why all the type?

    3. Re:Good for Mozilla by luciuskwok · · Score: 1
      I would prefer that the people working on Mozilla work on optimizing it so that it launches faster.

      The top ten usability problems in Mozilla

      Bugzilla bug tracker for startup performance

    4. Re:Good for Mozilla by TheOnlyCoolTim · · Score: 4, Insightful

      Putting your swapfile on this doesn't make much sense. You'd be buying memory, putting it in a special card that makes the memory act like a hard drive, then making that hard drive act like memory. It would be cheaper to just buy more regular memory.

      Tim

      --
      Omnia vestra castrorum habetur nobis.
    5. Re:Good for Mozilla by jonbrewer · · Score: 3, Interesting

      Something the article does not specify but which my software driven Ramdrive allows me to do is to actually load a disk image into the drive on bootup

      You wouldn't be so kind as to reply with a link to said software ram drive?

      I used this trick on my PowerMac 7100 back in the day, having loaded it up with 136MB ram, an insane amount for 1996... I used to run Marathon off the built-in System 7.5 software ramdisk. :-)

    6. Re:Good for Mozilla by eWarz · · Score: 0

      Not really, no matter how much RAM you have, you are still always going to need swap. IIRC WinNT/2k/XP all swap inactive/unused pages to disk. Although you could easily use a regular RAM Drive program rather then buying an expensive hardware solution.

    7. Re:Good for Mozilla by Feanturi · · Score: 3, Insightful

      Putting your swapfile on this doesn't make much sense. You'd be buying memory, putting it in a special card that makes the memory act like a hard drive, then making that hard drive act like memory. It would be cheaper to just buy more regular memory.

      Except that you can have memory from here to the moon, yet Windows and various programs running on it will still insist on using disk-based virtual memory anyhow. With XP, setting the pagefile to 0 MB for all drives tends to work for awhile, and through several reboots, but then suddenly Windows will pick a drive and make a 1.5G (the same as the physical memory in my box) pagefile there, without telling me. It only does that if I had it at 0. If I have set some other value, like 512, that will stick. My system has over a gig physical free most of the time, yet still has about 150MB or so allocated as paged. This device turns that stupid problem into nothing, voila! I want it bootable before I will buy one, but I can't wait to have one and point all my apps' temp folders at it, like Cool Edit and such, that would be mega-sweet. Getting to set a nice big pagefile on it as well would be a nice bonus, as Windows could leave me the hell alone about such issues and I wouldn't care that it was being used needlessly.

    8. Re:Good for Mozilla by Alan+Partridge · · Score: 1

      my thoughts exactly. I had a Mac with a Platypus BOOTABLE ram drive in it over 5 years ago.

      --
      That was classic intercourse!
    9. Re:Good for Mozilla by MrResistor · · Score: 2

      It makes sense if you need more RAM than your mobo can handle.

      I'm not sure it makes more sense then puting the $2k towards a machine that can handle more RAM in the first place, though.

      --
      Under capitalism man exploits man. Under communism it's the other way around.
    10. Re:Good for Mozilla by Anonymous Coward · · Score: 0

      ok.. well then why don't we just buy a bunch of memory, make a ramdisk of it.. mount it and copy over whatever you want in an init script.. and save the few hundred dollars for the card??? (assuming that you have the extra memory room on the mb)

    11. Re:Good for Mozilla by Anonymous Coward · · Score: 0

      Does linux make use of the sticky bit for executable files? If so, there would be no need to waste money on this, we could set the sticky bit on mozilla and it would be cached in memory after the first time it is launched (or at least in swap, but in which case, you need to buy more memory anyway).

    12. Re:Good for Mozilla by Toraz+Chryx · · Score: 1

      "I'm not sure it makes more sense then puting the $2k towards a machine that can handle more RAM in the first place, though."

      If you've got a dual athlon (or Xeon) rig with.. say.. 4GB in it, and don't want the slowdown pain of PAE, then one of these things acting as a scratchdisk might well be just what the doctor ordered :)

    13. Re:Good for Mozilla by Jedi+Alec · · Score: 1

      This is the one I've used most, but it's not free. While googling for where I found it I also stumbled on this website, but I have no personal experience with that one.

      --

      People replying to my sig annoy me. That's why I change it all the time.
    14. Re:Good for Mozilla by Jedi+Alec · · Score: 1

      Nevermind that second link...however, this article looks quite interesting...

      --

      People replying to my sig annoy me. That's why I change it all the time.
    15. Re:Good for Mozilla by v1z · · Score: 1

      I can't wait to have one and point all my apps' temp folders at it, like Cool Edit and such

      Sure. And the next time power fails after a long coding-session, all your data will be gone.

      I think this is silly. I would rather have a mainboard that supports a lot of memory, and applications/os' that take advantage of that.

      Then again, if it was bootable, it might be nice for a soundless system. But I'd still install a regular hd for "backups" of my data.

    16. Re:Good for Mozilla by Anonymous Coward · · Score: 0

      You are mistaken if you think eliminating the Windows pagefile improves performance -- it actually makes it slower. Their VM just likes disk backing for all physical memory (unlike Linux).

    17. Re:Good for Mozilla by Anonymous Coward · · Score: 0

      Sort of. NT *pages* to disk even when there is free memory. It only *swaps* when your working set exceeds RAM. There's a difference. If paging is slowing down your system, something's broke.

  6. Imagine a ... by zelphi · · Score: 0, Redundant

    ...

    Wow that looks amazing. I might actually consider buying one if it didn't cost twice as much as my current computer...

  7. What's the point? by wackybrit · · Score: 1, Insightful

    What's the point of this? You can already create RAM drives using the memory you have in your machine. You don't need a dedicated unit to do it. Heck, I could create meagre RAM drives on my 640KB Amstrad PC1640 (8086).

    Why not just fit your PC out with 4GB of fast DDR RAM and do it that way? That memory would be far cheaper than this card.

    1. Re:What's the point? by Mage+Powers · · Score: 2, Funny

      >What's the point of this?
      You must not be a geek if you need to ever ask that.
      >You can already create RAM drives using the memory you have in your machine. You don't need a dedicated unit to do it.
      Yes you can, but can you plug those ram drives into a UPS and keep the contents between reboots?
      >Heck, I could create meagre RAM drives on my 640KB Amstrad PC1640 (8086).
      So?

      >Why not just fit your PC out with 4GB of fast DDR RAM and do it that way? That memory would be far cheaper than this card.
      What if I want 4gigs of ram AND a ramdrive? I don't, one gig of ram is enough...

      Personally I don't get why people always expect products to have a really necessary use ;)

    2. Re:What's the point? by vlad_petric · · Score: 4, Insightful
      Well, in the world of architecture, small is fast and large is slow. Memory is already an order of magnitude slower than the CPU.

      Furthermore, RAM drives are really meant for servers. Such a server will most likely use a fast internal memory (like RAMBUS) and cheaper, slower & much larger SDRAM 100 for the RAM drive.

      The Raven.

      --

      The Raven

    3. Re:What's the point? by spinkham · · Score: 2

      I would love to have a small version of this (only needs to be like 8-128 megs) to act as the journal for my hard drives.
      This is persistent storage (as long as you have a UPS on the external power sonnection), and would be great to use for the journal of your filesystem, making it act like a fast write cache that was persistent. Would allow more write combining and such before being written out to the real hard drive.
      As you mention, more RAM as a cache pretty much would make up for any other use of this I can think of.

      --
      Blessed are the pessimists, for they have made backups.
    4. Re:What's the point? by walt-sjc · · Score: 2

      Some RAID controllers have this - they use NVRAM. It basically caches all the writes. When the power comes back, it continues the pending writes. Hence, no lost data due to the power dying in the middle of a write. Nice for transactional databases, as writes "commit" instantly.

    5. Re:What's the point? by stevejsmith · · Score: 1

      Ah ha, finally somebody has pointed out the obvious use! Servers! Most servers don't serve extremely large data contents (hence why you see smaller-than-average SCSI drives). People who run servers can afford the money for an extreme performance boost, and they leave them on 24/7, anyway.

    6. Re:What's the point? by Anonymous Coward · · Score: 0

      In case you've already maxed out your system memory.

      Most systems nowadays in the x86 class machines can't do more than 4 gigs of motherboard/bios supported memory, and most figure out 2 gigs still. If I want a monster, I can go with the Rocketdrive, albeit with lessening performance gains due to the PCI bus being maxed at 132mb/s and that fact that it is on the PCI bus instead of FSB.

      Personally, I would particularly enjoy a quad processor machine with 6 PCI slots full of 4 gigs per slot. 24 gigs plus say 3 gigs from system memory would do nicely for some extreme work, mpeg2 editing a minimum. Less waiting.

      If this company wanted to make it sell like krispey creme donuts at an elite modeling tryout, drop the price of the current (32 bit PCI) versions. I would think at this point 64 bit/66mhz PCI versions would be better suited for the server range and the price premium (they could go for more actually) and then they would get the mass market product of the 32 bit PCI versions for the "I want but don't have that much money" folks.

  8. OMG! by gibbdog · · Score: 0

    Can you imagine a beowulf cluster running with these things????????

    1) create kick-ass hard drive
    2) put it in a cluster
    3) ???
    4) Profit!

    1. Re:OMG! by Kuutti · · Score: 1

      Are you sure that would work?
      To play it safe, how about putting it in a BEOWULF cluster?
      Would that make more profit?

  9. Case-sensitivity police by Anonymous Coward · · Score: 0

    ram = male sheep
    RAM = Random Access Memory

    1. Re:Case-sensitivity police by Cyno01 · · Score: 1

      What about the truck?

      --
      "Sic Semper Tyrannosaurus Rex."
    2. Re:Case-sensitivity police by Anonymous Coward · · Score: 0

      the truck is named after the "male sheep", i'm afraid...

    3. Re:Case-sensitivity police by stevejsmith · · Score: 1

      The truck? Ram. Capital R.


      Slashdot requires you to wait 20 seconds between hitting 'reply' and submitting a comment. It's been 12 seconds since you hit 'reply'! Note: chances are, you're behind a firewall, or proxy, or clicked the Back button to accidentally reuse a form. We know about those kinds of errors. But if you think you shouldn't be getting this error, feel free to file a bug report, telling us: Your browser type Your userid "614145" What steps caused this error Whether you used the Back button on your browser Whether or not you know your ISP to be using a proxy, or any sort of service that gives you an IP that others are using simultaneously How many posts to this form you successfully submitted during the day Please set the Category to "Formkeys." Thank you.

  10. QikDrive by Anonymous Coward · · Score: 0

    Something similar here.

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

      Sorry, it should have been .net. So, here.

    2. Re:QikDrive by pandaman9000 · · Score: 1

      No pricing info. I know better than to believe there is ANY kind of bargain here. At least the company in the article lists the price of their product.

  11. Source code mirror by Istealmymusic · · Score: 1, Redundant

    system.ini:
    device=vdrive.sys /L:R /S:64M

    --
    "The lesson to be learned is not to take the comments on slashdot too literally." --Vinnie Falco, BearShare
  12. External Power Cord!?! by cscx · · Score: 5, Insightful

    And if someone trips over the cable, there goes your 2 gigs of data!

    Thanks, but no thanks, I'll stick with mah good ole Winchester disks.

    1. Re:External Power Cord!?! by AllTom · · Score: 3, Insightful

      The first thing that I thought of when I read the headline after, "hmm, interesting," was, "What?? RAM for storing data?"

      I've had problems enough with hard drives crashing and losing data without having to worry about having a power outage and losing everything. A UPS is a good idea for servers, and perhaps in some other special incidences too, but I wouldn't want to be tied down to having one. The electricity to my house is rarely constant, and lights flicker all the time due to lackluster electrical jobs.

      For me at least, 2 GB is not nearly enough to store all of my data anyway. If they find a way to assure me that I won't lose my data, and increase the size of the drive, then I may just opt for the enhanced speed. Until then, I'll stick with my current drive.

    2. Re:External Power Cord!?! by Feanturi · · Score: 1

      You don't use a device like this for storing important data, and you also schedule nightly backups of what's on it, in case the UPS fails or whatnot. It's a daily-use tool that speeds your productivity if you're using it as temp storage/workspace. The backups are to make sure you don't lose transitional stuff you might have there (such as software, like a game or something) if there's some disaster. If you're in the middle of editing a video clip with the tech you have right now and somebody kicks out the power, that sucks just as much as what we're worrying about here, if you set it up properly.

    3. Re:External Power Cord!?! by stevejsmith · · Score: 1

      Um...didn't anybody read the article? It has a UPS backup! Just give it a minute or two and it will backup all of the data on a physical hard drive. The UPS, however, can keep it alive for longer than that.

    4. Re:External Power Cord!?! by Babbster · · Score: 2
      A UPS is a good idea for servers, and perhaps in some other special incidences too, but I wouldn't want to be tied down to having one. The electricity to my house is rarely constant, and lights flicker all the time due to lackluster electrical jobs.

      Actually, you're exactly the person who needs around five minutes of UPS backup. The damage that can be done to a computer from short power interruptions isn't limited to just losing data currently in RAM but can extend to problems with the hardware itself. You can get five minutes of UPS backup for around $50 (or even a bit less) which would be perfect for the problems you describe - a problem which I share, and which I was happy to have solved by my company sending me a baby UPS. :)

    5. Re:External Power Cord!?! by Anonymous Coward · · Score: 0

      This is intended for servers that traditionally have large IO requirements. eg: caching proxies, web servers, mail servers, large databases, etc.

      You can't use system RAM since the maximum is already being used in the system to run the required applications (eg: web server needs 4G to run multiple backend processes for dynamic web pages).

      The expectation is that the server has a nearly 100% up time due to UPS, etc or that the data isn't critical, (eg cache, mail spooling). The company actually sells the entry level model without any external backup power. As it is the backup power solution is intended more to keep the data in the cache(or whatever) when the machine has to be brought down for maintainence.

      Nothing stopping you from replacing the plugpack external power source with its own gell cell power supply (That should last much longer than any UPS you may have, short of a generator.)

      I would have thought it was blatantly obvious that this isn't intended for normal storage. The Price per Gb is aweful, for anything more than 4Gb or so a Fibre Channel RAID array becomes cheaper, and that too can saturate a PCI bus.

    6. Re:External Power Cord!?! by nofx_3 · · Score: 1

      If the drive is to be used for things like swap space in photoshop, power will only be a problem between saves to your physical drive. If you were to have a power outage and lose the swap or scratch on the ram-drive you would be left with the last possible save.
      I think another great thing this drive could be used for is temp files like webcache and tmp files for office and what not.

      -Kappy

      --
      Visualize Whirled Peas
  13. GOOD! by NineNine · · Score: 5, Insightful

    The hard drive is some ancient technology that is the *easily* #1 cause of all computer failures. Other than the cooling fans, they're the last moving parts, and the most critical ones too... A fan dying may cook your computer, but a hard drive kills your *data*. It's high time that something came along to replace those damn things. I'm typing this on my PC with a 2 drive RAID because I can't afford downtime or data loss. That really shouldn't be necessary any more. Bring on the alternatives!

    1. Re:GOOD! by Mage+Powers · · Score: 2, Insightful

      *cough*DVD-Rom Drives spin*cough*

    2. Re:GOOD! by Anonymous Coward · · Score: 0

      That is completely false. The number one cause of all computer failures (the cause that acutally renders all other causes so extremely rarely implemented, that they can not be considered a cause at all) is the user.

    3. Re:GOOD! by Anonymous Coward · · Score: 0

      Takes a RAID array to power all that porn, eh NineNine? Whatever, dude. *rolls eyes*

    4. Re:GOOD! by mla_anderson · · Score: 1, Flamebait

      I thought MS was the #1 cause of computer failures.

      --
      Sig is on vacation
    5. Re:GOOD! by conway · · Score: 1

      Yes, mechanical failures are the bane of hard drives.
      But is keeping your precious data on a drive that will lose _all_ your data on the next _power failure_ better?!? Power failures happen much more often than HD failures in my experience.
      No, until we have huge, fast NVRAM, I'm sticking with my mechanical HD.

    6. Re:GOOD! by Anonymous Coward · · Score: 0

      I love it how you people all throw in those masturbatory "I'm typing/running this on" comments. Guess what? People used to have to write everything down on paper, because there weren't any computers. And once they did come along I'm sure your worthless ancestors were all out there with their quills and inkwells, demanding that they'd never change. No one cares. Things change whether you Luddites want them to or not.

    7. Re:GOOD! by Reece400 · · Score: 1

      And you were right! lol :D

      Reece,

    8. Re:GOOD! by Anonymous Coward · · Score: 0

      Jesus fucking christ. Why don't you take your 'LOL' using ass back to AOL you fucking clueless moron.

    9. Re:GOOD! by jusdisgi · · Score: 1

      The hard drive is some ancient technology that is the *easily* #1 cause of all computer failures.
      And here, this whole time, I thought windows (lack of) memory protection was the #1 cause. silly me.

      --
      Given a choice between free speech and free beer, most people will take the beer.
    10. Re:GOOD! by Reece400 · · Score: 1

      Well, I would you see, except that i've never used AOL in my life,,, as I doubt anyone with even a vocab exsiting ONLY of "LOL" would...

      Reece,

  14. Yes, but this one ... by Tensor · · Score: 5, Informative

    Keeps that data after the pc is turned off, which i bet your amstrad didn't do.

    It has an external supply that keeps the card powered.

    And i believe this is the whole point of this card, its pretty much useless otherwise.

    Also the xfer speeds are limited to PCI (66mhz) speeds, that is why "its only" 2x as fast as a U160 scsi.

    1. Re:Yes, but this one ... by Boone^ · · Score: 2

      ohhh, now I see. I thought the reviewer was rather dumb in saying "cons: can't boot from it". I was floored when I thought he expected to power cycle and have data there.

    2. Re:Yes, but this one ... by Anonymous Coward · · Score: 0

      Hmm. . . Although it may not be as fast, We could write a script that would read from disk on startup, and write the back to disk on shutdown. In fact a Makefile would be perfect for this; it could be run several times per day to sync the files.

    3. Re:Yes, but this one ... by chrispix · · Score: 1

      When you power cycle, you dont loose the data.. That is what the external power connector is for.. When the pci bus is no longer powered. The Ram Drive is still powered and retains its memory. As for crashes etc. It retained its memory just fine even thru an XP blue screen.

    4. Re:Yes, but this one ... by GiMP · · Score: 2

      'real' ram drives don't need external power supplies to keep running.. real ram-drives use non-volatile memory. This isn't much more than a card-bus pc with loads of ram and a disk-controller interface via the pci bus.. with an external power supply.

      If your machine doesn't need more than 1 gig of ram, put in 4 gigs and set 3 aside for a ramdisk.. rsync the ramdisk every 30 minutes (or as desired).

      Sure you wouldn't be able to boot from it, but it would be fast and the data would be retained.. at least in 30 minute increments ;)

      If linux supported something like a 'buffered raid' so that you could raid0 devices of varying speeds. mirror your ramdisk and your physical disk, with any changes to the ram disk being automatically copied as fast as it can be to the physical disk... without causing any latency or slow-down to the ramdisk... of course, with Linux's (in)ability to do I/O operations.. this could be devestating :)

  15. Why this beats a traditional ram drive. by lavaforge · · Score: 4, Informative

    This is really pretty interesting. The device has it's own power supply that actually allows you to save data when you shut down your computer. It doesn't seem like it would be too reliable, but it does provide a reason as to why this is better than a traditional RAM drive (provided you have it hooked up to a UPS).

    1. Re:Why this beats a traditional ram drive. by nuggz · · Score: 3, Insightful

      I don't reboot my computer, might as well have a ram drive. Heck with something like tmpfs being able to swap out it would be MUCH better.

      All we need is motherboards that accept more then a gig or two of memory.

    2. Re:Why this beats a traditional ram drive. by _ph1ux_ · · Score: 3, Insightful

      ya but does it ahve an external power adapter you plug into the wall - or a battery on it?

      Try moving to another machine with 2GB still alive on this thing...

      Although a really good application for this would be that guy running the game cluster - or any game for that matter.

      Run the whole game in the ram drive, everything, including the movies. Talk about speed.

    3. Re:Why this beats a traditional ram drive. by jafuser · · Score: 2
      My first thought in repsonse to this is, why not have a partition which mirrors the RAM drive in the background, at a low priority. So at worst case (power outage without a UPS), you lose minimal data. With a UPS, the mirror software would certianly have the partition up to date before the battery runs out.

      But then it occurred to me that this isn't much unlike just using a really really big drive cache, which would be much less expensive than the 3K for the device which this article features.

      My question to those more in-the-know than myself is, which system would be faster? Are disk cache algorithms more efficient than a constant mirroring-to-disk algorithm? Has there been much technological improvment in disk cacheing algorithms in recent years?

      My hypothetical interest would be to boot from a normal disk partition, then once finished booting, copy the OS drive to a mirrored RAM drive of sorts. Therefore, all of the DLLs, *.so's, temp files, etc. would all be much more quickly accessible.

      I recently read somewhere (perhaps on this site) that there was an operating system written quite some time ago which considered the hard disk itself as the "memory" and that RAM was just a cache for the hard disk. Interesting concept, which I also wonder how efficient would be in comarison to the other methods I mentioned above.

      Any way, maybe MRAM will come along and save us someday from the dual-storage standard.

      Perhaps in the more distant future (25 years or more), if bandwidth keeps up with it's current pace, we won't have to purchase hard drives, but instead purchase network storage space... In which case I doubt we'd need local hard drives.

      --
      Please consider making an automatic monthly recurring donation to the EFF
  16. Not practical by selectspec · · Score: 4, Insightful

    1. A DRAM "drive" suffers the fundemental problem that if the "external" power source is lost, you lose everything on the drive.

    2. 80-100 MB/sec sustained performance is nothing to write home about for DRAM performance. A RAID 0 stripe across 2 ATA drives could give you this same performance for about 1/4 the price without the power issue.

    Although its a long way off, MRAM offers a much more promissing application in the area of high speed RAM drives.

    --

    Someone you trust is one of us.

    1. Re:Not practical by delta407 · · Score: 3, Insightful
      A DRAM "drive" suffers the fundemental problem that if the "external" power source is lost, you lose everything on the drive.
      This raises the question as to why they didn't integrate a rechargable battery, sort of like an internal UPS, that would take system power when available and then give just enough juice to keep the RAM powered for, say, 24 hours of downtime. Such a drive would only really be useful in a high-performance server anyway, which is likely not to have 24 hours without power.
      A RAID 0 stripe across 2 ATA drives could give you this same performance for about 1/4 the price without the power issue.
      Yes, but then you have other issues -- heat, noise, and moving parts. Hard drives are far more prone to hardware failure than RAM is.
    2. Re:Not practical by Ed+Avis · · Score: 3, Insightful

      I suppose a good use of this is it may support much more RAM than you can get on the motherboard. You might have six PCI slots - filling each one of those with a RAM drive gets say 12 gigabytes of extra RAM or at least extremely fast swap space. With four DIMM sockets (which most motherboards don't have AFAIK) it would be hard to get more than 4 gigabytes on the motherboard.

      OTOH, if you have such large memory requirements you'd probably be using some serious 64-bit hardware and not Intel-based toys.

      --
      -- Ed Avis ed@membled.com
    3. Re:Not practical by Istealmymusic · · Score: 2

      You better hope the rechargable battery is solid-state. Otherwise, overload the power source and you'll have acid eating away at your bits.

      --
      "The lesson to be learned is not to take the comments on slashdot too literally." --Vinnie Falco, BearShare
    4. Re:Not practical by selectspec · · Score: 3, Interesting

      To be fair of course, DRAM drives do offer the following features and are used as "caches" in many large server farms (like google, ebay, etc):

      1. DRAM drives suffer no penalty to random i/o workloads while disks even in RAID configurations do suffer penalties.

      2. DRAM drives export a larger addressable cache area, extending main memory. Throw a couple of these 4 GB modules into your server, and you have essentially extended the cachable address space beyond the 4GB limit of 32-bit CPUs to 16GBs + 4 GB of main memory. For web farm servers this is a nice feature that can be cost effective.

      However, in no way should DRAM disks be confused with real drives, where persistence of data is truely important. For example, most RAM drives don't even bother with an external power cable.

      --

      Someone you trust is one of us.

    5. Re:Not practical by addaon · · Score: 2

      And even high end x86 boxes have 32 ram slots (my machine), compared to 10 PCI slots... which means that your max ram is 64GB, your max ramdrive, if each drive uses their highest-end model, is 40GB. Makes it look even more silly. Never mind that the 100MB sustained limit is almost certainly a PCI bus limit, which means having multiple ramdrives on one pci bus (my box has 3 pci busses, so if you wanted more than three ramdrives, at least two would compete for bandwidth) just is silly. Finally, they don't seem to support 66MHz/64bit pci, which would quadruple available bandwidth, although admittedly I didn't look too hard. It just seems this technology is silly for the low end, since a ram disk works better, and silly for the high end, since it's not really sufficient. Oh, well.

      --

      I've had this sig for three days.
    6. Re:Not practical by Ed+Avis · · Score: 4, Informative

      On the first-generation IBM PS/2s, the amount of ram on the motherboard (or in IBM-speak 'planar') was limited, with more added by plugging cards into the MCA bus. I have a Model 80 which has only eight megabytes on the motherboard but another 32 on a Kingston MCA card. Back then, RAM speeds were a lot slower and the new bus was fast - memory on the expansion card is only about twice as slow as that on the motherboard. (I haven't yet found a way of persuading Linux of this fact, I would prefer the kernel to use the lower eight megs preferentially.)

      There was even a feature called 'matched memory cycles' in the very early machines where the MCA bus would be temporarily underclocked when accessing memory so that it could work synchronously (cutting some wait states). But then the increasing speed of RAM and the fairly constant bus speed (MCA was 32 bits wide at 10MHz, standard PCI not that much better at 33MHz, while RAM access times have gone down hugely from 85ns to goodness knows what) made the idea look silly, and IBM abandonded MCA-bus memory cards for its second-generation models in 1992 or so. Nowadays you could never get away with using something so slow as the PCI bus for 'memory', so it has to be marketed as 'RAM disk'.

      --
      -- Ed Avis ed@membled.com
    7. Re:Not practical by gomoX · · Score: 1

      and what if I want to LAN party with my friend in Australia? With all the airport and stuff, that would take more time...
      I prefer sticking to my good ole' 7200 rpm disk where an unpowered week would only loose my BIOS memory...

      --
      My english is sow-sow. Sowhat?
    8. Re:Not practical by whereiswaldo · · Score: 2

      1. A DRAM "drive" suffers the fundemental problem that if the "external" power source is lost, you lose everything on the drive.

      This may not be such a bad thing. You could store 2 GB of sensitive data on it and if your computer is accessed in a non-standard way, you'd automatically shut down. (you get the idea)

    9. Re:Not practical by rodgerd · · Score: 2

      It's got another strike against it:

      PCI card instead of a unit with a standard interface. Dumb, dumb, dumb. It would be far more usefull as a bay-mountable unit that hooks into an IDE or SCSI interface, rather than requiring a PCI slot, drivers, and whatnot.

      For the prices they're charging for the RAM, I'd expect some sort of non-volatile RAM, as well. The cost to have them populate it is several times what SDRAM sticks cost.

    10. Re:Not practical by rodgerd · · Score: 2

      SDRAM is pretty power hungry - it needs to be refreshed continually. It doesn't have a power consumption on a par with your CPU, of course, but PC133 SDRAM may consume 10 Watts in normal operation. While it may be possible to lower that when the memory isn't being accessed, by the time you factor in the RAM power use, plus any other ICs that need to be on, you'd be looking at needing a heft charge for any kind of persistence.

      And the drive wouldn't be much value in a high-end server: the capacity isn't significant. I'd be better off putting more RAM in the server and letting the OS cache.

    11. Re:Not practical by addaon · · Score: 3, Interesting

      Exactly. And by using it as a 'ram disk' you're giving up the huge advantage that ram has, while not decreasing the cost much. I mean, if this system used 70ns ram, it would be just as fast given bus limitations, but much cheaper... cheaper, that is, if anyone made 70ns ram any more. What it comes down to is that if we want radical ideas like this to be feasible (and this is a radical idea, in the sense that no one thought about it when deciding the current pc architecture), we need a lot more flexibility in how systems are designed. I was recently working on a random number generator in hardware for crypto purposes, and the pci bus simply didn't have enough bandwidth, so we ended up fitting an fpga into a memory slot, the exact opposite of what this ramdisk is doing. What we need is direct access to the memory bus itself through some connector (or better yet, to the hypertransport bus between the cpu and the memory controller), which would allow devices like the ram disk, or simply ram cards like you describe, to work with the current pc architecture. Timing on such a bus would be a bitch, but you could assume it remains unused except for systems with truly special needs.

      --

      I've had this sig for three days.
    12. Re:Not practical by Jace+of+Fuse! · · Score: 2

      I suppose a good use of this is it may support much more RAM than you can get on the motherboard.

      Exactly. With your SWAP in the RAM drive, you are essentially running everything out of RAM.

      Swapping to the drive causes a greater performance hit than other read/writes.

      --

      "Everything you know is wrong. (And stupid.)"

      Moderation Totals: Wrong=2, Stupid=3, Total=5.
    13. Re:Not practical by los+furtive · · Score: 2

      But by using PCI the can overcome the bottleneck of older IDE setups.

      --

      I'm a writer, a poet, a genius, I know it. I don't buy software, I grow it.

    14. Re:Not practical by GameMaster · · Score: 2, Insightful

      The only real problem with that is that by the time someone has the money to buy one of these things they, most likely, arent running an older IDE setup. Even if they were, they could easily afford an add-in PCI card to get full ATA-100/133 support. This is more of a toy for someone that already has the fastest system they can get and wan't some way to make it even faster no matter what the cost.

      --

      Rules of Conduct:
      #1 - The DM is always right.
      #2 - If the DM is wrong, see rule #1
    15. Re:Not practical by Anonymous Coward · · Score: 1, Insightful

      boot from regular drive
      copy apps to ram drive
      run apps from ram drive, enjoying faster loading and perfrormance. Save files to regular drive.

      If the ram drive fails/loses power it's no big deal .. u still have your data on the regular drive.

    16. Re:Not practical by Ed+Avis · · Score: 2

      It's a pity that some of the research into making faster, physically smaller RAM modules hasn't gone into making smaller, cheaper ones. ('Fast, small, cheap' - pick any two.') I mean producing massive 128 gigabit memory sticks but running at a slow speed of 160ns, say. That could be used as swap space and disk cache, so that main memory becomes a kind of L3 or L4 cache in effect.

      I wonder what the yield is on current RAM chips, and whether the faulty ones would work reliably if clocked at a much lower speed? Probably the current yield is fairly high, and the answer to the second question is no, so we can't expect ultra-cheap supplies of slow RAM to hit the market.

      --
      -- Ed Avis ed@membled.com
    17. Re:Not practical by gl4ss · · Score: 2

      you can put 4g on these cards, and you can buy the card seperately.

      so, 4*6=24gigs.

      and if you're buying these price is definetely not an issue. very niche. but freaky fast seektime for some db/scratch/whatever....

      --
      world was created 5 seconds before this post as it is.
    18. Re:Not practical by rodgerd · · Score: 2

      If I can't afford a modern motherboard with a North Bridge connected IDE unit - say $100 at any retailer - then why the hell would I be in the market for a $2000, 2GB hard drive?

    19. Re:Not practical by Anonymous Coward · · Score: 0

      It's quite practical depending on what you want to use it for. This is the case for nearly everything--just because a product appears doesn't mean it suits your needs.

      If you have some medium range data analysis that's near random accessing and is more storage stressing than cpu stressing, this is ideal. Likewise, if you've got a shitting mpeg2 editor that thinks it needs to recheck the entire data stream when it cuts GOP boundaries instead of just cutting and pointing appropriately, this helps. (Of course, if you in the last category, get a new editor and save yourself a few grand, but there are some shops that have compatibility paranoia.)

      Your analysis is like someone bitching about ATI 9700 Pro cards or Nvidia 4600s--if you don't game, they aren't going to do squat really. I don't expect a gaming card to really help accelerate my CAD work. I don't expect an CAD video card to help with my gaming. (Yes, I realize nowadays there is some crossover in this market.)

      I don't want RAID. RAID acess speeds can suck. This has a 1ms access time. RAID systems generally do not. It's not about throughput, it's about sustained, immediate access and throughput. RAID systems tend to a) find then b) get throughput the larger the file size. This doesn't. After the initial 1ms seek, the throughput is immediate, not to mention that seek time is incredibly low. That's why it whoops RAID (although really high end raid with large caches get around this, but then they approach something more like this card than not).

      If you're crunching data in a known matter, this isn't really gonna help you--stick with RAID. If you've got unordered crap and calling it, use this.

      Personally, I've been eying this product ever since someone mentioned it to me in the comments section of the vram/ramdisk /. story a little while back.

    20. Re:Not practical by addaon · · Score: 2

      The problem is a number of transistor issues. 128 gigabits of memory takes 128 billion transistors, today. And if even one of those transistors is faulty, the whole chip is dead. Speed has nothing to do with it, if the chip is defective (not just unable to clock fast enough). Now, what should really be done is more work on using partially defective memory chips. Linux supports that today, but no other OS that I know of does; and even in Linux, it's not trivial, as you need to test your memory yourself, and map some of the memory as invalid. Now, it would be relatively possible to create a 128 gigabit memory chip (admittedly, a big chip) with maybe 1000 flaws... you can add a small rom to this chip saying which sectors (say, to the nearest kilobyte) are bad, so you could put it into a box and get 127.2 gigabits, without user intervention. Making chips this big is possible, but not easy, with relaxed timing constraints like you describe. It seems like maybe we should be using current DDR ram as L4 cache, and using massive sticks as main memory.

      --

      I've had this sig for three days.
    21. Re:Not practical by Ed+Avis · · Score: 2

      You can work around faulty memory in software (like the BadRAM project) but it ought to be possible in hardware too. If you make a stick that is 128 gigabites + N where N is some number of bits greater than there will be faults, and have some hardware remapping. This might be slow if you want to do it with only a few extra transistors (I don't know), but for slow memory it might work.

      This would be different to having a ROM with a defect list which is read by software: to the machine the memory would appear perfect. But I think that doing it in software is the technically better solution.

      --
      -- Ed Avis ed@membled.com
    22. Re:Not practical by jafuser · · Score: 2
      This is a very interesting idea. I have heard about the linux capability of using broken memory. I remember reading on here long ago about a guy who got 2GB of memory for free or ultra cheap (20 bucks?) which worked fine after using this error-mapping feature.

      It seems like using more and more levels of memory as "cache" to the next level down is inevitable for maximum performance. I wonder what asymptote we are approaching though (L5, L6, L7, etc...), and if that asymptote can be directly addressed smoothly instead of having discrete levels of cache, allowing for maximum benefit with the least amount of complexity...

      --
      Please consider making an automatic monthly recurring donation to the EFF
  17. What's new? by p3d0 · · Score: 5, Interesting
    You hear about ramdrives every six months or so. It never amounts to anything. I don't see why this would be any different.

    Fundamentally, you're always better just to use caching. Essentially, this amounts to a 2GB dedicated disk cache, except that the power supply ensures that the contents survive boots (though I don't know how it would do in a power failure). Anyway, how often do people reboot their machines nowadays? Stuff stays in my computer's cache for months at a time.

    So, why not just add the 2GB to your main RAM? Then the OS could use it as a disk cache if it were so inclined (and you'd be right where you are with a ramdrive) or else the OS could use it as actual RAM if you needed it.

    In short, RAM is just like a ramdrive except more flexible.

    --
    Patrick Doyle
    I mod down every jackass who puts his moderation policy in his sig. Oh, wait a sec....
    1. Re:What's new? by alanh · · Score: 2

      If your computer crashes, a dedicated ramdrive would presumably survive the reboot. Adding 2 GB of main memory wouldn't provide that kind of functionality.

      --
      - AlanH
    2. Re:What's new? by Anonymous Coward · · Score: 2, Informative

      In reality, caching is not always better. It has two weaknesses.
      1. Random I/O patterns do not benefit from caching.
      2. Latency, it takes time to fill the cache which from a disk is on the order of ms.

      Caching for I/O on random applications is only good if your cache is larger than your access pattern.

      Latency for most applications has a larger impact on performance than IOP/s and MB/s. RAM drives have extremely low latencies, so for some appliations it's better.

    3. Re:What's new? by p3d0 · · Score: 2

      Ok, well if that distinction is worth the extra $699 USD, to you, then go for it. I think I'll spend the money on another computer to use while the first one reboots.

      --
      Patrick Doyle
      I mod down every jackass who puts his moderation policy in his sig. Oh, wait a sec....
    4. Re:What's new? by Anonymous Coward · · Score: 0

      what's new is the recent OBVIOUS stories that are in existance only for advertising.

    5. Re:What's new? by mike3411 · · Score: 1

      So, why not just add the 2GB to your main RAM? Because I only have so many RAM slots, and my motherboard uses Registered ECC DDR ram that costs enough that I currently only have 512mb. But PC133 or similar SDRAM is very cheap, and I'd love a way to be able to use some, mebbe give it to Photoshop or 3DSMAX's swap file that are not system-critical. Granted, with the pricing of this card, budgetary concerns are pretty much null, but I see no reason someone can't make a PCI device for 512mb sticks of PC133 SDRAM for ~$60 each into my system, since 2gb for ~$300 would be of huge performance value for things like Photoshop or 3DSMAX. To get that much main system ram would cost me ~$1000.

      --
      Mod me down, and I will become more powerful than you can possibly imagine!
    6. Re:What's new? by mike3411 · · Score: 1

      Damn, forgot to end the italic tag after that first sentance. It's my fault for hitting submit instead of preview, but i'll be damned if Plain Old Text isn't still the best option.

      --
      Mod me down, and I will become more powerful than you can possibly imagine!
    7. Re:What's new? by da+cog · · Score: 1

      > In short, RAM is just like a ramdrive except more flexible.

      Uhh... isn't that a lot like saying that memory is just like a swap partition only not as slow? ;-)

      --
      Snarkiness is inversely proportional to wisdom because it emphasizes feeling right rather than being right.
    8. Re:What's new? by Anonymous Coward · · Score: 0


      To get that much main system ram would cost me ~$1000.


      Uh, but the ram-drive is ~$3000 - and anyway, wouldn't it be much cheaper for you to buy a complete new system with just 2 Gigs fo RAM?

    9. Re:What's new? by mike3411 · · Score: 1

      Try actually reading my whole post.

      --
      Mod me down, and I will become more powerful than you can possibly imagine!
    10. Re:What's new? by forged · · Score: 2
      Anyway, how often do people reboot their machines nowadays?

      How about every day at night for example ? Mine is next to the bedroom, so it's either I power it off at night, or I wake-up with a stupid humming sound in my hears the next morning.

    11. Re:What's new? by Anonymous Coward · · Score: 0

      If your budget requires you to buy slow RAM, maybe you should have bought a system that natively supports it. You are asking for a kludge that appeals the lowest end of the market (the people least likely to buy it)

    12. Re:What's new? by nathanh · · Score: 2
      In short, RAM is just like a ramdrive except more flexible.

      The RAM in a solid-state drive is often slower - therefore cheaper - and battery backed. Your system RAM costs perhaps $100/gig now. The slower RAM used in your solid-state drive wouldn't be 1/10th that cost.

    13. Re:What's new? by p3d0 · · Score: 2
      Caching for I/O on random applications is only good if your cache is larger than your access pattern.
      Same goes for a ramdrive. It's no good if your data doesn't fit on it.
      RAM drives have extremely low latencies, so for some appliations it's better.
      So do caches. I agree that you need to "warm up" the cache before it gives comparable performance to a ramdrive. In that case, see this.
      --
      Patrick Doyle
      I mod down every jackass who puts his moderation policy in his sig. Oh, wait a sec....
    14. Re:What's new? by p3d0 · · Score: 2
      The RAM in a solid-state drive is often slower - therefore cheaper - and battery backed. Your system RAM costs perhaps $100/gig now.
      Try again. The RAM for this ramdrive costs US$1150/GB.
      --
      Patrick Doyle
      I mod down every jackass who puts his moderation policy in his sig. Oh, wait a sec....
    15. Re:What's new? by Anonymous Coward · · Score: 0
      Your first post was refuting for budget reasons the original poster's suggestion to just add to system RAM. Hence, you were effectively defending the logic of buying the 2G RAM drive in question instead. Which is more expensive.

      To sum up, you're stupid.

    16. Re:What's new? by jafuser · · Score: 2
      The RAM in a solid-state drive is often slower - therefore cheaper
      Which would explain why this ram drive is so "cheap" at over $2000 for 2GB... =)
      --
      Please consider making an automatic monthly recurring donation to the EFF
    17. Re:What's new? by p3d0 · · Score: 1

      Only if you ignore the money. We all have swap partitions because they are dirt cheap. A 2GB swap partition costs something like $5.00 on a modern hard disk. The 2GB ramdrive costs $3000.

      --
      Patrick Doyle
      I mod down every jackass who puts his moderation policy in his sig. Oh, wait a sec....
  18. Can I use it for swap? by Thalia · · Score: 5, Funny
    Makes me wonder if I can use for my swap drive;
    1. The OS wants to store something in RAM, trys to allocate RAM and fails.
    2. The OS decides to swap out some memory based on an analysis of page usage statistics, so it grabs the handle to the swap file.
    3. Then, the OS streams the offending pages through file I/O subsystem, worrying about waits and updating page counters and such. This includes dragging all the data over a busy system bus.
    4. The receiving device stores it in RAM.
    Cool! What operating system could aspire to such levels of efficiency?
    1. Re:Can I use it for swap? by Anonymous Coward · · Score: 0

      ?

      Just buy more RAM. Cheaper and better solution anyway.

    2. Re:Can I use it for swap? by Anonymous Coward · · Score: 0

      That would make no sense at all.

      Just add memory to your system and don't even use a swap file...

    3. Re:Can I use it for swap? by luciuskwok · · Score: 1

      I thought this comment was funny (parent). It seems silly to put RAM on the other side of the slow PCI bus.

    4. Re:Can I use it for swap? by selectspec · · Score: 2
      Can I use it for swap


      Not very practical to use DRAM drives for swap unless you've got a 64-bit CPU and OS. First of all, it would be more economical to simply buy DRAM for your memory on your mother board. Any mother board that could justify the expense of a DRAM drive should support 4 GB of RAM. Well, for a 32-bit CPU, 4 GB is all you can have (swap is not used).

      --

      Someone you trust is one of us.

  19. Seriously by Anonymous Coward · · Score: 0

    What a shitty review. That was about one paragraph per page, with meaningless benchmarks and moronic insights that make no sense in context, and the writer must have been hit over the head with a brick a few times before writing it. At least we are punishing the site with a good Slashdotting.

  20. Solid State? by Wiener · · Score: 1
    Hrmmm...seems to me this has been tried before. A little thing called a solid-state disk.

    Maybe we should ask Quantum about this techonology. Oh wait! They ditched it almost two years ago!

  21. How This Works... Neat Facts by clinko · · Score: 4, Interesting

    Here's some neat facts. No real solution though. Reply with one if you have it...

    Ram = Fast
    Cache = faster ram
    On Board Cache = faster

    1. Processors used to not have a quick way to get to ram so cache was created (faster and expensive ram) and put on a chip.

    2. Cache proved to be too expensive so they put it off the chips (pII)'s. Celereon's even took off some of the Cache.

    3. Now that ram drives will be created, it's just another link in the chain to the HD.

    now it'll be:

    HD->Ramdrive->Ram->off chip cache->onboard cache

    Each one of those levels cost more as you move to the right. This just puts another link in the chain.

  22. Not limited to 2 GB by delta407 · · Score: 5, Informative

    The official website lists the capacity as 4 GB.

    1. Re:Not limited to 2 GB by Large+Green+Mallard · · Score: 1

      In an exceedingly lame move, the card is available in a number of configurations and will only work with that amount of RAM. IE, if you buy an empty 2GB card and then stick 4GB into it, it won't work, so you'll have to then buy the 4GB version..

      Crappy business model. How difficult would it be to just get it to sense how much RAM was on there and act accordingly?

    2. Re:Not limited to 2 GB by Nynaeve · · Score: 1

      You really should do a little research before jumping to conclusions, especially critical ones. The 2GB version uses 4 x 512MB unbuffered non-parity DIMMs. This is the kind you see on most 1 - 1.5 GB capacity motherboards, and they cost as little as $30 each. The 4GB version uses 4 x 1GB registered ECC DIMMs. This is the kind you see on Dual AMD motherboards, and they cost $200 - $700 each. My guess is that the 2GB version cannot support 1GB registered ECC DIMMs for the same reason my MSI KT133 motherboard can't.

    3. Re:Not limited to 2 GB by Anonymous Coward · · Score: 0

      No, the ECC has to do with the controller limitations or what Cenatek found worked and would approve of for their controller, aka data fidelity, or warranty purposes.

      The 4 gb rocketdrive is the exact same physical pci board as the lesser ones.

      You can see that all for yourself, since Centatek sells a RocketDrive DL, which is the RocketDrive without installed memory modules. You can upgrade any current version to a higher version, if available, with a PROM swap. Hence, it's not a different board.

      You can see this for yourself by simply going to the Cenatek web page, clicking on BUY in the top menu, and then on RocketDrive DL Upgrades.

      It's Cenatek's limitation probably. It's pretty likely that's it's due to their limitation since their asking a hefty upgrade price, although it could rather unlikely be that they chose this due to some expensive PROM and the amount of space to program it being so small.

      I suspect the matching 4 way dimms is also their limitation, not a controller limitation, since they wanted to support a limited number of memory configurations and PROM upgrades.

  23. RAM disk vs RAM drive by ThogScully · · Score: 3, Informative

    I know this article doesn't exactly seem to be chock full of information, but the comments can at least be intelligent.

    This is different from using a RAM disk and just using RAM for a disk drive. A RAM drive can actually store information - which is something that RAM disks, which aren't really storage devices at all, cannot do.

    This even means you can store stuff and it's still gonna be there when you reboot. Although, granted, this isn't exactly new technology. I remember talking with a company at Internet World probably 6 or 7 years ago that sold these things to big companies with deep wallets.

    --
    I've nothing to say here...
    1. Re:RAM disk vs RAM drive by tracydotcom · · Score: 1

      Although, granted, this isn't exactly new technology. I remember talking with a company at Internet World probably 6 or 7 years ago that sold these things to big companies with deep wallets
      No not exactly new or as good as some old tech. I had something like that on my Apple IIGS it was a card it had a wopping 1MB RAM and a battery and I could use it for mt boot drive wich was very cool to watch a IIGS boot in a couple seconds and this was like the late 80's I think

  24. Stupid Question by screwballicus · · Score: 2

    This isn't a criticism. It's an honest question. What kind of purpose necessitates this type of drive over, say, a big SCSI RAID? Assuming the performance of solid state storage will always be inherently superior to traditional mass storage, what purposes best make use of relatively small amounts of extremely fast storage?

  25. RAM drives are stupid by seanadams.com · · Score: 2, Interesting

    And here's why:

    You can put a couple gigs of RAM on your motherboard, where the bandwidth to the CPU is at least 10x the fastest SCSI interface. Run any modern OS on there, and all of that main memory is going to be used a filesystem cache. Voila: all the benefits of a RAM disk (fast seek, throughput) and none of the drawbacks (no need for a separate disk backup).

    If what you want is a TRUE ram disk, i.e. not backed by magnetic storage at all, then you can do this in Linux or FreeBSD by setting aside a chunk of main RAM as a file system. I don't know if you can do that in OSX or Windows...

    But a RAM disk on the SCSI bus? What's the point?

    1. Re:RAM drives are stupid by delta407 · · Score: 2

      Read the article; it's not on SCSI bus. It's a PCI card with an external power supply that acts like a regular hard drive and persists data between boots.

    2. Re:RAM drives are stupid by seanadams.com · · Score: 2

      Fine, I should have RTFA, but the exact same argument holds.

    3. Re:RAM drives are stupid by yerricde · · Score: 1

      >persists data between boots.

      the exact same argument holds.

      How do I "set[] aside a chunk of main RAM as a file system" that "persists data between boots"?

      --
      Will I retire or break 10K?
    4. Re:RAM drives are stupid by luciuskwok · · Score: 1
      How do I "set[] aside a chunk of main RAM as a file system" that "persists data between boots"?

      That's an OS issue. Some OSes have persistent RAM disks which stick around after a restart. You still lose the data if you shut down.

    5. Re:RAM drives are stupid by lakeland · · Score: 1

      Modify your halt command to also execute:
      dd if=/dev/ram1 of=/dev/hda7 (change partitions to suit).

    6. Re:RAM drives are stupid by yerricde · · Score: 1

      That's an OS issue.

      Is it an OS issue, or a BIOS issue? Some BIOS implementations clear all RAM on each reboot. And even if it is an OS issue, what if my employer forces me to use applications that are available only as binaries for a well-known operating system that doesn't support this feature? I could just use agressive disk caching settings within the OS, but that doesn't solve the problem of Pentium and Athlon motherboards that can't hold more than 3 GB.

      --
      Will I retire or break 10K?
    7. Re:RAM drives are stupid by Bert64 · · Score: 1

      AmigaOS used to support this, it was called RAD.. and it survived reboots and *most* crashes, if you had enough ram you could clone your entire os partition into it and boot from it. I really wonder why other hardware doesn`t support this idea, especially with ram being so cheap nowadays...

      --
      http://spamdecoy.net - free throwaway anonymous email - avoid spam!
    8. Re:RAM drives are stupid by ComputerSlicer23 · · Score: 5, Interesting
      Effectively, in the proper configuration on a Linux machine, this could significantly speed up certain specific operations.

      First off, run ext3 and put all of journal log file on. Poof, now you got a disk that has no latency pently for syncing the data. It will reliable be there when you reboot, so if you crash the log file is still there. You know all those benchmarks that Moshe Bar does where he turns off fsync() so he can push the CPU and memory to it's limits instead of the disk. He wouldn't have to do that so much any more.

      Some Oracle DBA's would trade their soul to get Oracle's transaction logs written to something like this. A drive that has no latency is very, very good. No it's not as fast as RAM because it's behind a PCI bus, but in a lot of ways, no latecy permanent storage is the holy grail to a lot of problems.

      If filesystems and OS's supported this, it's like getting a very flexible configuration for very high end SCSI cards. You know those really highend SCSI cards that have battery backed up RAM in them? The ones that sit behind that pokey SCSI bus? By putting the no latecy storage out in a place where you can get your hands on it w/ OS tools, you can custom configure it just the way you need it. You can upgrade it, you can add more. You can do a lot of things with this, that are much more flexible then any SCSI card will let you set up.

      No they aren't the end all be all of permanent storage, however they have very specific usages, in specific high end situations that make them extremely valuable. If this one doesn't have an internal battery that can hold it's contents for say 400 hours without power, I'm not terribly interested, but as soon as it can do that without external power, I'd pay for it in a heartbeat for the Database servers and the high performance filesystems we run at work. A number of the ext3 people have talked deployment of devices like this will really improve the performance of a number of filesystems.

      Kirby

  26. Swap FIle by hoagieslapper · · Score: 1, Redundant

    I wonder how well a system would perform using that drive for their swap file?

    1. Re:Swap FIle by Anonymous Coward · · Score: 0

      Systems would perform better if the swap file was on this drive. But if you are investing this much money into a RAM drive, you should just buy enough RAM so that you don't need a swap file at all.

    2. Re:Swap FIle by 7-Vodka · · Score: 3, Informative
      I'd have a hard time justifying spending $3000.00 for that thing as a swap file. My system has 1 gig of ram and never ever hit's swap. It's faster this way because my system ram doesn't have to go through the pci bottleneck.

      I would buy extra ram instead of this rocketdrive. The bandwidth of my system ram is 2.1GB/s. This rocketdrive benchmarks at 78MB/s.

      --

      Liberty.

    3. Re:Swap FIle by sixthofmay · · Score: 2, Insightful

      But if you are investing this much money into a RAM drive, you should just buy enough RAM so that you don't need a swap file at all.

      It doesn't matter how much RAM you have. Fact: Windows uses RAM as cache and harddisk as memory. Windows will still swap like crazy after it uses up all the free RAM for disk cache. Don't believe me? Open a few web pages and keep their windows in the background for 30 minutes. This will guarantee that they will be first in line to be paged out with the following operation: Copy about 4 GB of files, like as would occur when you burn a DVD-R. Windows will immediately page out your background windows to make room for the file cache. Try bringing those background windows to the front now and watch the system hang for a few seconds while it pulls them out of the page file. And if you happen to be doing I/O and/or have a high CPU load going on at the same time as you try to bring those pages to the foreground, the wait may be quite a while... After the windows have been pulled out of the swap, switching between them is quick until you leave them in the background again and do more large file operations.

      Very dumb but that's the way MS has designed this braindead VM system. And it has frustrated me to no end. On Windows 9x/ME, the problem could be easily fixed by adding MinFileCache/MaxFileCache settings to the system.ini file. NT-2000-XP, forget it. There is no fix that I know of. I've been searching for years for a solution to this. I've tried every cache adjustment program and the registry tweak to keep the kernal from paging (which doesn't work). My latest attempt to fix the problem involved using O&O's Clevercache, which had no effect. I now have some more memory on order to up my box from 640 MB to 1GB (the max I can stuff in, it's an old Abit BX6 Rev2). I plan to use about 666 MB for a RAM disk and put the swap file on it. Even though my application load is usually around 400 MB, which will cause immediate paging with only 333 MB available for the system RAM, I expect to see a huge performance boost over my current setup of 640 MB system RAM. Since Windows insists on running programs out of the swap file no matter how much RAM one has, this should finally fix the problem, albeit in a very kludgy way.

      This usenet thread is somewhat dated though quite applicable: Why do I need a swap file with 128mb of ram

      The reason why most people say adding more RAM fixes the problem is because most people aren't doing enough I/O to make the problem evident. Anyone who does AV editing and trys to surf at the same time (like me) will attest to the issue.

    4. Re:Swap FIle by ThePeeWeeMan · · Score: 1

      I wonder if you've heard of the DisablePagingExecutive registry key, among others. A google search revealed the following page.

    5. Re:Swap FIle by ThePeeWeeMan · · Score: 1

      Well, ok, the link didn't come out properly. Here it is again

    6. Re:Swap FIle by sixthofmay · · Score: 1

      I wonder if you've heard of the DisablePagingExecutive registry key, among others. A google search revealed the following page.

      Yes, thank you, but that's what I was referring to in my post. The setting has no effect on paging of the kernel or applications in Windows 2000, which is my current OS. It might work in NT though, but only works on the kernel, which really wouldn't help much. I'm really amazed Microsoft has never fixed this. Maybe they think this design is actually beneficial somehow... What's more amazing is how few people are aware of the bug. I move around several GB of data per hour and am excruciatingly aware of the issue. :(

    7. Re:Swap FIle by Anonymous Coward · · Score: 0

      Yes -- they made a policy decision with Windows. Do you want the file copy to complete faster now, even if it means that your IE window will come up slower later? MS says yes. Part of this is probably because they use basically the same OS for server and client versions.

      The best solution to this problem is a 15K drive for the pagefile :)

  27. Why not just use a RAM drive? by Ececheira · · Score: 1

    Rather than pay $3000 for 2 GB of RAM-drive, there are numerous software packages, both free and commercial, for Windows and Linux, that would allow you to do the same thing for a fraction of the cost.

    Some of the packages will even do a lazy mirror of the data to a HD so that on boot, the data is reloaded to the RAM drive.

    This seems overpriced for what it is...

    1. Re:Why not just use a RAM drive? by Anonymous Coward · · Score: 0

      I am interested in using a package to mirror data between a HD and a RAM drive. Please list the names of any packages (Linux or Windows, free or commercial) that you know of.

      Thanks

    2. Re:Why not just use a RAM drive? by Ececheira · · Score: 1

      The best-known one is SuperSpeed, which is available for all flavors of Windows.

      www.superspeed.com.

  28. Fair enough, but.. by wackybrit · · Score: 2, Interesting

    Okay, fair enough, I didn't see the bit about it keeping the data on there using an external power supply.. but..

    Most Slashdotters are the type who leave their PCs on 24/7 anyway, and run relatively stable operating systems. And if the power cuts out, you're going to lose the RAM drive anyway.

    I can see the use of this RAM drive in video setups or on DVD encoding/production desks, but for regular Joe (or even a Slashdot user)? No.

    1. Re:Fair enough, but.. by yerricde · · Score: 1

      And if the power cuts out, you're going to lose the RAM drive anyway.

      Even with capacitor-powered refresh?

      What about a UPS?

      --
      Will I retire or break 10K?
  29. Ecclesiastes was right by Anonymous Coward · · Score: 0

    There is nothing new under the sun.

    Remember "Bulk Core" and "BulK Ram"?

    Deja all over again...

  30. ramdrive by Anonymous Coward · · Score: 0

    Save $ and buy your own ram... create a bootable OS cd which copies itself to a virtual ramdrive on boot then periodically copies any changed (non-system) files to the primary hd... if broken/hacked, reboot and changed files are copied from the hd to the ramdrive. I'm surprised there isn't already a turnkey open-source solution like this available? I'd do it but i'm too busy at work :(

  31. These will never replace mechanical hd's... by SexyKellyOsbourne · · Score: 2

    At best, solid state storage devices will be used to house the most critical, most heavily read data on the hard drive for certain particular uses only.

    However, no one will ever go back to 2GB hard drives for the same prices as a 200GB hard drive, nor will anyone want to go that far back in proportion to Moore's law in the future in exchange for giving up their mechanical hard drives.

    Trust me, when we have a terabyte of hard drive space for a few hundred dollars, people will use them -- movies still take up an average of 1GB apiece, and with digital convergence, everyone will want to stockpile them, as well as have every song they've ever wanted to hear stored safely on their hard drive.

    1. Re:These will never replace mechanical hd's... by Virtex · · Score: 2

      However, no one will ever go back to 2GB hard drives for the same prices as a 200GB hard drive, nor will anyone want to go that far back in proportion to Moore's law in the future in exchange for giving up their mechanical hard drives.

      Along the same lines, nobody will ever adopt semiconductor memory in favor of core memory. I mean, sure, it's faster (80ns vs 1000ns), but at the extraordinarly high price and lower capacities, nobody will ever take it seriously. Trust me, when we have a megabyte of core memory for a few thousand dollars, people will use it.

      Or so the reasoning goes. History always seems to repeat itself.

      --
      For every post, there is an equal and opposite re-post.
  32. Silly by timeOday · · Score: 2

    Computers already have solid-state memory. 2 Gig isn't a particularly impressive figure anymore for system RAM. Running RAM over PCI is dumb, that's why we have a memory bus. A system with 1 or 2 gigs of RAM can cache so well that using all solid-state memory would hardly improve performance anyways, especially if it's on the other side of a PCI bus.

  33. $2,999 for 2 gigs of Ram??? by frovingslosh · · Score: 3, Interesting
    1440 born a day, equally spaced.

    That's an absurd price for what little there is to be gained from this. Clearly the cash would be better spent on a new MB with an extra 2 gig on it - it could be used as a ram disk if you really wanted, or as a cache, or for any number of uses beyond a silly-cone hard drive. Better to be able to deal with the memory as memory than memory pretending to be disk. And for a lot less money.

    --
    I'm an American. I love this country and the freedoms that we used to have.
  34. it's cool but... by venomkid · · Score: 1

    ...I can't think of a single good reason to buy one of these.

    It's too small to do video work, which is where I would need the IO.

    Much smaller, and you can just do it with a regular RAM drive, for much cheaper.

    Besides, that external power supply scares me...

    vk.

    --
    vk.
  35. The future that already was by jasonditz · · Score: 3, Funny

    That's great, but am I the only one who remembers having RAMdisks on my Atari 800?

    Axlon used to make 128 KB Ramdisks, now that was power!

    1. Re:The future that already was by FleshWound · · Score: 2, Funny
      That's great, but am I the only one who remembers having RAMdisks on my Atari 800?
      You probably are the only one who remembers anything about your Atari 800. =)
    2. Re:The future that already was by snarfer · · Score: 1

      I actually left Atari and worked at Axlon back then.

  36. According to the article... by myov · · Score: 4, Informative

    The bios is set so you can only put in the amount of memory that was specified by the card. So If I purchased the 2Gig empty card. My only option is to put in 4 sticks of 512 pc133 memory. If I wanted to upgrade my card to 4gig. I would have to pay for an upgrade, and then replace all the sticks of memory with 1024Meg sticks.

    --
    I use Macs to up my productivity, so up yours Microsoft!
  37. Too true, by Tensor · · Score: 2

    I, for one, leave my PCs on 24/7

    I also think that the only application of this is for volatile info that needs massive disk i/o ... encoding of divx and such.

    I believe all programs would benefit from 4gb of ram instead of a 4gb ramdrive, and i specially disliked the fact that altho you can buy a card wihout memory you can only use it with the ammount you bought it for (its "bios" is locked to that memsize) so you can't just go on adding mem.

  38. Enhancements.. by phreaknb · · Score: 1

    If this could hold more data (atleast 50GB>) I could see it being used in a server, or atleast a gaming computer. The only drawback is a dedicated source of power.

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

      Im sure people said the same thing about magnetic hard drives ...

  39. Quantum's Rushmore Ultra Solid State Disks by grey3 · · Score: 2, Informative

    Back in 1998, Quantum announces a DRAM-based hard drive. They offered two models, a 1.6GB version which was priced at $39,000 and a 1.07GB version which was priced at $28,000. They seemed revolutionary at the time, but the main drawback was always the price.

  40. Platter-level RAID by yerricde · · Score: 2, Insightful

    It has been tried in the past, but the problem was that the heads would get slightly misaligned in time and you'd have to reformat too often.

    To solve rotational misalignment in a platter-level RAID system, just treat the binary stream coming from each head assembly as a separately clocked serial stream, and combine them in the controller.

    It's also straightforward to solve radial misalignment, that is, when one of the heads is slightly too far from the hub or too close to the hub. While the drive is idle, non-destructively reformat the disk continuously, reading an entire cylinder/sector pair head by head and then writing it all at once.

    --
    Will I retire or break 10K?
    1. Re:Platter-level RAID by gweihir · · Score: 2

      To solve rotational misalignment in a platter-level RAID system

      Rotational misalingment is trivial to solve, agreed.

      Radial misalignment is impossible to solve, as modern HDDs (since the moving-coil was introduces) cannot format themselves!
      All the infromation used for alignment (servo information) is written with special heads in the factory and cannot be changed afterwards.

      --
      Most ACs are not even worth the keystrokes to insult them. Be generically insulted and ignored otherwise.
    2. Re:Platter-level RAID by FunkyRat · · Score: 2, Interesting
      ...modern HDDs (since the moving-coil was introduces) cannot format themselves! All the infromation used for alignment (servo information) is written with special heads in the factory and cannot be changed afterwards.

      That's interesting. I didn't know this. Does this mean that format option in the BIOS is no longer a low-level format?

    3. Re:Platter-level RAID by orangesquid · · Score: 3, Interesting

      Actually, yes. It's some sort of funky medium-level format, IIRC (and it may even screw up your IDE drives permanently). But then again, the true low-level format includes all sorts of special blocks that store tracking information and bad sector tables. You wouldn't want your BIOS to screw with that. I don't trust my BIOS farther than I can throw it! (And, btw, a 120G drive actually has 130G-150G of disk space... you just can't use it ;)

      --
      --TheOrangeSquid Is it any wonder things seem so awry? We swim in a sea of confusion and don't have to think to survive
    4. Re:Platter-level RAID by FunkyRat · · Score: 2, Interesting
      "It's some sort of funky medium-level format..."

      So... would this mean there's no real way to do a secure wipe of files on modern drives? Pardon me if I sound ignorant on this subject, because I am frankly...


      "...the true low-level format includes all sorts of special blocks that store tracking information and bad sector tables. You wouldn't want your BIOS to screw with that."

      You're, of course, correct. *sigh* I just guess I haven't progressed much in my understanding of disk drives from the old 8-bit days when your BIOS was exactly the thing that was supposed to handle all that low-level stuff.

    5. Re:Platter-level RAID by Izmunuti · · Score: 1

      "just treat the binary stream coming from each head assembly as a separately clocked serial stream, and combine them in the controller."

      The problem is that disk drive have only one read channel, the device that turns the analog signal coming out of the preamp, from the head, into the one and zeros. It's an expensive part and you would need one for each active head. Also, the disk controller's going to need additional pipelines and more memory bandwidth.

      "It's also straightforward...While the drive is idle, non-destructively reformat the disk continuously, reading an entire cylinder/sector pair head by head and then writing it all at once."

      The heads can wander several tracks apart so this approach would require a huge reduction in track density. I'm thinking about 5% useable capacity.

      The idea of the drive autonomously rewriting entire cylinders makes my skin crawl. The reliability problems with this are legion. (Like losing power in the middle of one of these updates.)

      Better, would be to use microactuators on each head. With these, the main actuator just gets the heads near the target track. Then, each head is positioned independently over its track by the microactuator. This is doable but not cheap. Now, with a much more complicated controls problem, the drive's going to need a heftier DSP.

      While it could be done (has been done actually), it isn't cheap, adds complexity, lowers reliability, and doesn't do anything for latency.

    6. Re:Platter-level RAID by Izmunuti · · Score: 1

      Writing the servo information is not a "format". It's _never_ been possible to rewrite this in the field. This is only done in the factory by special machines called servo track writers.

      A low-level format is different. In the old days, this would go out a rewrite all of the headers for every sector. These days, there aren't any headers so formatting is not much more than just writing every sector. There are some extra steps for defect management, but that's about it.

    7. Re:Platter-level RAID by orangesquid · · Score: 2

      You can secure-wipe only if you're sure the file hasn't been automagically moved by the drive's firmware because of bad sectors. There's some tools floating around that do this. Search freshmeat and google for secure delete, secure format, etc.

      --
      --TheOrangeSquid Is it any wonder things seem so awry? We swim in a sea of confusion and don't have to think to survive
    8. Re:Platter-level RAID by Reece400 · · Score: 1

      "It's some sort of funky medium-level format..." So... would this mean there's no real way to do a secure wipe of files on modern drives? Pardon me if I sound ignorant on this subject, because I am frankly... of course there is,, many ways... magnets, shredders etc. :D

      Reece,

    9. Re:Platter-level RAID by gweihir · · Score: 2

      That's interesting. I didn't know this. Does this mean that format option in the BIOS is no longer a low-level format?

      For a long time now. Actually there was a time in in between, where the servo information was stored on an extra platter with a servo-head, so low-level format was possible. While these HDDs could not completely re-format, the head-alignment from the original comment was possible.

      I think that period ended with ESDI-drives. (I had one 15 years ago. 2MB/sec transfer speed, incredibly fast!) Before that there where MFM/RLL drives with this principle. And before that there where HDDs using stepper motors that could do a full low-level format, since they did not use servo-information.

      My guess is that about 10 years ago the servo-heads where dropped and the servo-information integrated into the data-carrying surfaces. I think the main reason was that having one head do the positioning and another one the reading and writing was just not accurate enough anymore. Because of the geometry of this servo information (it is very short, slim stripes of data that fits between the ordinary tracks) the heads in modern HDDs are just not able to write it.

      I think that a low-level format on a modern HDD is either a no-operation or a surface-recertification (i.e. scan for defective sectors).

      Arno

      --
      Most ACs are not even worth the keystrokes to insult them. Be generically insulted and ignored otherwise.
    10. Re:Platter-level RAID by gweihir · · Score: 2

      of course there is,, many ways... magnets, shredders etc. :D

      Magnets are strictly for fools. Migth even be cheap to recover data from such drives. Shredder, blowtorch and acid is pretty good. Also just bending the platters makes recovery expensive.

      When I dispose an old HDD, I overwrite it several times and then open it, cut the platters in half and fold them one or two times. Still recoverable, but I would expect it to be very, very expensive.

      --
      Most ACs are not even worth the keystrokes to insult them. Be generically insulted and ignored otherwise.
    11. Re:Platter-level RAID by gweihir · · Score: 2

      Writing the servo information is not a "format". It's _never_ been possible to rewrite this in the field.

      While that is true, "low-level format" implies (at least to me) a complete restructuring of the surface. Everythign else is not really low-level. The trick is that some media (very old HDDs, current floppy disks) do not use or need servo information!

      Of course if we define "low-level format" to be the lowest level a drive can do, this all changes. But I do not believe that you can format an USB-dongle or a modern HDD. You can create a filesystem or check the surface, but not more. On the other hand you can low-level format a floppy disk.

      --
      Most ACs are not even worth the keystrokes to insult them. Be generically insulted and ignored otherwise.
    12. Re:Platter-level RAID by Reece400 · · Score: 1

      i'm not talking about fridge magnets,, i'm talking about large industrial type magnets :) combine this with, well, pretty much any of the others and you have a fool proff solution,, i never thought of the folding part,, that's a really good idea :)

      Reece,

  41. Nothing new. by Anonymous Coward · · Score: 0

    I know linux is the divind inspired work of god, but in the real high end world these drives are not too uncommon. I had one on a system almost 10 years ago. Of course it was a Cray.

    There are situations where they are very useful. Think of a multiheaded scsi array with a RAM based disk. It becomes a very fast disk that more than one machine can use simultaneously.

    For most systems and most uses, these drives are pointless and will always be pointless.

  42. Extending system RAM... by ipsuid · · Score: 2, Interesting

    The only justification I can come up with to purchase one of these cards is if you have already maxed out your motherboard system RAM.

    Does anyone know if this maps in as a normal ATA or SCSI controller? Or do you need a special windows only driver?

    If linux can recognize it as a normal block device, and I was rich enough to already have 4G of PC2700 on my mobo, then a mkswap/swapon on this device would become beneficial.

    Also, can you install more then one in a system?

    --
    It appears Ockham lost his razor and grew a beard.
    1. Re:Extending system RAM... by chrispix · · Score: 2, Informative

      This maps as an ATA Device. It needs a specific driver, and does not currently work as a boot drive. Regardless, it is supported by Windows 2000, XP, and NT 4.0 Red Hat 7.3 Free BSD Solaris 8/UltraSPARC II As for the power cord? It does not have to be in the whole time. Just while the computer is OFF. Although there are rumors on the Cenatek message board of a rocket drive with an on board battery backup..

    2. Re:Extending system RAM... by Wesley+Felter · · Score: 2

      If you were that rich you could just buy a motherboard that has 8 DIMM slots.

  43. Not that I'd buy one, but... by podperson · · Score: 2, Informative

    Most people can't allocate 2GB of RAM for use as cache or RAM disk because their computer can only *take* 2GB or less of RAM. Most PCs max out at between 512MB and 2GB RAM, most Macs max out at 1GB to 2GB of RAM.

    I'd suggest a better option would be a fast hard disk or RAID appliance with 2GB of cache.

    1. Re:Not that I'd buy one, but... by Babbster · · Score: 2
      Most people can't allocate 2GB of RAM for use as cache or RAM disk because their computer can only *take* 2GB or less of RAM. Most PCs max out at between 512MB and 2GB RAM, most Macs max out at 1GB to 2GB of RAM.

      "Tru' dat" as the kids are reported to say. BUT, for $3,000 you can pretty quickly get a motherboard/processor/RAM that will accommodate more than 2GB of RAM and probably experience more performance improvement - not to mention flexibility - than by purchasing the fancy Rocketdrive. Throw in a UPS and your RAM drive will probably last as long as you need it to (given a decent OS, of course).

  44. Applicability = affordability by yerricde · · Score: 0, Redundant

    Personally I don't get why people always expect products to have a really necessary use ;)

    If a product doesn't have a wide application, it won't enter full-scale mass production. If a product doesn't enter full-scale mass production, its price won't fall. If the price of a product doesn't fall, the person posting the comment will never be able to afford one.

    --
    Will I retire or break 10K?
  45. PCI bottleneck by Door-opening+Fascist · · Score: 4, Insightful

    The article mentions that multiple RocketDrives could be used in parallel. That would seem only to be practical on 64-bit PCI buses. One RocketDrive transfers 80MB/s, which is close to the maximum sustained bandwidth for 32-bit 33MHz PCI. 132MB/s is the burst bandwidth, and cannot be sustained for very long.

    In fact, I would think this drive would interfere with other devices that rely on the PCI bus. I doubt you could get 100Mbps (~12.5MB/s) on the same PCI bus.

    1. Re:PCI bottleneck by Anonymous Coward · · Score: 0

      If you had a 64-bit PCI bus, one RocketDrive would operate twice as fast (you wouldn't need to use two in parallel) than a RocketDrive on a 32-bit bus, because it's made out of RAM which has a max throughput of many GB/s. Anyway, if you had a 64-bit PCI bus, your motherboard would be a high class board and have the ability to utilize at least 64 GB of RAM.

  46. Plz read the article by Tensor · · Score: 2

    As you can see there: http://www.3dretreat.com/reviews/rocketdrive/page5 .shtml

    The test used sisoft adn HD Tach for testing.

    The speed is limited because of the pci interface, that is as fast as the pci was designed to work at.

    1. Re:Plz read the article by Trusty+Penfold · · Score: 1

      The speed is limited because of the pci interface

      So he's testing the performance of his PCI bus, not the performance of the disk as he claims. My point stands, all these reviews are worthless because the testers do not know what they're testing.

    2. Re:Plz read the article by vipw · · Score: 1

      While I'm sure you'd just cram the drive up your ass, almost all other computer users would actually have it controlled through a PCI bus what with it actually being a pci card and all.

    3. Re:Plz read the article by Anonymous Coward · · Score: 0

      Okay, think about this please, what's going to go faster, a HDD or your damned PCI bus?

      *Alex Trebek stands by*

      You guessed it, nanoseconds are faster than milliseconds! Give the guy/girl a cigar. :P

      The reviewers know exactly what they're testing, more than you do, as the throughput on a PCI bus is obviously faster than conventional PCI disk drive systems. Idiot.

  47. ups by Tensor · · Score: 2

    True, the smallest ups would probably power this card for more than a week.

    But i still would not put into this important information that i didnt have on another medium sowmehere else.

  48. POWER SUPPLY by Stoutlimb · · Score: 3, Informative

    Wasn't there just a slashdot story a while ago saying how it was Power supplies that were the huge cause?

    1. Re:POWER SUPPLY by evil_one · · Score: 1

      A female friend of mine came to me with a quandry the other day.
      It seems that she was moving things on her desk, and her tower fell over. "Now it smells funny."
      Sure enough, the jolt knocked a capacitor loose, and the PS went up in a foof of smoke on her. The 'funny smell' was that of roasted silicon.
      The resulting surge fried her CDROM, Hard drive, Motherboard. CPU, sound card, and burnt a hole through the first chip on her DIMM.
      AFAIC, power supplies are the worst offenders.

      --
      Desperation is a stinky cologne
    2. Re:POWER SUPPLY by Stoutlimb · · Score: 2

      "It seems that she was moving things on her desk, and her tower fell over."

      "AFAIC, power supplies are the worst offenders."

      AFAIC, users are the worst offenders, power supplies are second. Anyone who knocks their tower over, or drops their laptop, loses all right to blame resulting problems on hardware.

      Funny story though.

    3. Re:POWER SUPPLY by evil_one · · Score: 2

      I see no reason that a piece of electronics w/o any moving parts shouldn't be capable of matching the shock rating of a running hard drive. That means 30 Gs. (For the record, that's 30 Gs w/o error)
      In this case, it was a tip-over, not a drop off a desk, and the resulting PSU failure resulted in TOTAL data loss.
      I have seen many many cases of total data loss, and only 3 have been the direct result of user abuse, if you count this one. (Two others being installing Linux over windows and dropping a running PC off a desk.) The rest of them have been related to the PSU - surge damage, general part failure, overheating the entire system instead of shutting down, etc.)

      --
      Desperation is a stinky cologne
  49. Re:How This Works... Neat Facts by Fluffy+the+Cat · · Score: 4, Interesting

    HD->Ramdrive->Ram->off chip cache->onboard cache

    Each one of those levels cost more as you move to the right. This just puts another link in the chain.


    Sure about that? For the price of the Ramdrive, I could easily get 2GB of DDR. Hell, for the price of the Ramdrive I could get a motherboard that supported 64GB and fill a moderate chunk of it. That thing has lower speed and greater access time than main memory and costs more, so just using RAM as disk cache would appear to be more useful under the majority of circumstances.

  50. More work soulda been put into this card by Tensor · · Score: 5, Interesting

    If these guys had made this compatible with scsi, like emulating a scsi card and 1 device, so it could boot it would rock.

    From power off to up and runnig in seconds !

    This would be ideal to store an OS, even for a server, and have the HDs configured to copy the os back to the card and reboot in case it fails to boot from the card for some reason ...

    Hook the power source to a ups and you can probably keep the info for more than a week without external power should you need. (i mean, how much juice can this need?)

    1. Re:More work soulda been put into this card by friscolr · · Score: 2
      This would be ideal to store an OS, even for a server, and have the HDs configured to copy the os back to the card and reboot in case it fails to boot from the card for some reason ...

      kind of similar to RAID 1 with ramdisk/hd. after the mirror is rebuilt, take the hd out of the picture. re-insert hd and resync periodically for backups. won't decrease your boottime and is really esoteric.

      i did something similar in OpenBSD: howto and benchmarks

    2. Re:More work soulda been put into this card by NeoSkandranon · · Score: 2

      Let me get this straight, you want to put the OS for a server on something which loses all data when the power is cut?....If i were a manager, i'd have you shot for using those things. what happens when the UPS goes on the blink, or someone unplugs it by accident? I thought so.

      --
      If you can't see the value in jet powered ants you should turn in your nerd card. - Dunbal (464142)
  51. Question is valid by thasmudyan · · Score: 2

    Essentially this drive boils down to creating a very expensive and (for RAM that is) very slow ram disk. This disk isn't very big, too. It's only good point is that it stores data even between reboots and power-downs.

    But practically, it's no use. Areas that come in mind, already have a better solution than this:
    - Games: you're better off buying system RAM (perhaps even creating a software RAM disk), because it's cheaper and about 10x faster than PCI. The guy in the review was mumbling about virtual memory, which is just incompetence really (because you don't need VM as long as you have enough main memory)
    - High transaction servers: servers need more storage space than that. And given the high risk of losing data in case of a power outage, this medium is totally unusable.
    - Graphics: essentially the same as in games, just buy more system memory. There is no benefit in having this drive that is also quite small.

    There is no reason to use such a device. Only if RAM were much cheaper, and if the drive had much more storage, and if the PCI bus were much faster, and if system memory were some kind of other (more expensive, faster) RAM, ONLY THEN would it make sense to use it (and then only if mechanical storage would be far inferior by then).

    1. Re:Question is valid by walt-sjc · · Score: 2

      Pinhead. Just because YOU can't think of anything doesn't mean that there isn't a valid use. At a former company, we used a device kinda like this except it was external and looked like a scsi drive. Had it's own internal battery and hard drive for backing up the image.

      We only needed about a gig of space, yet the only other option was a massive raid system that would have cost 4 - 5x more. It worked PERFECTLY.

      It also works well on databases. You only per certain tables in it, not the entire database. Think caching proxies, web servers, etc.

      Yah, probably not much use for gamers / home users, but I SEROUSLY doubt that gamers are their target market.

    2. Re:Question is valid by Anonymous Coward · · Score: 0

      They are useful. If you run a large OLTP database, solid state disks are very useful for things like redo logs and rollback segments in Oracle (there are analogous structures in other DB's). These files are typically small enough to go on SSD. Where your application is very write intensive, you can improve performance by using a large cache on your RAID array, or move the high hit rate files onto SSD. Solid state disks are typically a *lot* faster than spinning brown things. They are hellishly expensive though.

      There are other applications that can take advantage, like anything that is constantly writing to a spool area at a fairly rapid rate.

      Mainframes have had this kind of thing for years. In Linux and Solaris (I'm sure other O/S's can do it too) you can also create RAM based file systems and really speed things up in some cases. They are destroyed when you reboot though...

    3. Re:Question is valid by Anonymous Coward · · Score: 0

      "There is no reason to use such a device."

      Database searching using extended and shortening search windowing, resetting up, and reanalyzing? Massive database table where the table is relatively stable and just needs periodic backups? Cutting and pasting massive mpeg2 files at 40mbit/s streams on a huge resolution using an incredibly small GOP? Working with that resolution?

      You seem to miss that the main reason for this drive are the cumulative reasons--it's all middle road. Price isn't cheap but it isn't horrible compared to other tech, transfer speed is decent although you can break it with a well setup RAID and multiple cards, latency is excellent for being on a PCI bus but not great compared to today's FSB. But there is no solution that plays on ALL of these.

      You also seem to miss that this could be used to overcome current high end server hardware--there's bound to be someone out there that wants it all on 1 box, has a PCI slot available, and wants to go over the motherboards 64 gigabyte memory capacity without spending upper 5 figures on a true high end server.

      If I was a video editor, this wouldn't be a bad investment if my time was worth over $100 an hour.

      How about more than 1? You won't get the sustained transfer due to the PCI bus limitation, but you can have 24 gigabytes at your fingertips with today's typical desktop pc, containing it's 6 PCI slots.

      And the company has acknowledged, in part, suggesting they are looking into a 64bit/66mhz version.

  52. Missing the Point by locarecords.com · · Score: 5, Interesting
    I think you are all missing the point somewhat...

    What if you could boot from this drive? If it were Flash Ram then presumably you could store your operating system on a RAM Drive and get it to boot instantly cutting down on the boring and annoying wait for the computer to start up.

    Another drive could be used for storing files and such like (if it were thought to be somewhat dangerous medium to *store*) but in anycase it would be lovely to get instantly booting computers.

    In addition, rather than booting, couldn't these drives make possible a kind-of ghost-like save boot-up state. ie Copy into memory very quickly the state of the computer just following boot up. Now that would surely speed up the booting process.

    And I know everyone might say, oh that doesn't matter, but even though I use a Powerbook which with OS X stays up almost forever - I *still* need to boot occassionally. And it is *painful* to wait for.

    Once it is built into my laptop I will be well happy... I hate chugging drives... and silence is golden

    --
    ---- The Open Source Record Label : : LOCARECORDS.COM
    1. Re:Missing the Point by Bishop · · Score: 2

      What if you could boot from this drive?

      You can't.

      If it were Flash Ram

      It isn't. The drive uses volitile DRAM.

      Wishing that a product was something completely different is useless speculation. Wishing a different product existed and affordable is different. M-Systems make solid state flash disks. A 4GB IDE flash disk costs about $3500 USD.

      Many of us aren't "missing the point." This DRAM disk as sold is not particularly usefull except purhaps in some limit roles. (I will note that I have yet to read a post where this device is better then more system ram.)

      The idea of storeing your system state at boot and loading that at boot has potential. My compture has a hibernate mode already where the system state is stored to disk and reloaded at boot time. I find that it isn't much faster to return from a hibernate state then to reboot in the first place . I am not sure how much faster booting as you propose would actually be.

      The important question is why do you care so much about your reboot times? Specifically why would you want to spend so much money simply to increase your boot times? I reboot my laptop fairly often as I prefer to leave it off while the laptop is being transported. The boot times don't bother me. What I would spend money on is a faster hard drive. A faster hard drive would speed up boot times, and increase overall system performance.

    2. Re:Missing the Point by Andrewkov · · Score: 1
      to boot instantly cutting down on the boring and annoying wait for the computer to start up.

      I don't know if this would help as much as you think it would ... If you watch either Windows or Linux booting, a lot of time seems to be spent doing other tasks than loading data from the HD, such as waiting for devices to initialize. So booting wouldn't become instant, but it would be faster. Plus my computer does a long RAM check which can't be skipped and takes a long time to spin up the SCSI disks, this is all before the OS starts loading... Not to mention that 8 second LILO delay! ;-)

    3. Re:Missing the Point by manaway · · Score: 1

      This would sure be great, except you can't boot from this drive. In other news, pigs still can't fly, film at 5.

    4. Re:Missing the Point by IronicCheese · · Score: 1

      Am I the only one who remembers the HP Omnibook 300 (and 425?...) where the operating system was Windows 3.1 on a PCMCIA card? Say what you will about the quality of the OS:
      = booting this machine was blazing fast
      = completely silent
      = extended battery life.
      my two cents.

  53. Sustained Performance vs. Latency by morzel · · Score: 5, Insightful

    "Sustained performance" is only a practical measure in a few uses (eg: multimedia). For most other things, latency (ie: seek times) has a far greater impact on performance. Even the fastest harddrives have seek times measured in milliseconds. With DRAM we're talking about nanoseconds.
    The fundamental problem of "power is lost" can be solved easily by adding a battery on the drive.

    --
    Okay... I'll do the stupid things first, then you shy people follow.
    [Zappa]
    1. Re:Sustained Performance vs. Latency by Anonymous Coward · · Score: 0

      Okay... I'll do the stupid things first, then you shy people follow.

      Nice sig
      8:)

    2. Re:Sustained Performance vs. Latency by Babbster · · Score: 3, Insightful
      The fundamental problem of "power is lost" can be solved easily by adding a battery on the drive.

      Isn't that "fundamental problem" already solved by plugging any important computer into a UPS? I think we can safely assume that anyone spending $3,000 on a RAM drive would consider their computer important enough to be on a UPS into which, presumably, this device would also be plugged.

    3. Re:Sustained Performance vs. Latency by morzel · · Score: 2

      Yup, but when the computer requires shutting down for any reason (which can be as benign as a kernel upgrade, OS crash or HW upgrade) you've got some extra trouble for safekeeping your data.
      Making the storage persistent by adding a technically quite simple feature (a battery) will make this independant of the system it is implemented in, even if the persistence is only for a short period of time.

      --
      Okay... I'll do the stupid things first, then you shy people follow.
      [Zappa]
  54. Some people can't afford ($) not to reboot by yerricde · · Score: 5, Funny

    Anyway, how often do people reboot their machines nowadays?

    I'll answer the related question, "why would anybody need to reboot a computer?"

    Some slashdot readers are lucky enough to live and work in an environment that primarily uses BSD or Linux. But unlike some slashdot readers, I, Damian Yerrick, live and work in an environment that primarily uses Microsoft Windows. Therefore, I have to use Microsoft Windows.

    Some slashdot readers are lucky enough to be able to afford personal copies of PC virtualization software such as VMware, so that they can run other operating systems within a window on their computer. But unlike some slashdot readers, I, Damian Yerrick, can't afford a VMware license. Therefore, I must run Microsoft Windows on the bare hardware, and if I want to run an operating system other than Microsoft Windows, I must reboot my computer to access it.

    Some slashdot readers are lucky enough to be able to afford to buy additional hardware to shield their other computer from exploits of newly discovered vulnerabilities in its operating system. But unlike some slashdot readers, I, Damian Yerrick, can't afford a second motherboard, CPU, case, and keyboard on which to run BSD firewall software. Therefore, if I want to keep my computer connected to the network, I must keep my computer updated with patches from Microsoft Windows Update. Those patches often require a reboot of the computer.

    Therefore, I, Damian Yerrick, cannot afford to own a computer system that does not have to be rebooted.

    --
    Will I retire or break 10K?
    1. Re:Some people can't afford ($) not to reboot by Kynde · · Score: 1

      But unlike some slashdot readers, I, Damian Yerrick, can't afford a second motherboard, CPU, case, and keyboard on which to run BSD firewall software [closedbsd.org].

      Therefore, I, Damian Yerrick, cannot afford to own a computer system that does not have to be rebooted.

      Blah blah blah. You can get a fully functional Pentium I computer for less that what you spend going out one night. Pentium I runs any *BSD or Linux just fine and not just firewalls, you can even run a little trimmed down X (nobullshit wm, say black box, avoid huge ram hogs, etc).

      Running linux is dirt cheap, for non business users _especially_ hardwarewise. I know this is redundant, but somehow people tend to forget that Linux doesn't have that high hardware requirements at all. I'm begging my Pentium 2 366MHz laptop to break so that I'd get a reason buy a new one, but as long as it works flawlessly I can't fake a reason to buy a new one because it runs linux and every app I use just fine.

      --
      1 Earth is warming, 2 It's us, 3 it's royally bad, 4 we need to take action NOW
  55. Re:NO, IT'S NOT.. by Anonymous Coward · · Score: 0

    If someone will mod this to Flamebait, I will track him down and kill him.

  56. Running out of DIMM slots by yerricde · · Score: 1

    Just buy more RAM.

    If I already filled all the slots on my motherboard with the densest RAM modules that my motherboard supports, buying more RAM won't help because it'll just sit in its box.

    --
    Will I retire or break 10K?
    1. Re:Running out of DIMM slots by luciuskwok · · Score: 1

      I don't mean to sound cynical, but why don't you buy a motherboard that supports enough DIMM slots to let you max out your RAM to what your OS lets you use? Motherboards are cheap and you can reuse your CPU, RAM, PSU, HD, etc.

    2. Re:Running out of DIMM slots by dsfd · · Score: 1

      I don't think the idea of using it as swap area is nonsense. What if you need 6 Gbytes of RAM (as I do) ?

      As far as I know, normal motherboards don't suport more than 3 Gbytes, even using 1 Gbyte modules that are very expensive.

      For me the main question (apart of price) is if this device runs in Linux.

    3. Re:Running out of DIMM slots by rodgerd · · Score: 2

      Buy a Xeon and use it's extended addressing, which will give you 64 GB of RAM. Or buy a genuine 64 bit hardware platform.

      While the latter is generally pretty expensive (unless buying, say, UltraSPARC or Alpha systems second hand), there's plenty of commodity hardware out there to do Xeon systems at a reasonable price.

    4. Re:Running out of DIMM slots by Bert64 · · Score: 1

      So you could buy a server-class motherboard, or go for a 64bit architecture that will far more easily handle such an amount of ram.

      --
      http://spamdecoy.net - free throwaway anonymous email - avoid spam!
    5. Re:Running out of DIMM slots by Tony+Hoyle · · Score: 2

      If you need 6gig you're presumably not using an Intel architecture anyway (possibly itanic but that can take loads of ram on its motherboards anyway).

      The max an intel can address is 4gig, and the practical limit is around 3gig. Any more and you're into segmented addressing hacks again, which just aren't worth it.

    6. Re:Running out of DIMM slots by dsfd · · Score: 1

      Well, it would be more exact I would need 6Gbytes, but I have to do with 4x0.5=2Gbytes + swap on dual K7 ASUS boards. This is why I was interested in the swap RAM disk.

      But, if I understood your comments, I cannot go beyond 4GB per process using Intel: It doesn't matter if it's RAM or swap.

    7. Re:Running out of DIMM slots by Elladan · · Score: 2, Informative

      To be more specific, you can't go beyond 2-3GB per process using intel, at least, directly. (You could access more indirectly, just not as actual memory.)

      The reason is that the kernel needs memory too. Say you try to load some data from disk. You call the read() system call, which switches to the kernel execution context. The kernel then checks to see if the data you're trying to read is available in the disk cache. If it is, it copies. If it's not, it schedules a load, puts your process to sleep, and when the load finishes, it copies.

      So, basically, either way, the kernel needs to be copying data from the disk cache to your program's memory space. This means, it needs to see both at once!

      The standard way this works is, all physical memory (which might be used as cache) is mapped into the kernel, normally limited to the high 1GB. The user process gets the low 1GB. So, when you switch to kernel mode, the kernel has all memory, physical and program-virtual, available to it.

      Now, some people have more than 1GB ram. The easiest thing for these people to do is use a 2/2 split, if they only have 2GB. This means the process can't use more than 2GB at once, but usually that's ok because most programs don't need that, really. A 1/3 split is also possible.

      However, obviously no straight split scheme like this is going to work if you install 4GB of ram! Instead, the kernel is going to have to play some trickery with the page tables and segment registers to get access to this extra memory. This way, it can support more than 1GB, up to 64. The user process of course is still limited to 3.

      The problem here, of course, is that doing tricks to get access to your memory in the kernel is obviously going to be slow. So, a kernel that actually tries to use more than about 1 (or maybe 2) GB of ram will be slower than a kernel which does not, and this is unavoidable. Now, this may be just fine, because that extra ram can be used for disk cache - and if your program uses a stupendous amount of disk space, even if the kernel is slower, the huge disk cache will still be a big help for you.

      But to make a long story short, >1 (or at most, 2) GB of ram will actually make your computer slower, unless you actually do something which uses all of that ram.

      None of this would be true, of course, on a 64-bit machine.

    8. Re:Running out of DIMM slots by arkanes · · Score: 2

      If I'm reading this correctly, then you're saying that the high end of RAM is slow because OS memory managment uses 32 bit integers for addressing. Wouldn't using 64bit integers(internal to the kernel, user processes still get normal 32 bit pointers) for addressing solve that problem? You take a performance hit on 32 bit systems, but it's probably not huge, and you can take advantage of 64 bit processors instantly.

  57. every 20 years by g4dget · · Score: 2
    In general, if your processor can address it directly, it makes more sense to put this memory on the motherboard and use it as regular RAM.

    People make these boards whenever the amount of RAM the processor can address becomes small compared to what you can afford, people start putting RAM into RAM disk drives.

    However, nearly $3000 for 2G of RAM seems excessive no matter what.

  58. Re: (Not So) GOOD! by KevinGale · · Score: 1

    Oh Yeah this will be a lot better than the ancient drive technology we use now. Every time the power goes out for more than a few minutes (or just a flicker if you don't have a UPS) you will lose all your data. Just what I want to store all my data on, NOT!

  59. Security by denisonbigred · · Score: 5, Interesting

    Most people complain about how this drive or RAM disks are completely wiped out by a power loss, but couldnt that also be used as a great security feature. If you have alot of data that you dont want someone (read: The Government) getting their hands on or taking as evidence, just keep it on a drive protected by a UPS, then if you need to wipe it out quickly and completely, just pull the plug. Or if a few lovely FBI agents come and take your computer, they do it for you.

    --

    "There's no way to rule innocent men. The only power any government has is the power to crack down on criminals."
    1. Re:Security by Anonymous Coward · · Score: 0

      how often do fbi agents come to your house and take your pc?! hasn't happened to me yet... (maybe cuz in canada we still have some privacy) ...

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

      and before all you lame ppl say it, we don't have the fbi either.

    3. Re:Security by vranash · · Score: 3, Informative

      You must've missed the article on here a few months/year back about the guy (@ MIT?) that was disassembling RAM and able to find the 'most used position' of transistors to recover data out of memory, similiar to how they can do it from mechanical hard drives if not completely wiped.

    4. Re:Security by Anonymous Coward · · Score: 1, Funny

      This probably still wouldn't be good enough.
      You should put a small explosive charge next to it just in case :)

    5. Re:Security by Shardis · · Score: 1

      Either that or a big ass electro-magnet. It tends to save on clean up. :P

  60. Cache should be expandable on hard drives by DarkHelmet · · Score: 4, Insightful

    This is just sad...

    3,000 dollars for something that has 2 gig of ram. I could get 2 gig of ram for a fraction of that amount... In fact, for the speed its giving, I could fill the thing up with sdram or edo ram...

    This is something I could imagine being useful with my hard drive... Why don't they make a standard plugin for hard drives... Make it where you can add cache directly to the hard drive.

    But wouldn't it be better to just have RAM instead of this?

    Not if you're going to go over 4 gig. You'd then need a 64 bit solution for that... If, on the other hand, you could add MAJOR amounts of cache to your hard drive, it wouldn't matter if you only had 4 gig of actual memory. You could run IA-32 as long as you like. You could have potentially gigantic databases without worrying as much about disk thrashing...

    It's going to be potentially a long time until a 64 bit winner in the PC world is declared... As time goes on, something like this may actually be viable. And as memory prices go down, we're going to be seeing a lot more 4 gig systems around...

    Or am I on crack?

    --
    /^[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,4}$/i
    1. Re:Cache should be expandable on hard drives by wik · · Score: 2

      You're partly on crack. Intel's Xeon processors have used 36-bit addressing (through PAE, physical addressing extension) for several years now. That gives a 64GB address space which you could use for a gigantic in-core file cache.

      You can't easily use this memory within a single process. DMBSs such as MS SQL Server and Oracle can take advantage of it, but they have to do their own memory management, anyway. A file cache could probably be implemented in a similar manner. Unfortunately for the people who try to build big iron machines out of Intel boxes, a 64GB address space is pretty small.

      --
      / \
      \ / ASCII ribbon campaign for peace
      x
      / \
    2. Re:Cache should be expandable on hard drives by rodgerd · · Score: 2
      This is something I could imagine being useful with my hard drive... Why don't they make a standard plugin for hard drives... Make it where you can add cache directly to the hard drive.


      Indeed. You already get that to a certain extent with RAID controllers, of course - battery backed RAM caches that can be retained in the event of a power failure. And a RAID card with heaps of RAM is a lot cheaper than one of these units.
    3. Re:Cache should be expandable on hard drives by newr00tic · · Score: 1

      why don't "they" just make motherboards with a separate battery for the onboard RAM.. it would be just as easy to use them for storage then..


      --
      A horse can't be sick, you know, even if he wants to.
    4. Re:Cache should be expandable on hard drives by drinkypoo · · Score: 2
      You are in fact on crack. It does not matter that there will not be a clear winner in the 64 bit world for some years because both intel and AMD's systems will work, and be supported by Linux and Windows and most other operating systems which now run on x86-compatible processors.

      Within two years or so I suspect that only budget PCs will be 32 bit.

      You are right about more 4 gig systems, but I think we're going to start seeing 8 gig systems...

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
  61. 4.7 GB of DDR for $37 by yerricde · · Score: 2, Funny

    For the price of the Ramdrive, I could easily get 2GB of DDR

    I can get 4.7 GB of DDR for $36.94.

    for the price of the Ramdrive I could get a motherboard that supported 64GB and fill a moderate chunk of it

    If your operating system crashes, what happens? If your OS publisher pushes out a "security update" and asks you to restart your computer, what happens? If you lose power, will your UPS be able to power your motherboard for as long as it can power an external RAM drive?

    --
    Will I retire or break 10K?
    1. Re:4.7 GB of DDR for $37 by Fluffy+the+Cat · · Score: 2

      If your operating system crashes, what happens? If your OS publisher pushes out a "security update" and asks you to restart your computer, what happens? If you lose power, will your UPS be able to power your motherboard for as long as it can power an external RAM drive?

      Using the RAM as disk cache, within about 30 seconds of data ending up there it ought to end up on disk.

    2. Re:4.7 GB of DDR for $37 by Bert64 · · Score: 1

      And if you reboot to install a security update, the os will sync the disks first. Similarly if theres a power failure the UPS will hold the computer up as long as it can, then instruct it to do a safe shutdown (complete with sync)
      If the OS crashes.. well then you lose anything in the cache which hasn`t already been written out to disk, which isnt likely to be very much. But what are you doing running an unstable os on a machine that is used to store important data anyway?

      --
      http://spamdecoy.net - free throwaway anonymous email - avoid spam!
  62. Re:timothy=crap by Matimus · · Score: 1

    shouldn't be timothy == crap;

    that is unless you are planning on storing "crap" at the memory location "timothy".

    --
    GENERATION 25: The first time you see this, copy it into your sig on any forum and add 1 to the generation. Social exper
  63. Re:Some people can't by Anonymous Coward · · Score: 0

    so you can't afford to not reboot your machine, then
    you really can't afford the ram disk drive either.

  64. Swap space?? by Chanc_Gorkon · · Score: 3, Interesting

    Could one use this for swap space? Swap could be regenerated between power off (say when you move the machine). Then you could have a startup script see if this thing was configged on boot up and if it was, use the swap. If not, it could config it as swap and then reboot? Am I off base here? Swaps would be lightening fast and if you happen to lose swap when powered off it ain't no big deal.

    --

    Gorkman

    1. Re:Swap space?? by khallow · · Score: 1

      I don't see any reason why this couldn't be used for swap space. However, there are two drawbacks. First, you probably get better performance to price if you add more RAM and use a regular hard drive for swap. Second, depending on your situation, there probably are better uses for the drive (eg, caching commonly used files).

    2. Re:Swap space?? by luciuskwok · · Score: 2, Insightful

      It makes more sense to max out your motherboard RAM and not have to go out to swap in the first place. If your motherboard is constrained the number in DIMM slots, you could always swap out the motherboard with one with more slots. Consider the cost of a motherboard ($300) vs. cost of a RAM drive ($3000).

    3. Re:Swap space?? by Chanc_Gorkon · · Score: 2

      True enough. But what should be really asked is why is the price of this thing so high? The only way I see this being even close is if they used CF instead of SDRAM. Even then the cost of the IDE interface and the CF cards (or chips if they repackage it) can't be that much. Of course the performance would suck with CF though.

      What I really see happening with something like this is if the server costs alot and the DB that is running on the thing is larger then the total available ram. You can't always go out and BUY a new server MB. You can go and get this. I do agree with maxing out the ram though instead of buying this. It makes more sense at the moment.

      I do think when the cost of CF comes down and the amount of space available goes up, that CF or something similar will start to be used as a conventional hard drive. It's going to happen and for some folks who use PDA's alot, it has happened. Maybe at some point OS's like CE and Symbian may be advanced enough to take over for the PC (NOT servers, but PC's.). You can say Linux is in that group and is sufficient for PC's running with CF HDisks, but right now the cost is just prohibitive. Some day those Winchester disks may just seem like another quaint technology like 8 inch, 5 1/4 floppy drives and (for alot of us) modems.

      --

      Gorkman

    4. Re:Swap space?? by lkaos · · Score: 2

      This sort of defeats the purpose of swap :)

      You see, the existance of swap is merely because RAM is costly. A RAM drive for the purpose of swap doesn't make sense because one could simply just add more RAM to one's system and disable swap.

      Now, having two types of RAM (a bunch on a faster bus--say DDR, and then a bunch more on a slower bus like PC100) would be rather interesting... It may not be as cost effective as it would seem but it would allow for some interesting caching algorithms.

      --
      int func(int a);
      func((b += 3, b));
    5. Re:Swap space?? by Anonymous Coward · · Score: 0

      >> You see, the existance of swap is merely because RAM is costly.

      I thought swap was there to allow developers to recklessly allocate memory, and not have to put any effort into making their apps memory-efficient! :)

  65. Overcoming RAM limits via swap by Kaya · · Score: 1

    I imagine this drive would be a useful workaround for the ~1.5->2GB RAM limit which exists on some 32 bit machines. A swap file on a drive like this would let a process use up to its available virtual memory.

    1. Re:Overcoming RAM limits via swap by luciuskwok · · Score: 1

      The 2GB limit on 32-bit machines will be overcome when 64-bit processors start shipping. This workaround would only be temporary,

  66. alternative - diskless clients by DrSkwid · · Score: 2, Offtopic

    plan9 users a multi-computer concept

    1 : file server - all it does is serve files and does backups to WORM. HD Crash only loses todays changes.

    2 : auth server - boots from the file server and issues authentication. crash - np reboot it and off you go

    3 : cpu server - runs the programs, if it crashes then so what, only data in it's memory will be corrupt, the file server will not have crashed

    4 : terminals - bootstrap from a floppy/cdrom/localhd to get authed and then into booting from the file server [or run a windows/bsd/linux client]

    One can then add new nodes for redundancy and scale. Local terminals can have local storage if desired

    --
    There are places where the networks are not touching,and there are places where they are-Boeing's Lori Gunter
  67. Mobo/DIMM incompatibility by Anonymous Coward · · Score: 0

    if you are investing this much money into a RAM drive, you should just buy enough RAM so that you don't need a swap file at all.

    Unless your motherboard is incompatible with the densest RAM modules.

    1. Re:Mobo/DIMM incompatibility by Anonymous Coward · · Score: 0
      Unless your motherboard is incompatible with the densest RAM modules.
      Probably a sign that it's time for a new computer.
    2. Re:Mobo/DIMM incompatibility by Anonymous Coward · · Score: 0

      If you have enough money to blow thousands of dollars on a pointless RAM drive, you can buy a high-end motherboard.

  68. so what happens... by nuckin+futs · · Score: 1

    when you have a power outage and you have no backup UPS? do you lose everything on it? Macs old and new, had the ability to do just that, but its biggest problem was losing data on it upon reboot or if you had a system crash.

    1. Re:so what happens... by Anonymous Coward · · Score: 0

      There's really no excuse to NOT have a UPS these days. UPS's are incredibly inexpensive (with small units at under $100) and even the smallest UPS's will suffice if you only plug the actual computer (and not the monitor and everything else) into them.

      Join the present and get yourself a UPS.

      - =^o.o^=

  69. Another example of military technology trickle dow by t0qer · · Score: 5, Interesting

    n.

    Most modern Fighter jets use ramdrives exclusively because the high-G manuvers, shaking, ect would cause a normal drives heads to go smashing into the platters. I know the B2-stealth has some, so does the F-16.

    When you're the goverment, and you want reliable killing machines, 250k for a 250meg ram drive back in 1987 isn't even an afterthought. It's a requirement. Now that it's dirt cheap to produce memory, it can finally trickle down in price enough to have become feasable for a civilian to afford one.

    I know originally the early drives were used to hold map data for the HUD, which was basically just the data gained from our digital elevation modeling sattelites launched in the 80's. Given the advances in 3d modeling and sattelite map aquisition, I would guess whatever system they're using today probably contains terrabytes of map data.

    I'm sure the old green vector graphic huds have been replaced with something a lot better to utilize the new data too. I'd suspect that in the actual control area there must be a LCD display, much like what you see on a modern 737.

    It must be one helluva video game for them pilots :)

  70. mod down - swap is only used when ram runs out! by honold · · Score: 0, Flamebait

    at least mod it as funny...

    he could just use the ram in his system and he wouldn't need to swap

    1. Re:mod down - swap is only used when ram runs out! by honold · · Score: 1

      flamebait? right, idiot.

      as you can now see, it's been (properly) modded as funny instead of insightful. i guess all of the people with mod points aren't complete morons.

  71. Secure Drive Space by Anonymous Coward · · Score: 0

    It seems to have advantages even beyond manually pulling the plug; this seems like a great way around the data-retention issues that plague standard HDs. Unless you *always* remember to use shred or some other wiping utility, bits and pieces of your files remain behind on ordinary magnetic storage. A file created and deleted on a RAM-based disk like this would be unrecoverable.

    Ordinary RAM disks would have this benefit too, but when you power off you either (1) lose all your data or (2) have to copy it onto other (unsecure) media. You could treat this drive as secure unrecoverable space, and just worry about encrypting your backups instead of regularly doing free-space wipes.

  72. You really by Anonymous Coward · · Score: 0


    Who here turns off their computer?

    1. Re:You really by Anonymous Coward · · Score: 0
      Who here turns off their computer?
      The ones who run Windows. No joke.
  73. PCI Problems by GoRK · · Score: 3, Insightful

    As others have pointed out, this 32 bit PCI card pretty much sucks. It outperforms, what, a single U160 drive on a 32 bit controller? By only a factor of two?!?

    You could easily smash the performance with a little U160 RAID on a 64 bit pci controller, and perhaps even with a single drive, though seek time would hurt a bit. At least it'd cost you a hell of a lot less.

    It's not battery backed either, which is pretty useless for anything this might need to do. Heck, without battery backup, it proabbly can't even survive a reboot to get that precious data back after a system crash!

    This reeks of an EE or Embedded Systems course assignment. It's barely a real product.

  74. Yeah, HUGE breakthrough... by Noose+For+A+Neck · · Score: 1

    Or, you could save money, buy a motherboard with a high memory capacity and mount a RAM drive in Linux. Lots more bandwidth than SCSI, too, if you use DDR.

    --

    Software piracy is victimless theft.

  75. High resolution video by donglekey · · Score: 2

    It seems that many people are wondering why anyone would invest in something like this, let alone multiple drives. One thing that this would be great for is working with high-res video, for animation, compositing and editing. A big problem for a very long time (and still even) was just playing back full resolution (720x486) video on a computer. For small things RAM can take care of it, for bigger things you need a scsi drive or a RAID. For higher resolution video like various HD resolutions, playback becomes difficult again. RAM doesn't cut it very well, because if you are working with HD animation or compositing it is probably full anyway. RAID Scsi or some sort of RAM disk like this are the only ways to reliably playback the sequences. It becomes a How much do you need? Anything I can get. sort of situation.

    1. Re:High resolution video by TheNetAvenger · · Score: 1

      Who in the world is *Still* using a computer that has problems playing 720x486 full resolution video? I have a 200mhz 80mb *OLD* Laptop with WindowsXP and can play videos uncompressed at this resolution without any dropped frames. I understand your argument, but I don't know of a computer made since 1997 that can't pull data from the hard drive fast enough to display this video. (And I am just referencing a 5gb 4200rpm laptop drive here) The SDRAM hard drive does not hardly have any practical uses, espeically when RAM is cheap. If you are needing faster IO for video editing then simply drop more RAM in your system. Most OSes will use the extra RAM for the Cache to speed things up. And If you need a RAM Drive to do video editing, buy more RAM, or a new CPU, Mainboard, and RAM; then run free RAMDrive drivers that are available for almost any OS. This will give you an EVEN faster Hard Drive.

    2. Re:High resolution video by Anonymous Coward · · Score: 0

      That doesn't hold up; at that price you could get a new motherboard and 4 or 5 or more gigs of real system memory, and work from a ramdrive.. that doesn't justify the cost here.

    3. Re:High resolution video by Anonymous Coward · · Score: 0

      Some people like to capture and edit video, not just watch it.

  76. Re:timothy=crap by Anonymous Coward · · Score: 0

    the guy is a PASCAL programmer, for crissake... leave him alone in his misery.

  77. this is retarded by Anonymous Coward · · Score: 0

    why is it over the pci bus? why not scsi/ide/usb2.0/firewire so you can boot off it? im assuming this thing remembers even after power is turned off. otherwise, whats the point?

    people saying this can be used as swap dont understand how swap works. swap is for low memory systems. it doesnt make your pc faster, it allows you to address more ram (so you dont run out). and this device would probably hog the pci bus. i mean wtf. depending on how you use your _windows_ pc, having 1 gig of ram and disabling swap can be significantly faster than having 1 gig of ram and 1 gig of swap. windows is stupid when if comes to paging and memory management. so getting more ram and disabling swap would make more sense than using this for the swapfile.

    why cant someone make a solid-state storage device that goes in a 3.5" drive bay and uses scsi? even 1 or 2 gigs would be nice. you could just put frequently used apps and the os on it. just think how fast doom3 would load off it or how fast win2k /linux would boot off it.

  78. Yeah yeah.... by sqrammi · · Score: 1

    Sure, this is nothing new. But there is something nice about 1ms access times to your data (which I assume this should be able to achieve). I think if you actually tried using this thing to load up a game or something you'd find it would perform more than 2 or 3 times faster than SCSI.

  79. Solid State Drive by AtariDatacenter · · Score: 5, Interesting

    I've had the pleasure of playing with RAM based storage devices at work. They're a lot of fun. The particular models we used were external, SCSI, memory based, with a battery backup and internal disk for long-term storage.

    The nice thing is that they can drive as many reads/writes as you can get out of the SCSI channel. Seek time isn't a factor at all. We're talking disk performance through the roof here! There are also UltraSCSI and other types that'll go even faster. But the only real limitation is the link between the drive and the computer.

    Still, the data rate doesn't approach what this PCI based solution has going. But what I use is a more 'enterprise' solution. You've got internal battery backup and disk backup. If the unit is off the mains, the battery kicks in. After 30 minutes, it stops all IO, dumps to disk, and shuts off. When power is restored, it loads back in from disk.

    This PCI solution is way cheaper than the external drives that I've used. Just it doesn't appear to have the reliability... or the commodity standards that'll let it hook up to just about any type of system. Still, quite neat!

  80. Semi off-topic by Jade+E.+2 · · Score: 1, Offtopic

    OK that site pisses me off. They pull that stupid ass 'split the article into multiple pages to get more banner views' trick, but A) they split them into 1 or 2 paragraph pages, and B) the only banner they're running is their own. So, what, they're splitting the article up so they'll pay themselves more? Or are they just trying to inflate their # of hits to try to attract more advertisers? (If it's the latter, congrats, /. just helped them more than they could have ever imagined!)

  81. I remember back... by randomErr · · Score: 2

    I remember back in my childhood (that would to early 80's) there was 2 similar devcies.

    Some of the Tandy 1000 series has MS-DOS 3.3 placed in a ROM drive.

    Shortly after that a company out in Californa test marketed a bootable ISA card that had Windows 3.1 and a small ramdrive. At the local Sears it was billed as being updatable to Windows 4.0 when it came out[Insert laughter here].

    The device was unstable because it didn't use Flash memory. The RAM they did use ate power like you wouldn't believe. Thus the battery life was short and you would have to reinstall your personalized setting.

    --
    You say things that offend me and I can deal with it. Can you?
  82. in the car by paradesign · · Score: 2

    i would much rather put this in my car than a hdd that will go smashing over every detroit pothole, and if your from teh area youll know what im talking about. if teh price comes down to be reasonable, this will be a nice high vibration environment solution to disk storage.

    --
    I want 2D games back.
  83. I don't understand why RAM drives are overpriced by MarcoAtWork · · Score: 2

    I mean, come on: the board with the interface and glue logic shouldn't cost more than $500-$1000 (and even that is really pushing it), while for the ram the manifacturer can use ram they already have that didn't pass testing and/or that is slower that what currently is sold these days.

    Obviously it's not good if you buy a stick of RAM for your PC and 100K out of 256Meg don't work, but for an HD-like application, where you have a map of 'bad sectors', it's not a problem.

    Heck, considering that nowadays 'bad' RAM chips are basically thrown away, I could see a 10gig model (external maybe, due to space constraints) going for half of what this 2gig model costs.

    Spending $2000 on 2 gigs of ram seems really gouging of the early adopters.

    --
    -- the cake is a lie
  84. Not cost effective or that fast by jrst · · Score: 1

    132 MB/sec xfer rate -- Nothing to get excited about; it's PCI bus bandwidth limited. I can saturate the PCI bus with RAID (IDE or SCSI) already. I can do better than 132MB/sec using a 64-bit or PCIX RAID controller, which this "drive" doesn't appear to offer.

    100,000 I/Os per sec -- That is smokin', but how many I/Os are going to be single-sector reads? You'd be better off with more main memory buffer space to reduce small I/Os, which gets back to the question of xfer rate.

    So you end up with a very high priced disk with none-to-exciting xfer rates but excellent seek times. Moreover, it takes up a PCI slot, which limits expandability.

    It would make more sense if they make it look like a SCSI 160/320 drive (or array). It would have far greater expandability; still have bus-limited xfer rate; but a slightly higher access time.

  85. Blah by JohnThreePound · · Score: 1

    These have existed for years! They're called Solid State Disks (SSDs). MTI and Imperial have sold SCSI, Fibre Channel, and CI (think VAX) versions of these for a LONG time now.

    The good ones have disk back-up so when a power failure happens, the data gets backed up to a regular IDE disk, and is restored at power on.

  86. Re:How This Works... Neat Facts by dsfd · · Score: 1

    Is there a PC motherboard that supports 64 GB ?

  87. Useful as the ext3 journal by Illusion · · Score: 5, Informative
    If this had Linux drivers, it would be terribly useful for an external ext3 journal.

    While profiling a high-volume qmail server with fast mirrored drives, I noticed that I could get at least an order of magnitude sustained mail throughput by eliminating the fsync() system call, which essentially forces the disk subsystem to stop whatever else its doing and get a few specific blocks all the way onto disk. You can't run it in production this way, as the SMTP RFC specifies that the mail must be actually on disk before the server can claim that its done.

    The problem is that magnetic-media drives can only seek a few hundred times per second. Regardless of their claimed sustained throughput, if you are writing a bunch of small files to disk, you are completely dependent on the seek time of the drive.

    But mounting a magnetic-media-based ext3 with data=journal and the journal on an NVRAM block device would essentially use this as a trusted write-cache. Linux will return from the fsync() system call as soon as the data is in the journal, which could happen instantly on an NVRAM disk as there is no seek time. It then reads from the journal in its spare time, sorts it to minimize seeks, and writes the data out to disk.

    I suspect that this should offer roughly the same speed as eliminating the fsync()s entirely.

    I was looking into ordering a similar product to test this. I found:

    --

    Aaron

    1. Re:Useful as the ext3 journal by chrispix · · Score: 1

      According to the website there are RedHat 7.3 drivers available.. And some Free BSD drivers too..

    2. Re:Useful as the ext3 journal by CaseyB · · Score: 2

      Then if you lose power after the fsync (and SMTP acknowledgement) and before the physical write occurs, you lose data. It's the same as using write-behind caching (no fsync) on a conventional filesystem. TANSTAAFL.

    3. Re:Useful as the ext3 journal by Illusion · · Score: 1
      Of course.

      Putting the journal on an NVRAM block device requires that it be able to keep its data through any conditions you are likely to encounter, such reboots and short-term power loss. There appeared to be several other systems which had enough battery power to copy the in-RAM data to flash or a hard drive.

      --

      Aaron

    4. Re:Useful as the ext3 journal by CaseyB · · Score: 2
      Ok, but then couldn't you just buy yourself the same reliability (UPSes, etc) on a regular disk subsystem, and then turn off fsyncs? If you're not actually doing a real flush to disc, it's all just handwaving and hoping that the cache is reliable.

      I think "virtualizing" fsyncs is just a bad conceptual idea, because you are end-running the whole purpose of their existence. Just turn them off, and tell people the reliability of write-behind caching is good enough, or do them for real.

    5. Re:Useful as the ext3 journal by TheLink · · Score: 2

      Some RAID controllers do it for you - they have a battery backed up write cache. Even if you turn of the machine before it actually writes to disk, when you turn it back on, the controller will write the stuff to the HDD. So I suspect it's unsafe to change disks after an unknown shutdown ;).

      Remember to schedule a proper shutdown and change the battery before it runs out.

      And also RAID5 = slow writes. So mirroring may be the way to go for reliability, especially if the RAID controller is smart.

      --
  88. How About........ by Anonymous Coward · · Score: 0

    A motherboard, that loads a drive image of the harddrive, to the RAM(the mobo would have to have 8additional slots). This way its still fast,

    When the user shuts down the computer it transfers a drive image of the RAM back to the HDD.

    OR EVEN...

    Once its booted up use something similar to RAID, any changes made to the (storage)RAM are also made to the HDD,

    *just an idea*
    T_D_H
    double_helix@hotmail.com

    PS: if you use any of my ideas to make money,i will hunt you down and killl j00

  89. Higher Capacity Available... by pocopoco · · Score: 1

    A company called Platypus Technology has an 8 slot (allowing up to 8gb) version of this product available. Larger capacity seems the main reason anyone would accept accessing SDRAM through PCI rather than the normal method so it seemed worth posting. Some prices can be seen at CDW.

  90. Re:How This Works... Neat Facts by rodgerd · · Score: 3, Informative

    Any Xeon motherboard. Not all x86 OSes support the Xeon addressing model, and it's a segmented addressing system that still restricts you to 4 GB chunks per process.

  91. Cool, but . . . by Anonymous Coward · · Score: 1, Funny

    I wish I didn't have to partition it in two for my GNU/HURD box.

  92. Can you... by Anik315 · · Score: 1

    Imagine a beowulf cluster of those!

  93. Perfect use for a RAM drive by Anonymous Coward · · Score: 0
  94. A hard drive made out of memory... by Anonymous Coward · · Score: 0

    ...would be called a soft drive, not a hard drive.

  95. Why pay that price? by Anonymous Coward · · Score: 0

    um, a much cheaper alternative to this has been around for years, it's called Memory File System.

  96. Nice try - but ... by Anonymous Coward · · Score: 0

    ... not really impressive compared to this badboy:

    http://www.cray.com/news/0204/xfersystem.html

    Quote:
    "The new system, compatible with Cray SV1e(TM) and Cray SV1ex(TM) supercomputers, includes a 224-gigabyte Solid State Disk (SSD) with a data transfer rate of 80 gigabytes per second..."

  97. Been there, done that, got the T-shirt by anonymous+cupboard · · Score: 3, Interesting
    Sorry, I was working with RAM drives 10 years ago. They are neat but expensive and somewhat more limited in their capacity. However, I can say with these things to store their hot files on, the world's largest electronic derivatives wouldn't be able to cope with the load that it does.

    The point is that with the drives that I have used (SCSI-U2W through fibre channel) is that they used good old fashioned interfaces which meant that they were plug compatible with older hardware.

  98. If i were you i would wait for MRAM by cybercomm · · Score: 3, Interesting

    I mean, with this type of technology i believe any geek would feel a **bit** insecure, for if the power supply to those rams goes out, you are doomed. I believe that the only benefits of this type of technology right no are UBER fast seek imes and R/W times. IBM is about 2 years away from producing a fully functional MRAM drive (i believe that they do have sa coulpe of prototypes now that work but their R/W times are absolutley horrendous) that will need no power to store data (once it is written that is). The other alternative would be to have some sort of internal RAID HDD with each platter (or side of the platter) accting as one independent unit, i believe ths may have been tried before, but there have been some problems with synchronisation? (anyone knows more about hat one?)

    --
    Live for the present, learn from the past, and dream of the future!
    1. Re:If i were you i would wait for MRAM by Anonymous Coward · · Score: 0

      In the late 1970's, my uncle had a computer that he could use, turn off, and turn back on; it would return in the same state that he left it in before power down. I wish that I could remember the name. . .

  99. Solid State Disks are effective DB accelerators by dbenhur · · Score: 1
    I see lots of comments asking why not just put in more main memory and let the OS cache. The reason is persistence.

    This sorta device can be used very effectively for large scale database systems. But the device reviewed here doesn't qualify because it doesn't have redundant power, a back-up hard-disk and a UPS.

    A Google search brings up Imperial Technology for example, which makes a line of DRAM disks and storage caches with lots of redundancy and multiple high-speed (USCSI, fiber channel) channels.

    If you have a high transaction volume database, putting your highest access tables and redo logs on a solid state disk system can produce 2x to 6x performance improvements even when you've already got gobs of server power and very fast disk arrays. Here's a success story involving eBay seeing 500% improvement with their Oracle installation on Sun E10Ks.

    These server class devices are a lot pricier then $3K, but when you've spent mid-five to high 6 or 7 figures on the hardware and six figures on your oracle enterprise license, another $10-50K to get four times the performance is easy.

  100. Re:What's the point? (silly design) by Black+Copter+Control · · Score: 2
    Why not just fit your PC out with 4GB of fast DDR RAM and do it that way? That memory would be far cheaper than this card.

    For a lot of the suggested uses, a (software) RAM drive would be about as good this thing.

    About the only thing that this drive provides that makes it better than a software drive is the fact that it's got it's own power supply. This means that the data on the hardware ramdrive will survive a system crash/power cycle. Unfortunately, their prices don't (seem to) include a separate battery backup, so you should budget an extra couple hundred dollars for a UPS dedicated to the drive. I'd actually pay for that, even if I already have a UPS for my computer because -- if you're paying the extra hundreds (or thousands) for this box, you'd better be paying for the persistant data feature. If that's the case, the last thing you want to happen is for your data to be lost the first time you had a blackout long enough to outlast the UPS.

    My expectation is that this machine doesn't eat much power.. In other words, even a small power supply should supply it for a day or more if it's not also powering a computer.

    Now for the reasons why this card isn't too useful for most data:

    • Programs: Why store programs on this drive? At that price, I'll just use a startup script that populates a software RAM drive whenever I boot up. Unless you have a program that absolutely must be running as fast as possible after boot, that extra wait isn't going to hurt most people.
    • Cache data: especially with transient cached data, a software RAM drive gives you most of what you need.
    • Temp Data: (e.g. scratch files for compilers, etc). Same as Cache data.
    • read-mostly Databases: Once the data is first accessed, you're better off to pay for a few gigabytes of regular RAM and assign it to your database cache. If your database doesn't have a decent data caching algorithm then you'd better find yourself a better database.
    • read-write databases: This is one place where this works nicely -- between the fast access and data persistence across a reboot, it might be worthwhile -- but I'd reiterate the comment about putting the RAM drive on it's own UPS. Remember that if you have a hardware failure that requires a motherboard replacement, you won't be able to unplug the board's power cable until you've backed up the data. (heh, heh).
    A well designed board would emulate a regular drive controller. That way, you'd be able to use it as a normal disk -- including being able to boot from it. As it is now, you'll need dedicated drivers for this thing -- including for Solaris and Linux. In other words, a lot of the most promising markets for this card are closed

    BTW:

    • Hardware RAM drives aren't new. There have been implementations of those things floating around for years.
    • Linux has a really good disk cache system. Among other things it makes it really difficult to test the I/O subsystem on a machine with 6GB of RAM (had to do that once). You end up needing a program to flush the disk cache after every run.
      And it's free (in both senses of the word)!

    --
    OS Software is like love: The best way to make it grow is to give it away.
  101. Okay.. by mindstrm · · Score: 2

    I'm not trolling here, and I'm not saying "this is crap".

    Can someone who knows say what this is really useful for.

    As many have pointed out "it could be used for swap" is silly; more onboard ram would be faster and cheaper.

    1. Re:Okay.. by Pointer80 · · Score: 2

      It could be used for a queue disk for your MTA.

      --
      [%- PROCESS life -%]
  102. interesting by zogger · · Score: 2

    --see another niche for this, diskless laptop, has dual hot swap batts, auto shifting and sleep cycle if both get too low.

    Also, the ram on the card and "in the way" down on the mobo is a valid complaint engineering-wise, a better design would have it fit in a regular drive bay, then just run it's own cable with pci edge to an available slot.

    Another thought, take yet another drive bay and have an internal UPS that is dedicated to this drive (or your normal ram somehow). How much juice does it really take to keep ram turned on and not lose data? I honestly don't know, is it a huge amount? Would a regular normal size l-ion laptop bat keep it on for like days or hours or minutes or what? Seems like a nice thing to have for desktops anyway, again, have it reside in a drive bay.

    If it's not invented will whomever snags the idea plz send me some cash? My "new" box is a 200.... thankew....

    %^)

  103. Platypus - What you really want is Platypus by Anonymous Coward · · Score: 0

    What you really want is a Platypus.

    They have internal and external units, both for cache and as RAIDed hard drives.

  104. Want speed? Check out Conduant by Phrogz · · Score: 2

    How's 200MB/s sound?

  105. Real power is in random IOPS by PseudoThink · · Score: 1

    I've done research into buying similar ramdrives. The main purpose in buying one is usually not to increase bandwidth, it's to minimize the time per random-access IO operation. Even the fastest SCSI hard disks have about 4-5ms random access times. These RAM disks have random access times measures in microseconds, and are typically 2-3 ORDERS OF MAGNITUDE faster on random IO than even a SCSI RAID array. So what do you need random IO for? Databases. Ebay and Amazon already use RAM disks heavily, and I'd be surprised if Slashdot couldn't benefit from using them too, if they already aren't.

  106. Blah that's silly by photon317 · · Score: 3, Interesting


    If you're willing to fork out the money, there's several manufacturers who have been puttng out genuine static ram drives for a while. They have microsecond access times, sizes up to 80-ish GB last I saw, IDE and SCSI interfaces, and can have sustained bandwidths limited only by the bus speed. They also consume less power, generate less heat, and don't fail as often because there's no moving parts. They solved the limited write cycle problem by having the drive logic remap blocks of data to spread the write wear around the drive.
    FOr a bleeding edge example, check out E-DISK's soon-to-be-available Ultra320 drive (they're released other similar drives before, just not at this performance level):

    Size: up to 155GB
    Access time: 33-48 us (microsecond)
    IOPS: 9500 - 50000 per second
    Burst data rate: 320 MBps
    Sustained data rate: 230 MBps
    Full Erase (Security feature, press a button): around 26 seconds.
    ECC error correction, MTBF around 2 million hours, 10 year data integrity.
    Write life-cycle of in excess of 100 years at 100 GB of writes per day.

    --
    11*43+456^2
    1. Re:Blah that's silly by photon317 · · Score: 2


      Heh, of course I should mention that such drives can cost up to $1000/GB for the low-end models up to 8GB in size. I'm sure the cost/gig goes down on the larger drives, but I wouldn't expect this 155G Ultra320 monster to go for any less than $78K, probably higher :)

      --
      11*43+456^2
  107. This is new? by r2ravens · · Score: 3, Interesting

    At Comdex, a long time ago (maybe as much as 10 years), I stopped by a booth that had this wonderful new technology - an external hard drive which was made entirely of RAM! Current hard drive quantities of RAM(don't remember the exact capacity, but it was significant.) And it was only $15,000 (comparable drive space at the time was one tenth the price.) Wow! (Ok, sarcasm off)

    I asked that man what would happen if the power was lost. He said that the box had a battery and a hard drive of the RAM capacity inside. If the power was lost, the battery would power it long enough to write all the data to the hard drive. I asked what the advantage was over a regular hard drive. He said access speed and no moving parts. Ok, great benefit, but it didn't seem the value was there for 10x the cost of a drive itself. Anyone remember this?

    I started waiting years ago for someone to come up with a board where I could plug in all those 256k, 30 pin SIMMs that we took out of the Mac Plus' when we upgraded them to 4 MB of memory so I could use them for storage. Never happened (that I know). Now I'm waiting for the same thing for this ever mounting stack of 4, 8, 16 and even 32MB, 72 pin SIMMs.

    Where is the real innovation? I mean, our favored OS here can run well on all this old hardware - 486 and the like, but where are the little trinkets for us cheap SOB's like me? I just want a 5 1/4 external case with a 25 pin D connector that will connect to my SCSI card. The board inside should have jillions of 72 pin SIMM sockets (in pairs is ok, multi-level board is ok) and a connector for an old ATAPI 2 or 3 Gig laptop drive. The case should have room for a little battery to do what that really expensive drive could do years ago to backup in case of a power failure. Hell, I'd even pay 50 bucks or so for it. Any takers?

    I'm not an EE so I'm not up to making it myself, but someone out there would consider it a fun project...

    You know, reuse, recycle, make the world a better place. I don't want to have to throw out all this memory or sell it for a quarter a stick. I guess I could use the dremel tool, drill little holes in them and make geek earrings, but I don't wanna have to do that either.

    If anyone has any ideas, lemme know. :)

    BTW, no need to call me a cheap SOB luddite, I already did that...

    --
    War is Peace. Freedom is Slavery. Ignorance is Strength. - George Orwell or George Bush?
    1. Re:This is new? by pjrc · · Score: 2
      The board inside should have jillions of 72 pin SIMM sockets (in pairs is ok, multi-level board is ok) and a connector for an old ATAPI 2 or 3 Gig laptop drive. The case should have room for a little battery to do what that really expensive drive could do years ago to backup in case of a power failure. Hell, I'd even pay 50 bucks or so for it. Any takers?

      I'm planning to add a project to PJRC in the next year that is essentially this... but using 168 pin DIMMs (which are collecting now that higher performance PCs use DDR).

      Saddly, $50 is a unrealistic for a low-volume product. The "controller chip" is a FPGA that costs almost $50 by itself in modest volumes. A large multi-layer circuit board is also needed (most of the surface area is to mount the DIMM sockets). Finally, low volume BGA soldering and x-ray inspection isn't cheap either. It's a very different world making several hundred niche-market boards vs millions of cheap ethernet cards. A board like this with 12 or 16 sockets can't realistically be sold under $350 (under 1000 per year volume).

    2. Re:This is new? by Crispin+Cowan · · Score: 2
      The "recycle your old SIMs" has a problem induced by the exponential growth of memory sizes. Following Moore's Law, memory doubles in capacity every 18 months. The mathematics of a pile of things that double every 18 months is that the current 18-month generation is larger than the entire pile of everything that came before it.

      So while you can putz around and try to integrate a bunch of differently-timed old memory cards onto a single mobo, or you can just go spend $50 on a new stick for the same benefit. The choice is pretty clear.

      Crispin
      ----
      Crispin Cowan, Ph.D.
      Chief Scientist, WireX Communications, Inc.
      Immunix: Security Hardened Linux Distribution
      Available for purchase

  108. Platypus by Anonymous Coward · · Score: 0

    This kind of thing has been around for a while...
    Here

  109. 100x gain where latency is at issue by j_dot_bomb · · Score: 2, Informative

    That is the real gain of solid state drives. If you have say a database with lots of small writes then your speed is limited by seek time of drives of around 5ms. You can add more spindles to help in some situations. With SCSI solid state drives they max out at 8000 trans per second (usually) because of the scsi controller.

  110. Volatile? by vandy1 · · Score: 1

    I know of some memory available *right now* that is *not* volatile and runs at *huge* speeds. Admissably, it is only available in 256kb (32KB) sizes right now, but a 64Mb (8MB) version is almost ready for sale

    Go to Ramtron Corporation or NV Technologies to see more!

    Michael

  111. Mac OS 7.5.3 by rapidweather · · Score: 1

    I have a Macintosh Quadra 660av with system 7.5.3 on it, and a "ram disk" is set up, so I use it for the browser's disk cache, hoping against all hope to speed up the loading of frequently-visited web pages. This thing is slow, even compared to my IBM PS/1 with an AMD 586 upgrade processor, and 32 mb of 30-pin ram and a 25 mhz bus, running Windows 98.
    There's only so much I can get out of the ram on these machines, but improvements can be made over time. One secret to keeping the Quadra from locking up is to use matching ram sticks. I can go quite a while now without a lockup, and I consider myself lucky to go over an hour ;-)

    1. Re:Mac OS 7.5.3 by Alan+Partridge · · Score: 1

      maybe you could get a paper round and save up a couple of hundred for a 21st century computer...

      --
      That was classic intercourse!
  112. It's RANDOM I/O that's implortant by walt-sjc · · Score: 3

    Oh please. Encoding of a serial stream has ZERO need for really fast I/O. All you need is a normal drive that has a high enough sustained transfer rate to handle the stream. Any normal hard drive is up to the task.

    Think of applications that need to randomly access the drive. Think web servers, caching proxies, databases, etc. We had a custom app that needed to write to around 40,000 files simultainiously, and read from them randomly. The only feasable solution was a rather large RAM drive system. The one we used was external, had it's own hard drive for backing up the image, UPS, etc., hooked up to the normal SCSI bus, and cost around $12K for a 2G box (this was a number of years ago when RAM was much more expensive).

    Nice thing was NO DRIVERS. It was a SCSI drive to the OS. You could boot off it if you wanted to.

    Soliddata.com in case you are wondering.

  113. Slashdot going to hell by Anonymous Coward · · Score: 0

    Lot cheaper to buy a motherboard that will handle 4 gigs of DDR RAM, than blow $3K on this very very old idea.

    I used a ramdisk back in my Atari XL days. That was way cool. Of course, back then we didn't have an OS that would use available RAM as cache. Now we do, which is why this thing seems like a stupid waste of money.

  114. Pricing Sucks by SQL+Error · · Score: 4, Insightful

    This is potentially interesting, but there are several problems:

    1. The pricing model sucks. The entry price of $399 is too high for a card with one chip and four DIMM sockets. And that only supports 512MB. To go to 1GB, 2GB or 4GB you have to pay hundreds of dollars more - even though the only change is a BIOS setting.

    2. The RAM pricing is absurd. These guys need a reality check, pronto.

    3. The board takes standard PC133 NON-PARITY RAM. No way in Hell would I trust my data to something like that. Honestly, this is just plain stupid. The board is too expensive for the home market and no-one sane is going to put non-ECC memory in a server.

    [As a side point: Even using standard DIMMs, you could do some sort of block-ECC at the driver level (or in the controller chip) and use the fourth DIMM as a parity device to recover from on failures, like RAID-3. Alternately, you could treat each DIMM as a 48-bit device and use the remainder for ECC and Chipkill. There's nothing on Cenatek's site to suggest they do anything like this, though.]

    There's a few other things that annoy me: the lack of specifications (while they have a list of approved memory modules, they point-blank refuse to provide the required memory specs on their support forum). Also, the board appears to require four identical DIMMs, which is a royal pain in the bum. Expandability? What's that? Low entry cost? Don't got one of those either.

    So this board appears to be worthless for its target market and overpriced for anything else.

    One-word review: Sucks.
    Score: 3/10.

    Memory is absurdly cheap, and a properly thought out board (even one that implements the ECC in software) at the right price has a market waiting. I know a lot of people doing embedded Telco apps would love something like this. This card isn't it.

    The Platypus card is also over-priced, but it does support (indeed, requires) ECC, and also goes up to 8GB.

  115. We did this in 1990 with Mac SE by jmardres · · Score: 0

    There was a kit you could buy that was a drive assembly with SIMM slots. I think the max was around 40 megs? but it was totaly a RAM based drive and we would boot from it. Wow was it fast! Has anyone seen one of these since? I would love to have one for my collection.

    --
    FAMOUS LAST WORDS: Ha! They couldn't hit an elephant at this dist...
  116. *ONLY* a factor of TWO??? by fishbowl · · Score: 3, Interesting

    Performance gains of "almost a factor of two?"

    Does anyone else read that as an endorsement of the usefulness of buffering and other performance technologies applied to disk drives?

    I'd imagine that applications in ruggedized systems or devices that need to be exposed to significant acceleration or zero gravity will be more important than the speed increases, but, I'm quite surprised that a 15krpm SCSI drive comes this close to a RAM device.

    One other benchmark that would be useful, would be to compare the speed to the normal RAM in a given system. Is it a net gain to have your RAM on an expansion card? Or would a RAM drive on the regular memory space be better? Is this more or less expensive than system RAM?

    --
    -fb Everything not expressly forbidden is now mandatory.
  117. Instant Virtual Memory by Vegan+Pagan · · Score: 2

    Assuming that a RAM drive uses memory that is slower and less expensive than high end PC3200, but still much faster than a magnetic disk, perhaps main memory could start shrinking and accelerating, acting more cache-like.

  118. How hard woul d it be... by Polo · · Score: 2

    How hard would it be to make a REALLY CHEAP commodity ram board. Something with about 20 slots that you can fill with your old pc66 ram or with el-cheapo 512m sdram chips with crummy specs.
    On pricewatch they are $28/each. 4g = $224 = 8 slots

    Or maybe it could take half-broken or really sub-spec chips with errors that can be mapped out or software ecc'd. A bogus 512mb chip with 1 chip
    bad might be $10, but have 450m usable.

    Don't even bother with power backup in the design, market it to gamers.

    Possibly, you could integrate it with a disk controller and just have a lot of cache. The disk would just get faster the longer the system was up. Maybe you could tune things to pre-cache certain files or say that a certain parition was always read entirely into ram (like the / partition or c:\windoze) Or put the swap parition entirely on it and don't worry about losing it.

    Also, it would also be cool to have a cdrom drive with 700mb of cache that starts reading the disc sequentially the moment it is installed in the drive.

    But the key here is commodity. $795 for an unpopulated 4g board seems high.

  119. I have a bootable ram drive for sale... by Blowit · · Score: 1

    It is a 10GB unit which runs under SCSI and is bootable. You can have your whole OS running on RAM. The price new is $80,000, however, if interested, I can sell it for $15,000. If anyone interested post a reply here. Otherwise, check EBay next week for the word 'Solid Data' and you will see the unit there for sale (not up yet).

    --
    *Headline News* censorship shuts down the Internet! More at 6PM!
  120. Re:timothy=crap by Anonymous Coward · · Score: 0

    Pascal would be something more like Timothy := 'crap'; to store at address.

  121. Not for home users... by Jah-Wren+Ryel · · Score: 4, Informative

    I don't know why a hobbyist website is reviewing this unit - the target market is not for hard-core gamerz or other home user types. Solid state disks are primarily used as database accelerators. Although the throughput of a solid state disk like this can be easily beat by a reasonably small raid, it takes a much larger raid to beat the io/s rate. If you have indices that don't fit in ram, you stick them on the solid-state disk and watch your database speed up by an order of magnitude.

    Alternatively, as at least one other poster has already mentioned - if you use a journalling filesystem like ext3 or rieserfs, then putting the journal on a seperate solid-state disk is a huge performance gain.

    --
    When information is power, privacy is freedom.
  122. Re:NO, IT'S NOT.. by Anonymous Coward · · Score: 0

    Yeap. It's nice to have Mafia behind ya. A single slashdot user is just a statistic kill. So less these so called "professionals" know about this business.

  123. SSD is old hat by gelfling · · Score: 2

    SSD - solid state drives are quite old. The problem has always been cost. 3 thousand bucks for a coupla Gig is astonishingly expensive. You'd better have some amazing requirements like Dynamic DNS zone file transfers on the order of 30-50MB/sec. Or something equally high end.

  124. Intel always thought so... by danshapiro · · Score: 2, Funny

    I used to work at Microsoft, and spent three years in the drivers & kernel group for Win98 and then Win2k. It was a running joke that every year Intel would give us a presentation showing a graph of the price/performance of flash vs. hard drives. The curves would cross in something like four years from the date of the presentation. Of course, evey year, the axes changed, but the graph (and hence the time until convergence) never did...

    --
    This posting is provided "AS IS" with no warranties, and confers no rights.
  125. Hmm... by Anonymous Coward · · Score: 0

    Didn't we do this before, in the time of 16-bit ISA bus and Cyrix 486 processors?

    I believe they were called Hard Cards. So what makes this one so special?

  126. A non-volatile RAM drive would be revelutionary by cartman · · Score: 2

    The article benchmarks are for _bandwidth_, which is irrelevant. Mechanical disks get good bandwidth already (The RAM drive only gets 2x as much). What matters is _latency_; disk latency is about 1,000x as great as RAM latency.

    Some applications are latency-intensive, for example, OLTP and other database applications. Databases don't care about bandwidth; they care about latency. And just "adding more memory" will NOT work because database transactions do not complete until a record is written to NON-VOLATILE storage. (Losing committed transactions after a power failure is unacceptable).

    At present, all the big database boxes have like 500+ drives. Why? They don't have nearly that much data. The reason is because lots of disks working in parallel mitigate the terrible seek times of mechanical drives. Lots of read/write heads seeking in PARALLEL, each over a small portion of data, leads to much better seek times. However, a SINGLE RAM drive would provide FAR better seek times than all those mechanical units working in parallel.

    At present, companies spend millions of dollars on huge drive arrays, not because they need more space, but because they want to mitigate terrible seek times. A RAM drive is faster and cheaper than this.

    The only reason _this_ ram drive would not work is because it is not really "non-volatile". With a database, the data _cannot_ be lost. An internal "battery backup" is not sufficient. (How long will the battery last? Can you really be guaranteed that all the data can be copied to disk? etc).

    A RAM drive that had truly non-volatile RAM and that was in the 20GB range would sell to owners of large databases, even if the drives were very expensive. The technology probably exists to do this now.

  127. Why not in 3.5"/5.25" form factor with IDE by fatbitch · · Score: 1

    Everytime I read about ram disks - they are pci based.

    Is there any reason why a ram drive could not be manufactured in the same form factor as a 3.5"/5.25" hard drive with an IDE interface?

    In this way you could have a simple swap replacement for a mechanical drive with a fast solid state one ? With the price of memory now - make a board that takes standard memory (allow it to be stacked sideways to take plenty) and add battery backup - at 34ukp(~45$) for 512megs you could have an impressive - fast piece of storage?

  128. I remember one of these from 1986 by chill · · Score: 2

    It was called a BattDisk, from DKB (Dean K. Brown) and was on a Zorro II card for an Amiga. It held a total of 2 Mb and could be booted from -- making a blazing fast boot for the machine.

    --
    Learning HOW to think is more important than learning WHAT to think.
  129. 'External Supply' by The+Monster · · Score: 2
    It has an external supply that keeps the card powered.
    It's a lot more expensive to buy this thing than a UPS, which can signal the computer that it's running low on battery so that the ramdrive/disk cache can sync out to the real HD before the power shuts off. Only reason that wouldn't work is if the OS crashes, so I can maybe see a PCI card like this with an onboard IDE or SCSI port, and its own processor (would not have to be anything fancy here), capable of committing everything to HD transparently to the CPU for Windows users.
    --

    [100% ISO 646 Compliant]
    SVM, ERGO MONSTRO.

  130. if you don't need the whole 2gigs, by jazperbg · · Score: 1

    this is better. if you like removable stuff

    --
    jasp
  131. Not a new idea by RallyDriver · · Score: 2

    This has been done many times before, from consumer products (Commodore Amiga 600/1200 in the early 90's supported proto-PCMCIA flash memory cards) right up to Cray Research (the Cray 2, targeted for the CFD market, had optional "normal" speed memory add-ons which could be addressed like filesystems called "SSD")

  132. Re:Memory isn't that fast.. by willy_me · · Score: 2
    This ram drive thingy has a 6 _micro_second latency (if memory serves), roughly 1000X faster. Stick that in your RAID pipe and smoke it. :)

    Actually, memory has a much slower latency then that. In fact, the latency hasn't changed much from the early 90's when we were all using 8 bit SIMMs. What has changed is that we now stream consecutive words of memory out at very high speeds. So while a 400MHz DDR memory module may be able to send a word every 2.5 uS, it still takes ~ 40 uS for that first word to arrive. And only consecutive words can take advantage of that bandwith.

    And you also forgot to mention that all this data still has to go through the HD controller. Doing so greatly reduces the speed benefit gained from using memory.

    The thing I really do like about this setup is that it would be perfectly quiet.

  133. Re:I don't understand why RAM drives are overprice by Anonymous Coward · · Score: 0

    That Xilinx chip I bet is no more than 100 bux. Full-speed PCI logic doesn't require a million gate $$$ FPGA.

    I suspect if you were willing to write up some code that card wouldn't cost more than say $75-$100 to make yourself.

  134. Re:How This Works... Neat Facts by drinkypoo · · Score: 2

    I don't know about you but I'm planning to go Hammer. I suspect that some of the 8-way hammer motherboards will support at least that much memory. I doubt the workstation (1-2 CPU) chip will end up on boards supporting more than 8GB or so, but 1GB should be enough for me. 512MB hasn't quite been enough.

    --
    "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
  135. Underachievers! by billcopc · · Score: 4, Insightful

    I don't get it.. let's assume, in the name of generosity, that U160 actually pushes 160mb constantly. Then the rocket drive pushes 320mb constantly. Now we've got PC3200 ddr ram that can theoretically push 3.2 gigs per second, while this rocket drive only does a tenth of that.

    What's the damn point ? It has to go through some sort of slow-ass bus anyways.. it's not like it has precisely timed local access to the northbridge, like traditional ram.

    It would be better for motherboard (and chipset) makers to accomodate buckets of ram sticks, so we can allocate a real RAM disk using 8 or 16 sticks of 512mb/1gb ddr.

    --
    -Billco, Fnarg.com
  136. Ram disk and coda, so happy together by drinkypoo · · Score: 2
    You know, you could use one of these in a net-booted system that booted to coda instead of NFS. Have it cache the files used most. Ostensibly you won't be rebooting much so the only time your network will be stressed much is on boot. You could even have a little swap on it for those operating systems which get pissy without any, though I suspect anything you'd want to netboot would be pretty good anyway.

    Using this and a peltier cooler with a really good (big) heat sink, and an overdesigned power supply, you could build a PC with no moving parts whatsoever. Then all you need to do is hook it up to a flat panel display, and you've got a silent, low-emissions computer with VERY fast access to frequently use files. The perfect thing to put on the nightstand.

    --
    "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
  137. Nice Idea, but it has some BIG problems by leonbev · · Score: 2

    Would YOU want to trust this thing to save your important data? After looking at the specifications, I saw two BIG problems with it right away:

    1) It needs a separate "wall wart" power supply to be plugged into the card to keep the data stored on the drive when the computer is off. So, what happens when the power goes out? Or, the power supply fails? Or, (most likely), some moron accidently unplugs it? That's right, total data loss. For the price they are charging for this thing, it should come with some sort of an Uninteruptible Power Supply built INTO the unit.

    2) The card uses standard PC133 memory, which is less reliable memory type than the ECC memory that is supposed to be used in servers. An application like this practically DEMANDS ECC memory, to make sure that single-bit errors aren't slowly corrupting your data.

    Sadly, this thing isn't any better than a glorified RAM disk. I wouldn't store anything more important than a swap file on it.

  138. Re:How This Works... Neat Facts by cgleba · · Score: 2

    LOL. . .or for really big systems:

    1) Tape
    2) Compressed RAID5
    3) RAID5
    4) RAID10
    5) RAID0
    6) Ramdrive/buffer cache
    7) RAM
    8) L3 off-die cache
    9) L2 on-die
    10) L1 on-die
    11) CPU registers

    Slowest to fastest; cheapest to most expansive.

  139. QX-10 Flashback by Anonymous Coward · · Score: 0

    Boy, this is cutting edge...assuming we're in the mid 80's. I had a 2 meg (I know it's not gig but bear with me) RAM drive that had an external power supply with battery backup. You could put several (up to 4, I think) of these in the computer. Sound familiar?

    I also had a QC-PC card that was basically an IBM XT on a card. I've been seeing that concept pulled out of the archives of ancient history as well.

    And IBM's going to spend billions of dollars developing time-sharing.

    Does this mean we're all out of ideas?

  140. dealing with mixture of fast and slow RAM by David+Jao · · Score: 2
    I haven't yet found a way of persuading Linux of this fact, I would prefer the kernel to use the lower eight megs preferentially.

    This is actually possible to do in linux 2.4. Believe me, I am an expert on this kind of thing, as my situation is similar -- the Intel pentium chipsets only cache the lower 64MB of RAM, so on systems with more RAM you would like to tell linux to use the lower RAM preferentially.

    The secret is the slram.o module in the MTD section of the linux kernel. See here for the full scoop. This module doesn't solve everything; in particular, linux doesn't disk cache as effectively when slow ram is in use. You'll just have to see for yourself whether it's worth it or not.

    1. Re:dealing with mixture of fast and slow RAM by Ed+Avis · · Score: 2

      The link you posted to explains how to set up a RAM disk using the extra memory; that has been possible with Linux for a long time. But it doesn't really do what I want.

      The lower, fast memory is only eight megabytes on the two particular systems I'm thinking of. If I used a process whose working set was greater than eight megs (or allowing for the kernel and X server, six megs) it would 'thrash' constantly to and from the RAM disk. Of course this is not nearly as bad as thrashing to physical disk, but it could be a lot worse than having a full 40 megs of RAM to use, even if most of that is slower.

      The extra memory I have is real memory, you can address it just the same as RAM on the motherboard. If there is a need to, the kernel should be able to map processes into this slower RAM and run them from there, or run a process partly in faster and partly in slower RAM. Also, it should be able to choose between using the slower RAM for running processes, for 'swapping' or for disk cache, whereas if you set it up as a RAM disk it cannot be used as a disk cache. I would like the kernel to use the whole memory space but just *prefer* the lower eight megs, and maybe the memory manager could occasionally migrate pages between slow and fast memory depending on how recently they have been used.

      In fact the machine has three memory speeds: the lower 8Mbyte, between 8Mbyte and 32Mbyte which is across the MCA bus but still cached by the processor's L1 cache (and I think by the L2 on the motherboard); and above 32Mbyte which is uncached. A simple RAM disk arrangement may be better than nothing but it is not ideal.

      Does anyone know how I can tell Linux that some of the RAM is faster and some slower, while still having enough in total to run bloated apps like Emacs and Netscape 4.x without swapping?

      --
      -- Ed Avis ed@membled.com
  141. U160 15,000 rpm hard drive... i think not. by ltwally · · Score: 2, Interesting

    The Rocket Drive itself looks wonderfully impressive... thought the price may be a bit extreme. I noted two things from this article, however:

    1)The Rocket Drive only attaches through a regular 32-bit/33mhz PCI slot. You would expect at least a 64-bit/33mhz card... if not faster than that. The drive itself may not be able to transfer faster than 100 MB/s, but you must also consider the other devices attached through that PCI bus. This device can easily hog nearly all the bandwidth available. Not exactly an ideal situation.

    2)The drive that is compared against the Rocket Drive is claimed to be a Ultra160 15,000rpm drive. This would not be a bad choice for comparison, since it is the fastest single type of drive available... and the Rocket Drives direct competition. However, how many 15,000rpm drives have you seen that average out with a 13.1ms latency, and cannot achieve an average throughput higher than 38 Mb/s? None that I know of. I happen to own a 36gig U160 10,000rpm Cheatah. My Cheatah, using the same synthetic benchmarks, can pull under 6 ms latency with an average throughput of 49 Mb/s.

    No, I'm not trying to tout my drive's speed. I'm simply pointing out that the implementation of this device is a little strange for a device designed for extreme workstations and mid-range servers. And that the benchmark numbers of the comparison drive are at best waaaay skewed. They simply cannot be correct. A 15k rpm drive IS MUCH FASTER THAN THAT!

    That being said... who wouldn't like a 4 gig ram-drive?! :)

    --



    /dev/random
  142. magnetic memory by hashmap · · Score: 1
    I remember a presentation at a Physics Seminar at my university, a guy from a big government funded research lab came to tell us about magnetic memory, a kind of memory that works just as the hard drive does, only that it can be addressed electronically and without moving parts.

    The cool thing about them was that they would completely do away with the concept of hard-drive and memory as separate entities. They would not require electricty to store the information only to reset it.

    The guy was very sure of himself (some head-honcho) and promised to put the semiconductor industry out of buisness. I haven't heard anything more about this ever since.

    Just imagine how cool it woudl be to be able to unplug your system and turn it back on and getting it back in the exact same state that it was.

  143. Solid State drives not new but better ... by bkontr · · Score: 2, Informative

    Solid State Drive have a place in high end computers primarily and not for computers used by comsumers. SSD technology has many advantages over mechanical drives, unfortunately price isn't yet one of them. When the technology becomes cheap and is sensible enough for standard PCs then you'll see the technology readily available for most consumers. As many people here have already pointed out, todays PC can't really integrate SSDs without slowing data throughput and that would really defeat the primary advantage of these devices. I found a good link to a SSD manufacturer that explains this all very well: http://www.sparcproductdirectory.com/curtisart.htm

    --


    "You helped our nation celebrate its bicentennial in 17 -- 1976." --George W. Bush, to Queen Elizabeth, Wash
  144. Re: (Not So) GOOD! by Anonymous Coward · · Score: 0

    Duh, obviously this type of throughput is more important in *fast* operations. Things where it doesn't take months to run, only hours. :P

    Think about it....

  145. Lame.. just do this. by MikeFM · · Score: 2

    The only real point of a device like this is to provide ram-based harddrive emulation to those sucky OS's that for whatever reason don't support this basic feature.

    I often run items such as my database or proxy server on a ram disk to improve speed and lower wear and tear on my drives. If you have a UPS that sends a signal when you're about to lose power then write a script that will dump your ram disk to real disk when power is going down. Obviously you also run it on normal shutdowns and if you care much for your data on a cronjob. Then just add a startup script that'll dump that data back into the ram disk. No sweat. Same functionality, faster, and much cheaper than this drive.

    With this ram disk I can just imagine what happens to your data if your coworker accidently pulls the power cord free while messing with wires.

    --
    At what price learning? At what cost wisdom? The price is a man's peace of mind, and the cost is his life.
  146. Re:How This Works... Neat Facts by Anonymous Coward · · Score: 0

    I have an ancient BX that supports 1GB. The only boards that top-out at 512MB nowdays are really lowend stuff -- which ain't where you are going to see any sledgehammer stuff.

  147. I'll wait for this replacement by malloci · · Score: 1

    http://www.lcs.ece.cmu.edu/research/MEMS/

    I still don't think I'd pay $3k for a 2gig replacement. Especially when there is a lot of headway being made in MEMS technology (site above).
    I think I'll wait until it becomes a mainstream product.

    1. Re:I'll wait for this replacement by John+Sullivan · · Score: 1
      I still don't think I'd pay $3k for a 2gig replacement.

      Especially when you can buy 4x512Mb CompactFlash cards, 2x2-port PCI->PCMCIA cards, and 4xCF->PCMCIA adapters for a third of the price. Less if you go for 256Mb CF cards and 4x2-port adapters (if you have PCI slots to burn).

      --
      This is my World Wide Web of Whatever
  148. Re:timothy=crap by Anonymous Coward · · Score: 0

    your mouth=crap

  149. Procuring a 586 box? by yerricde · · Score: 1

    You can get a fully functional Pentium I computer for less that what you spend going out one night.

    Thanks for the suggestion. Do you suggest looking on eBay first? Or is there a better idea?

    --
    Will I retire or break 10K?
  150. Re: Who said anything about programming??? by Anonymous Coward · · Score: 0

    The oldest and most traditional use of '=' is to show mathematical equality.

    Go soak your head.

  151. Re:How This Works... Neat Facts by pjrc · · Score: 2
    Sure about that? For the price of the Ramdrive, I could easily get 2GB of DDR.

    Maybe. Most motherboards have three DDR sockets, but if you use unbuffered (inexpensive) IMMs with chips on both sides, most motherboards will only work with one or two of those DIMMs. Generally, you need buffered/registered DIMMs if you are going to use several.

    Over at pricewatch.com today, 1 GB DDR DIMMS are listed between $324 to $480, depending on the speed and vendor. 512 meg DDR DIMMs seem to be in the $120 to $160 range, but those are not buffered/registered... so it's very unlikely you could get four of them to work on a normal motherboard.

    Hell, for the price of the Ramdrive I could get a motherboard that supported 64GB and fill a moderate chunk of it.

    Again, you'd be looking at an expensive server motherboard, and it would likely require the very expensive registered/buffered DIMMs.

    That thing has lower speed and greater access time than main memory and costs more, so just using RAM as disk cache would appear to be more useful under the majority of circumstances.

    This might be true, if you could inexpensively add that much memory, and deal with the volatility.

    A few times I've considered adding a solid state disk project to PJRC.COM.... it's likely have 16 DIMMs sockets at about half the price of this gadget (they used a big xilinx FPGA... same basic idea).

    Unbuffered 512 meg SDRAM (not DDR) DIMMs are selling at about $30 each these days... maybe the value in having an extreemly fast non-volatile 8 gigabyte disk at $830 would be better??

  152. Re:How This Works... Neat Facts by Anonymous Coward · · Score: 0

    What x86 class motherboard can you get 64 gb support? Seriously, I want to know. Even if it's only 16 gb, this would be useful for me.

  153. Re:Memory isn't that fast.. by mlyle · · Score: 1

    Please note:

    A microsecond is 1 * 10^-6 seconds. 1/400,000,000th of a second if 2.5 nS. 6 microseconds through a HD controller seems quite attainable and is supported by the benchmarks.

  154. PCI is the right interface for this by billstewart · · Score: 2
    The PCI interface is faster than IDE and most flavors of SCSI - the only reason SCSI could be helpful is that it lets you locate the RAM disk box externally, which makes it easier to do power supplies, battery backup, etc., as well as making it a bit easier to stack multiples of these on your machine if that's what you want. But except for power, it's probably more reliable to put it inside the case with your CPU. Drivers aren't a big deal - either they can provide them (they should be dirt simple), or more likely they make the device look like an IDE drive so it doesn't need separate drivers.

    I agree that the pricing structure is silly. It should be one price for the board, and either add your own RAM or let them sell you RAM with a small markup.

    --

    Bill Stewart
    New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
    1. Re:PCI is the right interface for this by rodgerd · · Score: 2

      Uh. No.

      32-bit, 33 MHz PCI 2.x - which is this unit - has 132 MB/s of bandwidth, peaki, burst. More like 80-90 sustained. It's shared with other devices on the bus. Ultra160 has, well, 160MB/s. You can have it on 66 MHz/64 bit PCI cards that work on a 500+ MB/s bus, or you can integrate it into the motherboard and have it go via the North Bridge and get the FSB speed as a peak.

      Likewise, IDE peaks at 133 MB/s or 150 MB/s for serial, and on most modern motherboards feeds into the FSB via the North Bridge, getting much better peak bandwidth.

  155. You don't use more for speed, you use it for space by billstewart · · Score: 1

    You don't use multiple RocketDrives in parallel to make them transfer data faster - you use them to keep more stuff on Rocketdrive instead of disk. It already goes fast enough, or if it doesn't go fast enough, you really need system main memory.

    --

    Bill Stewart
    New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
  156. Encrypted file systems are better for that. by billstewart · · Score: 2
    For most people, the real threat model isn't the FBI breaking their door down - it's their laptop getting stolen. Be sure to keep good backups somewhere.


    There are several different versions of encrypted disk partitions and encrypted file systems that need you to enter the password to mount them, and which read/write all data to/from the disk in encrypted form. That way, if you power the system down, they're not readable until somebody types in the password. I'm not aware of any that have duress passwords built in (which scribbles the partition if you use it instead of the correct password) or cover-material passwords (which give the Feds some innocent cover material if they use it, e.g. the "backup" copy of /usr/ or something.) So if you live in a country that has thugs who will beat you up until you give them the correct password, only keep your dangerous material in RAM, and if you live in a country with an NSA-quality bunch of people who actually want to recover *your* material, keep it on an encrypted RAM disk, but otherwise, a regular encrypted file system will work fine.

    --

    Bill Stewart
    New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
  157. Also for DBMS and NFS journal accelerators by billstewart · · Score: 2

    These products have been around for a while for journaling space for DBMSs, and the Legato Prestoserve board which was an NFS accelerator. NFS had the similar problem that the protocol requires you to write stuff to stable storage before ACKing a request, and a meg or so of battery-backed RAM was enough to cache a couple of disk tracks, making the whole system much faster.

    --

    Bill Stewart
    New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
  158. Rotational / seek latency are zero by billstewart · · Score: 2

    Dude - it's not there just to give your machine more RAM, it's there to be much much faster than your disk drive. The speedup isn't because it can push data a bit faster than SCSI can - it's because real disk drives have ~8ms seek times and ~8ms rotational delays, so the number of separate items of data you can write to your disk are limited by how fast the disk spins around and the heads slide back and forth, not by how fast it can pump data once it's in the right place. It *would* be nice if the motherboard could handle more memory, but for this application, large quantities of cheap memory are just fine, and you can save your northbridge and AGP port for stuff that needs to be fast.

    --

    Bill Stewart
    New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
  159. Disk latency 10-20 years ago was SLOW by billstewart · · Score: 2
    Remember how slow disk drives were 10-20 years ago? None of this 15000rpm, you were lucky to get 3600. And the seek times weren't 4ms, they were often 85ms for a full swing. Clever disk scheduling could let you optimize the way you used it, and RAID let you amortize it in different ways, but fundamentally you had to wait for mechanical stuff to slop around before you could read or write anything. (A decade or so ago, Margo Seltzer did a Usenix paper on disk scheduling that showed that rotational latency had started to be more important than seek time, which was a surprising change for most of us...)

    This gives you your bits right now, and they were just marvellous as journalling accelerators for databases or NFS filesystems.

    --

    Bill Stewart
    New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
  160. Author Measured the wrong stuff by billstewart · · Score: 2
    I'm also surprised, but remember that this device is limited by the PCI bus, while RAIDed disk drives at full crank may use enough bandwidth that somebody bothered inventing Ultra-Wide-160 SCSI instead of Wide-80 or whatever the previous generation of SCSI was. So it's slower than the RAM can do, but still faster than the disk drive. The real comparison is for applications that are affected by latency, not throughput, because that's what these things are great for.

    It might be possible to build a device like this that's more cost-effective than system RAM, though this one isn't priced that way. You're trading the cost of a board for the ability to use cheapo PC100 or PC133 memory instead of PC2100DDR or whatever the latest and most expensive stuff is, and if you're careful, you can design it so it's not subject to the same memory limitations that the motherboard is, though that may be difficult with a 32-bit PCI bus. It'd be faster if it ran off the AGP bus instead of PCI, but that limits the applications to servers with slow or no video adapters, while PCI is probably good enough for most users who may want this to accelerate their graphics applications as well.

    --

    Bill Stewart
    New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
  161. Two words : Bubble Memory by AppyPappy · · Score: 2

    You heard it here first.

    Actually, I did a senior paper on it......in 1981.

    --

    If you aren't part of the solution, there is good money to be made prolonging the problem

  162. Cheaper Solution by SBrickWork · · Score: 1

    Ever since I learned about the differences between RAM and a HDD (especially with respect to virtual memory), i've always thought about an alternative...

    Assumptions
    1) large amounts of (system) memory are cheap and fast
    2) OS (and resident applications) generally use MUCH less memory than us computer geeks tend to have
    3) virtual memory slows us down :)

    so...
    assuming we have a new system w/ 1 GB RAM (even 512 would work, depending on its application) using the old RAMDISK drivers, couldn't we create a "drive" using the RAM... for virtual memory?

    now... i've watched for a while now, and everything seems proportional... we have a 486 with 64 RAM, and the OS used ~20-30 MB... we have a pentium with 128 RAM and OS uses ~40 MB... we have a PII with 384 RAM and the OS uses ~80 MB (ok... so we're gaining an advantage here)... the trend continues...

    I've always wondered what would happen if the virtual memory had a response time of 6ns :D

    -me

  163. Re:How This Works... Neat Facts by CarnageCJB · · Score: 1

    W00t!! If you do this, you shall be enshrined in the halls of geeky goodness for all time!!! (Plus, you'll get to be my new best friend.) :)

    --
    Sig (appended to the end of comments you post, 120 chars)
  164. Last Post! by alpg · · Score: 1

    Eh, that's it, I guess. No 300 million dollar unveiling event for this
    kernel, I'm afraid, but you're still supposed to think of this as the
    "happening of the century" (at least until the next kernel comes along).
    Oh, and this is another kernel in that great and venerable "BugFree(tm)"
    series of kernels. So be not afraid of bugs, but go out in the streets
    and deliver this message of joy to the masses.
    -- Linus Torvalds, on releasing 1.3.27

    - this post brought to you by the Automated Last Post Generator...