Slashdot is powered by your submissions, so send in your scoop

 



Forgot your password?
typodupeerror
Data Storage IBM IT

Interchangeable Data Storage Bricks? 185

Posted by michael
from the rated-n-for-not-as-easy-as-they-say dept.
shokk writes "EWeek is reporting that IBM is working on a concept called Ice Cube Storage Bricks that uses a conductive ceramic or mylar plate to transmit data between bricks across an air gap. Research center staff member Robert Gardner says that the idea is 'to walk up to the system, attach the storage and then walk away.' No mention is made of what happens when a brick in the middle of the cube needs to be replaced and the whole thing needs to be disassembled. To be really effective, this would need to be teamed up with some sort of a backplane, but the tech is new and neat."
This discussion has been archived. No new comments can be posted.

Interchangeable Data Storage Bricks?

Comments Filter:
  • No mention of... (Score:5, Informative)

    by TechnoLust (528463) <kai DOT technolust AT gmail DOT com> on Friday December 17, 2004 @11:42AM (#11116712) Homepage Journal
    "No mention is made of what happens when a brick in the middle of the cube needs to be replaced and the whole thing needs to be disassembled."

    Well, except for where it was specifically mentioned in the article.

    The bricks can use cheaper, less reliable components because the failure of a single brick or even several bricks will not shut down or corrupt data in the other bricks, because the data is mirrored in other sections of the array or in backup systems, he said. As a result, defective bricks can stay in place until they are replaced as part of scheduled maintenance, Gardner said.
    It's getting bad when the person submitting the story doesn't even RTFA.
    • "It's getting bad when the person submitting the story doesn't even RTFA." Oh C'mon, he's still a slashdotter isn't he?
    • I dont think it would be too difficult to replace a brick during the scheduled maintance. They would probably need to shut down the data for 5 or 6 minutes, remove the defective brick, and it's back up. However this can be done during the end of the day because the other bricks have a mirror.
      Seems like a really great idea.
      • Well I wonder if it is like current raid where you have to stack them back in the same order in your "Rubics cube" looking stack. That would be a pain if the one in the middle went bad.
        • by rcw-work (30090)
          Well I wonder if it is like current raid where you have to stack them back in the same order in your "Rubics cube" looking stack

          What kind of RAID setup do you have that doesn't write a GUID of what the disk is, as well as what all of the other disks in the set are, to each disk in the array?

      • Not sufficient (Score:3, Insightful)

        by GunFodder (208805)
        Nowadays many data sources must run 24/7 because they serve data worldwide. It really shouldn't be necessary to shut down the data source to replace a disk. RAID on SCSI can already support hotswapping. The only nuance here is to make sure the physical design of the array allows the operator to replace any cube without removing others.
        • Re:Not sufficient (Score:2, Interesting)

          by jessecurry (820286)
          well at least allow him to remove any cube without having to remove all mirrors of a specific drive.
          The physical design will probably require some optimization. If you wanted to mirror each drive to four others you could have four stacks, each rotated slightly in their arrangements, then a service tech could remove all of the drives leading up to a certain drive without interrupting the data flow(or really an entire stack). The data center would simply have to make a chart detailing the order to remove the
        • Re:Not sufficient (Score:3, Interesting)

          You people are getting all worked up over vaporware. IBM in 1996 claims that terabyte hologram cubes that can write nonmechanically with a light flashing was supposed to be available in a decade. It's pretty much 2005, and I see no sign of that.

    • by grub (11606) <slashdot@grub.net> on Friday December 17, 2004 @11:57AM (#11116900) Homepage Journal

      It's getting bad when the person submitting the story doesn't even RTFA.

      Reading the articles goes against the RFC.
    • Even that statement doesn't explicitly mention disassembly during scheduled maintenance.

      However, one can reasonably conclude a brick in the middle would need some disassembly to make it physically accessible.
    • by FFFish (7567) on Friday December 17, 2004 @12:30PM (#11117280) Homepage
      The solution is easy, too: there are three ceramic pads. One merely executes a Towers of Hanoi routine to work one's way down to the defective brick.
    • Sorry, but leaving a TB of data down for a week until the next scheduled maintenance is not my idea of a solution. People pay real $$$ for this to provide real benefits.
      • Once again, if you will RTFA (or even just the snippet I quoted), you will see that it is a REDUNDANT system. The article says that multiple cubes can go down, and all the data is still available, like it is in a RAID array.
        • Including the RAID5 performance hit [adaptec.com] for losing the redundant drive? That calls for an immediate system maintenance just to get the server back to normal performance, not just waiting for the next normal maintenance. And are you really going to let your RAID array sit on a failed drive hoping that you don't lose another any time soon? That's just friggin sloppy. It happens and that's why many server vendors are now moving to double-parity [sanz.com] systems.

          Sorry, taking the server down for any reason at all is ju
      • Sorry, but leaving a TB of data down for a week until the next scheduled maintenance is not my idea of a solution.

        You don't get it. No data is down at all. 80 GB of storage may go down, but the data is already replicated in the other bricks, and accessed in exactly the same way before and after the failure. And scheduled maintainence probably isn't next week, it may be four years from now when the agglomeration dwindles to 75% operational and you junk the whole thing in an upgrade.

  • by jcostantino (585892) on Friday December 17, 2004 @11:42AM (#11116716) Homepage
    If you have to replace a block in the middle and the pile collapses, does the server crash and you lose?
  • Dendrites. (Score:4, Interesting)

    by Anonymous Coward on Friday December 17, 2004 @11:43AM (#11116733)
    "EWeek is reporting that IBM is working on a concept called Ice Cube Storage Bricks that uses a conductive ceramic or mylar plate to transmit data between bricks across an air gap. "

    Kind of like a neuron.
  • Legos (Score:5, Funny)

    by nizo (81281) * on Friday December 17, 2004 @11:43AM (#11116734) Homepage Journal
    The bricks can be assembled "in a big pile of bricks or it could be a one-dimensional wall of bricks," which could make maintenance even easier.

    I knew that playing with legos would come in handy sooner or later.

    • When I read this in the article, I wondered to myself, "How can I assemble a physical set of things into a one-dimensional wall?" And as I think about it more, a wall can't really be one-dimensional...
    • Obviously, this is going to make the sysadmin job much easier and, quite frankly, dull.

      To compensate, I recommend they shape the bricks like tetris blocks.
    • How long before "The Star Wars Ice Cube Storage Bricks Saga"? LOTR-ICSBS?
    • Starting with the thing you quoted:

      The bricks can be assembled "in a big pile of bricks or it could be a one-dimensional wall of bricks," which could make maintenance even easier.

      Last time I checked, walls were at least two-dimensional. Though, I'll grant you, a one-dimensional wall would be easier to maintain than the two- variety, unless you want the things to stay in contact the whole time.

      Called CIB (Collective Intelligent Bricks)

      Borg what now?

      CIB is an effort to make highly reliable sto

    • So now a "wall of bricks" is one-dimensional? As opposed to a zero-dimensional line I suppose.
  • by bchernicoff (788760) on Friday December 17, 2004 @11:43AM (#11116735)
    How long before we see sites dedicated to storage array building contests?
  • by koi88 (640490)

    No mention is made of what happens when a brick in the middle of the cube needs to be replaced

    Or, when the ice melts?
  • by gUmbi (95629)
    Did anyone else immediately think of the Superman's Fortress of Solitude? Guys?...Guys?..No?
  • storage tank.. [slashdot.org]
    I recall another /. article about a storage brick as well, but I can't find it.
    • Storage Tank is software, not hardware. It virtualizes all your storage into one bigass logical storage unit, which you can then attach your hosts to over a switched fiber or similar network. It's a very clever set of abstractions and protocol conversions.

      I know a few of the guys working on this project, and they're most definitely software people.
    • This also works for cpu chips: see the Sun Research [sun.com] article on the sibject.

      Both sound like lego bricks shoved into slots in a backplane (;-))

      --dave

  • by nizo (81281) * on Friday December 17, 2004 @11:48AM (#11116790) Homepage Journal
    Called CIB (Collective Intelligent Bricks)...

    That name for the individual bricks, coupled with the fact the picture they have on the website of the partially constructed collection looks kinda like this [google.com] is rather disturbing.

  • by GillBates0 (664202) on Friday December 17, 2004 @11:48AM (#11116793) Homepage Journal
    the couplers are actually able to transmit data through the extremely thin layer of air between one brick and the next

    the term "air borne viruses".

  • Call me a luddite, but I find the hype around "new and neat" technologies a bit worrying. To me, the obvious problem of having to disassemble an entire block of these things just to get to one failed device is an indication of flawed design.

    It's a neat idea just like hotswapping was, but it's going to be a while before it's affordable and reliable. I'll wait for that, I think. Until then, I'll just try to imagine a beowulf cluster of these things and stick to my tried and true server setup, sans bricks.
    • Imagine a beowulf cluster. Just try not to think about replacing a brick at the bottom of the stack...
    • You don't worry about a single brick. Consider a wall of these things like a RAID array made up of a few hundred drives. The failure of one cell/drive/brick is irrelevant, and as the TFA says, you ignore it until its scheduled to be replaced.

      Besides, you don't have to assume they're in a wall. There are plenty of configurations that could allow you to easily access whatever bricks you need.

      It doesnt seem as though the bricks need to stay in the same position either, so you can pull from the bottom, plo
    • I'll wait for that, I think.

      Yes, you will... This is a *prototype* still.

      You know you're getting old, btw, when everything new prompts the question "why should I care?" You can stick with your rods/hogshead while the rest of us move on.
  • by Number44 (41761) on Friday December 17, 2004 @11:50AM (#11116815) Homepage
    Caveat: I'm an employee of IBM's Storage Systems/Technology group, but I'm not working on that particular project. I am only discussing things that were in the previous press releases about this product so you won't get anything confidential out of this post.

    The original intent, when this was previewed a year or so ago, was that dead bricks would just stay in there and not require disassembly. See http://www.almaden.ibm.com/StorageSystems/autonomi c_storage/CIB_Hardware/ [ibm.com]
    for some more discussion.

    The concern I have (my role in storage systems is error isolation and recovery) is that when you are running all these individual cubes, each one is trying to isolate what might have happened to its peers (or to itself) and when an error starts to propagate from one cube to the next, which it will invariably do sometime, you could end up with multiple cubes saying "IT'S THAT GUY!" and shooting him (ie, cutting him off) when in fact it was yet ANOTHER cube that started the whole thing by corrupting a message and is innocently sitting there not showing any failures.

    So assuming that situation occurs, you have 1 failed and 1 not-failed cube which need to be fixed, and shutting off the failed one requires removal, which isn't part of the service model for the product. Needless to say, I'm going to be REALLY impressed when they get this working. My peers at IBM are awesome when it comes to storage, so I'm actually not being sarcastic when I say that.

    • by Anonymous Coward
      Ask yourself how biological systems handle error propogation?
      • That's a pretty trite answer but I'm on vacation, so I'll respond.

        Let me throw it back at you this way: assume you are SPRINTING a marathon, one that lasts a whole year. You are contractually obligated to run as fast as you can, at peak speed from the start to the end and you can't stop for anything, you have to eat and drink and eliminate on the run.

        Now let's say you catch a cold, or the flu in the middle of the race. Your biological system starts to steal resources to increase white blood cell counts,
      • Is that like when chickens see blood on a comrade in the henhouse?
  • Deja Vu? (Score:1, Funny)

    by rocket97 (565016)
    I remember reading about this a year or so ago.... ON SLASHDOT....
  • I imagine a plausible idea to solve the "middle brick" failure would be to have trays of bricks that you can slide out in the event of failure.

    A simple RAID 5 type system would be able to mitigate the potential loss of a tray of bricks while the dead brick was swapped.

    A more intelligent system may be able to actively monitor the health of each brick, detect a failure, shuffle data around, and plot a path on a screen to the dead brick.

    ie. "To replace brick 1234, please remove brick 2345 first. Then remo

    • If you really have a huge grid, just leave the dead brick there. As long as you have a way to switch it off, what's the big prob?

      An alternative is if having a lower storage density isn't a problem, then you could make the cooling channels bigger and the you could have mechanisms or robots to move the dead bricks out via these channels.

      AFAIK google just leaves their faulty PC nodes in place, and has schedules when the faulty nodes are cleared out.

      As long as you have a reliable and effective way to isolate
    • ie. "To replace brick 1234, please remove brick 2345 first. Then remove 4532. Then remove 9786. Then remove 4575. Now remove 1234, replace. Now reinsert previously removed bricks"

      Do not deviate from the prescribed route, or data and/or user termination may result. Please see the included reference DVD [imdb.com] for more information about navigating to broken nodes.
  • So it's just like a fancy RAID setup. Very Borg-like ;)

    What the advantage storage-wise? If it spreads the data across all the bricks wouldn't you lose a lot of storage space? I guess the point is ease of use.

    The water cooling would be interesting to see, especially for the center Brick in a pile. That also defeats the purpose of ease of use if the center brick fails.

    I don't have any experience with RAID. I'm too poor :(
  • My interchangable data storage bricks are my computers.
  • No mention is made of what happens when a brick in the middle of the cube needs to be replaced and the whole thing needs to be disassembled

    IIRC, their idea is that when a brick dies, you just leave it there. Imagine a big room as a circle. You build bricks around the circle starting in one corner of the room. As you "upgrade", you stick new bricks on to one end. If a brick dies, screw it, just stick another one on at the end if you need it. When you run out of space at the end of the circle, you start dis
  • "No mention is made of what happens when a brick in the middle of the cube needs to be replaced and the whole thing needs to be disassembled." - http://www.hasbro.com/jenga/ [hasbro.com]

    • You take a brick from the bottom and you put it on top,
      You take a brick from the middle and you put it on top.
      That's how you build the tower; you just don't stop.
      You keep building that tower putting blocks on top.
      It teeters and it totters, but you don't give up;
      It weebles and it wobbles, but you build it on up.
      You take a brick from the bottom and you put it on top,
      You take a brick from the middle and you put it on top,
      'Til someone knocks it over, and that's when you stop...

      'Cause your ass got fired.

  • This is stupid.

    This comes from a research lab where people have too much money and too many signs everywhere that say, "Think of a new idea." Current storage solutions aren't so broken that they need this kind of fix. If you want to be so frickin clever why don't you work on some high density, cost effective way to eliminate moving parts from storage.
    • by Number44 (41761) on Friday December 17, 2004 @12:01PM (#11116948) Homepage
      Wait one damn minute here.

      As they say in the army: "If it's stupid but it works, it's not stupid."

      We spend billions on research, and only a fraction of the technologies that we invent (yes I am an IBM employee) turn into real products, but that's the whole idea.

      Think of copper interconnects. Think of the 'pixie dust'. Think of the Power5 architecture. All of these things are working their way into YOUR badass PC of the future. These weren't the only things we came up with, but our process DID create them.

      We must look really far forward and not sit on our laurels, that's a great way to lose the game against our competitors.
  • by jejones (115979) on Friday December 17, 2004 @11:54AM (#11116858) Journal
    ...nother brick in the mass storage unit.

    Darn. Doesn't scan.
  • by Anonymous Coward
    IBM Makes Progress with Storage 'Bricks'
    By John Pallatto
    December 16, 2004

    IBM has made progress over the past year in developing a new water-cooled, modular mass storage system designed to be highly fault-tolerant and make more efficient use of electric power and cooling capacity.

    Called CIB (Collective Intelligent Bricks), the storage system is under development at IBM's Almaden Research Center in San Jose, Calif. IBM officials discussed its work on the prototype intelligent brick storage system with gave
  • by Yartrebo (690383) on Friday December 17, 2004 @11:54AM (#11116865)
    You can already fit about 2TB is a large desktop case. These cubes only store 60GB/cube.

    I would rather use loads of desktops, each with a local RAID array. Depending on bandwidth needs, I would either connect them to a common gigabit ethernet router (not so scalable) or set up dedicated routers in a tree heirarchy with larger and larger pipes as you get near the root.

    Scalability should not be too much of an issue, and with 10 or so HDDs in a single case, you don't waste too much electricity.

    Naturally, they would be running Linux.
  • by lxs (131946)
    If I had patented this idea when I had it ten years ago I would have been rich! (Let's for the moment gloss over the fact that I'm too dumb to design a working prototype.)
  • I think they should get Frank Gehry working on some new sculptural/architectural designs with this technology, so companies can go back to the good old days of showing off their data center to the world with a huge wall of glass. Aww, screw it, just cover the whole thing with titanium plates. Same effect.
  • ...Ice Cube Storage Bricks...

    In addition to storing corporate data, they play rap music [donmega.com] and scratch records.

    When are they coming out with Snoop Dogg Storage Bricks?

  • Is an easily removable drive really that great of an idea? What if I trip on the power cord and knock the whole stack over? It seems to me that there is some benefit derived from drives that are securely in place.

    I think that the real invention here is not the drive array itself, but the connector that is used. This would be a great way to dock things like handheld devices, cell phones, and cameras. It would also be great for portable media. It seems like it could be called "electrical connections fo

  • by nmec (810091)
    Imagine a beo....

    ahh forget it you know the rest
  • Now I understand what the point of this is, that if you have some room with dimensions W*L*H you can definitely fit more space into it if you fill the entire room with cubes, as opposed to just covering the walls with racks.

    But as a people are mentioning, what about maintenance. You have a big stack of cubes, with something wrong in the middle, you have to dissassemble a bunch to get at it. And even if the data is mirrored on another brick, what happens when you have to remove that brick to get at the

  • This reminds me of the old Gerry Anderson puppet-based TV show Terrahawks. The bad guys had evil cube shaped robots, that could stack on each other to make big laser cannons, and the like.

    When our data bricks start to kill people, we'll know IBM's up to something :)
  • by enosys (705759) on Friday December 17, 2004 @12:12PM (#11117060) Homepage
    I don't see what's the point of sending data through the air when you have to make connections to the bricks anyways. Each brick has to have a power connection and that isn't through the air. They could easily just add a high speed serial interface to that connector.

    They also talk about water cooling this system. Those connections are even harder to deal with. Hoses are always going to be thicker and more difficult to handle and there's the possibility of leaks, especially when connecting and disconnecting hoses.

    • I don't see what's the point of sending data through the air when you have to make connections to the bricks anyways. Each brick has to have a power connection and that isn't through the air. They could easily just add a high speed serial interface to that connector.

      The high speed connection is something you simply don't want anywhere near the power connection. Power is noisy beyond any comprehension when you're talking high speed communications and data integrity. So you don't want the second connect

    • I know it is asking a lot to read the article, but you could have at least looked at the picture.

      It clearly shows the cooling system, which is made of sealed aluminum columns that the bricks are slid over. There are no hoses and no connections to spring a leak.

    • I think the point is simplicity in management:
      More info [ibm.com] provided by IBM.

      No wire management
      No network management
      No device management

      It should be no more difficult to administer than a pile of Lego bricks.

      I think with this design they've accomplished this.

      Read up more about it. I think all your issues are addressed and moot.
  • No mention is made of what happens when a brick in the middle of the cube needs

    Maybe a solution to something like this would be to have some kind of rubik's cube like configuration where the data would still be accessable as long as it was connected to at least one other block, but you could move the blocks around in a preset way along "rails"
  • by LionKimbro (200000) on Friday December 17, 2004 @12:37PM (#11117385) Homepage
    I know that they are evil, because I've seen what they do.

    Just watch Laputa. Near the end of the movie,- you see that Laputa is composed of these very same intelligent brick computers.

    In answer to the question: "How do you replace the broken bricks in the middle?" ...the answer is: It's all automatic. The bricks rearrange themselves in mid-air, and the broken bricks fall out.

    It's true.

    Just watch the movie; It explains everything.
  • Many years ago, there was a toy electronics kit like this. Each component was sealed in a little plastic brick, and the bricks were connected by magnetized plates. You could put together an AM radio, and it looked like a Scrabble board.
  • Soon, you will have a good excuse excuse for playing Enigma, Sokoban, or other box shuffling clones: "I am just excercising a failure recovery procedure for the cube in the middle, sir."

    You can even play a breakout with a baseball in the real world with that technology.
  • I wonder how long it will take for us to get to a holographic (graceful degradation of bytes if a bit goes bad,) type storage.

    Instant (well light speed through a solid critalline medium) retrieval would be just what the newest DB2 database would need.

    I smell copyright agreements in the wind.
  • I KNEW this sounded familiar!

    See [slashdot.org] here.

    From this current story, it sounds like they've made some improvements, but the two are basically the same...

  • I don't expect reporters (at eweek or elsewhere) to accurately report on technical details, but it would be nice if they could at least get names of people spelled correctly.
  • I recently watched some video feeds showing a prototype Cube [imdb.com], which was then advanced to a Hypercube [imdb.com] design. I had no idea that IBM had managed to miniaturize the system so much, or that they were even working on this project.

  • From the photo, it looks like they're using Opto22 [opto22.com] I/O modules as part of the system. I didn't think I'd ever see those things used in a computer setup! It looks like a fun project.

"Pascal is Pascal is Pascal is dog meat." -- M. Devine and P. Larson, Computer Science 340

Working...