Slashdot Mirror

← Back to Stories (view on slashdot.org)

RHIC Computing Facility Crosses the 1 PB Mark

Posted by michael on from the infoglut dept.

Martin writes "Brookhaven National Lab's RHIC Computing Facility (RCF) announced yesterday that the amount of data from the physics experiments at the Relativistic Heavy Ion Collider (RHIC) crossed the 1 PetaByte mark. A mail that was sent around to the RCF users contained a GUI screen shot (which is removed from the mail archive) that showed the number of MegaBytes transferred as 1,000,400,143. The RCF web pages have some pictures of the tape silos that hold the data. RHIC and the experiments have been discussed on ./ a few times, look here, here, and here."

51 comments

  1. I think that they can handle a few slashdotters. by kabocox · · Score: 1

    Well, if they have more than a PB, then they should easily handling a slashdotting!

  2. Just how big is a petabyte... by MissMarvel · · Score: 3, Informative

    Thanks to the definitions page:

    A petabyte is a measure of memory or storage capacity and is 2 to the 50th power bytes or, in decimal, approximately a thousand terabytes.

    A terabyte is a measure of computer storage capacity and is 2 to the 40th power or approximately a thousand billion bytes (that is, a thousand gigabytes).

    A gigabyte is a measure of computer data storage capacity and is "roughly" a billion bytes. A gigabyte is two to the 30th power, or 1,073,741,824 in decimal notation.

    What's bigger?

    An exabyte (EB) is a large unit of computer data storage, two to the sixtieth power bytes. The prefix exa means one billion billion, or one quintillion, which is a decimal term. Two to the sixtieth power is actually 1,152,921,504,606,846,976 bytes in decimal, or somewhat over a quintillion (or ten to the eighteenth power) bytes. It is common to say that an exabyte is approximately one quintillion bytes. In decimal terms, an exabyte is a billion gigabytes.

    1. Re:Just how big is a petabyte... by zelphior · · Score: 4, Informative

      Actually, data storage isn't measured in base 2. A megabyte is 1,000,000 bytes. The prefix mega indicating 10^6. A gigabyte is 10^9 bytes. A Terabyte is 10^12 bytes. A petabyte is 10^15, or one million billion bytes.

      --
      If you can read this then I forgot to check "Post Anonymously"
    2. Re:Just how big is a petabyte... by Anonymous Coward · · Score: 0

      In reality that wasn't how they were invented though. Those were just the close approximations to what in realtiy were base two numbers.

      Quickshot

    3. Re:Just how big is a petabyte... by Anonymous Coward · · Score: 0

      I think you're in the minority.

    4. Re:Just how big is a petabyte... by A55M0NKEY · · Score: 3, Insightful

      Avogadro's number is approx 600,000,000,000,000,000,000,000 atoms per mol. If you were to store an an exabyte of data in one mol of material then each byte would have a budget of about 600,000 atoms. That may be doable...

      --

      Eat at Joe's.

    5. Re:Just how big is a petabyte... by mnmn · · Score: 1

      Youre right. They havent crossed the petabyte yet. I cant wait till Maxtor comes out with Petabyte IDE disks, my video collection will reside on it. I'm sure theyll come out with games that will take 25% of THAT drive.

      Next is the Exabyte. Whats after that?

      I'm also curious why they use tapes and not just rows and rows of cheap IDE disks. Each IDE carrying 250GB at $250 will cost em $1 million plus taxes, shipping, backplane etc, and of course one full-time guy to constantly replace the failed disks with new ones. I think that should be cheaper and more reliable than mountains of tape.

      --
      "Give orange me give eat orange me eat orange give me eat orange give me you." -Nim Chimpsky
    6. Re:Just how big is a petabyte... by KnightStalker · · Score: 4, Informative

      It's probably worth mentioning that of course this is a redefinition of the traditional meanings and will probably irritate the same people who object to the phrase "Native American". But as in that case the traditional usage is entirely wrong. New standards are slowly being adopted. Although I rarely use them myself, I think using "mebi" etc. are preferable to coopting the SI prefixes. (Knuth doesn't like them).

      --
      * And remember, it's spelled N-e-t-s-c-a-p-e, but it's pronounced "Mozilla."
    7. Re:Just how big is a petabyte... by dnahelix · · Score: 1

      "Actually, data storage isn't measured in base 2" ... anymore so marketing can make you think you're getting a bigger hard drive than you really are.

      --
      Slashdot Eds Link Anonymous Posts With Logged Posts
      They Are Vermin Feeding On Each Other's Feces.
      I Hate \.
    8. Re:Just how big is a petabyte... by Zathrus · · Score: 2, Informative

      one full-time guy to constantly replace the failed disks with new ones

      And this is why they don't. Tape is vastly more reliable than HDs are, particularly when you're talking about this much data. As long as you don't need realtime (or even near realtime) access to the data then tape is the better choice. Even with that much data a robotic tape server can serve you the data from any one tape with only a few seconds of access time plus however long it takes to spool the tape. Probably under 5 minutes for any given data segment.

      BTW, if you want a more accurate cost analysis, you have to go RAID. That'll jack your prices up considerably, and now large segments of your array will be down at any given time in order to restore the continuously failing drives.

    9. Re:Just how big is a petabyte... by Anonymous Coward · · Score: 0

      I don't like them either.
      Mebi sounds so fucking stupid.
      If I had to choose, I'd go with Knuth's suggestions.

    10. Re:Just how big is a petabyte... by Idarubicin · · Score: 3, Interesting
      Avogadro's number is approx 600,000,000,000,000,000,000,000 atoms per mol. If you were to store an an exabyte of data in one mol of material then each byte would have a budget of about 600,000 atoms. That may be doable...

      It's eminently doable. That's 75,000 particles (atoms or molecules, depending on the species used) per bit--a huge number, still.

      The problem comes in storage and readout. If I have to flip bits manually using a scanning electron microscope, that's no good.

      On the other hand, let's assume that the work can be done optically, using a scanning laser. Take something the size of a vitamin E molecule; it absorbs visible light readily. Lying flat on a substrate, it would have a surface area (*very* roughly) of about 75 square angstroms. 75,000 of those would cover an area of about five million square angstroms. If arrayed over a square, that's about 240 nanometers on a side, or the diffraction limited spot size of a 480 nm wavelength laser.

      Yep, it could be done. A monomolecular layer on a flat substrate; about half a kilogram of molecule. Perfect--a petabyte for your laptop! But--that would cover a total square area of six or so square kilometers...somewhat awkward to scan with a single laser, and a bit clumsy to carry.

      --
      ~Idarubicin
    11. Re:Just how big is a petabyte... by Anonymous Coward · · Score: 1, Informative

      After the exabyte would be the zettabyte (10^21) then the yottabyte (10^24). As far as I know we have not defined any prefixes above yotta since there are very few things that it would be usefull for.

    12. Re:Just how big is a petabyte... by NonSequor · · Score: 3, Insightful

      But it has to do with more than marketing. That's just a fortunate coincidence which they are more than happy to make use of. Base 2 measurements are used for RAM because most RAM produced holds a power of 2 number of bytes. This is not true for many other storage devices, including hard disks.

      Personally, I think that defining a kilobyte as 1024 bytes is only useful very little of the time. In general it is less convenient than displaying units in terms of the number system that we have been taught to use since we were young.

      The ultimate goal of any software designer should be to make the software conform to the user's whims. Too often people lose sight of that and adapt themselves to the computer's arbitrary needs instead.

      --
      My only political goal is to see to it that no political party achieves its goals.
    13. Re:Just how big is a petabyte... by Gamasta · · Score: 1

      That'd be the definitions of someone who sells HDs for them to look bigger. To reach a decent Petabyte I think it requires 1 073 741 824 Megabytes (2^30), not the 1 007 ... ... as pointed out in the article or 10^9 as in the parent. (all in MB)

      I also think people should remember that 10^6 bytes is just close to a megabyte. No need to alter the definitions. Most of the times, you just need approximations anyway. When you need the exact amount of bytes (like, when you want to say: I passed a PB!) you do the math.

      --
      reason defies logic
    14. Re:Just how big is a petabyte... by Sgt+York · · Score: 1
      The media of a modern hard disk is normally a thin layer of iron oxide over an aluminum substrate. I don't know how much iron oxide is typically used in hard disks (any engineers know?), but 1 mol of Fe2O3 would be 160g (~5.6 oz).

      I imagine that the thin coating of iron oxide on the platter of a hard drive actually represents orders of magnitude less material than 5.6 oz.

      I think we may have already acheived and surpassed this kind of information density. Does anybody know how much mass is represented by the media layer on a hard drive?

      --

      There is a reason for everything. Sometimes that reason just sucks.

    15. Re:Just how big is a petabyte... by Idarubicin · · Score: 2, Interesting
      I think we may have already acheived and surpassed this kind of information density. Does anybody know how much mass is represented by the media layer on a hard drive?

      Off the top of my head, I don't know the mass of the media layer on a hard drive, but it's easy enough to find the areal density of the data.

      IBM's 'pixie dust' (AFC) technology promises densities of up to about 100 billion bits per square inch. That's (roughly) 1000 square angstroms per bit. In other words, about an order of magnitude more area than in the grandparent post's fanciful thought experiment. Not only that, but the layer of iron oxide used in hard drives--though very, very thin--is not monomolecular.

      Note that the great grandparent poster was asking about an exabyte of storage--1000 petabytes, or a million terabytes. Shaving three orders of magnitude off of that makes the problem much more manageable--though RHIC has still done a heck of a job accumulating a petabyte of storage space.

      --
      ~Idarubicin
    16. Re:Just how big is a petabyte... by Anonymous Coward · · Score: 0

      Huh. I thought that only stood for transmission rates, e.g. 10 megabits per second would be 10,000,000 bits per second. Around here we call decimal megabytes "japanese megs", and point our fingers at them in a derisive manner.

    17. Re:Just how big is a petabyte... by Anonymous Coward · · Score: 0
      The ultimate goal of any software designer should be to make the software conform to the user's whims. Too often people lose sight of that and adapt themselves to the computer's arbitrary needs instead.

      You, sir, are full of shit. The task you describe is patently impossible to achieve on account of the users' whims being tied to their physical-psychological selves, causing said whims to fluctuate with emotions and state of mind. A computer program, as it is currently defined, cannot be that flexible without severely compromising functionality.

    18. Re:Just how big is a petabyte... by NonSequor · · Score: 1

      What I'm talking about is just an ideal. If I have some sort of task I wish to complete, I want to be able to set the computer to the task without having to reformulate it for the computer's sake. Computer programs should be designed to accomodate as wide a variety of needs as possible (within the scope of their function of course).

      The best example of a program that does well in this regard is Mathematica. It allows me to implement a wide variety of algorithms involving a wide variety of mathematical objects and for all of the tasks that I have encountered, I do not have to concern myself with the details of the implementation of these mathematical objects.

      The user should never be required to understand aspects of the implimentation unless there is absolutely, positively no other way for them to accomplish their task without doing so.

      Of course, these are matters of philosophy, but I feel justified in these opinions since ultimately computers are made to be tools and it should be as easy as possible to use them for whatever we wish.

      --
      My only political goal is to see to it that no political party achieves its goals.
    19. Re:Just how big is a petabyte... by SagSaw · · Score: 1

      It depends on who is doing the measuring. Companies who make storage media often use the system you describe, while software actually performing the reading and writing most often use 2^10 = kilobyte, 2^20 = megabyte, etc. since it reflects what is (more or less) actually happening on the media.

      --
      Come test your mettle in the world of Alter Aeon!
    20. Re:Just how big is a petabyte... by mdenham · · Score: 1

      When you start getting to equipment like this, though, areal density just doesn't cut it anymore - you're probably stacking hundreds (if not thousands) of "platters" for this.

      Bits per cubic centimeter is a perfectly good measurement for things like this (it works for current HDs as well, but even a 300GB HD right now only has a density of 2.07 * 10^10 b/cc [heh, "only"]).

      BTW, I was hoping this was referring to IBM's current R&D project that was in SciAm around the beginning of last year (nanodrives) - which will probably lead up to areal densities of 10 Tb/sq.in. (100x what the parent's link is capable of) and volume densities of 5 Pb/cu.in. or so... which would make a 1 exabyte device take up roughly half the size of your current minitower system's case (a box 8" x 16" x 13" would hold it, but not any sort of cooling equipment or power supply). ...and now that I've rambled on and on, I should probably point out that this kind of setup is still 10-15 years away and will probably run around $50,000 anyway at that point. (First site to get one of these: Google, so they can do full-out archives of every site. I predict government nastiness against them not long afterwards. :->)

  3. in the health care industry by jjshoe · · Score: 1

    and we have more of those silo's then they do :)

    --
    -- botsex is {grep;touch;strip;unzip;head;mount} /dev/girl -t {wet;fsck;fsck;yes;yes;yes;umount} {/de
  4. Weeee by NanoGator · · Score: 4, Funny

    "RHIC Computing Facility Crosses the 1 PB Mark"

    Tomorrow's story:

    "RHIC Computing Facility Slashdotted, Crosses the 2 PB Mark." Some will complain of dupes, others will say RTFA.

    --
    "Derp de derp."
    1. Re:Weeee by flewp · · Score: 1

      I'm waiting for them to cross the PB&J mark.

      --
      WWJD.... for a Klondike bar?
  5. The obvious: by jtosburn · · Score: 2, Funny

    showed the number of MegaBytes transferred as 1,000,400,143

    That's a lot of copies of MyDoom!!!!!!

    With apologies....I'll STFU now.

  6. Interresting take from my co-worker by Captain+Rotundo · · Score: 3, Funny

    We are but a few miles from BNL, so I thought I'd mention this interresting fact to my co-workers, one of them said "I thought a 'peda-bite' had something to do with Michael Jackson" :)

  7. Time to FIGHT! by yardbird · · Score: 3, Funny

    We all must FIGHT Wal-mart and the other proponents of RHIC! This 1 PB milestone is yet another erosion of our privacy and will not.. what? Oh, never mind.

    --
    Free, legal music for iTunes users.
    1. Re:Time to FIGHT! by Cragen · · Score: 1
      Is that the number of bytes that can be processed (bitten off, so to speak) while one eats a PBJ? (Which, by the way, in my 12-year-old son's case, is darn near one second!)

      cragen

  8. "Mail" is a mass noun by Pingster · · Score: 2, Informative

    Some nouns can be counted, like "two sticks". Others cannot, like "rice".

    "A mail was sent around" is just as grammatically incorrect as "She ate a rice" or "That boy has a courage". The poster should have written "Mail was sent around" or "A message was sent around".

    1. Re:"Mail" is a mass noun by daeley · · Score: 1

      Hell, they could have said:

      "A mail sent to RCF users contained..."

      and been much more consise and spiffy.

      Eschew surplusage!

      --
      I watched C-beams glitter in the dark near the Tannhauser gate.
  9. Luigi Mario's comment on the situation. by L.+VeGas · · Score: 0, Offtopic

    If I had a petabyte me in a silo, I woulda shoota it in the head!

    --
    Best Windows Freeware
    1. Re:Luigi Mario's comment on the situation. by Anonymous Coward · · Score: 0

      Sounds more like Jar-Jar Binks

  10. Image link by infernow · · Score: 2, Informative

    Here's a direct link to the image, if you're feeling lazy.

    --

    that that is is that that is not is not

    1. Re:Image link by Anonymous Coward · · Score: 0

      What's with the bevels? And people call Windows ugly...

  11. Mention it not! by presearch · · Score: 1

    The Relativistic Heavy Ion Collider??
    It's nothing compared to the Great Hyperlobic Omni-Cognate Neutron Wrangler of Ciceronicus Twelve.

  12. My first spelling flame on /. by Crash+Gordon · · Score: 1

    But I really think it's justified:

    the experiments have been discussed on ./ a few times

    Maybe we're supposed to read it backwards to reveal a secret message, like "Taco is Dead" or something?

    1. Re:My first spelling flame on /. by Anonymous Coward · · Score: 0

      i read the comments just to see all the ./ rants & raves and not-funny comments. Sadly, all I found was this one.

  13. screen shot *is* available in the archive by jpn · · Score: 2, Informative

    The screenshot attached to the email message is available here.

  14. Nice Racks. by stevesliva · · Score: 1

    Mmmmm, rack-mounted.

    --
    Who do you get to be an expert to tell you something's not obvious? The least insightful person you can find? -J Roberts
  15. Compression by DarkHand · · Score: 2, Funny

    Someone needs to introduce them to a little company called PKWare...

  16. Waste of tax dollars!!! by DAldredge · · Score: 1

    No one needs that many MP3's and that much porn!

    1. Re:Waste of tax dollars!!! by Patrik_AKA_RedX · · Score: 1

      Yeah! No one needs more than 640kb.

  17. Hmmmm, a petabyte... by Anonymous Coward · · Score: 0

    Were they transfering an RMS speech about GNU/Linux?

  18. Re:I think that they can handle a few slashdotters by Josh+Booth · · Score: 1

    They'd only stand a chance if they had a petabit network connection with a petahertz Pentium 4 on the other end. The petabytes of storage is for the log files.

  19. Big Deal by Zork+the+Almighty · · Score: 2, Funny

    That's still only half the porn on the internet.

    --

    In Soviet America the banks rob you!
  20. Old TV screens by spectrokid · · Score: 1

    What the f*ck are these old B/W TV screens standing on their side in the middle of the table? Do they have some "legacy" apps running on an ENIAC?

    --

    10 ?"Hello World" life was simple then

    1. Re:Old TV screens by AlphaFreak · · Score: 1

      The TV screens are connected to cameras in the tape silo arms.

  21. Wow... by voss · · Score: 1

    http://www.rhic.bnl.gov/RCF/GuidedTour/HPSS/

    If you look at the third picture...isnt that an orgasmatron? ;)