Slashdot Mirror


Inside the Lucasfilm datacenter

passthecrackpipe writes "Where can you find a (rhetorical) 11.38 petabits per second bandwidth? It appears to be inside the Lucasfilm Datacenter. At least, that is the headline figure mentioned in this report on a tour of the datacenter. The story is a bit light on the down-and-dirty details, but mentions a 10 gig ethernet backbone (adding up the bandwidth of a load of network connections seems to be how they derived the 11.38 petabits p/s figure. In that case, I have a 45 gig network at home.) Power utilization is a key differentiator when buying hardware, a "legacy" cycle of a couple of months, and 300TB of storage in a 10.000 square foot datacenter. To me, the story comes across as somewhat hyped up — "look at us, we have a large datacenter" kind of thing, "look how cool we are". Over the last couple of years, I have been in many datacenters, for banks, pharma and large enterprise to name a few, that have somewhat larger and more complex setups."

137 comments

  1. Rendering by Anonymous Coward · · Score: 2, Funny

    Only a few boxen are used rendering and effects. The rest is to track and calculate sales of Star Wars merchandise.

  2. 300tb by Anonymous Coward · · Score: 1, Insightful

    Is that all? Most datacenters that house more than 1 large customer usually starts at about 300tb, nothing to write home about. Most customers using sap use a lot more.

    1. Re:300tb by morgan_greywolf · · Score: 1

      Is that all? Most datacenters that house more than 1 large customer usually starts at about 300tb, nothing to write home about.
      Yeah, I was a bit disappointed as well.

      By mid-year, my pre-production lab will have 150TB. Our production datacenter, just for PLM alone, has something like half a petabyte.

    2. Re:300tb by Anonymous Coward · · Score: 0

      300tb was referring to ILM's high speed storage, there's actually a bit more total storage than that figure.

  3. Am I the only who finds this funny... by kalpaha · · Score: 1
    passthecrackpipe writes:

    Over the last couple of years, I have been in many datacenters, for banks, pharma and large enterprise to name a few, that have somewhat larger and more complex setups."
  4. Hmm? by vladsinger · · Score: 1

    I'll just assume it runs linux. Did it say in TFA?

    1. Re:Hmm? by hjf · · Score: 1

      On Oracle Magazine ( http://www.oracle.com/technology/oramag/oracle/06- may ), they said they used Linux for their "render farm" (I hate the word farm, computers aren't cattle), but designs were made in other platforms (SGI, Mac...). Finally, everything, even every single rendered, uncompressed frame is stored on an Oracle database (which runs on Linux).

    2. Re:Hmm? by gEvil+(beta) · · Score: 4, Funny

      Nope. They run LucasOS. It's perfect for their needs, since it's constantly being updated to suit his vision.

      --
      This guy's the limit!
    3. Re:Hmm? by Anonymous Coward · · Score: 1, Interesting

      > everything, even every single rendered, uncompressed frame is stored on an Oracle database

      WTF? Jabba the blob is not impressed, why would they do that? Wouldn't it make more sense to store metadata in the db and the actual image data on XFS RAID?

    4. Re:Hmm? by notoriousE · · Score: 0

      A quick scan shows that they are running Solaris 8 guess they are living in the past :)

      --


      And then there was E
    5. Re:Hmm? by jones_supa · · Score: 1

      It runs SCUMM, of course.

    6. Re:Hmm? by ATMD · · Score: 2, Funny

      They're certainly living a long, long time ago.

      --
      Nobody else has this sig.
    7. Re:Hmm? by hjf · · Score: 1

      don't ask me. They claim to have a 300TB Oracle database. whatever works for them, right? anyway check the article I posted, maybe I misunderstood it.

    8. Re:Hmm? by Schmiggy_JK · · Score: 2, Funny

      Hopefully its security is better than that of the Death Star...

      --
      Insert something witty here...
    9. Re:Hmm? by elfurbe · · Score: 1

      "I hate the word farm, computers aren't cattle"

      If they were cattle, it'd be a render ranch. Render farm implies a soil metaphor to me. Every machine I add to my render farm is arable soil, waiting to be planted with precious digital seed to yield my crop of rendered data. A ranching metaphor is much harder to construct.

    10. Re:Hmm? by hjf · · Score: 1

      ok. first: what the fuck? second: "A farm is the basic unit in agriculture. It is a section of land devoted to the production and management of food, either produce or livestock." (from wikipedia).

  5. Silly ILM should Google it :-) by Anonymous Coward · · Score: 0

    I don't mean use the search engine, I mean drop the expense of rack cases and server boards for their render nodes. Google just velcro a bunch of cheap hardware to a shelf. If ILM did this, they'd get 2 nodes for the price of a 19" rack case alone.

  6. That's really not that large by 192939495969798999 · · Score: 2, Interesting

    There are many corporate data centers larger and more powerful than that, it is much more impressive if the entire thing can run one giant application. Still, I'm pretty sure that Google's new datacenter wipes its ass with a datacenter the size of this one.

    --
    stuff |
    1. Re:That's really not that large by rtaylor · · Score: 5, Funny

      Still, I'm pretty sure that Google's new datacenter wipes its ass with a datacenter the size of this one.

      I'm pretty sure Google's datacentre has evolved beyond the need for an ass.

      --
      Rod Taylor
    2. Re:That's really not that large by Paradise+Pete · · Score: 1
      I'm pretty sure Google's datacentre has evolved beyond the need for an ass.

      I think they needed some to negotiate that slippery slope in China.

    3. Re:That's really not that large by Zen · · Score: 1

      Yeah - that datacenter is nothing. I don't consider ours that big either, but the company I work for (non profit in the healthcare insurance industry) would be ranked around #40 on the global fortune 500 list if we were for profit.

      We have a couple PB in online storage just for our mainframe, much less online storage for Lotus Notes, a few thousand servers of varying OS's, speeds, and feeds, a large SAN that contains online backups for all of those servers, much less our tens of thousands of high density tapes stored in silos with psuedo-online storage.

      I'm not good with the actual numbers, but I know ours would blow this away without even blinking, and we're out of space and have already broken ground to double our size.

    4. Re:That's really not that large by sgt_doom · · Score: 1

      I'd have to agree. Ever check out Organized Crime's data centers? We're talking super hugh, here.....

    5. Re:That's really not that large by geobeck · · Score: 4, Funny

      ...I'm pretty sure that Google's new datacenter wipes its ass with a datacenter the size of this one.

      A conversation overheard recently over the ether:

      Lucas DC: Hi! I've got 11.38PB/s and 500TB!

      Google DC: Hah! I've pulled bigger queries out of my back end.

      ...although I'm not quite sure what that says about Google's "interfacing preferences".

      --
      Find environmentally and socially responsible products on http://buy-right.net
    6. Re:That's really not that large by straybullets · · Score: 1

      I know ours would blow this away without even blinking, and we're out of space and have already broken ground to double our size. supersized as it is, one datacenter is nothing when it's alone :)

      come back when you have multi site workload balancing coupled with a full activity recovery plan !

      --
      With that aggravating beauty, Lulu Walls.
    7. Re:That's really not that large by Zen · · Score: 1

      Yeah - that is already being worked on. That is the current top priority for the senior executive management. We expect it to be finished by late 2008.

  7. Meh....SDSC has 2 PetaBytes of online storage by Danathar · · Score: 3, Informative

    San Diego Super Computing Center (SDSC) has 2 Petabytes of online Storage with 400TB for researchers. They have 18PB of archival tape storage.

    Still....I like datacenters. The hum of equipment. 65 degree temps and lower. I once had my cube re-located to a tape library. Quiet...peaceful place

    http://www.enterprisestorageforum.com/hardware/fea tures/print.php/3634881

    1. Re:Meh....SDSC has 2 PetaBytes of online storage by wik · · Score: 1

      Hum of equipment? Either it's not much of a datacenter or your hearing is already shot.

      --
      / \
      \ / ASCII ribbon campaign for peace
      x
      / \
    2. Re:Meh....SDSC has 2 PetaBytes of online storage by fons · · Score: 1

      I hear you.

      All the blinking lights, the spaghetti of cables. I love it.

      I've actually never been in a datacenter. But I love to read articles like this one.

      Hopefully one day I'll get a tour in one of these myself.

    3. Re:Meh....SDSC has 2 PetaBytes of online storage by FuegoFuerte · · Score: 1

      Please, if you love the spaghetti of cables, NEVER go anywhere NEAR a datacenter I have to work in. Those who believe in spaghetti cabling should be strung up in it and left to die slowly, suspended above the air vents in the cold aisle so they dry out and preserve nicely as a warning to others who might be tempted to spaghetti-cable.

      Velcro straps are a wonderful thing. They should be used liberally in the cabling of a cabinet, to avoid this spaghetti you speak of.

      Oh, and touring a datacenter is interesting for about the first 5 minutes, if that. After that it's "hey, more blinkenlights. more cable. more cold air blowing up my legs out of the floor. more fan noise. can we go yet?"

    4. Re:Meh....SDSC has 2 PetaBytes of online storage by Danathar · · Score: 1

      Well come on! I was trying to be brief and poetic :)

    5. Re:Meh....SDSC has 2 PetaBytes of online storage by wik · · Score: 1

      What? I can't heeeaaaaar yooouuu! :)

      --
      / \
      \ / ASCII ribbon campaign for peace
      x
      / \
  8. Rhetorical bandwidth? by Peter+Cooper · · Score: 4, Funny

    Is that the speed you can talk at?

    1. Re:Rhetorical bandwidth? by Anonymous Coward · · Score: 0

      Nothing makes it more obvious that a person is a fuckwit than his misuse of common words in a technical article. I can't pay attention to all the specs the poster mentions, because he's obviously mentally handicapped.

  9. Another interpretation: by Uncle_Al · · Score: 1

    A rhetorical question does not expect an answer...

    ...so maybe "rhetorical bandwidth" is a nice way of saying that the data flows only in one direction? ;-)

    1. Re:Another interpretation: by ozamosi · · Score: 1

      Like half duplex or something?

      Or maybe it's what the Wifi-figures are. Rethorical Bandwith. "802.11g is 27mbps full duplex. That is 27mbps in each direction. So we have 27 rethorical mbps times two, which sums up to *drumroll* 54! :D"

    2. Re:Another interpretation: by Barny · · Score: 1

      Nope, its just UDP ;)

      Hey, maybe we could have a new mod code, +0 Rhetorical. Making it so no-one can post a reply to it ^_^

      --
      ...
      /me sighs
    3. Re:Another interpretation: by mrscorpio · · Score: 1

      Yeah, I think he means "theoretical" but just wanted to sound smart.

  10. I find it funny that Slashdot... by Animaether · · Score: 4, Funny

    ...would post this as a news item. Front page, too.

    Let's break this down submission down..

    "Hi. I found this article on the web that totally didn't impress me, I think they fiddled with the numbers to make themselves look better than they are, and overall I really couldn't give a shite."

    Yes. Obvious front page material for a Sunday!

  11. 300TB? by slashmojo · · Score: 1

    300TB of storage in a 10.000 square foot datacenter

    Can fit 300TB in a single rack these days.. or is that a 10 square foot datacenter?

    1. Re:300TB? by Anonymous Coward · · Score: 0


      Seagate currently do a 750GB 3.5" drive
      so 300TB / 750GB = 225 drives

      225 drives at 1.5" high each = 28ft

      so if we layed them out at say 8 drives per 1U rack unit wide = cabinet 3.5ft tall

      and they needed 10,000 sq ft for something that would fit under the stairs
      LOL

    2. Re:300TB? by Anonymous Coward · · Score: 0

      whoops math was a bit skew

      300TB/750GB = 410 drives

      410 * 1.5" = 615" / 12" = 51 ft

      51ft / 8 drives per rack = 6ft cabinet

      so it would fit next to the stationary cupboard

  12. Submitter by kevin_conaway · · Score: 5, Insightful

    Well passthecrackpipe, if you and your vast knowledge of large scale datacenters are not impressed with the story, why the hell did you submit it?

    1. Re:Submitter by Anonymous Coward · · Score: 2, Interesting

      Nomen est Omen.

    2. Re:Submitter by Vreejack · · Score: 1

      Let's play editor and re-word this summary

      Here is Nothing Interesting

      This place you never heard of before is so incredibly irrelevant, it's almost surprising. Their moderate hype is somewhat misleading; if I hadn't mentioned it you might have been fooled, had you cared.

      --
      "Will future ages believe that such stupid bigotry ever existed!" -- Ivanhoe
  13. Storage vs Archiving by Anonymous Coward · · Score: 0

    How do they Archive the movies? TFA mentions that Pirates of the Caribbean was 60tb.
    I work with post production for short, independent movies. I have my main RAID where I keep the movies while I work.
    After it's done, I archive the TIFF image sequence (that goes to transfered into film) in a HD. It's probably hard to archive 60tb. Do they just throw away the digital copy?

    1. Re:Storage vs Archiving by Anonymous Coward · · Score: 0

      Read and weep. Database in filesystem weenies rejoice, although I'm usually opposed it's a better solution than a full-blown RDBMS.

      Also worth noting is that ILM will probably have the entire Oracle source tree mirrored and termination provisions in their licensing deal. The vendor lock-in problem should not be an issue for ILM whereas a smaller house would be insane to do this.

  14. 10.000 square foot datacenter is SMALL by Secrity · · Score: 2, Informative

    10.000 square feet for a datacenter is not very impressive. The datacenter that I work in did a relatively modest 100,000 square foot EXPANSION which was the result of absorbing an adjoining atrium. I suspect that the power equipment and air handlers may take up 10,000 square feet.

    1. Re:10.000 square foot datacenter is SMALL by Anonymous Coward · · Score: 0

      10.0 square feet while small, is incredibly precise. I'd say my data centre at home is ~8 square feet but that's an off the cuff estimate. To know it's 10 square feet within 3 decimal places... wow.. just wow.

      I wonder how accurate their ruler is.

      -1 Facetious

    2. Re:10.000 square foot datacenter is SMALL by daverabbitz · · Score: 1

      I was wondering the same thing, why are they using european style numbers in feet, seems kind of strange to me.

      Unless they do mean 300TB in 10 square feet, that would be impressive!

      Now if they can just get it down under $20K and under 2kW, then that's exactly what I need at home.

      --
      What could be better than a jet powered motorcycle? http://www.youtube.com/watch?v=u8l6GTHLSWE
    3. Re:10.000 square foot datacenter is SMALL by Citizen+of+Earth · · Score: 1

      10.000 square feet for a datacenter is not very impressive.

      Indeed, I have a larger closet in my apartment!

  15. All that just to make Greedo shoot first by Anonymous Coward · · Score: 0

    What a fucking waste.

    George Lucas has jumped the shark.

    Then the shark ate him. Then shit him out. The shit washed up on a beach, dried out in the sun, and was pissed on by a dog.

  16. Can we find the drive Jar-Jar is on by $RANDOMLUSER · · Score: 5, Funny

    and format it?

    --
    No folly is more costly than the folly of intolerant idealism. - Winston Churchill
  17. That's really not that large-Viagrasize it. by Anonymous Coward · · Score: 0

    "Still, I'm pretty sure that Google's new datacenter wipes its ass with a datacenter the size of this one."

    And the NSA datacenter can pick it's teeth with the Google datacenter.

  18. OP doesn't seem very impressed... by been42 · · Score: 3, Interesting

    So why submit this if you don't like it? Why not at least title it "Lucasfilm thinks it's soooo great."? I'm sure you've seen bigger data centers, and you can type 500 lines of code a minute, and maybe you defeated a ninja in hand-to-hand combat, but for the rest of us "normal" nerds it's still neat to read about the machines that get the work done in a business. Of course it's hyped up, it's a press release disguised as news. Take it for what it is, relax, and try to imagine those 2,000 servers in a secret cave under your house, manipulating the stock market in your favor. That's what I do.

    1. Re:OP doesn't seem very impressed... by Capt+James+McCarthy · · Score: 1

      "Take it for what it is, relax, and try to imagine those 2,000 servers in a secret cave under your house, manipulating the stock market in your favor. That's what I do."

      Actually, I think these systems generate the 'Jabba the Hutt' like features of Lucas we see on interviews. Those chin ripples look so real.

      --
      There are no loopholes. It's either legal or it's not.
  19. RHETORICAL? by Anonymous Coward · · Score: 1, Interesting

    How about theoretical? *yawn*

  20. Penis.... er.... Data Envy? by Snydley+Whiplash · · Score: 2, Insightful

    Why all the negativity toward Lucas? Jar Jar's dead man, let it go. George said he was sorry already. I think it's a good story. It's absolutely fascinating to me to see how they make movies today, how much data gets pushed around, and how they make sure that the creative people have access to what they need, when they need it. And they do all this to support incredible time schedules, with boatloads of cash riding on every second. I don't know how anyone can say that this isn't an impressive operation. As for Lucas thinking they are so great... well, they pretty much are. I'd say that being organization that created the special effects for tons of blockbuster movies and being nominated for several major movie industry awards pretty much gives them some bragging rights.

    1. Re:Penis.... er.... Data Envy? by linguizic · · Score: 1

      This really has nothing to do with this discussion, but I feel it must be injected somewhere into it anyway:

      http://www.landoverbaptist.org/news0899/jar.html

      --
      Does this sig remind you of Agatha Christie?
    2. Re:Penis.... er.... Data Envy? by Anonymous Coward · · Score: 0

      You know that's a satire site, right?

  21. And they drive to work at 2400mph by viking80 · · Score: 2, Insightful

    300TB storage and 11 petabits/s bandwidth.

    This means

    A) they can push their entire storage through the network in 300*8Tb/(11Pb/s)=200ms.
    or
    B) the article author does not have a clue.

    I think an anlogy would be: I drive back and forth to work everyday, or 400 times a year. My speed on each trip is 60mph, so in a year my speed is 60x400 or 24000mph.

    --
    don't cut it off www.mgmbill.org
    1. Re:And they drive to work at 2400mph by Jesterthe3rd · · Score: 1

      It's more like "There are 10,000 cars in this city, driving at 30 mph, so there speed is 300,000 mph!"...

    2. Re:And they drive to work at 2400mph by jeremy_hogan · · Score: 1

      > I think an anlogy would be: I drive back and forth to work everyday, or 400 times a year. My speed on each trip is 60mph, so in a year my speed is 60x400 or 24000mph.

      I think the better analogy is: "You drive to work each day at light speed, despite work being less than an hour away." In other words, their entire data array can do the Kessel Run in less than 12 parsecs. Which is good if you are creating, sharing and batch rendering massive 3D and/or compositing fx files across a network.

    3. Re:And they drive to work at 2400mph by Guspaz · · Score: 1

      More like, in New York City, 10 million people commute to work each day (making up figures here), each traveling down the road at 50km/h. So the aggregate commute speed in New York City is 46% the speed of light!

  22. data center by ralph1 · · Score: 1, Interesting

    Guess they have not been to a hospital data center yet. Should check out someone like dow chemical.

  23. which one makes the story... i think its down. by Jackie_Chan_Fan · · Score: 1

    barf

  24. 11.38 petabits? by Nighttime · · Score: 4, Interesting

    As in reference to THX 1138?

    Of course, it could just be a coincidence.

    --
    I've got a fever and the only prescription is more COBOL.
    1. Re:11.38 petabits? by bgii_2000 · · Score: 1

      I agree, it just a joke.

    2. Re:11.38 petabits? by vladsinger · · Score: 1

      And of course, the article makes the same speculation.

  25. For all the knocks of this center by WindBourne · · Score: 2, Insightful

    I have to wonder how many systems they have? They accomplish a great deal with what is a fairly small area. I would guess that they each computer has major ram and is simply NFSed back to a central server.

    What I have found funny is the number of ppl who are speaking of how big their centers. Offhand, I tend to suspect that those centers could go on a MAJOR f%^&ing diet and need to have their budgets cut to a fifth. And finally, it is time to fire a bunch of the incompetents who can not run a tight center.

    --
    I prefer the "u" in honour as it seems to be missing these days.
    1. Re:For all the knocks of this center by Zen · · Score: 1

      I'm not following you here. Yes, I am one of those who responded with some rough stats about the datacenter I work at. I also stated that I didn't even think mine was that great (big was the word I used). Because it's not. But it beats the crap out of the Lucas one, which is the story, so when you can relate to it and build on the topic, then it is an ontopic post and adds to the topic of conversation.

      How can you state that other companies datacenters are too big and extremely wasteful when you have no idea what those companies do, what their legal departments say they need to keep (storage), what types/brands of bigiron they use which require massive amounts of space/cooling/power/storage, etc? How about executive level policies that dictate that servers should not run multiple apps? Now that one surprises many of my friends at other companies, but when they think about it, they wish that their company had a policy like that so that an app crashing does not take down another app. When a single hour of downtime in your datacenter costs your company over $4,000,000 not to mention loss of brand name status, competitive edge in mergers and acquistions, and other non-tangible costs, you tend not to sweat the 'small stuff' - like a $100M datacenter. It's definitely not overkill in the least bit with large companies. It pays for itself in 25 hours of downtime. A large company who dramatically cuts their IT budget and fires people is either one who is quickly going out of business, or one that is prepping themselves to be taken over by a larger company.

    2. Re:For all the knocks of this center by that+this+is+not+und · · Score: 1

      When a single hour of downtime in your datacenter costs your company over $4,000,000 not to mention loss of brand name status, competitive edge in mergers and acquistions, and other non-tangible costs, you tend not to sweat the 'small stuff' - like a $100M datacenter.
      Speaking as just a 'regular folks' person, that sort of organization sounds strikingly like a big "athletic supporter" for a few big-balls management types. As such, it needs to have the fuck crushed out of it.

      A large company who dramatically cuts their IT budget and fires people is either one who is quickly going out of business, or one that is prepping themselves to be taken over by a larger company.
      Or it's an operation that has been bought out by a larger company, who are flushing out all the wasteful bullshit that when on because the former management were stupid and overinvested in IT bloat.
  26. coldframes by Anonymous Coward · · Score: 0

    Back when cavebadgers were common pets and mascots, they kept the mainframe rooms pretty chilly. All those glaciers and stuff ya'know. The electric bill was cheaper then, too.

  27. Nothing compared to my Sempron rig... by gatkinso · · Score: 2, Funny

    ...running FC6 x64.

    Why? Because my rig has never so much as contained - much less rendered - an image of Jar Jar Binks.

    Pwned.

    --
    I am very small, utmostly microscopic.
  28. 300TB in 10,000 sqft is a lot? by willith · · Score: 2, Interesting

    The datacenter at one of my employer's satellite sites has four CLARiiONs, at 2 racks each, a 5-bay DMX-3, and a 4-bay XP1024, for 380TB raw, in 3,200 sqft, along with thirty racks of servers, a P595 mainframe, and several multi-rack computing clusters. There's plenty of cooling and it's really not THAT crowded. Managing to pack 10-12 racks of storage into a 10,000 sqft data center is not anything noteworthy.

    1. Re:300TB in 10,000 sqft is a lot? by Anonymous Coward · · Score: 0

      hate to burts your bubble but a p595 is not a mainframe, that is IBM's 64way unix box. I know this because I'm the guy that comes out to fix them.

  29. Save the cheerleader, use the Force... by Manchot · · Score: 1

    Now I'm disappointed. I had hoped Masi Oka would be working there.

  30. Get a clue retard by Anonymous Coward · · Score: 0

    Not every application scales out as well as google, retard. Google gets millions of requests per second that take relatively little computing power per request to process. In a two hour movie there are only (24 frames/second)*(60 seconds/minute)*(60 minutes/hour)*(2 hours)=172,800 frames to render out, but at a resolution of 4096x2160 pixels, each frame takes a while to generate.

    When you have to push around so much uncompressed image data, subdividing the rendering of each frame into work for several servers doesn't make sense because then you have to handle all the image data twice: once to render each piece, and again to send the pieces to another node and assemble them into a full frame. With the millions of dollars ILM has at their disposal, they probably have people on staff doing analysis more thorough than your google-fanboy handwaving. Why don't you shut your mouth unless you actually have a clue.

    1. Re:Get a clue retard by trimbo · · Score: 1

      but at a resolution of 4096x2160 pixels, each frame takes a while to generate.

      Where'd you come up with this resolution? I've never worked on a movie where the final rez was higher than 2K. I can only think of one set of elements I rendered at 4K -- a bunch of badly aliasing Mental Ray renders. A halfway decent renderer will let you get away with rendering at a lower rez than needed for the final comp.

      Not to say your point isn't a good one though. Google's velcro and duct tape solution to server farms isn't really appropriate for the needs of 3D rendering. Plus, visual effects studios just don't have Google money to throw at custom farm solutions. On their scale, it's much more effective to just pay Dell or HP to take care of it.

    2. Re:Get a clue retard by ATMD · · Score: 1

      Goddammit, as soon as I post in this topic I see something like this.

      Someone mod this troll down, please.

      --
      Nobody else has this sig.
    3. Re:Get a clue retard by Anonymous Coward · · Score: 0

      mental ray for production work is suicidal. PRMan is more than 10 times faster and the physical inaccuracy is irrelevant.

      Glass

    4. Re:Get a clue retard by Mysticalfruit · · Score: 1

      All I can think of is that it's their internal standard for a wide screen HD feed.

      Just an idea.

      --
      Yes Francis, the world has gone crazy.
    5. Re:Get a clue retard by Anonymous Coward · · Score: 0

      Who suggested that these nodes run different software than the current set-up? The comment was about hardware, about increasing capacity for less cost - the fastest hunk of junk in the Galaxy.

      > Why don't you shut your mouth unless you actually have a clue.

      Only a cock-smoker fails to practice what they preach.

    6. Re:Get a clue retard by Anonymous Coward · · Score: 0

      None of the companies I've worked at (or know about) get "HP or Dell to just take care of it".

      Everyone one of them (FrameStore-CFC, Pixar, Weta, ILM, DNeg, MPC, etc. etc.) roll their own solutions, both hardware and software.

      Also "Rendering below the resolution required for the final comp?"

      Are you just picking randoms words out of thin air? The idea of up-scaling a render for compositing is retarded.

    7. Re:Get a clue retard by trimbo · · Score: 1

      That's right. If you have a renderer that does adaptive supersampling decently (aka not Mental Ray), you can render below your final resolution and get away with it. It seems like you have a lot of experience, so I can't imagine that you haven't been somewhere at 5am trying to get 3 hour renders out for a post session at 9am. Those are the times you're thankful you have a renderer where you can actually get away with rendering some elements at .75 or .9 rez and still have them look good.

      And what the hell are you talking about "roll their own solutions, hardware and software"? If you watched TFV in TFA, you would have seen that ILM flashed Dell badges among others. And as everyone knows, Pixar was in bed with Sun for years. Granted, I don't really keep up with what other people buy anymore, and I can't speak for Weta, Framestore, and the other smaller shops you mention. The companies I've worked for had deals with HP, Compaq (nee Digital), and Dell (x2). They were all film studio size deals, which might explain the different experience.

      You should go on record instead of posting as an AC, I'd love to actually have an on the record conversation with someone else in the business.

  31. Hardly a coincidence by NthDegree256 · · Score: 2, Informative

    This is the Lucasfilm datacenter. That number finds its way into all sorts of Lucas-related material.

  32. But? by Anonymous Coward · · Score: 1, Funny

    Will it run Vista? Sounds like they might need to upgrade!

    1. Re:But? by that+this+is+not+und · · Score: 1

      There is yet another University surplus equipment auction coming up the end of March that I am looking forward to. Because I have enjoy messing around with older equipment. I am hoping that 'Vista' will push more good boxes my way at low-low prices. Not that aging x86 boxes is my main interest (unless it's REALLY old and runs CP/M-86 or Microsoft Xenix.) One of the things I specialize at the auction in is the weird old Unix stuff. Sun and SGI boxes that none of the 'jelly stain on the necktie' noneck bidders even understand, let along will bid on. "Can You Install Windows On That?" they ask incredulously as I cart the skids of gear out to the truck.

  33. 60TB a movie...300TB total? by vee_anon · · Score: 1

    Does anybody else find it questionable that he said Pirates of the Caribbean required approx. 50TB of storage, and the next one will require 25% more....but then goes on to say that there is total storage space of 300TB in the data center. Thats basically enough to store six movies of equivalent size to Pirates, so where are all the rest of the movies they make stored??

    1. Re:60TB a movie...300TB total? by FlunkedFlank · · Score: 1

      You mean the rest of the movies they have ever made or the rest of the movies they are making at the same time? As soon as a movie is done all of the data is offlined to backup storage. 300TB is for the 2-6 movies they tend to be working on at a time.

    2. Re:60TB a movie...300TB total? by Anonymous Coward · · Score: 0
    3. Re:60TB a movie...300TB total? by VENONA · · Score: 1

      Above, an AC posted a link to http://www.oracle.com/technology/oramag/oracle/06- may/o36lucas.html which sez the answer to your question is 'tape'. Makes sense, I suppose. Storing old movies which require TB don't sound like something to store on- or near-line. I doubt much of it is reusable, on a day to day basis. When you launch a major project (make Greedo shoot first or something) for it, then it's in the books, and you have a business requirement to fill on-line storage, acquire more if you need it, etc.

      --
      What you do with a computer does not constitute the whole of computing.
    4. Re:60TB a movie...300TB total? by UncleTogie · · Score: 1

      A thought I just had...

      If they DID have the storage needed to have ALL their films onsite, and there was a 'net or physical security breach, wouldn't their loss/exposure be a lot larger?

      Just a couple o' pennies worth...

      --
      Don't tell me to get a life. I'm a gamer; I have LOTS of lives!
    5. Re:60TB a movie...300TB total? by VENONA · · Score: 1

      Could be, but I doubt it. In the case of media stuff, the loss is probably proportional to immediacy. If a game, movie, CD, even an operating system (Google on Vista leaks) leaks widely, just as the thing is supposed to be ramping sales in huge way, it has to hurt, say, stock share prices.

      If it's old, and stolen copies are already widely available, the losses probably aren't perceived as so immediate and crushing. That's not to say those losses aren't harmful in the long run--just that they aren't necessarily *perceived* that way. The real figures would obviously vary on a case-by-case basis. The third installment of Pirates of the Carribean is obviously more immediately valuable than some random programmer's backup program.

      In general terms, the security gameplan would be to strictly limit physical or network access to the work in progress, and any ancillary data concerning it--budgets, cost and deliverables projections, etc., while the project is active. When the project is complete, take it offline, and require physical access--tape vault or something. When you do that probably goes back to immediacy. A year after the third installment of Pirates of the Carribean is out (probably much sooner, maybe *before* official release), perfect copies will be widely available.

      Which makes you wonder if backup media in a tape vault is even worthwhile, as a business case. The metadata might be worth more (licenses, tech notes, or whatever) than even the viewer content of an HD movie, which you can (probably safely) presume is going to be widely available soon after (at a minimum) release. Attacks against HD DVD (recently mentioned here on Slashdot), like all attacks, are only going to get better.

      Sorry if this seems incoherent. Thought-provoking topic for a security guy. But things are busy just now, and this is only Slashdot, after all.

      --
      What you do with a computer does not constitute the whole of computing.
  34. And it's in a national park by Animats · · Score: 1, Interesting

    There's considerable unhappiness in San Francisco about Lucasfilm's operation. It's in the Presidio, which used to be a military base and is now a national park. It's the only national park which has to make a profit, due to a Bush Administration deal. Letterman Army Hospital was torn down to make room for the Lucasfilm facility. The San Francisco Bay Guardian complains about this constantly, as they try to keep the Presidio from turning into an industrial park. The Lucasfilm move to the Presidio was something of a dot-com boom excess, when people thought SF was the place to be.

    Pixar, in Emeryville, Tippett, in Berkeley, and Dreamworks, in Redwood City, are the innovative animation companies in the Bay Area. And of course, there's EA, SCEA, and some other game companies. Lucasfilm doesn't seem to get much attention.

    There are data centers in San Francisco proper with far more storage, too. The Internet Archive has several petabytes of storage. There's a large colocation facility at the 6th St. offramp from I-280.

  35. Lucasfilm pay is mediocre too by rk · · Score: 2, Interesting

    They wanted me to move across the continent from a place with average cost of living and a 10 minute commute to work in San Francisco (right in the city, not even an outlying area) for about a 15% increase in pay. The only way I could afford that would be to take on a 2-3 hour commute and even then I'd have to run an even tighter ship, financially speaking, than I do now.

    I suppose they were counting on the "cool factor". The job was cool, but not so cool I was willing to stick a stake through the heart of my family. Right after this, I read that Lucas donates 170 million to his alma mater. Hey George, why not donate 10% less and actually pay your people something more since you're insisting on setting up shop right in the freaking Presidio?

    600 Tbyte of disk in total can't be right. I wrote an application a couple years ago that has 6 terabytes of disk allocated to it to cache its work. This was for a single app. Admittedly, we worked with fairly big data files where I was working, but I've got to think Lucasfilm's files are way larger than my 1-2 gig files.

    1. Re:Lucasfilm pay is mediocre too by MobileTatsu-NJG · · Score: 1

      "I suppose they were counting on the "cool factor"."

      That goes for artists, too. Ever since Star Wars, ILM and Lucasfilm have inspired a lot of people to get into the industry. The first place the apply to is ILM. My guess is they've got so many applicants just yearning to do something on a high-profile movie that they can get away with low wages. (or at least 'low' relative to the cost of living there...) I honestly don't know the people there actually manage to work there and stay afloat. I've heard stories of four to five people sharing a place and still having trouble scraping by. I personally think that if they're going to do that they should locate themselves somewhere where they don't have such ridiculous living expenses. But, as long as it's working, I don't see that happening.

      I dunno, this whole topic is sad for me. I'm at a stage now where ILM would consider hiring me, but I'd probably have to turn it down for the same reason you did. I've heard this same story several times now. It really makes me wonder how much talent they've let slip through their fingers. It also makes me wonder how they actually manage to pull these projects off.

      --

      "I like to lick butts!" by MobileTatsu-NJG (#32700246) (Score:5, Informative)

    2. Re:Lucasfilm pay is mediocre too by GnuDiff · · Score: 1

      Apparently there is much more talent around than previously thought?

    3. Re:Lucasfilm pay is mediocre too by MobileTatsu-NJG · · Score: 1

      "Apparently there is much more talent around than previously thought?"

      Yes and no. From what I understand, they have their work flow set up sort of like an assembly line. A bunch of people work on very small chunks of the project. It's boiled down to a point that not a lot of 'talent' is needed so much as a pair of hands to work the mouse.

      That's probably a gross over-simplification, but to me that sorta makes sense now. The work load is distributed to a LOT of people and there's more predictability and less error. Not the most fulfilling job I can think of, though. I've had several people tell me they'd never want to do that again.

      --

      "I like to lick butts!" by MobileTatsu-NJG (#32700246) (Score:5, Informative)

  36. Graphics processing power by nicolastheadept · · Score: 1

    The majority of Lucasfilm's processing power is used for Graphics generation for ILM (unlike say Google). I think the hidden message of this article is they could get a huge screen and projector, play, for example, Crysis on full settings including 64x Antialiasing and Anisotropic Filtering, at 4320p with 22.2 surround sound and say to Sony, "Thats TrueHD!"
    http://en.wikipedia.org/wiki/UHDV
    http://en.wikipedia.org/wiki/22.2

    --
    09 F9 11 02 9D 74 E3 5B D8 41 56 C5 63 56 88 C0
    1. Re:Graphics processing power by nicolastheadept · · Score: 1

      Just found myself another link of this http://www.nhk.or.jp/digital/en/superhivision/inde x.html

      --
      09 F9 11 02 9D 74 E3 5B D8 41 56 C5 63 56 88 C0
    2. Re:Graphics processing power by Anonymous Coward · · Score: 0

      well, the irony would be that they would be doing it with.. Sony projectors, heh. (likely, anyway). I have seen UHDV in person, using four overlapping sony SXRD projectors, and it is quite awesome (i cannot comment on the 22.2 sound-- it sounds good to me, but so does a $1k stereo.. film is my specialty).

      Also, playing realtime 8k material isn't THAT tough (like.. not "10000sqft datacenter tough"). Granted, it's not easy, but you could build a windows based setup to do it for just a few hundred thousand dollars (plus projector(s)). Your point is relevant though.. their storage and computing is specialized in manners that traditional storage facilities aren't.. but not any more specialized than similar render and post houses.

  37. Eh by khallow · · Score: 1

    I guess that depends on what the internal temperature of the machines will be at the hotest parts of the day. If the AC and outside thermal insulation isn't up to snuff, you might need to go into a day with some pretty cold temperatures just so your servers stay viable, heat-wise by the end of the day.

  38. Actually, it's impressive. Most impressive... by Boss+Sauce · · Score: 4, Interesting

    As somebody who (ab)uses that particular rig daily, the article misses the point about what's so awesome about the system.

    It's a good sized datacenter, but what it's able to support in processing ability is the impressive part, and that the fat bandwidth runs at capacity almost all of the time by the demands of processing jobs. Proprietary software doles out jobs 24/7 to thousands of procs all over campus-- including artists' desktop machines-- for heavy duty computation: rendering and simulation and whatever it takes.

    I can't imagine a facility where so many people are creating and pumping so much data around.

  39. Their datacenter has a droid! by AaronW · · Score: 3, Interesting

    I toured their new facility in San Francisco. They have over 300 10Gbps ports and all PCs are connected via gigabit. Their datacenter was 2/3 full of dual-Opteron servers running SuSE Linux (though they were considering switching). Their server room was spotless. No cables were visible anywhere, but I did see a Roomba moving about the floor. The fellow who ran it said that since they're ILM, they have to have droids.

    The facility was absolutely beautiful. When going between two buildings on an overhead walkway I saw the Golden Gate bridge with a nice orange sunset behind it. I wish I had my camera with me.

    They said that they have many dedicated OC-48 pipes to various studios and can handle just about any format, since every studio uses their own format. They convert it to their own internal format, which I believe they open sourced.

    When they moved from Skywalker Ranch, it was completely seamless. They had an OC-192 (10gbps) link running between the old and new facility as more and more equipment was migrated to the new facility but people continued to work at the old one.

    -Aaron

    --
    This post is encrypted twice with ROT-13. Documenting or attempting to crack this encryption is illegal.
    1. Re:Their datacenter has a droid! by kv9 · · Score: 1
    2. Re:Their datacenter has a droid! by antdude · · Score: 1

      Where was it? I missed it.

      --
      Ant(Dude) @ Quality Foraged Links (AQFL.net) & The Ant Farm (antfarm.ma.cx / antfarm.home.dhs.org).
    3. Re:Their datacenter has a droid! by poot_rootbeer · · Score: 1

      The facility was absolutely beautiful. When going between two buildings on an overhead walkway I saw the Golden Gate bridge with a nice orange sunset behind it.

      What's the point of building a data center with a beautiful scenic view? Computers can't see, and even if they could they wouldn't appreciate it.

  40. Relative perspective by nemesisprime · · Score: 1

    The point of the story was to display ILM data crunching power as impressive for a POST PRODUCTION house. Not "the greatest data center in the world". Compared to any other post production house, ILM is pretty darn impressive.

  41. Hey, it's Lucasfilm, so it's automatically cool! by jhylkema · · Score: 1

    Nevermind the fact that there are much larger and complex setups out there, as others have pointed out. Nevermind the fact that Star Wars was a ripoff of a Japanese pulp science fiction novel.

  42. Theoreetical carrying capacity by MadMagician · · Score: 1

    Theoretical bandwidth is a chimera. All the cars on Los Angelos freeways at a given time, carrying boxes of tapes -- now that's some theoretical bandwidth. What matters is achieved write and read capacity -- I believe the record is 14.5 Gb/s sustained.

  43. Meh..Cemetary has 2 PetaCoffins of offline storage by Anonymous Coward · · Score: 0

    "Still....I like datacenters. The hum of equipment. 65 degree temps and lower. I once had my cube re-located to a tape library. Quiet...peaceful place"

    So's a cemetary, but you don't see people willing moving in there.

  44. Bullshit or Calculation Error : 569 NICs/server ! by wtarreau · · Score: 2, Informative

    TFA talks about 2000 servers equipped with 10 Gbps network cards.
    11.38 Pbps is 11380 Tbps or 11380000 Gbps. This means that each
    server has 569 network interfaces !! This is total bullshit. If
    they had said they had 10*2000*2 = 40 Tbps, it would have been
    based on more real (though irrelevant) data.

    I hate it when ignorant journalists post meaningless data for public
    consumption.

    Willy

  45. Wisdom goes only to the wise by Anonymous Coward · · Score: 0

    "as somewhat hyped up -- "look at us, we have a large datacenter" kind of thing,..."

    And just what kind of statement *did* you expect from a Lucas operation? Have you learned nothing from his movies, grasshopper?

  46. Negotiation is important. by WindBourne · · Score: 1

    We techies really sux at Negotiations. Sadly, the more hard core you are, the less business savey we appear to be. I have been stuck around 100K. A friend of mine with less education and experience was offered a job at MS. He was originally offered 85K (this was 8 years ago). He said no and held out for 150K, stock options, and benefits. They came around and re-offered him. I do not know exactly what it was (per contract, he was not allowed to say), but he says that it was more than what he wanted. After seeing the house that he picked up in the Seattle area, I believe him. For all I know, he had MS give him the down payment for it.

    Considering the team that he was on, I was more surprised that he was offered so low at first, but that is what business ppl do. We all have to learn when and how to negotiate better. Perhaps CS/CE should take up classes on this.

    --
    I prefer the "u" in honour as it seems to be missing these days.
  47. They run OS X. by Anonymous Coward · · Score: 0

    This is LucasFilm, not "SucksBecauseWereCheapFilm", so they probably run OS X, God's own operating system. Faster and more secure than Lin-sux.

    1. Re:They run OS X. by ewanm89 · · Score: 1

      It probably runs gentoo so they use up that bandwidth and cpu power upgrading all the time.

  48. LOL.. sigh by Anonymous Coward · · Score: 0

    Judging by your post. You know no knowledge of running anything other than you own computer. They are using NetApp storage and uptime are critical so it matters what you choose to put in your datacenter.

    1. Re:LOL.. sigh by Guspaz · · Score: 1

      300TB is still nothing, even with insane redundancy.

      For example, assume you've got Sun Fire X4500 servers, and that you take them with the stock 500GB drives. 24TB per 4U server.

      Now let's assume that you run RAIDZ2 on each server, dedicating 2 of the 48 drives to parity. That's 23TB per server. Now let's assume you want some redundancy, as in, completely separate failover capacity. You mirror every single server with hot standbys. Easy with ZFS, you can mirror the file system in real time without any issues. So we get an effective 11.5TB per 4U server.

      Now, we need 300TB, so that requires 27 servers. 108U, or three 42u racks, with each rack having 6u for network infrastructure, load balancers to do the failover to the hot-standby units (or even localized UPS if you want double UPS coverage).

      3 racks. With pretty decent redundancy that allows two drives per server to fail before you need to switch over to the hot standbys, and that's ignoring the fact that each X4500 server has redundant power supplies and allows hot swapping of drives and power supplies. THREE RACKS.

      Explain to me why they need a 10,000 sq. ft. datacenter for three racks worth of servers? Yeah, I know, AC, UPS, generators, all that stuff takes up room, but I could fit a lot more than 300TB in a 10k sq. ft. datacenter.

      Sure, I'm no expert, and I might be missing some important considerations, but even I could set up a 300TB high-uptime file storage network without needing an entire datacenter to do it.

    2. Re:LOL.. sigh by 2meen · · Score: 1

      Explain to me why they need a 10,000 sq. ft. datacenter for three racks worth of servers? Yeah, I know, AC, UPS, generators, all that stuff takes up room, but I could fit a lot more than 300TB in a 10k sq. ft. datacenter. I'm just guessing here, but the fact that they use the datacenter for rendering on the 5000 CPU's he mentions in the video-tour and not just for storage might have something to do with it.
    3. Re:LOL.. sigh by drsmithy · · Score: 1

      Now let's assume that you run RAIDZ2 on each server, dedicating 2 of the 48 drives to parity.

      No-one would do this in a production environment where performance was even a passing concern (or if they did, they shouldn't have) - firstly, because parity-based RAID configurations are (relatively) slow and secondly because RAIDZ[2] (or parity-based in general, really) arrays shouldn't be any bigger than about 8 drives in total, or performance (and reliability) start to go downhill.

      It's reasonable to assume you lose at least half the raw space in redundancy using RAID10 (or equivalent), to get the best performance - probably plus another drive or two for hot spares. So double your estimate of 3 racks to 6.

      (I agree 300TB is nothing particularly impressive, however.)

    4. Re:LOL.. sigh by Guspaz · · Score: 1

      5000 CPUs isn't particularly impressive either when you consider 1U quad core quad processor machines. Up to 672 CPU cores per rack. Pretty insane power requirements as far as density is concerned, though.

      Let's not forget that the Sun X4500 is a quad-processor beast itself, and you're not going to saturate all 16 (possible) cores with storage demands, unless you're processing the data locally.

      A more dedicated processor such as the Cell (which would seem to be ideally suited for software rendering) would reduce the space/power/heat requirements significantly, although I'm not sure of what kind of enclosure you'd need. Assuming you're not shoving PS3s into a datacenter, the Cell comes on PCI-X cards. I'm sure there is some enclosure designed to maximize the number of PCI-X cards in a limited space.

      I don't think their datacenter is bad, by any means, just that the technology exists to do what they're doing in much less space (and possibly cheaper).

  49. major factual errors or there's a time machine too by Anonymous Coward · · Score: 0

    Am I the only one catching stuff like this?

    "4000 frames, each frame took 23 hours to render..."

    MEANING ((4000*23)/24)/365 = 10.5 years????

    Wow, they must have a time machine there too. Seeing as the film in question, Poseidon, was released last year.

  50. Darth Lucas by Anonymous Coward · · Score: 0

    I can just see it now...

    George Lucas: Any attack made by the Media against this data-center would be a useless gesture, no matter what technical data they have obtained. This station is now the ULTIMATE POWER in the universe. I suggest we use it.

    Old-School Star Wars Fan: Don't be too proud of this technological terror you've constructed. The ability to destroy a prequel trilogy is insignificant next to the power of losing respect from millions of Star Wars fans.

  51. Pelosi's Presidio Re:And it's in a national park by gojomo · · Score: 1

    Though anything in the SF Bay Guardian should be taken with a grain of salt, it should be noted that publication blames now-Speaker Nancy Pelosi (D-San Francisco) for the Presidio arrangement, not the Bush-41 Administration. Since the legislation was passed during the Clinton-42 administration, blaming it on either Bush is farfetched.

    But the course taken wasn't unreasonable. The Presidio was already developed when it was a military base. Turning it into a traditional, naturalist national park would have required un-development, destroying pre-existing housing, buildings and roads. (Restoring it to its native grassy sand dunes would have required deforestation.) Mixing updates of the prior development with other expansion of public use and re-naturalization made sense -- and given the immense value of just the already-developed real estate, having the whole project pay its own way should have been a no-brainer.

  52. Re:Hey, it's Lucasfilm, so it's automatically cool by pozitron969 · · Score: 1

    Care to mention which Japanese pulp sci-fi novel was ripped off? Just curious.

  53. what a bunch of BS by SQLz · · Score: 1

    Imageworks has almost twice as much gear as they have. They are just blowing smoke out there ass.

  54. To borrow from Fark.com by DragonHawk · · Score: 1

    * This thread is useless without pics! *

    We want our nerd porn!

    --

    dragonhawk@iname.microsoft.com
    I do not like Microsoft. Remove them from my email address.
  55. Hope none of the datacenter ops are starwars fans by b1rdy · · Score: 0

    The temptation to hit the EPO (emergency power off) button so they could experience the "dark side" must be too tempting.

  56. Prequels Scripts by bill_mcgonigle · · Score: 1

    Right after this, I read that Lucas donates 170 million to his alma mater. Hey George, why not donate 10% less and actually pay your people something more since you're insisting on setting up shop right in the freaking Presidio?

    He could have invested that same 10% in the world's best script writer for the Prequels and thereby realized a 10x ROI from now-former-fanboys actually buying the DVD's of his movies and thereby able to both raise pay and donate more money. But ego is a terrible vice.

    This from a guy who wrote his college entrance essay on George Lucas and wanted to work for ILM (before he got smart and grew up).

    --
    My God, it's Full of Source!
    OUTSIDE_IP=$(dig +short my.ip @outsideip.net)