Slashdot Mirror
Pixar Eclipses Sun with Linux/Intel
lieutenant writes "Pixar Animation Studios is replacing servers from Sun in its render farm with eight new blade servers from Rackspace. In all, the blade system contains 1,024 Intel 2.8GHz Xeon processors, and it runs the open-source Linux operating system. Pixar has ported its Renderman software to run on Linux." I'd love to see their electric bill ;)
How fast they can now render over the old Sun servers?
(imaging a Beowulf cluster of THESE!)
1024 xeon's? jeeze, my electric is $120/mo with one amd and one intel running half the time.
My god, I thought they had trouble scaling Linux that far. Seriously. How the hell do you do that when "stock" linux doesnt like 8 CPUs?
Tequila: It's not just for breakfast anymore!
I assumed that Apple created their Xserve rack-mounted servers for exactly this purpose: not just for animation studios, but for Pixar in particular (since Steve Jobs runs both companies and does things like selling Pixar DVDs to Apple to give away in promotions, thereby increasing the number of DVDs sold at launch, getting his movies in front of more people, and of course providing more incentive to buy whatever it is he's bundling the DVDs with).
I guess the density of the blade servers is higher than the Mac servers, but it would have been a big boost to the Xserve's credibility if Pixar had chosen to use a ton of them. Perhaps Apple will make a new server (Xblade?) that's more suited to this use. It wouldn't surprise me...
One of the advantages of *nix is that if you code is well written then you can write once and compile anywhere (except possibly windows), so it's nice to see a company showing that this is possible. It's a shame they chose Xeon's though. The Xeon is the latest in a long line of chips which evolved from the 8086, a fairly nondescript 16-bit chip. It still caries a lot of legacy bagage around with it and so has to run several times faster (and drink several times as much power generating several times as much heat) as a well designed chip in order to go as fast. Intel and AMD are able to sell chips which compete with RISC chips only because they sell enough that they can seriously outspend everyone else on R&D making a dead architecture last just a little longer. It would have been nice if the Alpha had been able to compete with x86 on price when NT4 was released, maybe then we'd have left the x86 ship for good. Whenever I here someone suggest OS X or Solaris on x86 I always wonder what they have against the OS that they want to cripple it by putting it on such an evil architecture.
I am TheRaven on Soylent News
I could have sworn that the software couldn't run at all in 64 bit. I'm just wondering if they didn't take a step down when they converted 64-bit optimized code to run on regular high cache 32-bit pentiums.
Great for linux and anyone who has half a brain knows that you can make a very nice system from the Intel Xeon chips and Linux. But Sparcs aren't x86's and they certainly don't run the same. I've been running a server off of a pII 400 mhz Xeon with 2 megs cache on it for nearly 4 years now. It's never failed me yet and I have no intentions of upgrading anytime soon, but then again I'm not rendering anything in 3 deminsions either.
Doesn't dreamworks use this type of technology already?
Damned MPAA members ... we hate you because of your strives for world domination, but then you go and support linux ... bastards we just love to hate you.
Lastly I'm really surprised that Pixar didn't go for a server farm of OS X boxen, just goes to show ya, right tool for the job. Maybe they'll throw darwin on their at least.
Ignore the "p2p is theft" trolls, they're just uninformed
why didn't Pixar go with macs .. i keep hearing from mac fanatics how much better they are .. and how powerful they are .. if thats true .. why didn't pixar buy the xserve for the render farm? ... if its not good for the goose .. how can it be good for the gander
given the G4's that sit inside the box are easily out-performed by Intel/AMD these days.
G4s still have one of the best vector units in town (far better than MMX/SSE, see Ars Technica for more details), and the kind of stuff Pixar is going to be using them for (ray tracing I assume) is perfectly suited to opperation on an AltiVec unit. I wouldn't be surprised if, with properly optimised code, a G4 couldn't replace 2-3 Xeons in this particular application. (No, I'm not saying that a 1GHz G4 Mac is faster than a 3THz P7 before I get any flames)
I am TheRaven on Soylent News
I teach MCSE courses down in Chatsworth, recently we got a lot of Engineers from boeing coming over for Windows XP classes. Why? They're dumping all their Sparc Stations and moving to XP on cheap Intel hardware. Its faster, and 2/3s of the applications they need run it already. The last third they were working on.
The IT people I talked to were surprisingly happy with XP so far. These were all Unix only kind of people actually.
The other thing they were doing were looking into dumping their Crays in favor of LINUX clusters. The comments were along the lines of how much faster and cheaper it was to put together a cluster of a 100 cheap Intel boxes than getting a new Cray. That, and they were all already familiar with the unix style interface. On top of it all, the GUI interface (I think they were running Gnome) was so much nicer than CDE on Solaris.
So Sun it getting it from both sides- Cheap Wintel boxes and Cheap Linux boxes. No wonder they finally relented and released Solaris 9 on Intel.
The executives at my company are very interested in linux, because of the outrageous leap in processing power per dollar, and the reductions in CPU-based licensing costs for software like Oracle is staggering. The concern, though, is stability.
Sun Fire and Enterprise servers are really expensive, but they stay up all the time. Swapping a failed processor or NIC or memory stick without halting the box is really important on a mission-critical server. Likewise, a well built Sun box never panics, and if it ever does, Sun will insist that their engineers look at the crash dump to figure out what went wrong.
I think Linux has won the performance battle, but what about the stability battle? You need to win both to win the war.
Anyone get the feeling that Sun's "brightest hours" are behind them? As others have mentioned, they're getting hit from the Windows XP side, as well as Linux. If Solaris dwindles as a result of this, and becomes a niche/high-end item, what does this say for HP, SGI, and the rest of Unixen?
I've been thinking in terms what are/will be the Big Three:
Linux, Mac OS X, and that other thing.. uh, Windows XP. I wouldn't bet on traditional Unixen as a growth area, by any means. Won't be long for some companies to become "Unix-free and Windows-free" zones...
For some reason, I just can't seem to resist nit picking here. BSD has been mature enough for professional use for quite a long time now.
In fact, I seem to remember a time (pre-Solaris) when Sun systems ran a form of BSD.Look, the mean-time-to-failure of a hard drive is 15,000 to 20,000 hours. This means that a hard drive stops working at Goole every hour of every day. Truly 24/7.
If you were to look at their dumpster in the back alley, you'd find about 170 hard drives dunked every week.
Wouldn't you cheksum every data transfer under those conditions too?
Its all about the distinction between shared and distributed memory architectures. Different applications benefit from different types of parralelism which the above architectures provide. If to solve the problem independent chunks of code can be run that require no communication at run time then clearly a blade type solution (distrbiuted memory) is viable, but if the calculations are co dependent on each other and require communication of interrim results then the overhead of communication can quickly become the critical path and shared memory parallelism becomes a better solution. It also depends on the level of parralelilsm built into the implementation of the algorithms inside pixars redering program itself.
Its one damn thing before another. (Dick Bird 1999)
Of course, in addition to that there'll be the demand charge. Unfortunately, I have no idea what the going rate on that is, but my understanding is that for a high-consumption user, that part of the bill is MUCH higher than the regular KWh part. At least, thats what they told me when I used to read meters.
For those who don't know, its basically a charge based on the peak amount of power you drew over the course of the billing cycle. They take that peak (~76KW in this case), and multiply it by a constant (on the order of 10 or 100, depending on the customer), and multiply that by whatever the rate is (I don't think its the same rate as they multiply KWh by). Anyway, they always told us to be extremely careful reading the demand, because being off by even the lowest order digit could cost the customer thousands extra in some cases.
The most important linux skill is how to use internet for help, not any unix skills. For a newbie, it is a hit or miss affair. He grabs a modern desktop oriented linux, installs it in 30 or less minutes, if all of his hardware are supported and all programs newbie wants are already installed, good news, we have a new linux fan. Chances are, that won't happen.
If something goes wrong, it is best option for linux fans that newbie just forgets the idea, right then. Most probably he now has a functional system but with a non-functional usb mouse, cd burner or a sub-optimal refresh rate. He will want to fix and use the system. It is just the mouse, or the printer, or excel documents. He almost succeeded in this linux thing!
Wrong. He still misses the crucial skill.
He will try to fix it and fail, seek help and fail again, try to skim docs and fail, learn where to seek help and fail, read documents and seek help at the correct place with the correct attitude and if he has some luck, succeed at last. Now we have a brand new whiner instead fo a fan. Worse, he half knows what he is talking about.
Eveyone whines about windows all the time too, but it is not the same thing. We don't want scared potential new users. In case of windows, user already knows how much of that whining is about a real problem, that is not the case with linux.
Solution is aiming higher. Linux has to be considerably easier to use and install than windows because non-techie users just have a lot of experience with windows. Even if the fix isn't optimal, there is always a fix a phonecall to someone you know away. Linux doesn't have nearly the same installed base so is denied the luxury. Linux still requires a crucial skill; it shouldn't.
In some areas (considering desktop) linux already is better than windows and in others, it is not too far behind. But it has to better on all fronts. Till than, linux is not ready. You can argue that had market shares of linux and windows magically flipped, we would be saying windows is not ready. Probably you would be right, too. But market share (or rather, user base) has not magically flipped and that is not irrelevant.
I know, I should have read the grandparent.
Gentlemen, you can't fight in here, this is the War Room!
"you'll still just be a whiny 14-year-old living in Mommy and Daddy's basement."
.
.).
Or a financial analyst for a leading semiconductor supplier, besides, you are the one who is doing the whining, but I digress . .
You seem to have established many assumptions about how a desktop should work, one such assumption is desktops, servers, and every other MS product should be a separate system ENTIRELY. Therefore, though Linux is good for the server, it ain't ready for the Desktop. However, I believe the post Internet era changes this completely (ironic that you compare Linux to Windows 3.1 . .
The fact of the matter is that, up until open source (to me, synonymous with "the Internet"), all software came as square pegs. This is because square pegs are much easier to produce than customized pegs. Proprietary software, which doesn't utilize the power of the Internet to its fulliest, is limitted to the square peg model. This can work great in niche markets (which is why MS is trying to make niches all over the place), but it depends on controlling all standards within the market, which is increasingly difficult as the Internet progresses and as more and more people learn how to program. And, as we see with adoption of Linux, when you don't have to use a square peg, a lot can be gained.
But, I suppose my biggest argument is based on the fact that the majority of the world does NOT own desktops. The definition of "Desktop" depends on this majority. For these users, who lack the assumptions you have been conditioned with, Linux is already a superior product and is being adopted at a very fast rate. As time passes, thanks to Linux, this majority will gain access to "the Desktop." Of course, since Linux is constantly improving itself, I will never really be able to prove that it was ready when I made this post, but reality tends to be grey, like that. Not so black and white, as some people see it.
However, I am afraid that without a Madonna song playing in the background and a video of someone flying around, I have failed to convince you. Oh, well . . . I can't say I cared much to begin with. Linux is definitely ready for the desktop as far as I am concerned, regardless of what you think.
Disclaimer:
I am not the spokesman of Open Source. Nobody is the the spokesman of Open Source. Using stereotypes is an indication of a simplistic mind struggling to oversimplify a complex world. Using stereotypes for the Open Source community is down right ludicrous. So get a grip and come to terms that people can still share software even if they don't always agree . . .
Sdelat' Ameriku velikoy Snova!