Slashdot Mirror
In The Works: Windows For Supercomputers
Robert Accettura writes "According to ZDNet, Microsoft may be feeling threatened by Linux gaining ground in the High Performance Computing (HPC) arena. As a result, they have formed a HPC group to bring windows to these systems. It makes a mention of how clustered computing may be a target. I guess the only thing better than crashing 1 computer at a time is crashing an entire room full at once."
I guess Bill thinks it's time to slow the worlds fastest computers to a crawl. Apparently they aren't crashing enough, too.
by Mike Buddha -- Someday the mountain might get him, but the law never will.
I guess then the computer wouldn't be so super :o)
When I tell an object to delete this, am I killing it or telling it to kill me?
I hope those guys have good firewalls.
Ydco co
Yeah, this will be a step forward for mankind.
"It looks like you are building a cluster, would you like me to tell you how Microsoft can bring it to it's knees?"
... will they crash more quickly or more often than mine does?
Great- when the cluster gets hijacked by spyware and the like- it can send out 3 millions spam emails a hour as opposed to the 5000 a Dell does now.
Is it just me or does the notion of a GUI on high performance computers sound at bit pointless. I thought the point of HPC was to crunch masses of numbers - not something joe average will want to do any time soon. So what's the point of a pretty (and resource hungry) windows interface?
Because every Node needs a Windowing System in Ring 0.
Free as in mason.
Next logical step is probably:
Guns made safe for children!
Coincidence? Of course not, this has been a strategy since the days of BASIC. Microsoft copies all the good ideas. Of course, it makes a bad and buggy copy, but, hey, that's what a marketing dept is here for, right?
The right to offend is far more important than the right not to be offended. (Rowan Atkinson)
So our super computer says you have an error in module 226383639272 and to press enter... erm... I don't know how to handle that..... let me check my books...
--- [Insert intresting Sig here]
i think billy & co finally figured out how to get big enough iron for longhorn >D
It's not so unreasonable. MS has to expand, and this is one way to go. It will be tough since MPI seems to be the standard, and it will take some time to embrace and extend on an existing standard. (It's been done before though.)
We don't like to have clusters running any windowing software, so it would be a tough sell for us and a big change for the MS culture to get rid of windows. Then again, I used to use xenix.
The other big thing is the lack of a command line. Sometimes I wonder if MS has engaged in an all out war against the command line. If they are successful it will mean one less place where the command line is useful. I'm already starting to feel nostalgic for my keyboard...
When they decided on which platform to use for rendering the water on "The Titanic", they complained when a NT reebooted the computer wanted a screen, keyboard and mouse to boot up again. So they ended up with Linux on the Alpha boxes because of this.
All we need now is a BSOD joke and I'd swear that everytime I read Slashdot it induces a timewarp back to 1998.
Avantslash - View Slashdot cleanly on your mobile phone.
...certainly seems to want a finger in every pie.
There's mischief and malarkies but no queers or yids or darkies within this bastard's carnival, this vicious cabaret.
Blue Death in mainframes.
Andrej
I assume that the people who need these computers really know what they are doing and would rip the microsoft sales people a new arsehole if they tried to bullshit them with 'vaporware' or crap features....Its one thing to try and convince a bean counter that windows is a better platform but a totally different activity trying that with people who know what they are doing.....
A thousand processors...
A terrabyte of RAM...
Trillions of pixels per second...
Processed at multi-terraflop speeds...
Drawing the fastest BSOD ever!!!
But...nobody WANTS a Beowolf cluster of these...
Any technology distinguishable from magic is insufficiently advanced. - Geek's corollary to Clarke's law
This action from Microsoft is proof positive that they are taking notice of the recent accomplishments of Linux and are trying to counter them with strides of their own in areas that are not their specialty. If nothing else then this is positive for everyone because not only will Linux continue to improve and develop on its own but now both MS and Linux will develop to compete with one another making the overall user computer using experience better for everyone involved. I know everything MS does is looked down upon by the /. majority but this really should be seen as "a good thing".
Please do not let scientific accuracy interfere with the intended humourous/interesting/insightful value of this comment
The same as ever - whenever Windows is mentioned, lots of wisecracks about crashing is posted. Did you imagine they'd port Win95 or Win3.11 to HPC? Duh. They'll port something like WinXP or W2K3, and guess what - those are quite stable OS'es. Of course you CAN make them unstable, but that goes for PenguinWare as well...
Ah well, I better put on my flamesafe suit - I forgot to criticize Microsoft...
Black holes are where God divided by zero
Why in the world would someone want to run a bloated GUI based operating system on hardwared designed specifically to provide services (servers) to it's customers? Unix is great in this aspect as (at least for the most part) running xdm and serving up a graphical interface was intended primarily for end users requiring execution of applications in multiple windows. Unix servers used to NOT run xdm (or any graphical engine) for the purpose of streamlining and providing efficiency and better utilization of system resources. Windows (even in the current Win2003) is far too large for use in a high performance computing environment. Bill my man ... get a clue ... windows isn't for everything!
1) You know that 5 million dollar box in the corner? It's not working now. Press OK to format all your terabytes of meteorological data.
2) Why did the chicken cross the road? Because your supercomputer is hosed. Press OK.
3) D'OH! Press OK.
stuff |
If you run Windows on a 1000-node supercomputer, do you need a volume license? Also, MS will probably ask for a per-user license for running Office...
Well, I hope they are stripping out the GUI and all the crappy little programs (i.e games, Accessibility Wizard, etc) I don't think the market can support a new Microsoft super commputing OS. What would the advantage be for using this over linux/unix variants?
for the tech specs, check out my clan website here. I've written a Java App to cluster my windows boxes together like a beowulf cluster. It owns.
New Windows HPC viruses anounced!!
- They will infect other pc's quicker
- apply more dammage
- Be able to perform a DOS using only one cluster
And Microsoft could build software into its desktop version of Windows to harness the power of PCs, letting companies get more value from their computers. It's a technology that's applicable to tasks such as drug discovery and microchip design.
sounds a lot like seti@home, folding@home, or the grid project. Another example of embrace and extend. It's definitely going to be interesting when pc's are networked for spare cpu cycles as a normal everyday event. Maybe the can use all that cpu power to get some AI to rewrite windows code so its bulletproof.
Do you need a website upgrade?
Well, for a 1000 cpu cluster, you have to pay for 1000 licenses. These however do not provide technical support which is available as an option...
how many mice will that require?
This guy named Darien is apparently promoting "Windows Mainframes." Apparently a "Windows Mainframe" uses the cost-effective *cough* "Windows Datacenter Edition." The Unisys ES7000, one of the says you can buy 'Datacenter', starts at $35,000. Yeah! Cheap! And that gets you four processors... "mainframe" indeed.
Google decided to use extremely large clusters of single-processor PCs and Linux.
Microsoft will need to offer some type of very low cost, gui-less, remotely manageable, stripped-down windows if they really want to compete against Linux clusters. Even then, they would be competing with both FREE and YEARS OF EXPERIENCE.
Napster-to-go says "Fill and refill your compatible MP3 player", which is a lie. It's not MP3. It's WMA with DRM.
Been around for awhile - I have no idea how it works or what it is used for.
However it pops up alot in MSDN when I am looking for help.
I am very small, utmostly microscopic.
Interesting statistics:
cluster database
Andrej
Can you imagine a massive cluster of servers infected with the RPC or Sasser Worms?
I'm sure Microsoft will probably develop this and market it as a network performance testing tool.
Wow, not even in my craziest dreams, I would have thought, that the requirements for Longhorn will be so insanly high!
Finally, someone to balance the thread! Well, tip the scales in the MS direction a little, anyway.
/. folk haven't used Windows since 1997 - it's a bit better than it was, and as this guy pointed out, it's easy enough to build an incredibly unstable *nix box...
You do distinctly get the feeling that 90% of the
sig:- (wit >= sarcasm)
First I thought how useless this is - Microsoft trying to modify Windows to sell a few dozen licences to run on dozens of different platforms (each supercomputer is custom-designed, no?). Also - the programs that run on these machines are just huge sets of calculations, and the operating system is irrelevant... you probably don't even need one...
But then I RTFM - they just setup Windows to simplify clustering. Linux has had that for long time. Nothing to see here, please move along.
"Argue with idiots, and you become an idiot." -- Paul Graham
I find it naturally that MS tries its luck in the HPC world, but windows surely does not fit the bill.
Thomas S. Iversen
Ive been laughing like a madman for 5 minutes on the train because of this. Now im getting wierd looks from all the other passengers. Thanks /.
No offense to gates but i doubt the takeup of this will be high, given microsoft's reputation for processor resource abuse. The windows source must look like this:
while(extraprocessingtimeisfree) {
doafewforloops
}
i guess gates, etc. are suffering major tech envy over the fact that windows is still pretty much laughed at when it comes to serious computing. all the csi (computational sciences and informatics) labs at my university run linux now (they used to be indy workstations, now they're beefy dell boxen) and except for the professors' personal machines and the office machines, every single machine in the cs department runs some kind of unix.
ignoring the fact that the cs department has several important people who have a healthy hatred of microsoft, i don't think they'd every buy a windows cluster because (surprise, surprise) none of their software would work on it.
This just in... the internet has crashed. Repeat... the entire internet has crashed.
Apparently, all major servers and clusters running government-mandated "Windows HPC" have severely malfunctioned and automatically reformatted the entire internet. Thousands of IT workers and webmasters have reportedly killed themselves by jumping out of top floor... um... windows. Could irony BE any more ironic?
Developing...
That's what industry standards are for.
You could just as easily make the argument, 'Standard Oil was good for the world because it standardised the chemical mix of oil, so everyone can expect the same lead content etc'. But of course, in every industry which is not monopolistic (while it may be oligopolistic) the way to solve this problem is not through dictation from one company to everyone, but through consensus on industry standards.
That was the whole point of the Open Group and the (1 year too late) advent of CDE--you agree on a system of library interfaces, protocols, file formats that will form the basis of your open systems desktop, then you can have as many implementations by as many vendors (or open source people) as you want, and they're all compatible. What's more, they can all LOOK completely different if you want--but they all play the same way with the same software. So, you have competition and alternatives, but compatibility at the same time.
NEITHER Microsoft NOR open source people are doing this of course. It requires a commitment to following published standards, and a consensus around them in the industry. THAT is the way to achieve consistent desktops--not stifling competition and making everyone accept your particular implementation, but agreeing on ground rules for compatibility and following them.
Just like thousands of lines of code that do nothing but obfuscate the surrounding code's function. Get a bunch of shiny new x86 boxes, put 'em in your supercomputing data center, and run Windows HPC on them. It'll confuse the shit out of people.
Research shows that 67% of those who use the term "research shows", are just making shit up.
... these new Longhorn system requirements are getting quite high?
.. codename "domino" ?
Living is a horizontal fall
Most supercomputer users aren't going to want to plonk down literally millions of dollars in software licences to Microsoft - they'd rather be spending this money on either plugging in more hardware or on building and refining their analysis engine.
What could MS conceivably offer that would counter this?
I would imagine that the hardware used in HPC would be very, very varied. Putting an OS on would probably require modification to the source code, especially with a system like windows, with everything integrated into the kernel. I can't see a closed source OS being used for an application where mainly custom programs are being used anyway, and performance is more important than anything else. If you have access to the source, unneeded features can be disabled (eg. sound, usb, mass storage devices, etc.) And besides, why waste processing power on a GUI anyway?
Also, by integrating everything into the kernel, stability is compromised. In your desktop computer, stablility is somewhat less important than when you have hundreds, or thousands of computers doing parallel calculations for a nuclear weapons simulation.
that billyonerrors lameNT about way too much not ever being enough (no matter who gets hurt) is just more bad hysteria buy now?
tell 'em robbIE?
all is not lost.
consult with/trust in yOUR creators.... no point in overheating (peacing off) the main processors any further. many of us probably would not enjoy a full reboot right now. get ready to brighten up anyway, just in case.
The "EGEE" project, responsible for the European Grid, announced (bizarrely, at the time), that Linux would be the #1 platform and Windoze #2 for the European Grid... but now it is clear that the bureaucrats running the EGEE project are probably getting healthy kickbacks from MS as part of this HPC push.
This was touched on earlier but not fully expanded; Google isn't a search engine. It isn't a portal, or a SP, or even a web engine. It's an operating system, deisgned to run on thousanmds of servers, be self-healing etc etc. There's much more about this back here Cue, MS scalable OS for clusters. The first rule of "embrace and extend" is working out what to embrace, and I think they hit the nail on the head.
The Slashdot Paradox: "100% Overrated"
Just dont forget to install cygwin and XWindows.
In theory there is no difference between theory and practice. In practice there is. - Yogi Berra
The NT kernel only supports up to 32 or 64 CPUs, IIRC. I think it's because the scheduler has one centralised list of CPUs to dispatch threads to, and it quickly becomes a bottleneck for performance. When you have too many threads to dispatch to too many CPUs, this list is completely locked. The MACH kernel has a thread-list per CPU, and dispatches new threads or moves existing threads in a distributed way, so there's no bottleneck (hence MacOS X's performance on clusters ?). I could be completely wrong here, though, correct me if you know better. So my guess is that MS will have to redo the scheduler of the NT microkernel. I don't know about the VM subsystem...
Maybe we deserve this world ?
That with "Penguinware" if you find it crashes you can fix it by tweaking the offending source code. Thats why you don't use odd numbered kernels in a production environment. You wait until all the bugs are ironed out
/dev/mem" as root).
Kernel 2.6.6 is more stable than 2.6.0, because o the massive patch storm caused by people reporting bugs.
The only way I can crash a production kernel is either to overclock the machine like crazy or to do something really dumb (such as running "yes >
The moderators really should of moderated this -1, ignorant.
It occurs to me that the greatest FUDmongers have lately been the Linux crew on this site. High overhead, insecure, plenty of ways to rag on Windows, but unstable? XP just ain't, despite all the people who I'm sure will land on me saying "Well mine just crashed yesterday! Okay, it was 3.1 running on a toaster oven, but still!"
It's amazing how all the so-called Microsoft tactics at which Slashdotties have expressed such theatrical shock get trotted out when they're doing the fighting.
Sorry to interrupt, please go back to your holy war. . .
The only acceptable defense of scientific results is to say that they were the product of the Scientific Method.
Microsoft could create a specialized version of its widely praised programming tools
Which ones are those??? Who the heck is "widely"???
So they want to yet one more thing Windows Update will have to fix? Maybe they should try to get the bugs out of exisiting Versions or maybe work on Longhorn...
But of course not! They want to make something new, wasting developers (Windows itself is a waste of developers) on this.
I don't think it will fly, but I suppose Microsoft will make more of them one-sided ads, saying that Windows HPC will be the best thing since sliced bread.
I guess we just have to wait and see...
x86, oh yes, I'm pro.
Yeah right, like a beuwolf cluster of anything needs a crash happy alpha blended GUI. My name is AgentPothead and I'd like some of what Gates & company are smoking.
Friends don't help friends install M$ junk.
Heh heh... Hey, imagine a Beowulf cluster of Win... ... *barf*
Beware: In C++, your friends can see your privates!
"But a Microsoft product would theoretically integrate better with Windows desktop machines, and if the company can serve up an impressive offering, Linux could be in for a tussle."
Just had a bad thought -- I wonder if their version would include digital rights management code in the server product ... wow ... what a thought.
One more area where they will pour gazillions of $$$ . Money the make with... Windows. Every time I buy a PC, I already pay for the devellopment of a stupid game console I will never use and for dickheads who want to open Excel on their mobile phone. I guess XP licenses will go up again next year, and then I will know I am gratefully contributing to the Clippy-cluster. Bwèèk.
10 ?"Hello World" life was simple then
So where is the expected flood of "Imagine beowulf cluster of that" slashdot comments?
There you are, staring at me again.
Actually some of the recent worms out in the wild have done the 'roomful of BSOD' quite well at many locations ...
Tomas
If you disable the "Automatically restart" setting under the "System failure" section of the "Startup and Recovery" dialog then you will get a bluescreen in Windows XP instead of a reset - if the computer were to suffer a bluescreen worthy error of course :D
I'd invite you to look at Xbox as an example, and the operating system which that runs. There is no requirement for Windows to include a friendly GUI, animated characters, BSODs or any of these other 'hilarious' /. stalwarts.
We played dungeons and dragons for 3 hours.....then i was slain by an elf
OK, so who has been saying good things about VB? Huh? Own up! Yeah, you. I'm looking at you!
everything looks like a nail
more proof that Microsoft (and a huge chunk of the IT industry), Games Companies, Movie studios, Record Industry et al have run out of new ideas
MS already knows its struggling to sell that bulky expensive wordprocessor for the 10th time
Yay... my favourite A/C posts again!
/. could do with a little more surrealism.
These posts have the air of having been seen in visions or passed down from the mountain-top.
What's the frequency, Kenneth?
you run Windows on your cluster and Linux on your desktop!
Microsoft announced today that they had seen Apple doing something interesting and will now be doing the same thing.
Film at 11
--James
There are some good points so far. This will be a "good thing" for everyone involved. MS just raised the ante for HPC (well, said they are starting a group that may possibly raise the ante). Guaranteed they will do the following:
Provide some relatively easy to use/configure clustering tools
(Hopefully) Lose the GUI on all nodes but the master node, and provide failover to a basic (and I do mean very basic) GUI to other nodes if need be
Improve their RIS services which should filter down to their other server offerings
Remove the friggin GUI from Ring 0 (well, pipedream I'm sure but hey, everyone can dream, right)
Remove ALL fluff from the install. A truly whittled down server install would do wonders for stability
These and other improvements I'm sure (hope) will be included. Look, anytime MS gets into a new area they backup shoddy products with marketting hype. This is something they can't use marketting to get themselves out of as easily. We're not talking about little projects here or there needing clusters. We're getting into the big leagues now and this is not something they can afford to have a misstep on. I know, it sounds way too dramatic but think about it. If MS fails on this one, no amount of marketting is going to win back mindshare. This isn't a bunch of home users who liked Bob and play their Xbox all day, these are universities, graphics houses, research groups, etc. They cannot and will not settle for a product just because it has the MS name. It does actually have to work and do so at a level equivalent with everything else out there. I won't even go into a price comparison as I'm sure there will be plenty of promotions to ge tthis out there in a few years when it is finally released in a stable, packaged form (if ever).
To make a long rant short (too late): MS entering the HPC arena = Good Thing. Competition = Good Thing.
and remember Bill Gates and company still think winNT is a microkernel!
Don't Tread on OpenSource
Please man -
;)
get your facts straight.
First off, the whole GUI environment didn't originally come from Apple (Lisa, or anything else) - it came from Xerox PARC.
your second statement, is nothing but a very good business strategy. Give the users what they want.
your third statement - is unsupported. Do you really think that they JUST NOW started working on this?
and finally - your last statement - simple rebut: Oh yeah, I've never EVER come across any buggy Macintosh/Unix/Linux,(insert OS name here) etc. code. Bugs are natural - we are human, and make mistakes. But at least they do make efforts at patching/new version more often then not.
Ya know, nothings perfect. But no worries here. Your points are typical.
If I had a penny for everyone that bitched about the problems in the world, or in software and did anything about fixing them, I'd totally be a billionaire.
On the other hand, if I had a dollar for every time I saw someone go after a bug and try and fix it, I'd be near broke.
Thanks for the penny.
Oh no, hang on, it doesn't. Ever. I boot up in the morning, switch between video and photo editing software hundreds of times throughout the day with regular use of MSIE and Eudora as well, and then I shut it down at night without it having crashed once. Every day. For years.
Old versions of Windows crashed a lot. Current versions don't. Fact.
This is part of the reason why Linux isn't gaining mainstream acceptance fast enough. Linux advocates talk about all these imaginary flaws in Windows and people out here in the real world think "well that isn't my experience at all". The effect is to create a distance between regular people and Linux advocates, which in turn pushes the mainstream acceptance of Linux further and further away. Linux needs to be seen as "the other big operating system", not some niche software used by a minority who seem to have a totally different experience of Windows than the rest of us.
It has just stuck me...
... are we seeing the greenhouse effect!
With many of the worlds computers running windows...
For problems, seek only the simplest solution, complexity brings with it more problems.
Well, I guess it's time for everybody else to abandon this space, because Microsoft has it all covered.
Maybe you could claim Linux is "gaining ground" compared with Unix, if by "gaining ground" you mean "continuing to increase its dominance." But saying Linux is gaining ground on Microsoft in HPC is like saying an increased defense budget for the U.S.A. will help it gain ground on the military might of Botswana.
I read slashdot all the time, Im a Windows user and all of the software I write is for Windows / MS environments. I'm a little sick of all the bashing MS takes. They have made leaps and bounds in operating system stability over the past few years, and if the people who used their systems actually kept them up to date, most of the problems (virii / worms) that all of you people scream about wouldnt be happening.
?SYNTAX ERROR IN LINE 42
bastard, ya beat me by 1 post! :)
::jafomatic
In the November 2003 list....
At 68 - a Windows based system at Cornell from Dell with 640 processors (it originally started out at 320 on the list with 252 processors).
At 128 - a Windows based system in Korea with 400 processors.
So Windows doesn't cluster?
It sounds like Wolfpack, Microsoft's clustering system for NT (circa 1997) is back. I guess Microsoft thinks we've forgotten about the last time they tried to get into this market. It didn't go well for them.
Am I part of the core demographic for Swedish Fish?
sweet! i really need this windows HPC stuff so i can twiddle with my spreadsheets...
Well I agree with you. I do think it more likely that Microsoft would at the very least turn off the graphical part of Windows, remove it completely, or possibly re-write it from scratch.
What I really don't understand is why it would be necessary or smart to brand such a product as Windows at all. Windows means graphical user interface, and the way it's presented ties quite closely to desktop use. It definitely doesn't mean the remote administration that's likely to be required for an HPC, and trying to remotely administer a Windows box is usually quite clumsy compared with a unix box unless you drop a lot of the traditional Windows UI stuff that's often so tied into its operation.
When I think of Windows, and I don't think I'm alone, one of the first impressions that comes to mind is a relatively klunky monolithic GUI-dependant operating system that spends a lot of time drawing pretty front-end pictures. This almost certainly isn't an accurate picture of what's actually happening all the time and it's not to say that Windows couldn't be adjusted to work in other ways. But it's a first impression.
You can at least argue that the graphical side of things is good for usability on the desktop (even though usability realistically takes a lot more than pretty pictures), but why on earth would Microsoft want to continue that image into an HPC market? Surely they have completely different customers in that market with different goals that likely don't include chewing processor time on pretty pictures for the UI.
To me at least, it'd make much more sense for Microsoft to simply create a new operating system here from scratch (or buy a company or whatever they do), and call it something that's not Windows. It could be Microsoft HPC Server, for instance, and be completely independent from Windows. Microsoft can then claim that their new OS specialises in HPC tasks, and it'll also give them an independent OS product to push in the future if either it or MS Windows collapses.
People complain that Open Sourcerers don't innovate. But isn't this an example of Microsoft copying us? So isn't this a clear example of Microsoft playing catchup to OSS innovation?
Or minesweeper for that matter? Honestly, I wondered when this day would come. I knew Microsoft was embarrassed that Linux is taking HPC by storm and ruling the roost in clustering. Meanwhile, Microsoft makes no showing at all in HPC and a relatively poor one in clustering.
Now, does it make sense for Microsoft to try to be first in everything? No. Will they try like some sort of neurotic overachiever? Yes. They can't win this one on merit, though, unless they open the source code, eliminate licensing fees, and ditch the GUI and tons of other crap they force into every installation. Only bribery, PHBs or sheer Microsoft cheerleading would get someone to pay to load Windows Server 2003 on a HPC cluster. There are people that dumb, but few of them are scientists.
Why do people think that BSOD jokes are just soooooo last century? I'm sick of people making assertions that they've gone away. I had a BSOD last week with WinXP.
And I can reproduce it reliably. I just try not to use that particular cheap digicam now, because after I've used it I get the BSOD on shutdown.
I've seen several /.ers mention that a GUI O/S is not the right front end for an HPC platform. And that HPC platforms are custom-built for specific data crunching applications. I agree.
Unfortunately, as monolithic as Microsoft is, they can't possibly have the resources to implement custom operating systems and applications in the HPC arena and create a monopoly as they did in the retail world. Microsoft is good as the "one size fits all, weekend-warrior, x86" computer installations. (Kinda like McDonalds gives you a nice, unoffensive, generic burger.)
IMO - these non-MS-dominated platforms are where Linux and other OSS initiatives have a real opportunity. Linux can be tailored exactly for the application at hand. If you have the source code and a savvy coder and sysadmin, you can custom build your environment, not waste $$ or CPU cycles.
It's become obvious to me that Microsoft represents commercialized retail-sector computing. The good thing for us is that custom implementations are still required and may in fact be making a comeback. Maybe people are starting to realize that Microsoft is not a be all end all. And in fact, are hindering innovation as much or more than they seem to promote it.
The pendulum swings in both directions people, I for one am holding my breath for it to swing back to decentralized, custom implementations.
If cisco can make IOS work on Massively Distributed Multiprocessor Systems (MDMS) for CRS-1 (http://www.cisco.com/en/US/products/ps5763/index. html) [announced today], then doing the same for Windows should be a cinch.
Arent' there more recent examples?
What about 'faster' cluster systems? Are there some with fewer processors then 600 that runs similar hardware with a different OS?
Where's the link to this list?
How can we verify context without that being provided?
If you ignore the other uses of a tool, does that make the tool less useful, or you less useful?
Maybe I'm wrong but wasn't Windows 2000 Datacenter Server supposed to be basically this same thing? Guess we can sweep that under the rung and try again...
it came from Xerox PARC
Doug Engelbart, while we're all getting our facts straight.
A lot of people seem to be concentrating on the "windows crashes a lot" idea. That's not quite a fair judgement of windows anymore. The only time I've had problems with Windows 2000 and above is poorly written drivers, or anti-virus software. As long as you choose hardware with proven drivers and don't run anti-virus software (firewall it and run minimal services and no IE) Windows should be very stable.
With that said, I think there's other problems with windows as a supercomputing cluster. The first I can think of is lack of a low-bandwidth interface. Linux you can ssh into and get results, control processes, etc. Windows requires a high bandwidth terminal services. In other words it's harder to control remotely.
Other people have brought up the licensing costs, but I'm sure MS would offer huge deals just to get their foot in the door.
I think the biggest problem is just historical and cultural though. The scientific community has a 30 year history with Unix, is familiar with programming in that environment, and has a lot of legacy code that's written for it. They just aren't going to take to a windows environment easily at all.
AccountKiller
Those aren't MS approved methods of performing that particular task ;-)
'And all the monkeys aren't in the zoo Every day you meet quite a few...'
I know everything MS does is looked down upon by the /. majority but this really should be seen as "a good thing".
Like the donkey said "I have a dragon and I'm not afraid to use it." Microsoft is in a monopoly position and they're not afraid to (ab)use it.
Since Microsoft has realised they can't make neither cheaper nor technically superior products, they fight dirty.
The policy was for a long time to not add any new service without trying to make it a Microsoft-only service. (MSN, Kerberos and DNS to name a few).
And in addition Microsoft now tries (sucsessfully) to patent the thing that makes it Microsoft-only, to prevent similar functionality being implemented in competing products (and thereby all interopability).
Microsoft is not a "fair player", not even remotely, and with the money and political friends they have, having them anywere doing anything else than decomposing, is not "a good thing"
echo '[q]sa[ln0=aln80~Psnlbx]16isb572CCB9AE9DB03273snlbxq' |dc
Mods, remember the guidelines! Try to be positive! Don't go on powertrips and using all your points to mod people down. If you don't feel like modding someone up, just don't mod them. You're destroying the community! There's too much negativity here!
It seems that most people here don't know the following:
There is already a kind of high performance Windows server - it's called Windows 2000 Datacentre, it runs on boxes like the HP superdome mainly for bigassed databases. In general these servers are treated like mainframes - they aren't rebooted - they don't need to be!
You don't need to have direct access to the GUI of a windows box in order to use it. Usually you connect using an RDP client, a la X server.
Even mainframes have a local console and these are offen GUI in nature, it doesn't mean that the machines are slow.
Please stop this mindless microsoft bashing - bash them if they deserve it, but as this product isn't available yet, it seems a bit premature to slag it off.
Now, instead of comparing the cost of running Linux on a mainframe with the cost of running Windows on a PC they'll be able to compare the cost of either on a supercomputer.
Truth in advertising from Microsoft - another first!
John
There has been a lot more progress from installing and configuring Slackware 3.0 to Mandrake 9.2 than between the stability of MS-Windows 98 and XP.
...I install HPC Windows. We run a few SGIs, our biggest being the SGI Origin 3000. We'll probably shift to either a Linux Beowulf cluster or Apple G5 Xserve cluster in the future, since the type of problems we need to solve don't typically need a single image machine using ccNUMA. I doubt Microsoft will be coming up with anything that will be able to run as a large single image for some time now and by then the competition would have moved forward even more. This is Windows HPC Vaporware so competitors will waste time and divide their resources trying to be Windows HPC compatible on their hardware. They did it with Windows NT in the beginning when they supported MIPS, PowerPC, Alpha.... The best strategy would be to ignore Windows HPC, but I know there is a gullible hardware manufacturer born everyday that will buy into Microsoft's sales pitch.
Show us a step to unisntall the GUI from Windows.
After that I want to run MS branded Web and DB servers.
ANd all should be documented, not dirty hacks.
IANAL but write like a drunk one.
I can't wait to see that, also, MPI implemented as a web service running on IIS.
I have never seen a platform that is capable to spawn so many viruses and worms every week.
You could not do that in a shitty platfrom in which everything was down half the time.
IANAL but write like a drunk one.
Linux is perfect for clustered due to the price and because any superfluous processes can be taken out. It's a lean mean clustering machine. There is NO way Microsoft will succeed. They'll demand an exorbitant amount of money per CPU and will not allow the freedom to tweak.
If someone says he and his monkey have nothing to hide, they almost certainly do.
Sure, there are x86 clusters. But there are also an awful lot of IBM supercomputers using Power chips, HP supercomputers using PA-RISC, heck even Apple clusters using PowerPC, SGI machines, Sun supercomputer nodes, and so on. There are a large number of strange and mysterious chips built explicitly for supercomputing that would never be seen in any other kind of use. There are also a large number o different interconnect technologies.
Since Windows is a closed source operating system, are Microsoft volunteering to port Windows HPC to whatever architecture you happen to come up with? What about the bugs that occur when they write this port? How long is it going to take to get Windows stable on an unusual architecture if only Microsoft can change the source but only you can do the testing?
At least with a custom kernel or Linux you can work on the system yourself until it's up and running, and if you're in the business of installing and running clusters/supercomputer, you can probably afford to pay programmers to write an operating system for nodes in that cluster/supercomputer.
Last I heard, the Windows NT 5.x kernel (2000, XP, 2003) was not even endian-clean any more, let alone portable to RISC or VLIW architectures. Why do you think it's has taken Microsoft so long to port to x86-64 and Itanium?
Or are Microsoft going to "mandate" that we use x86 processors for all our cluster needs in the future?
Given that he died in 1996, I guess that would indeed be something worth waking up for.
Not to fan the flames, but get real. I run a homebrew GNU/Linux box (still a 2.4 kernel, I'm lazy) at home, and XP at work. At work I can get almost a week out of a boot before Windows chokes on itself and needs to restart. At home, the local power grid and my lack of a UPS determines how often I restart.
Sure, Win2000 and XP are more stable than 95/98 or the travesty that was ME. So it has "come a long way". But let's not be silly and try to call it as stable as GNU/Linux. One crash a week, hell, even if it were once every six months, still seems pretty unstable to me. If that's an "out of touch" point of view, so be it. An OS shouldn't just decide it's had enough and flake out; I don't care how long it's been running.
Anywho, clustering something even the tiniest bit unstable just seems like a funny idea to me. We've all seen Windows behavior when too much stuff is open or a flaky driver has impaired its ability to operate, things gradually failing, the cursor suddenly trapped in just a portion of the screen, swap thrashing as though it were a sign of the apocolypse... The mental picture of racks and racks full of convulsing, imploding Windows boxen when somebody fires up the wrong version of Quicktime is just priceless.
With .NET bytecode it would (theoretically) be possible to migrate processes between different hardware architectures. You could build a heterogeneous cluster and have processes all running on the hardware most suited to them. In theory, at least. In practice this is an interesting research area.
I am TheRaven on Soylent News
They picked a good title: Cluster, as in Cluster Fsck.
I've witnessed more problems with clustered MS systems than stand alone systems. Drive failovers that don't; SQL failovers that don't; IIS eating memory in clustered mode when in standalone, the same app does just fine, most problems of which require a reboot. And have you ever tried to update the SP or hotfixes on a cluster? What a nightmare.
Anyone who would allow Windows in there HPC environment should have their head examined.
Is there anything preventing Microsoft from grabbing an existing Linux distro, putting some proprietary HPC tools into it, and rebranding it as Windows HPC edition? The possibilities are firghtening.
-m
#
# Modus Ponens
#
I'm sure minesweeper on 512 cpus will be much more fun!
All we need now is a BSOD joke and I'd swear that everytime I read Slashdot it induces a timewarp back to 1998.
How about:
In Soviet Russia, Windows imagines a beowulf cluster of YOU!
Now take it! All my karma! Just burn in front of my eyes!
wasn't this the recomended hardware for longhorn?
c:/> mpirun -np 32 winmine.exe
Signatures are for stupids.
Finally we'll get faster crashes! And faster reboots too! Oh no, they'll need all the CPU cycles they can get to run Longhorn within the Bochs emulator!
cpghost at Cordula's Web.
This sort of statement would be fine if it meant anything. I suppose you are insinuating that Windows is prone to crashing and that other OS's (e.g. Linux) are not. I use 2k at work at XP at home. I never see BSOD.
My wife on the other hand uses Linux at work. She has been compelled to request a move to Windows because Open Office (1.0 and 1.1) regularly crashes the OS when opening MS Office documents. By crashing the OS I mean the screen goes blank and then you get the BIOS memcheck! Irrespective of any arguments about MS Office document compatibility how can a user mode app (Open Office) bring the house down in a supposedly protected OS environment like Linux?
No doubt people out there will be thinking things like, Oh, just upgrade to kernel 2.6 etc. etc. This is fine, but these same people are judging Windows by the performance of Win 95/98. Play fair folks! Have a look at XP - it really is a sweet piece of kit.
I've nothing against Linux but I think that it would be good if people were a little more balanced in their opinions. The whole debate is worse than religion sometimes!
Windows update...
I'm sorry Dave, I'm afraid I can't do that. I am still updating all 1000 systems with the last security patch!
Does that mean that there will be a multi-threaded, SMP-enabled High-Performance version of MSN messenger available in the future?!?
I'm currently admin for a HPC system, and in those long 'hours' of POST-ing several CPU boards, I'd really welcome such an innovation to help me pass the time...
No electrons were harmed sending this message. Wait,
Actually the cornell "theory" center has or at least had a few reasonably large windows based clusters. I did a postdoc over in the CS department ages ago and ported some code over the the linux side. You can basically ssh into the cluster and standard make works (actually I seem to recall having the switch the "/" to "\". The cluster was something like 4 processor boxes glued together w/ myrinet w/ some sort of queueing system. They also had a slew of 2 processor boxes. My experience w/ them was most of the "crashing" had more to do w/ the myrinet drivers and the MPI implementation (which was a commercial MPI). Once those stabilized it ran as well as a normal linux cluster i.e. you submitted jobs they ran :) I went to a day long "windows HPC" conference back then which was a bit entertaining (btw the clusters were basically free for cornell) People only had good things to say about the cluster, but i think its was a bit opportunistic. One thing that was quite obvious was, if machines are free people will run/port to anything *but* when it came to using your own (or grant) money to buy a machine - even over at cornell - which to be honest had quite a stake in "windows based computing" people would go for a linux based cluster (which had already popped up in quite a few departments at that time)
-bloo
Whenever MS makes something it tends to become commonplace and easy to use. If they make windows able to run as a beowulf-like cluster, there'll be thousands of new developers with a reason and platform to make clustered applications for.
Imagine getting a bunch of windows applications behaving like Apples X-code, automatically offloading heavy work to available units on the net - you could give that third overspecced laptop in two years to the PHB, not with a tear in the eye but a grin, knowing that it will spend 80% of its cycles compiling your code instead of running a screensaver.
Imagine being able to share CPU resources from a machine like you share a folder, and being able to immediately use that power for your compiler, database, renderer or whatever?
That would just rock IMHO, no matter who makes it happen.
It is a bit sad, to see all of you slashdotters bashing MS.
;)
Haven't you learned it yet.
Rule#1 NEVER, BUT NEVER underestimate your enemy!
Rule#2 Know your enemy!
MS actualy won most of the ground against Novell in the user access resource sharing space
MS actualy won lots of gound against the formal SQL servers
whereas they had a shaky beginging, they nearly killed all their competitors.
think about it!
1. they laught at us
2. they fear us
3. they fight us
4. and then the victory is complete.
it doesn't just apply to Linux or the opensource community. so stop laughting and get your keyboard cracking to make HPC possible that with a few clicks.
Then you can laught for a while that MS wasted lots of money to develope something to slow.
Klanglor
PS: if you read the zdnet article, MS is plaing to use the unharnest capacity from its desktop with one server to load balance it.
PPS: equaly, MS can win the server, OS can win the client.
PPPS: get your keyboard cracking!
I love this whole idea of Windows on a supercomputer! Just think of how fast a spam drone it would make!
Windows only technical asset is a (relatively) good GUI.
And, as we all know, *ALL* mainframes, supercomputers and servers absolutely must have GUIs!
After all,
Memo at Los Alamos Nuclear Laboratory:
"Please be advised that Deep Blue will be rebooted this afternoon at 5:PM in order to complete the installation of Service Pack 11. All jobs currently running and queued will be lost, even those which have already accumulated several years of processor time. We expect Deep Blue to resume normal operation sometime in early August. Thank you for your cooperation, LANL Informatics Department"
Fire and Meat. Yummy.
Bragging rights? The ability to persuade PHBs or PHDs (pointy-haired deans) that they can save money if the MSCEs that administer their secretary's computer can administer the Physics department's machine?
I wonder if spammers could derive any advantage from taking over a cluster on Internet2...
Yep, Linux never crashes, Linux is great, Linux is good, plus lot's of Linux shit :|
hehe... thanks for keeping me honest guys!
Windows crashes all the time for me. It crashes more often than 95 ever did. And it runs less spiffily than 95 did even on my old retired for parts 233 MHz pentium 1. I see more CPU resources used for no added value. I don't give a damn about one thing the latest windows does that windows 95 doesn't except for protected memory, but even then windows manages to die often in such a way that I can't kill whatever task is giving it a hissy fit. It manages to overutilize a pentium 4 however, for web browsing and email.
Eat at Joe's.
MS Windows is a general purpose OS with lots of overhead built in to support backward comatability. These Giant super computing clusters, in part, are dedicated towards a single purpose, redering images for movies, for example. Does using a general purpose OS that doesn't allow for that level of tuning make sense in a supercomputer? I would guess not, but perhaps there is a limited market. The other issue here is that one of the things that makes these spuercomputing cluters cost effective is that the cost for the operating system is $0.00. If you have a 1024 node supercomputing cluster at perhaps a $1000 a node, based on approx pricing for Win2K Enterprise, that's just over a million dollars extra. That's a chunk of change. Since most programs that require the power of a supercomputer also requires custom programming anyway, why not build it on an OS that doesn't cost you anything that also has a proven track record in this environment? Heck if you're eager to spend an extra $1,000,000 donate it to the FSF. Just some outloaad thinkin' G
Shop smart, Shop S-Mart.
Nothing else to say.
MMO Quests are like orgasms:
You may solo them, I prefer them in a group.
Or better yet, crashing a distributed network. But seriously, this could prove useful. In a couple of years when everyone's got a supercomputer (they'll need it to run longhorn remember, I'm sure someone will post something like "minimal windows for super computers in only 500 mb!" here on /.
This signature has Super Cow Powers
Hey Microsoft, how about letting us write a cluster resource DLL in .NET? It's a real pain to dig out VC++ 6.0 to do it.
Some better examples wouldn't hurt, either.
Chip H.
I've got a half-completed VW Beetle original in my garage with a Porsche 900 turbo engine in it.
I've had some difficulty finishing it, though. It keeps crashing due to the large amount of acceleration, as it appears the VW's suspension isn't built for such speeds.
~/ssh slashdot.org ssh: connect to host slashdot.org port 22: too many beers
Especially if you have old or weird hardware, e.g. an Aureal sound card.
I have had entire clusters go down due to OS error.
As a Linux advocate I would appreciate it if we could all just focus on promoting Linux rather than putting down other operating systems. Constant attacks against Windows are completely unnecessary; attacks against Linux from MS are necessary for them because that is SOP for MS, but two evils do not make a good. We don't have to be like them. We don't have to use FUD as a tactic.
I don't even understand why this article has been posted here in the first place. The only possible reactions it could have drawn given the context are fear and loathing. If the audience response is predictably going to be overwhelmingly negative, why post in the first place? Is the posting of this sort of article equivalent to an Orwellian "2 minutes hate" session? Was any constructive discussion expected?
The ES-7000 is a machine that is up to 32-way (at the time I was using them about two years ago).
Against our wishes our client purchased one instead of a small cluster. Now aside from the price difference, the stability sucked. We were only running IIS, Apache, SQL Server and Tomcat. The machine needed to be rebooted every day. Yes a million dollar machine running windows needed to be rebooted ever single day.
So my point in relating the story is that MS has a LONG way to go before they are able to really handle supercomputer sized machines. But I do wish them good luck, because they have smart people that will bring some good ideas to the table. On the other hand GO {Linux, FreeBSD, OpenBSD}
It is kinda like lada announcing their entry into Formula 1. Sure it can be done but excuse me while I collapse in hysterical laughter first.
People who object to the BSOD jokes mention that XP and 2k3 crash far less (they still do) but forget to mention the insane memory requirements. Oh and don't look at the memory in use reports from task managers. look at what 3rd party programs can use before swapping starts.
You are the first one I read to point out the x-box. Well there is some logic to this. But basically x-box is dos. One task, 1 processor. Not exactly super complex stuff.
With the new x-box if it is everything they hyped it up to be they are closer. It has been said many times before that modern consoles clustered could make an excellent poor mans super-computer.
Just remains the question if MS can cluster their own stuff. In theory there is no reason why not. But in theory there is also no reason why IE couldn't be the best browser out there, windows the most secure and stable, and clippy not so fucking irritating. MS somehow continues to prove they just can't do it.
As for who would buy it? Linux and others are often blaimed for not being userfriendly but me thinks that those who run supercomputers hardly care about a gui and are smart enough to hire good operators.
MMO Quests are like orgasms:
You may solo them, I prefer them in a group.
(not sure if you are a MS apologist but it sure sound like it) As long as you choose hardware with proven drivers and don't run anti-virus software (firewall it and run minimal services and no IE) Windows should be very stable.
Yet whenever Linux fails to run some obscure soundcard or mozilla does not display every webpage exactly the same as IE, then all of opensource has just proven a failure.
The old "If a page fails in IE then it is the pages fault. If a page fails in Mozilla it is Mozillas fault." is still true I guess.
So you can only run windows with certain hardware, with certain driver versions, no Internet explorer and no anti-virus. Riiiiiiiight.
Well it is true enough I guess. I only use my windows machine for games and it is fairly stable. Nothing like my linux machine wich measure reboots in hardware installs and power failures but still, it doesn't crash as much as previous windows.
Your last point however is oddly lacking in historical knowledge. The entire computing community had a history with Unix. Then they switched to windows. Now they are switching back.
MMO Quests are like orgasms:
You may solo them, I prefer them in a group.
Consider the famous 'CALDERA INC.'S MEMORANDUM, IN OPPOSITION TO DEFENDANT'S MOTION FOR PARTIAL SUMMARY JUDGMENT ON PLAINTIFF'S "PRODUCT PREANNOUNCEMENT" CLAIMS"
The purpose of announcing early like this is to freeze the market at the OEM and ISV level. In this respect it is JUST like the original Windows announcement. ...
Mhyrvold elsewhere explained at length how Microsoft killed VisiCorp with vaporware: Microsoft "preannounced Windows, signed up the major OEMs and showed a demo to freeze the market and prevent VisiOn from getting any momentum. It sure worked VisiOn died, VisiCorp died...
Clippy you bastard! How many times do I have
to tell u I am a linux router and I don't
know what a "clusterificated mega throbbery BSOD error - insert floppy disk in drive A" means!... No I don't know what a windows update site is either - perhaps you mean a lindows update site?
And paying a per-user/per-processor licencing fee at the same time.
I'd rather have someone respond than be modded up.
There is no GUI running on any of the processing nodes. They boot up into a multiuser mode off the network, and stop short of starting up Aqua or anything like that. Then they do their thing.
You need external boxes running OSX and local applications that provide a GUI.
THIS THING CAN TURN ON A DIME, MACROSSZERO STYLE ALSO FUCK BETA, ~NYORON
2) Compile BOCHS
3) Load Windows
One of the mainframe guys I used to know at IBM claims to have seen this done (Although I must admit that I didn't witness it personally.)
I'm trying to teach myself to set people on fire with my mind... Is it hot in here?
then again, MS is driven by money. If they believe it is worth it, they may do it.
The statements I partially quoted are not directly attributed to Microsoft (in fact, one is a suggestion by a customer). And even if they were direct quotes from Microsoft, the word "could" carefully qualifies the items as speculation, not promise. Although I have worked for altogether too many software companies who methodically equate "could" with "does".
I'll fix it for you...
I assume that the box has 128MB of memory. If it has more, the issue is probably elsewhere.
I think there is a bad spot on the swapfile. Replace the hard drive. Also, boost memory to 256MB.
Should be fine then.
Ratboy.
Just another "Cubible(sic) Joe" 2 17 3061
like fixing the page cache and swapping behaviors so that the page cache doesn't force sleeping processes out of memory.
You know, little things like that.
Having to buy 2GB of RAM for a single machine is one thing.
Having to buy 2GB for each of 64 machines is a different story.
THIS THING CAN TURN ON A DIME, MACROSSZERO STYLE ALSO FUCK BETA, ~NYORON
Back in the days when dinosaurs ruled the machine room, big customers with big problems and big accounts could get operating system and compiler source code.
The biggest reason Unix became the OS of choice in universities in the 1980s was the availability of source, which made it possible to port it to new platforms.
Linux today is all about hardware flexibility - "Linux on my wristwatch" is still a little funny, but "Linux on my pocket PC/XBox/random-hardware" is not a joke.
The parent post has it right - the bleeding edge usually is on non-commodity hardware, so it will always tend toward I-can-port-it-myself OS solutions.
To a Lisp hacker, XML is S-expressions in drag.
That argument hasn't been valid since Windows 98!
Does this mean that Microsoft will issue a new version of fortran or will we have to use F-flat from Visual Studio? I guess they will also need to issue their own versions of BLAS/LAPACK/IMSL as they wouldn't want someone else controlling low level functionality of the actual HPC code that has nothing to do with Windows.
I make my face look like this and concerned words come out.
You ran windows as your cluster dumbass... THAT'S WHAT HAPPENED!!!!
||| I still can't believe Parkay's not butter.
...excellent comment. Pity about the mod.
The swapping behavior of Windows is really quite outrageous.
I'm using VMWare to run Gentoo under XP and if I have to work with Office and such for a few minutes it starts swapping out Linux...what a pain. You'd think 2GB of RAM would be enough to avoid swapping (~512 for VMWare) but you'd be wrong. Wrong!
Previously, Cornell had been mainly in the IBM camp, running an SP-2 under AIX, and before that, various Big Blue mainframes. So the move to Windows might have been seen as liberalizing!
Personally to me, coming from a university environment, this seemed to be Cornell whoring for corporate dollars as NSF support of supercomputing went into the tank. The technical case for open-source Unix-like software is hard to overcome, but the CEO/CFO mentality is easily swayed toward "supported" MS/proprietary solutions.
Financial applications were emphasized. My one contact with the group was a memorable meeting for the Wall St. crowd that Dell and Cornell put on at the Windows on the World restaurant (dripping irony) on top of the World Trade Center, less than a year before 9/11.
-Bromo
Fiat Lux.
Isn't that kind of like putting cheap gas in a ferrari?
I've started fiddling with Apache on my Powerbook, and looking at the logs I've gotten long strings of slashes and characters and such as a SEARCH request. I researched it, and found that it's an attempt to buffer overflow IIS on Windows.
You hear that Windows? You're junking up my Apache logs. Grr.
Will Apache run on Windows without using IIS? (Maybe an alternative) If so, why use IIS?
I've got more mod points and GMail invi
Isn't Microsoft working on a Quartz Extreem clone to shunt all the GUI work to the graphics card anyway?
Does the Cray YMP support ?
Not so bad after cooling my head down, but...
The only really interesting thing in (r)TFA (I didn't get MS but perhaps there too) is that they redesign their system to use wasted cycles for corporate purposes. Like the google scientific program or so. Also, they surely will try to make a good HPC environment but I doubt it's possible with all that GUI floating around.
BTW, why didn't they make a small kernel that loads drivers, handles processes, does TCP and basic IO, and loads API as DLL when needed... Oops... Sorry, it seems I'm a Linux user. Damn...
WYSIWIG, but what you see might not be what you need
We never intended to release Windows HPC for supercomputing. Our intention was to line out the minimum hardware requirements for Windows Longhorn. We apologize for any confusion this may have caused.
B&S
Imagine having to listen to all thoses machines do the little startup jingle at boot time.
If you try to fail and succeed, which have you done?
It's wonderful, now that:
- spammers can process thousands of spam using the supercomputers they 0wn3d.
- spyware can transceive and process information, catalog and data mine it easily
- worms can spread thousands of copies of themselves using the supercomputers they infected.
- viruses can do much more damage at the speed previously unthinkable before.
- I can watch pr0n in WMV format without the computer crashing to a halt.
Sounds to me like you don't make a living as a server admin.
Anyone who binds lame drivers to their kernal and then winges on about the kernal blowing them out of the water needs to learn something about administering computers.
You want to do this on your home machine? Fine, go for it. You want to do that on production server? Here's your walking papers. Don't ask for a reference.
Microsoft is addressing the trend of using COTS (commerical of the shelf) products to build large to terrascale computing systems. One of the most popular COTS systems is the x86 based platform because it is cheap, reliable and readily available. MS says: "Hey, we run on x86. Let's see if we can get into this market." And I say come on in.
Lots of people assume the big decision to running a multi-machine computer is choosing the OS, but I don't care what the OS is, once you have 2000 copies of it, it isn't that easy to manage. The current supercomputer market suffers from a lack of quality software.
Mainly this stems from some of the attitudes I've seen in this article (paraphrasing):
"We'll run UNIX because it is inherently remotely administratable": OK, and next kernel release for your UNIX, how do you upgrade 2000 copies of it?
"Ok, we'll run Linux and control our own kernel updates and make it run exactly how we want.": Ok, then once you've customized it beyond anything that anyone else in the world wants, how do you keep it updated to new releases? It isn't that easy anymore.
And... "We'll hire some software developers to hack together a solution, it shouldn't be that hard. Some Perl or Tcl/Tk and we're all set.": Psh, ya. That's what they all think.
Anyway, these trains of thought have lead to each major vendor (SGI, HP/Compaq, Cray, etc) having their own flavor of installers, managing agents, OSs/Kernels, etc, but nothing that really develops into a unified effort. Each one of their machines is fairly unique.
This is a place where Microsoft excells. Because they will basically say, "we don't care how anyone else is doing it, here is how we are going to do it". And if history says anything, they'll make it work, and (eventually) it will work well.
I've worked on many gigaflop to multi-terraflop machines and I can easily say that if someone could pull together the resources to develop a system where I can run and manage a 2000 node system as seamlessly as my desktop, they will get my money. "evil empire" or no.
Sorry final rant: Supercomputers are *hard*. Yes, you can hack together a cluster of linux machines in your basement or school and it works great but, along with lots of other things, success doesn't scale. Don't knock anyones attempts to help the community until you've spent 48 hours at a terminal trying to get a couple thousand nodes to hang together long enough to get actual work done.
I doubt anyone in the 'traditional' HPC industry is going to be interested in porting their apps to windoze. Currently, virtually every supercomputer runs some unix-like system, and there is a quite high degree of portability between systems (as there has to be to be able to do HPC - if it takes a year to port your codes to the new machine, then the machine is already obsolete).
This action from Microsoft is proof positive that they are taking notice of the recent accomplishments of Linux and are trying to counter them with strides of their own in areas that are not their specialty.
Either that, or Bill Gates got tired of having Steve Jobs call him at one o'clock in the morning and gloating, "Nyahh nyahh, our supercomputer makes headlines around the world, where's yours?" ;-)
--R.J.
Electric-Escape.net
That's the real reason for the Windows supercomputer...to achieve 300+fps in Doom III and let's not forget DNF; it might even bring the swiftest supercomputer to its knees.
"Look Lois, the two symbols of the Republican Party: an elephant, and a fat white guy who is threatened by change."
You just said it again!
Seriously, how about "Would you like a Super Computer, or a Windows PC?"
--
"Outlook not so good." That magic 8-ball knows everything! I'll ask about Exchange Server next.
Microsoft Windows + Supercomputer = Commodore Vic20
;->
Also, an infinite number of monkeys sitting at computer terminals typing would eventually come up with Microsoft Windows only the result would actually work. In theory.
Longhorn is going to be the the HPC version of Windows!!! Just not in the good way...
the preceding comment is my own and in no way reflects the opinion of the Joint Chiefs of Staff
This reminds me of the one poor soul that lives on the Beowulf list. He's probably the only guy that runs a Windows cluster. Occasionally, he'll post something and the entire list will either point out how absurd it is that he is running windows on a cluster or some other such nonsense. I think more Windows clusters will be a Good Thing, at least for this guy, so that he is no longer alone in the world ;)
What I want to know is when the Linux/FOSS code in the MS clustering code will show up.
The beauty of closed source is: when you steal open source, nobody finds out!
"Overwhelming Evidence?"
M$ will never succeed in HPC because:
- There's no money in it. The HPC market is too small and too expensive for M$ to support. There's not enough thrill in the kill.
- You must customize the kernel. To add H/W CPU perf counter support, remove ACPI interrupts, shrink the kernel's memory footprint, remove/add un/necessary services, etc). You can't do this in a closed kernel like Windows. The M$ solution is to build a monster kernel. That's a no-go for HPC.
- 95% of the HPC community is extremely cost sensitive. They spend as little money on hardware as possible and even less on software. The M$ O/S *starts* at $300 per node, and all its tools are closed, commercial, and so, more expensive (compilers, debuggers, profilers, libraries, etc).
- Few or none of the myriad HPC libraries has ever been compiled on non-Unix O/Ses. Is M$ going to reengineer all of these for Windows? For FREE?
- No HPC support staff or users know Windows. Why should they learn it? Just to please M$?
- All of M$'s fielded HPC systems have been fully underwritten by M$ (Cornell, NCSA, UCSD). This won't happen when *others* have to foot the bill.
Randy
MS Windows isnt suited for theese specialiced tasks at all. Morphing MS Windows to suit cluster calculations will make it a totally different product than MS Windows. What do you need to do big calculations? A spreadsheet, a develpers framework for GUI applications or a nice driver support? MS Windows doesnt fit in and i cant see how it brings anything that big clusters need except licensing costs.
The only thing i can imagine is that MS is pissed about their inability to take on linux where linux shines while linux is inching into every area where windows shines. They still havent recouped much of the amount of servers on the internet they lost to apache. Their effort to sponsor big IIS webfarms havent made any dent into apaches marketshare. Even if they have given Windows and IIS away it was still cheaper with apache and some *nix version. I fail to see how windows should make things easier because you dont really want a monkey making the calculations to put into theese serverfarms. They are used by highly professionals that dont benefit much from ease of use.
HTTP/1.1 400
This windows update will prevent a malicious website from taking control of your super-computing cluster.
Find a job you like and you will never work a day in your life.
One thing that may be a serious hindrance to Microsoft edging into the supercomputing market is that people who do serious supercomputing are fairly reactionary. Note that I'm referring to people who burn the vast majority of the CPU time at the US's national supercomputing centers - astrophysicists, plasma physicists, molecular dynamicists, people who run QCD (quantum chromodynamics) simulation - and also those who work at government labs doing simulations of nuclear bombs and such. Take a look at the various supercomputing center websites - NCSA, SDSC and PSC - and look up the amount of computer times various groups use. Those doing the most computing, and getting the most science done, are doing truly old-school supercomputing
One of the main reasons for this that that these people (I'm one of them) write and use simulation codes that have a VERY long lifetime - in astrophysics there are codes that are 20-30 years old and still in wide use. This is because these codes first and foremost have to solve whatever equations you're interested in CORRECTLY, and second off, solve them FAST. People base their academic reputations on the results of these codes, and are very interested in making sure that they get the right answer. In some fields (astrophysics being the one I know the most about) people can spend 10 years developing and adding science to a code.
Now, this is a reasonable thing on a unix machine. From the user's point of view, one supercomputer really isn't all that different than another. You just need to figure out where the various libraries and compilers are, but once you do that, you type 'make' and are up and running. So if Microsoft wants to break into the traditional supercomputing market, in order to entice hard-core computational scientists into trying their products they'll have to make it so that codes written for unix systems can be ported over essentially transparently - have the same libraries, the same types of compilers, etc. etc. Frankly, that doesn't seem like a likely thing to me. But then again, I'm one of the crusty old school big-iron computational physicists, so my opinion might not be all that forward looking. All I really care about is what platforms let me get my job done the easiest, and that seems to be the various unix and unix-like systems out there right now.
Lets put it this way, you're comparing the relative stability of your average linux box to the relative stability of your average windows box.
Sure, but there is a MAJOR flaw in this argument.
Who's boxes are they?
Of course the basic Linux user is going to be a little more technical.
But let's say each user wants to be hands off (I know I did when I was running Linux). That means just running programs, browsing, occasonally installing some stuff.
I dual booted between Windows and Linux like that for a few years, not really admining either system.
At the end, the Windows install was a half-working pile of crap, while the Linux system ran about the same as it started out. That's just how things go from the way each system is designed, Windows is constantly adjusting the registry and the service packs can wreak havoc at times. Even runnign a background security patcher on the Linux system, stabiliy or decay programs was never an issue.
I know for sure that if I were responsible for just turing a box over to a user and having to maintain the stability of that box, the last thing on earth I would give them is Windows - because I could be sure to have to do SOMETHING to that Windows box over the course of a year, wheras I'd probably leave the Linux box alone without issue. For home users anyone who asks me gets one answer - a Mac. They also do not decay in the same manner Windows do (it gets a little more clogged over time, but not to the same degree).
The Linux side does not have to win at all. Windows does have some nice things about it. There is nothing as polished as Office and calendaring for anything but Outlook is in a bad state. But Windows computers simply decay, that is a fact of life observed again and again and again in the real world, in multiple situations. I am just trying to point that out since you would not admit to that before.
Your replay is not arrogant at all, but you need to go back and re-read your whole thread.
"There is more worth loving than we have strength to love." - Brian Jay Stanley
One thing that hasn't been touched on, and part of the reason Linux advocates criticize MS so much, is that MS is trying to take over the world. By that, I mean they wish to have a hand in everything. Gaming market, PC market, Server market, HPC market, Movie market, Music market, News market.
What's next?
I'm posting this so that you (the moderator) have some context to consider twitter and not mod him up whenever he posts his filler preformatted rants about installing Knoppix or whatever that unfortunately get him karma every single time and allow him to continue posting his trademark toxic crap (read on) day in and day out. You may consider this a troll - I consider it community service. And I ain't kidding.
If you're a /. subscriber, I invite you to look through some of his posting history. I guarantee that you'll be hard pressed to find someone that is more "out there" than twitter. You'll also probably notice he's got quite an AC following. Don't just read his posts, make sure you go through the replies.
For example, in this recent post twitter not only calls the OP a troll but attempts to "tell it like it is" while making some vague argument about "GNU". Yes, if you're confused, you're not alone. The reply (modded +4) proceeds to simply destroy his bogus argument. You will notice he did not reply. This is what some people call "drive-by advocacy". A sort of I'll just leave you with my thoughts here and move on to the next flamebait kind of deal. In fact, he almost never replies because he knows that his fanatical arguments simply do not hold up to any sort of discussion. It's not that he's chosen the wrong cause - he's just going at it in a completely wrong way.
More? Just read though this post and the subsequent replies. I guess this stands on its own.
More? Bad spelling in astounding conspiracy theories, more offtopic FUD and uninformed "I'm right, look at me" rants, promptly proven wrong. Worse even, twitter wants to be RMS, apparently (that first one is a winner). I mean, really. You think?
FUD, FUD, FUD, FUD, offtopic FUD, and more FUD. This guy is like the Monty Python SPAM skit, but with FUD and more FUD instead of canned meat. Amazed
My appologies - I couldn't resist
Bring on the 128-processor home gaming systems!
While you're astroturfing for Microsoft, don't forget to mention that unlike Windows, Linux has no support, is difficult to use, and no "good" software is written for it.
Oh! And that the BSOD doesn't ever happen any more and that cooperative multitasking is WAY better than preemptive.
Microsoft does! Heck, they even testified that IE cannot be removed from Windows, not the GUI, but Windows. It ships on all of their home and server products. And since they say it cannot be removed, I presume the GUI can't either by association. In short : If they make no distinction why should we?
All kidding aside, Windows is as pervasive as it is because of it's UI, not it's quality engineering. Without it, it has no advantage over any of the myriad proven OSes on the market, in fact there isn't much reason to use it at all. In a server room that is. Basically, the same situation we find ourselved in today.
Let us imagine an operating system capable of
understanding mathematical language, being able
to do complicated mathematical operations and
presenting the results in a optimized graphical
way. Think of a kind of intelligent combination of Mathematica and Matlab. Even under these
conditions it would be hard to convince scientists to use it. Just imagine what would
happen if one of the developers made an
unintentional programming mistake...
a beowulf cluster of PCs running Windows...
We will need a new unit for measuring the speed of Windows clusters: BSPS = Blue Screens Per Second (smaller numbers are better)
---
Lousy rotten karmic retribution.
This time wasting os bad/good thrashing should be directed towards productive things such as adding more platform support to the GNU MP Bignum Library ( http://www.swox.com/gmp/#CONTRIB ).
Adding visual studio compatable build/makefiles to this is a necessity.
Computer hardware is just hardware, the OS is less important for numerical computations. Anybody else use the very limited os that came with the intel hypercube?
Now we can get 30 fps on Doom III
So far, they don't compare at all well with various Linux/UNIX implementations. However, I'm sure they'll manage to get their nose under the tent flap where either they paid their way in, or a PHB thinks that it'll leverage his existing stock of desktop machines. My lab built a couple of turnkey systems for the later scenario, where the given reason was that the typing pool cpus could pitch in some cycles to the cluster after hours. What really happened was that the non-com tasked with managing the systems was trained as an MCSE, and he wanted to stick with what he knew, come hell or high water.
Luke, help me take this mask off
You must be doing something wrong. I've run KDE 3.1 on a 333MHz PII and it ran fine. My favorite machine is a 650 Athlon Slot and KDE 3.2.2 works without a hitch. The only thing that's slow is Kmail's mail fetching utility, but you can speed things up with kcron and fetchmail and then simply checking your local mail. KDE is large and offers lots of services, but the whole point was to lessen the burden of those services by creating a rational framework. KDE, which easily fits on live CD's, within your computer's RAM and even on embedded devices is wildly successful at meeting it's goals.
Other nonsense you write about Microsoft's development project compared to KDE's is pure M$ propaganda. Microsoft is incapable of implementing the vast array of changes that people want but free software does so by it's nature. Anyone who might be scared off from trying KDE by comments like this can debunk them in about five minutes by trying out a copy of Knoppix or Mepis.
Friends don't help friends install M$ junk.
``This is on hardware that runs Linux just as well as the rest of my machines.''
Yup, sounds like a hardware issue...
Please correct me if I got my facts wrong.
Maybe they should consider making it useable for ordinary computers first. That whole slither before you can crawl thing.
Where do you think Clippy came from? I've participated in two focus groups and came out of both wondering what kind of mind-disruption ray was being used on me, because in both of them I said some things I really wanted to take back.
You have to be smarter than your users. I realize MS tries really hard to do UI, but they can't seem to do it anywhere near as well as Apple. I think Apple doesn't have to rely as much on focus groups, possibly because they aren't run by robots.
B is already a problem. The windows approach to locking the desktop is utter crap.
It drives me up a tree that for Win2k anyway (I won't do XP - the license is too toxic) the "official" way to lock up a feature is to lock up whatever happens to be the UI they offer. That leaves malware free to make changes, because they do access the API directly, and the hapless user of the desktop can't change it because the UI is locked out.
Concrete example: you can make IE start with a particular page. You can grey out the option to change that page. Hostile website can still hijack the start page. "Oh, gee! We never thought that criminal computer trespassers would ever deviate from the path we selected for them!"
with Linux and Mac doing desktop clustering, it was only a matter of time before M$ had to show something to big business, more a token effort than a real push, IMHO.
There was an unknown error in the submission.
Alredy happened: Ongoing Linux/Solaris Compromise Epidemic.
So we can skip this topic and jump to the next one: We can start speculate about the impact of some Windows HPCs infected with some worm on the Internet. And then speculate further and compare that impact on what we alredy experienced with those hacked Solaris and Linux clusters.
:) or better :| ?
hany
I guess the only thing better than crashing 1 computer at a time is crashing an entire room full at once."
Obviously you havn't used a recent copy of windows since roughly 2001. The "Windows always crashes, so it sucks" argument is void. I've run winXP for 3 years and have only seen it crash twice. Last time I used linux, KDE puked constantly.
You guys are all wrong, MS is just going to start calling a dual or quad CPU pentium a "super computer." Not a bad idea, long horn (a type of cow...) is going to need a super computer to run on, have you seen any of the specs and requirements?
OK, so now you have a big cluster of NT machines of some description that can be used as a high performance cluster - what do you do with it now? The applications that run in those sort of situations does not run on a MS operating system, it has all been written for high performance environments. Any software for this sort of cluster would need to be ported (to a VERY different system) or specially written. It would take as many years to happen as it did for programs like AutoCAD to get windows a chunk of the computer aided design market, instead of only being run on workstations.
I am sure that a lightweight enough OS could be produced by MS (like WinCE) to run without too much overhead, but it would give you yet another version of windows which is not compatable with the others.
Per CPU or per connection licences would put such a system completly out of consideration in a lot of cases. Why get a pile of cheap commodity hardware and OS licences if you can get a Sun of similar performance and a connection limit only imposed by hardware for the same price?
Your sources are simply incorrect. Windows XP 64-bit edition (yes, this is a real version of Windows that ships with Itanium systems) has been running on Itanium since late 2002. XP was also, in fact, demonstrated running on AMD64 (now called X86-64) when AMD debuted its prototype hammer processor line to the public. This occurred months before Suse's linux distro was ready. (Granted, Suse's eventual release beat MS to market, albeit with poor driver support.)
The fact that NT for x86-64 has not been released yet does not mean that NT was difficult to port. NT actively runs on tens of thousands of Itanium and Itanium2 systems daily: IA64 shares almost nothing in common with x86. The hard part lies in getting hardware vendors to supply 64-bit device drivers to make sure that 64-bit Windows looks and feels like 32-bit Windows. Last I checked, nVidia was one of the few vendors that really shined in this area.
The Hardware Abstraction Layer (HAL) subsystem, which is one of the core features of the NT kernel's design from its inception, is what allows Microsoft to port NT with relatively little development effort (testing is another story). Porting NT takes two steps: First, the NT kernel itself (written in C) needs to be recompiled on the target platform. Second, a new HAL must be written for the target platform, mostly in assembly language.
The decision to drop NT support for MIPS and PowerPC was purely business-related: there simply weren't enough sales to justify the support expenses involved with maintaining another release of Windows. I suspect (although I have never heard anything like this mentioned for obvious reasons) that someday Itanium too will eventually be dropped from the NT menu as x86-64 begins to dominate the 64-bit server market.
Zealotry and ignorance go hand in hand. Most of the folks here are so happy using Linux that they haven't peeked out of their own little worlds and looked at Windows in nearly a decade.
I know it's meant to be a server OS, but I'm running Windows 2003. It's easily my favorite MS OS since DOS 6.22, and possibly the best OS I've had the pleasure of using. It seems to share a lot of code with XP, so I have no idea why XP has to face so many problems... this one's fast, stable, pretty secure so far (I'll give it a few years before I conclude anything...) feature-packed but not bloated, easy to use, AND backwards-compatible.
Windows users could easily make jabs at Linux for its weaknesses these days, but what do they have to prove?
windows has been clustering for years, where do you think the phrase "cluster fuck" came from?
I propose Slashdot's new modo -> "Slashdot: a savage hypocracy"
MS is just mad because they haven't written the cluster software, thats why they are throwing $$$ at the trojan authors. They probably want to hire them. =)
Be seeing you...
"wish granted"???? teh wow, twit!!!1! that is teh insitfull title 4 teh yuor post.
Really? Who is selling them? Outside of HP, who is shipping large quantities for Windows? SGI is only shipping lots of Itanium2's in their high performance linux machines for this sort of activity: high perf science. You can probably count the number of Itanic systems shipped by Dell and IBM a week on yer digits w/o getting naked.
I frankly have low thoughts for any app that can ever get so broken you cannot start it up, even with no starting document.
If an app crashes on startup, it should at least offer me an option to erase all settings to give me a chance to have it start up. Of course for Office that probably would be "resintall Windows". I've written a number of apps like that that can at least revert to a state you can use them if something goes terribly wrong.
"There is more worth loving than we have strength to love." - Brian Jay Stanley
/humor
/humor
Playing Quake on a Cluster, 1600x1200@75fps using the conference room retro projector on a 30 feet screen along with 2-300 close friends and relatives...
You're new here ?
It takes 40+ muscles to frown, but only four to extend your arm and bitchslap the motherfucker
Nuff said!
Not in my expierence; my Linux installs always seem to get something broken (keyboard in X, sound, X in general, Gnome shell, UDMA) and I can't fix it. Who do I blame? Myself; I am not very good at Linux (yet).
Why do you blame yourself? Have you tried a bootable distro? I have no idea why you are getting issues like those (keyboard in X!!!) as I have never scene a problem. Mostly if we need a linux box at work we just throw linux on and we are done.
Odds have nothing to do with it, and the number of people with different expierences is irrelevant. I'm sorry that your co-workers have so many problems; what are they doing wrong?
Odds have everythign to do with it apparently. It's not just my co-workers, it's friends, family, and random strangers on the street that find out I know anything about computers!!
So what can I say when a sampling of thousands of people over the years yields problems, and I have about three cases such as yourself that encounter no difficulty at all? How am I supposed to infer from that sampling that Windows is at all stable? I can tell you right now that if Windows were as stable as you claim I would have eated a few hundred less cookies and other foodstuffs throughout my life for helping people with issues.
Something specific has to be broken. Part of the problem is that you are treating Windows like some kind of black box that can't be diagnosed. You shouldn't give up so easily. What is the error message? Is it an unhandled exception or just a message box? Which process causes it? You said it's at startup: how is it started? Find out which objects are opened by the process, and what libraries are involved. You suspect the registry; find out which registry keys are opened and how.
The problem is that for all intents and purpouses, Windows is a black box because oeping that box is very unpleasant. Also MS apps in particular are rather conjoined with that box, thus causing further grief by slightly enlarging the size of the box.
The program in question is PowerPoint. I only suspect the registry because it has been a source of great threchery in the past. Just by running Powerpoint, or opening a powerpoint file I get the error:
VC++ error
Runtime error
R6025 Pure Virtual Function Call
Why would I want to go to all the effort you suggest? Why should I even? I am done, I installed OpenOffice and have moved on with my life. For me I have reached the optimal solution in that I get to keep all installed software, and get an app that is pretty much as good as PowerPoint (in some ways better as they have a few nice features, the UI is just not as polished).
Note that at home I use OfficeX under OSX and am quite happy with that arrangement. The interaction between the app and OS is much more distinct and so dealing with problems that may arise is much easier.
What if I said: The KPanel of KDE crashes every time I start the computer, no matter what I do. This is RH9. How do I fix it?
Is that enough information? If it's not enough information for Linux, how can it be enough for Windows?
Is it really doing that though? Or is that a made up example. Linux has a lot fewer examples of things like these that just die unexpectly after some time of use. Initial setup failures are different than system decay. It's not like my Powerpoint has always been screwed up, and I hadn't installed anything for weeks when it stopped functioning.
Now let's talk about ability to fix. If a Linux app is really having an issue, it's far more feasible to do remote support on that problem by running a few commands (like ps) or send on a core file. Your suggestion of literally debugging what is wrong with Powerpoint or seeing what registry entries it uses is far more complex.
One difference is that the source code is available for Linux, but not Windows. Is that really so big a difference? Sure, if I knew where to look, and knew what I was doing, and had th
"There is more worth loving than we have strength to love." - Brian Jay Stanley
... the Hardware Abstraction Layer? Of hiring Dave Cutler away from Digital?
.NET is to make code "managed" and therefore make the legacy Windows OS less prone to crashing from software not written by Microsoft (and for those portions of Windows components that are re-implemented in .NET). Microsoft is doing this so they WON'T have to re-write Windows to get it away from the kernel/ring 0 GUI and VMSisms. It's such a mess that no billion-dollar pile can fix it.
.NET is just .HYPE in that regard. Or more accurately, an afterthought, as Windows/Itanium is (and Windows/Alpha was). Microsoft has them just so they can say they have a product for those platforms. Same story as always.
Been there, seen that. The only purpose of
Microsoft has no interest in platforms other than x86;
Windows on clusters....Sounds like a clusterfsck to me :)
My MythTV HowTo
Well, it's not as if the dedicated Microsoftie couldn't make Linux crash....
Nor is it impossible for a Microsoftie to keep a Windows box running for a year or more...
But, both of these would require a tremendous amount of effort, because neither is the norm. Normally, Linux doesn't crash. Normally, Windows does.
It isn't so much a matter of what is theoretically possible, but more of feasibility and customer need. Microsoft is really ignorant regarding HPC - they're talking about using it for computing power for an excel spreadsheet or SQL database?! Never mind the fact that the first would have to involve an idiot programmer and the second ignores factors of scale (updateable databases don't scale well in clusters - which is why mainframes are still around. And not to flame, but if your Excel spreadsheet needs supercomputer-class computing power, you're either doing something wrong or you've picked the wrong development environment.)
These folks are profoundly ignorant of what HPC is actually used for. They have no understanding whatsoever of the HPC environment. And this is why, though Microsoft may build it, no one will buy it - just like Windows NT on MIPS in 1996-98 - remember that? Microsoft was supposed to break into the "UNIX Hardware" realm with NT on MIPS, but the only problem was that they sold only 2 copies!
Microsoft simply doesn't have an enterprise mindset. They simply don't know what their customers are using HPC for....
The society for a thought-free internet welcomes you.
Microsoft programmers get frozen with fear when they're dealing with a machine as complex as a PC with MS-DOS.
There were more lines of code in Microsoft's Winfile than there were in all of System 7.
That's how bad they are. Believe it. MS can make a frigging rubber band complicated. Anyone with pride and respect for the industry hates them not because of monopoly stuff but because as programmers (get this Bill) THEY SUCK SO BAD LONG AND HARD.
Microsoft won't hire anyone with a major working record (unless it's to be one of Bill's consiglieri, and that's not a programming job) because they aren't malleable enough. And this is no guesswork - this is what MS themselves say.
So how the F are they going to manage a really complex system?
Just think where we'd be today if IBM mainframes were programmed by Microsoft. What a bunch of idiots. If you ain't an idiot when you walk in the door there, you are when you leave.
And Bill - yes you Bill Gates you little shit - you may be the richest person in the world, but you're a FUCKING ASSHOLE.
The infected university supercomputer is really not that different from the infected campus, which admins have been dealing with for years.
Finally, many university supercomputers are already on the Internet. I've worked with 7 supercomputers at three schools, all had their head (node zero) accessable through the Internet. That was where we logged in, compiled and tested our jobs, and queued them up for running on the rest of the network. Two of the clusters had each node internet accessable, and (interestingly for this topic) one of the clusters, a bunch of multi-processor P3s, was running Windows NT on each box.
//TODO: Think of witty sig statement