Slashdot Mirror
Windows Cluster Edition
eth8686 writes "Microsoft is aiming to have its first cluster version of Windows ready in time for a supercomputing conference this fall." From the article: "The next version of the Compute Cluster edition will extend to Microsoft's .Net programming infrastructure, letting developers write software using the C# programming language, he said."
a thousand blue screens a thousand times faster!
/* oops I accidentally made a comment, sorry */
What is the fundamental difference with the "cluster version" of Windows? OS X clusters just fine and there are no "special editions" other than a few software additions that hardly count as a different OS. And Linux requires very little to get it in a cluster compute configuration.
.Net programming infrastructure, letting developers write software using the C# programming language, he said.
.Net is easier and more secure.
However, Theimer said the cluster version will include some restrictions on how the version can be used to prevent companies from performing standard Web hosting or other functions.
Wow. When you compare this to the standard capability of OS X, it seems like a real rip off. You get reduced functionality. Why?
The first version will reproduce many basic features of Linux clusters, Theimer said.
Then why not use Linux?
The next version of the Compute Cluster edition will extend to Microsoft's
Ah, I see why now. But what impetus is there to use the first version if this is coming in the second version? Kinda like Windows 1.0 I guess.
Although such code runs more slowly than C programs running directly on Windows,
Aauuummm........
writing programs in C# that run atop
Says who? It certainly is/will be easier but more secure is something that has yet to be proven. To date, the track record is not impressive.
Often, Theimer said, it's more important to have a program as soon as possible than to have it running at peak performance, he said.
Ah, the fast food approach to software design. Don't you know that stuff makes you code obese and causes an early demise necessitating frequent checkups?
A third version will include developer improvements to ease programming on clusters. It also will include high-level management tools and will help customers integrate their high-performance computing equipment with the rest of their infrastructure, he said.
This is going to be in the third version of the release? I guess they have been looking at Xgrid, Pooch and other software and it will take them two versions to integrate what others have already got.
Seriously, Microsoft. Please come up with some innovative features and give us something that no other vendor offers or in a package so slick that we cannot help ourselves, but to purchase the Microsoft solution. This is nothing that is not offered elsewhere in the market, but has the appearance of locking us further into a Microsoft paradigm.
You guys have the right idea in that cluster computing is going to be a bigger market than it currently is, but you have to be more hungry and learn again how to ship software that creates desire and meets your customers needs in a timely fashion.
Visit Jonesblog and say hello.
try cluster fuck.
Did anyone else immediately see this as the "first clusterf*ck version of Windows"?
--dv
Insert witty saying or aphorism here.
...a beowulf of^H^H^H
I didn't "see it coming", but it's not unexpected. When was the last time you heard "Windows" and "cluster" in a sentence without some vulgarity attached? Meanwhile, Apple's been in the news with its clusters and is catering to the distributed computing with software like Xgrid and Xsan, not forgetting support for distributed compile in Xcode.
Microsoft is behind on this, and they're now playing catch-up. I suspect we'll see a few cluster-related items from them in the next year.
That what was all this school was for... to teach us how to solve our own problems. -- janeowit
Windows Cluster Fuck Edition?
There, it's been said.
"Look Lois, the two symbols of the Republican Party: an elephant, and a fat white guy who is threatened by change."
It gives new meaning to the phrase Clusterfuck
Imagine having to reboot a whole cluster after the BSOD.
... Beosloth cluster of those.
Imagine a Beowulf cluster of........
No, wait, it's just too terrible to comprehend.
Ripping an new rectum in the fabric of spacetime.
does it run Linux?
Bits of News
Bits of News Giving you the latest bits.
If you're spending $millions on a cluster, it's more useful to spend the money you'd spend licensing MS software on more computers for your cluster.
cost benefit analysis.
oh come on someone was gonna say "beowulf cluster" eventually, and i have "Karma: Excellent" so might as well be me getting flamed
my karma will be here long after I'm gone
Bring on the Beowulf cluster jokes. For once, on-topic.
Don't blame Durga. I voted for Centauri.
Every edition of Windows I've ever tried has been a pretty reliable cluster-f*ck, where's the news here ;)
From the article: "The next version of the Compute Cluster edition will extend to Microsoft's .Net programming infrastructure, letting developers write software using the C# programming language, he said."
Who said that?
At least, that will be the corporate management perception.
This move could put clustered computing in the mainstream.
Agile Artisans
Imagine a Beowulf cluster of ... oh never mind.
On second thoughts, should this be called a "Grendel" cluster?
Let's see... half the resources, twice the security risk and ten times the price???
Where do I sign up to throw my IT budget down the drain?
This is my sig. There are many like it but this one is mine.
...which is what they built DBSOD (Distributed Blue Screen of Death) on top of. You can't call it windows without BSOD. DBSOD over MPI finally gives windows customers what they've been waiting for.
"Although such code runs more slowly than C programs running directly on Windows, writing programs in C# that run atop .Net is easier and more secure."
.NET object too. Or are we suddenly downplaying that "feature" of .NET because MS wants to kill C/C++ once and for all and dictate the terms of how programmers will program.
VB.NET? Managed C++? These things make
I work in the field (sysadmin for a 800 node cluster), and this is pretty laughable. Microsoft is desperate for the "street cred" of being able to handle high performance computing. Sun, IBM, Dell, HP, Apple all have it. Microsoft doesn't.
If they want so much as the proverbial foot in the door, they must 1) release all (as in *ALL*) of the source code under a GPL or BSD license, 2) make it available for free to all comers, 3) have user's 3rd-party apps (ISE-TCAD, CFDRC, etc) ported, and 4) provide a knowledge base equal to (All Linux + BSD hackers) * Google.
And that only gets their foot in the door.
... all those jokes about "will it be able to run Longhorn" or "can it build Gentoo within 3 days".
Even this meta-joke is getting old.
Serious scientific computing falls into one of two implementations: Either a tried and true "dusty deck" implementation, or a coding to some new fangled architecture. If Microsoft is really peddling C# as a distributed high performance distributed computing environment, they probably won't win the hearts of the dusty deck people. It will be interesting to see if Microsoft ports something like a parallel Fortran. C# may provide access to a lot of system internals and the .NET framework, but scientists will have to spend more time porting their code then they might want.
In theory, since this is most likely based on a .NET framework and will be a variation of either WindowsXP or Windows Server 2003, and development language supported by the .NET CLR would work for parallel distributed computation.
As someone who has run code on a Cray and who has 45K SETI@home units I say that choice in the clustered supercomputer OS market is good.
It references the original "coming out" article which states:
So now I'm curious... Are they selling to managers, who use the windows i/f and want to think they can "get the job done" on the new server cluster? Or are they trying to suggest that no one in corp uses un*x systems?
I think what Microsoft really needs to do is come up with a line of kitchen appliances. I for one would buy them. I mean, hey, maybe then I could learn how to cook! Imagine having the same interface on the fridge and the coffee maker! Oh sure, some whiny liberal will probably complain that they don't NEED the percolate button for their ice cream, but this is America! Choice is what made this country great!
Note: /. may edit out the
tags.This tagline brought to you by 1500 monkeys in just under 17 years.
We just got our copy in the mail to test it. We been talking to MS about this for about a month now. We're going to do a comparison of it over clustering Linux boxes. Same hardware for both clusters. See how they perform.
DarkMantle I been bored, so I started a blog.
From the article: Theimer said; "We want to be competitive with something like Red Hat."
That shouldn't be a problem. At these prices Windows 2003 is already cheaper. It's only when you start adding CALs that Microsoft gets more expensive and people won't be buying a lot of CALs for a supercomputing cluster.
I must say "Thats the stupidest thing I've ever heard"
Obligatory Simpson reference, "I'm from Canada, people think I'm a little slow, eh."
Those who can make you believe absurdities can make you commit atrocities. - Voltaire
Looking at the MS licencing, Bill Gates would perhaps be the only person able to afford to run this...
As anyone in industry the last few years, clusters are ABOUT to be the new hotness. This is a good move for microsoft as pretty much most of the clusters out there right now are running some linux variant.
Religion is a gateway psychosis. -- Dave Foley
...Time to move on to the next level of M$ bashing jokes. And no I am not an microsoft apologist either...
Yet again, Sir Bill Gates, KBE innovates and leads the software industry ahead into the future. Bravo.
geez is going to be a fscking bitch
I beat you and I didn't say frist post!
I thought it said Windows Cluster Fuck Edition ..
.. then i realised i was right.
I thought i was wrong
But did i read "Custard Edition"?
HAD
At least a funny, if not an insightful.
What a waste...
1's and 0's should be free.
C# is a winner for these kinds of applications: it is far simpler and less error prone than C++, yet it offers crucial features for compute-intensive jobs like value classes, multidimensional arrays, efficient genericity, overloading, an efficient and simple native code interface, and some other language improvements.
Sun really screwed this up with Java: if they had taken the scientific and numerical communities seriously and added the necessary features to Java, Java could be the undisputed winner in this market. Instead, Sun kept Java proprietary, played politics with it, and ultimately turned into a bloated web applications platform.
Sun has been claiming that they will be coming out with a separate Java-like numerical language, but that will likely be too little too late.
*Sits back*
:(
In Soviet Russia, M...ahh fuck it.
Imagine a Beow...bah never mind
BAHAHAHAHAA - Cluster...baaahhahah - oh you guys are serious - Sorry
If I were building a top 500 tho I think Microsoft would have a hell of a selling job to do. For them I think it's a long, up hill battle against experienced vendors.
A feeling of having made the same mistake before: Deja Foobar
One welcome our cluster overlord from Redmond..
__________ Leave me alone I'm compiling a RPG II program on my S/36...Thanks to metamucil I'm a Regular Meta Moderator
"When you buy a cluster, the price per node in the cluster is going to be reduced" compared to regular Windows, Theimer said in a presentation at the Intel Developer Forum here. "We want to be competitive with something like Red Hat."
This is idiotic. One can download Redhat for free and use off the shelf software to set up a cluster very quickly. I don't think Microsoft is going to release TCO comparisons for this application any time soon.
After all, I am strangely colored.
The term "supercomputer" and "cluster" is used frequently throughout the article and the comments. As I don't deal at all with those things...Could someone help out the less knowledgable and explain. Thanks
Why does Windows want to run inside big boxes?
Because it's got cluster phobia.
Clustering was started on platforms like Sun and Linux. Yet, there is no mention of that in your posting--you talk as if it was Apple and Microsoft. Yeah, Apple has been in the news because they put themselves there.
Cluster computing is still the domain of Linux, BSD, and Solaris, and there is no indication that that is changing at all, glitzy press releases from Apple and Microsoft notwithstanding.
Here's a top 500 server that runs windows. Buy a clue thanks.
Have you ever been to a turkish prison?
Do they seriously propose to put a Windows machine on the TOP500 list? Puhleeeze. These systems were built for performance AND cost rationales. MS isn't going to make an afforable version of this and MS consulting will build one maybe two of these as an interesing project. But that's it.
Starnage. Making a MicroSloth joke is a toss up. The same joke will be modded "Insightful" and "Funny", and then at another simular point, "troll" or "flamebait". What gives?
Also more secure because it gets more fixes (Not because it needs more because it was badly made to start with.) /p?
"I may be full of crap about this game, and I may be wrong, and that's fine." -Jack Thompson
FTA: "Even Microsoft's Excel can benefit, he said, noting that some businesses have worksheets that can take hours to calculate."
Ah, I knew Microsoft would come up with a new way to force new hardware. Now companies will need a server farm to run Office BWE 2010.
(BWE: BloatWare Edition)
Ruby on Rails Screencast
Now you only need 4 AMD 64 3700+'s to make windows as fast as linux on a 500MHz system :)
and coming next, the special "Cluster F*ck" edition of Windows.
befuddled (noun) 1. Unable to create a pithy sig
1's and 0's should be free.
Imagine running Linux under VMware on each node of one of these Windows clusters and using that to implement a Beowulf cluster.
Any increase in computing power is completely offset by the enormous time it takes to activate your cluster. For instance, a cluster size that could compute the effect of green house emissions 100 years out in a matter of seconds, would take 200 years to enter all those cd keys and activate.
Oh yeah, don't read the article as usual... they're not saying it's a cluster version... it's the beta of longhorn and it's system requirements ARE a cluster.
Microsoft has got to fix this naming convention of theirs, unless someone is really trying to tell us in secret how messed up things really are?
"It is a greater offense to steal men's labor, than their clothes"
Wind*ws Cluster Fuck Edition
but not as a whole different version of Windows. It would be good at Universities to have all of the Micro$haft Winblows crashstations handling some of the heavy lifting instead of being idle most of the time while chinks check their webmail.
Quoted: "We have developed Windows for Clusters for those computers with significant processing power, but not enough to run Longhorn" a Microsoft spokesperson said.
First of all, scientists are no dummies; C# is a much nicer language than Fortran 77 and (with the right class libraries) nicer than Fortran 9x, and it's not a very complicated language, so they'll probably just use it.
Furthermore, a lot of scientific libraries are now written in C and C++, for which there are already compilers with CLR backends.
But there is no need to recompile: unlike Java, C# and the CLR have very fast and easy to use native interfaces, so you can just keep your existing binaries and call them from C#. This is also important for calling things like PVM and MPI.
But, yes, you probably will also see Fortran-to-CLR compilers.
Technically, I think C# is a great language for scientific and cluster computing, unlike, say, Java. Whether you want to use Microsoft-designed languages, APIs, and/or software is another question.
Cluster != huge expensive computer engine. With software like clusterKNOPPIX (I was just playing with this today), it's really easy to take all of the computers in a research lab (that are already connected to the internet) and turn them into a load-sharing cluster. This is different from a super-computer, although you can presumably get some of the benefit if you are also running MPI (I haven't tried that locally yet). In case you don't understant the purpose of such a cluster it's so that when I want to launch 100 simulations (say to do a parameter sweep, which is embarrassingly parallel), I can launch them all from my local computer and openMosix will automagically distribute the workload across all computers in our lab.
Personally, I'm glad Windows is getting in the game, just like I'm glad when the US gets competition in the space program. Competition, it's a good thing (tm). :)
Ben Hocking
Need a professional organizer?
17 different definitions, but you'll get the idea
For a BSOD joke?
...it was found to actually be working and when the lack of crashing was investigated, it was found someone went to each server and booted a hacked-up cluster version of Knoppix. No one noticed anything because they couldn't figure out how to use their Windows workstations to connect to it very much either. Stranger still, the CD trays refused to give up their contraband and actually tried to close and break the WinCluster CDs before they could be put in properly.
If my grammar and spelling are off, I am [distracted/tired/careless] (take your pick)
Even Microsoft's Excel can benefit, he said, noting that some businesses have worksheets that can take hours to calculate. Today, such work requires third-party add-ons such as software from Platform Computing. However, Theimer said that Microsoft may be interested in offering that capability itself.
So it'll be twice the cost and half as effecient, and you'll still have to call Microsoft to activate it. Sounds great.
Tluin natha Linux xxizzuss uriu olt bwael mon'tun.
Wow, imagine the power of thousands of computers all linked together and er crashing.
Networked BSOD.
Wow - virus' and spyware for clusters!
128 BSOD's.
...at the development lab already running it!
:%s/Open Source/Free Software/g
YTARY!
You might want to read this post near the top.
You can hold down the "B" button for continuous firing.
Does this mean I have to reboot N*R times when installing (where N=number of nodes, R=number of reboots required when installing/upgrading windows). That would make it 128*7=896 times for a 128 node cluster, based on my last XP install. If seperate install needed for each node, hmm, 128*6h=32 days straight for install. Yay!
This must be how they expect to be able to run longhorn with reasonable end user performance.
A cluster in every home!
Can I run Windows ClusterF under WINE on a Linux Cluster.
I think its just a typo it meant to say Windows Clutter edition
Stop mixing your sci-fi stories! Keep your damn star wars the hell away from my trek! gnar!
...all of the cluster turned into a huge super-spam-zombie.
Think about Night of the Living Dead. Think about the uberpsammer. Think about the spam leviathan.
I'm waiting for the first such incident where such a cluster might push out one million spams a second....
windoze cluster??? = hahahahaha
also considering the EULA of windoze and the high price for a windoze license per CPU, closed source that can not be modified @ the source...
when Linux is FREE & OpenSource, & is much more secure and stable, Linux already makes a great cluster...
this just smells like official MSFT_FUD to me...
What happened to the 'data center edition' of NT/2000 ?
Last i heard that was also clusterable...
---- Booth was a patriot ----
I've always felt the same way... Shouldn't the *TRUTH* be more powerfull to lies? I think this is the achillies heel of religion, their admission that even they don't believe what they say. They don't want alternate viewpoints taught because *THEY* spread the lies, *THEY* spread the FUD.
Religion is a gateway psychosis. -- Dave Foley
Beowulf and Windows
and
Beowulf Cluster Computing with Windows
I followed the link, then downward several levels without seeing any claim this was ever in the top 500. Perhaps I just missed the text. But there were pricing and offers of help, nonetheless, the claims seemed to be circumspect given the performance level of your claim.
Is this my failure, or is your link just FUD too?
You can make a turtle fly at speeds breaking the sound barrier aswell.
Is the turtle designed for that?
Yes.
Is it capable of that?
It's in the Top500 list, isn't it? If it wasn't capable, it wouldn't be doing it. Simple as that.
Please answer those questions
Just did.
So, basically, you implied Windows isn't good enough to run as a Top500 server, someone pointed out that it already does, and now you're defending it by saying, "Even though it is, it's still not good enough?"
This kind of crap really makes the community look immature.
Wow, those have got to be the easiest supercomputers to crack. I mean, wow.... So does that mean that when one crashes, all of them crash? Probably not, because then it wouldn't ever have time to do any supercomputing....
I'll just stick with throwing Linux on a cluster of cell-processor computers, maybe just a bunch of PS3's would suffice....
Then use what many in the high performance compupting field do: Fortran. There is at least one advanced C++ development project I know of that has Fortran as its core deep in the bowels of the FFT routines... for efficiency reasons. It's just plain faster.
Plus, how many buffer overflow exploits have you seen recently on Fortran programs? :-)
-- This
No, customizing a special-purpose supercomputer system is not the same as writing a desktop application. And yes, I know what I'm talking about.
What keeps me going is my inertia.
Using ms-dos 5.0 could be faster than windoz on the same machine. You want it customizable? Use .bat scripting!
I'd just be happy if MS offered high-availability cluster support in C#. Right now, you have to use the generic resource service, and I'd much rather be able to write custom cluster resource dlls in C#.
Chip H.
The worlds greatest virus ... in a cluster!
hmmm!
Someone is going to spend a lot of time on the telephone dictating license numbers to activate an entire cluster...
letting developers write software using the C# programming language
What does this mean? Developers couldn't write software using the C# programming language before?
If you take a look at the worlds largest supercomputing project, it uses a distributed computing system, and it's for the most part os agnostic, but, the target software has not been compiled for _all_ availble platforms. For reference, check out seti@home. Granted, this project is of a scale that it deserved a customized message architecture, so it's quite unique overall.
Clusters in general are utilized to solve problems in a distributed manner. In the scientific community, MPI is used, and in the web hosting world, clusters are used for load balancing and high availability. The reality is, both of these tasks can be very application specific, and operating system agnostic. In theory, there is no reason a properly written MPI application cannot be deployed on a cluster consisting of half linux, and half windows machines. In reality, such applications tend to rely on artifacts of having identical nodes, and it would be a lot of extra work maintaining a code base such that it can be arbitrarily launched on both platforms. Its far more efficient to tune it up for a single platform, and just use the same platform across the entire cluster.
In the load balancing world, same issues will surface. There is really no reason you cant use a mix of windows and linux based apache systems to back a load balancing cluster. Again, it would be a LOT of extra work managing the mixed configuration, and ultimately, that gets kind of pointless.
Out in the real world, clustering did focus in on linux rather early in the game, because it's open source, hence the folks doing clustering had the option to actually make changes to accomodate thier clusters. There are numerous models to choose from, ranging from a really simple MPI implementation where each machine is virtually independant, and simply passing messages via some high level api, all the way down to the OpenMosix implementation where each machine in the cluster just has the appearance of 'yet another processor' on the overall host. In the former case, applications need to be custom written for the cluster, in the latter case, no modifications are required to applications. Two vastly different architectures, that both fall within the buzzword 'cluster', but are so far removed from each other, there is no similarity other than the fact both use a lot of computers.
A move by microsoft to produce a 'cluster centric' variation of windows actually validates the linux cluster more than anything else can in the marketplace. It demonstrates clearly that the cluster buzzword is gaining enough traction in the management mindset that microsoft needs a presence in that area.
It'll be interesting to see what the final form of the product really is. If it's just a set of gui configurators to manage an MPI system, it's really nothing that couldn't have been done as a third party add-on, and an admission that no third parties were interested in tackling this high end portion of the marketplace on the windows platform.
If the clustering system turns out to be a full process/thread level migration system, akin to the mosix implementation, it'll have a lot of potential, simply because applications do not need to be re-written in order to take advantage of the cluster, assuming ofc, the application already has enough smarts to distribute it's workload amongst multiple processors. the last time I checked (and it's been quite a while), excel is not smart enought to distribute it's calcs amongst multiple processors, something to do with the single threaded nature of serial calculation.
The final proof of technical issues will come over the next few years, and it's going to be an interesting thing to watch. There is going to be a significant amount of support business generated in migrating clusters from one platform to the
Actually, clustering started on platforms like Appolo and Cray. Learn some history before you try talking trash. Here, I'll help the education: google for ["oil exploration" clustering]. Look for mentions of platforms from the 80s. Profit.
Cluster computing is still the domain of Linux, BSD, and Solaris, and there is no indication that that is changing at all, glitzy press releases from Apple and Microsoft notwithstanding.
(Emphasis added.) And where do you think Apple got clustering capabilities? [whistles sweetly, waits...]
Really, I don't see anywhere where the GP poster said anything about Apple inventing clustering. Of course, that shouldn't stop you from demonstrating your ignorance and bias on slashdot...
For the record, I haven't owned a Mac in almost 10 years, and I can't stand their legal stance. I am considering an iBook, once I really need to ditch this poor, abused, aging TP running Debian that I type this on... although I do hate the way the keyboard feels.
I forget what 8 was for.
"I felt a great disturbance in the Force. As though millions of processes cried out in terror and then suddenly halted."
-=GuestFox=-
"With all the security and virus reports we get everyday, customers have started to associate malicious code as features."
"Several customers have expressed concern at how long virus take to run, and hackers are complaining about their code exploiting buffer overflows and other security related issues in software development as taking to long to execute and exploit at run time."
"We thought long and hard, how we could optimize efficiency and innovation by innovating ourselves and responding to wishes of our customers."
"Welcome, here is Microsoft Clustering. Never before have your buffer exploits and viruses execute at such speeds."
"We've had excellent feedback from hackers, virus writers et al." -- 'This is great, prime example of Microosoft innovation. Now, my virus runs so fast, the moment you hit the damage is already done! Thanks Microsoft!'
Microsoft reports that they are pleased with the customer feedback, Bill Gates is reported to give a thumbs up and replied with 'Don't mention it'.
I thought we already had a Cluster version of Windows!
:S
Aren't hacked zombie machines actually being run as a cluster and on Windoze as well?
DEAD DEAD DEAD DELETE ME
Your network security may be very tight, even with air gaps in between. However, buffer overflow exploits do not have to be caused by a network attack - they could be caused by something in the data that is being processed. As "supercomputing" becomes adopted for business use, the data being fed to your apps starts to come from external sources and could contain data that contains attempted exploits.
We wrote off network driven buffer overflow exploits for a long time until the Morris worm really showed that they could happen. Data driven buffer overflow exploits may be difficult to engineer but the possibility definitely exists. Don't forget that they might be engineered by insiders with access to design specs, etc. but not actual access to all the data. Submitting a query to the cluster that then triggers an exploit that writes restricted data into your report would be a real possibility and quite useful for industrial espionage. Or, just putting in something that is known to overflow a commonly used library could be used to just crash the cluster as it attempts to crunch the data.
A beautiful lack of a mind... let me make a much of nonsense example and blabber...People like you that make OS into religion need a brain transplant. I am sick and tired and seeing a bunch of morons claiming they know a lot about Windows or Linux and how one is better than the other when in real life they barely know how things work. I just hope someday people like you will learn more about the systems instead of just creating and communicating more and more FUD be it about windows or opensource.
However, Theimer said the cluster version will include some restrictions on how the version can be used to prevent companies from performing standard Web hosting or other functions.
Later: .Net is easier and more secure.
Although such code runs more slowly than C programs running directly on Windows, writing programs in C# that run atop
My question:
If this OS is going to be so hobbled that it can't even play well on the internet, is it really going to be deployed in a way that makes buffer overrun exploits and the like a big concern? If it can only be a cluster, then it's going to be locked away somewhere well away from the pokes and prods of your neighborhood script kiddies.
Just think about all those millions of computer running windows out there, being unused, left on at night, and wasting cycles. Now, imagine if all of these computer could down a service pack that easily makes them part of a cluster...
Now imagine a new virus that takes control of all these computer and uses them to illegally as part of some orgs cluster to hack or break some code...
You maybe slow so here's another link with less text so not to confuse as much as the previous link. Reading is hard isn't it?
Have you ever been to a turkish prison?
I don't use Ms Windoze.
But, millions and millions of people do. And there is a lot of wasted processing power out there.
A lot of distributed computing emphasized on Windows (pseudo) operating-system, because of the vastness of wasted processing power.
Yes, distributed computing is suppose to be cross-platform or platform independent.
But, I see no reasons (technically) why we need a Windows pseudo-OS cluster.
A note to the designer of the system. Make sure they do not connect the cluster to the Internet, please. We have enough machines out there spreading viruses, worms, trojans, spywares, etc. We don't need a super-computer to do that.
Let me say this again (original post got modded out of existence by moderators without any classical education): A cluster of machines with this version of Windows is a _Grendel_ cluster, not a Beowulf cluster. And of course we know who wins the benchmarks battle.
PS: Before modding me down - look up Beowulf/Grendel on wiki.
Ya know what? You're an asshat.
Plus, how many buffer overflow exploits have you seen recently on Fortran programs? :-)
:)
Oh, we have them. We work them the same way as unix mail viruses: on the honor system.
hawk
Finally a system that can run Longhorn!
Hehe, that's nice, now even non-technical people will think they can build a supercomputer.
:-)
:-)
:-), but I still don't qualify windows as server OS)
Maybe that's not a bad thing, but as we all know, windows only gets right(sort of) in the third try or more
Windows 1.0 (crap)
Windows 2.0 (crap)
Windows 3.x (worked)
Windows NT 3.1 (crap)
WIndows NT 3.5 (crap)
WIndows NT 3.51 (worked)
Windows NT 4.0 (crap, I hate it
Windows 95 (crap)
Windows 95 osr2(kinda less crappy)
Windows 98 (ubber sluggish crap)
Windows 98 se(with 98lite works OK)
Windows ME (THE MOST CRAPPY OS IN HISTORY)
Kernel 5.x
WIndows 2000 (crap) You have to reboot to change an IP, what a JOKE!
WIndows 2000 SPx(kinda crappy)
Windows XP (crappy desktop)
Windows 2003(Worked, actually this one I use, is the best server to be used as desktop I know
Win2003 is the best windows yet. And if they base Cluster in 2003 but without the bloat, they might have a chance. Like a post before, customizaton is KEY, and a lean OS too, don't want to spend cycles on stupid processing eyecandy.
Maybe M$ is waking up, more and more they are making good tools to monitor the OS, (nothing compared to Solaris DTRACE), and command line tools.
Cluster = command line progs, not GUI, AFAIK.
So making it possible to automatize CLI functions, is very necesssary.
... and somehow I don't think Windows was either. They both just happened.
This issue is a bit more complicated than you think.
If you want C# then why not mono? Then you don't have to spend the license fees for all those Windows boxen. Seems pretty obvious. Linux already clusters quite well, just add Mono/C#.
Bitter and proud of it.
"C has a really crappy track record of being secure"
C doesn't kill people, sloppy programmers kill people.
C is just a language; it is neither secure nor insecure. It depends on how lazy the programmer using it is. I'm thrilled there's a thing called C# that helps sloppy programmers. Warn me if anybody writes an OS in that bloated pig.
But C by and of itself dosn't mean code is insecure.
Need Mercedes parts ?
Imagine if long horn was entirely scaleable across multiple processors and was also application independent? I mean if your gonna steal an idea why not steal the whole dream! They most likely have allowed the likes of unix/sun/bsd to develop this market before beginning the process of subjecting it. They may be holding there tech in reserve for years to do this. Now the evil empire strikes back. Apple I implore you to fully grid implement OS X now!
Obviously, when I said "yes," I was referring to Windows.
In the same way, Windows was not designed for clustering.
Not that you'd have any insight into the development of Windows NT, but the fact it DOES do clustering already disproves your argument.
Please, mod parent up.
Running Windows on a supercomputer is about like running Embedded XP on a real embedded device, like an elevator control system. It is neither designed for nor is capable of meeting the needs of these markets.
LedgerSMB: Open source Accounting/ERP
I just got screwed up by inconsistent quoting styles, I get it now.
Windows CE is taken, they should call it Windows CF.
Am I the only one that read this and think Theimer and MS have no clue what clusters are designed to do? Using a spreadsheet to do lots of number crunching is an application problem. You are using an application in ways that it was not intended. That's far different than an OS performance issue where your application is limited by what the OS can do and need some way to tweak the OS to perform better. How is MS Cluster going to solve this spreadsheet problem? Is that spreadsheet going to run across hundreds of machines? My solution would be not to a use a spreadsheet in the first place. There must be some other more suitable application.
I may be cynical but I see this as another ploy by MS to expand their revenue by bloat. As their software gets more bloated, the average consumer will be forced to use newer and more powerful OS to run it. I'm sure that MS will be tickled in 2010 when you need a 64 way processor just to run BackOffice 2009 so they can charge your company for a license for each of the the 64 processors.
Well, there's spam egg sausage and spam, that's not got much spam in it.
The NT line (on which, current OSes such as Windows 2000 and XP are based) has always been a full OS.
The Legacy Windows line (Win3.1, Win95, Win98, Win ME) ran on top of DOS for the most part. Arguably, these were mostly shells at the earliest, up through fairly full-featured API extenders, at the latest.)
Project Manager: "Ok guys, you have the week off"
Researcher: "What?! We just got the new 1200 node Windows cluster in!"
Project Manager: "That's just it, we turned it on and got a kernel panic BSOD, it's going to take about 7 days to dump the physical memory"
I am a physiker (Physicist?) and worked with a lot of mathematiker (mathematics?). Until recently I programmed on big irons & clusters. We all used only one thingas : Fortran. We programmed on cray, On Origin, on cluster. And we (many groups over many countries) used Fortran. Why is that ? 40 Years worth of mathematical libraries. Extremly optimised compiler code, generating machine code as packed as direct assembler code. And a community you can talk to to get code snippet or code solutions hand on. MPI with years over years of experience.
... And forcing another language... Only a manager would buy such a system for scientifics, and the scientific would snicker while formating all HD and install an OS where High performant Fortran does exists.
Fat chance in hell any of us use anything *BUT* fortran. Why should we care for new language which do NOT BRING ANYTHING to us and force us to port many many libraries, debug again what is mostly now bug free, and start over ? Man. Get a clue. And Make a MS-FOrtran for that cluster and MAYBE if for the same price we get better performance you might get a chance. But for worst performance and same price
As for security... What security ? By the time your are on the cluster you should already have been thru with security, through a front end. The Cluster is to be used for high performance calculation NOT for securly checking bounds of arrays.
Frankly I think this offer is only directed towward marketing/enterprise which use their cluster for ANYTHING but mathematics.
C. Sagan : A demon haunted world:
http://www.amazon.com/gp/product/0345409469/
visit randi.org
they would be awfully big...
...if the compute nodes can be configured to boot into non-GUI mode because who needs GUI for the compute nodes??
And what about remote access of the compute nodes. WIll openssh be included (via cygwin)?
Carpe Diem: Seize The Day!
Clusterfuck ?!
Yes, but according to the microsoft ad embedded into this article , linux does not have a TCO lower than windows. As a result I'm now going to switch over to MS as a server platform. All I care about is cost, I don't care about how it technically works. I'm glad I saw that ad!
*cough* sell out *cough*
MR. AD !!
Imagine a beowulf cluster of BSODs.
There. I said it. Happy?
Give me my freedom, and I'll take care of my own security, thank you.
Is it MS FAILOVER Server they are talking about ??
In the same way, Linux was not designed for the deskop. It wasn't even designed to have 3D games or be used by joe sixpack, and we've seen the usability problems that have resulted from KDE and GNOME kludging it to do what it was never designed to do. (And I'm sure you're going to say "Of course Linux kernel 1.0 wasn't designed for that, but Linux 2.6 was!" But Linux, while it was (at least supposed to be) a from-the-ground-up rewrite of UNIX, it still kept enough of the original design to be seriously flawed with respect to the desktop (see any usability test) and games (see how many of the games come for Windows and how many come for Linux). GNOME and KDE added to the capabilities, but never fixed the design.
First of all, Java and C# both achieve C-like performance.
Second, researcher time is far more valuable than compute time, so saving 10h of programming time with 1000h of compute time is often worth it.
Third, using a well-designed high-level language improves quality of results: who knows how many of your C-based computations have yielded incorrect results because you failed to initialize a variable or because a stray pointer wrote to the wrong array?
Fourth, even slow, interpreted languages are commonplace in high-end scientific computing (Matlab, etc.): you write the inner loops in Fortran or C and the rest in the HLL. Even if C# were too slow to write the inner loops (which it is not), you can use it in that way. In fact, the idea that you seem to have that a normal scientific researcher is capable of writing efficient inner loops is silly: if you need high performance, you need to use libraries like BLAS, ATLAS, LAPACK, etc., and you can call those from C# as easily as from C or Fortran.
Go visit a few research labs
I don't need to visit one, I work at one. I'm sorry there are still lots of people like you around who evidently don't really know what they are doing, but that's your problem, not mine.
If you think either of these has the performance to compete with Fortran/C for intense numerical computing, I have a few large bridges to sell you.
...
C itself doesn't have the performance for intense numerical computing. When people do intense numerical computing in C and they care about performance, they usually rely on numerical libraries created by specialists. In my experience, the average C or Fortran programmer wouldn't be able to produce a high-performance inner loop if his life depended on it (and they usually don't even know how far away from the limit they are).
If you're going to call library routines for your inner loops anyway, it doesn't matter what you do it from: Matlab, C#, C, Fortran,
Having said all that, C# is actually about as fast as C or Java in practice. Unlike Java, it is very easy to call libraries. Unlike Matlab, you can actually write sequential inner loops in it and have them perform reasonably well.
I don't think I said anything about which C# implementation or cluster tools to use. In fact, cluster computing with C# has already started independently of Microsoft, Microsoft's product announcement just creates more interest in this area.
And, yes, I agree: Linux + Mono is the way to go: a proven, open, high-performance cluster platform with a high-quality, open source language and runtime. I don't think Microsoft will be able to compete.
you've got to be kidding me!
:-)
Then use what many in the high performance compupting field do: Fortran.
Because they are too lazy to learn a REAL programming language. Like C.
There is at least one advanced C++ development project I know of that has Fortran as its core deep in the bowels of the FFT routines... for efficiency reasons. It's just plain faster.
Maybe because you are using the Intel compiler, that chews Fortran and spills highly optimized code. But sorry, you CAN'T beat hand optimization using ASM/Intrinsics in C++ for FFT (or any other kind of code)> just read the bloody Intel manuals!
Plus, how many buffer overflow exploits have you seen recently on Fortran programs?
Zero programs, zero bugs!!
how long until
You are right, I missed the obvious link that was placed second in the note. However, I still find it odd considering the depth to which I searched the Cornell site that they did not mention it along with their other marketing information.
Yes reading is hard when you are trying to wade through uninformative, stupid posts. In this mass of verbiage it is too easy to miss a cogent argument.
Again my error, thanks.
... specifically written to target this system?
clusterf*ck ?
SI (which stands for shark infested) Waters
"I never metadata I didn't like."
No sig for now.
The first thing anyone wants to do who has built a cluster is performance testing.
.NET framework EULA requires that you get written permission from MS before publishing any benchmarking infomation about the .NET platform.
.NET carries the same anti-free speech restriction. So we can probably publicize C# and CLR performance in a cluster, but not comparable Windows cluster performance.
I noticed last week that Microsoft's
I doubt Mono's implementation of
Given that the .NET platform will be supported on the Cluster version, it may make the cluster computing market more accessible to companies who currently employ big mac flipping vb programmers. A standard platform for companies to develop for would certainly make it easier to produce software for the ever increasing complex configurations of clusters, homogenous or otherwise. This should free up a lot of time for the researcher to run experiments. Why should researchers spend more time worrying about parallel algorithms and optimization routines than about their own projects? I see M$ going into the Cluster market like how it introduced DirectX to make audio and video programming easier for the average programmer. Of course, OpenGL was already available at the time, but that's another story. Not every researcher (or undergrad student) is an expert Fortran programmer.
... as if millions of cluster nodes suddenly blue screened in terror and were suddenly silenced.
+1 Funny!
I like my women like my coffee... pale and bitter.
Bitchin'. The entire supercomputing community has been up in arms over the problem of how screwed they are by lack of decent C# support.
This is terrible. Think of how we may all be spammed by those who will use it for the purpose. Windows on non-clusters may become even more unviable due to attacks originating at such clusters. So those who want to use windows may better buy such clusters to be protected from such attacks. M$ will say this later ...
Prof(Miss) A Mani CU, ASL, AMS, ISRS, CLC, CMS, IEEE HomePage: http://www.logicamani.in Blog: http://logicamani.blogs
Correct. A couple of people here seem to be theoretizing about the pros and cons of Windows vs. Linux in a compute cluster. These folks (and M$) disregard the customer. I'm working as a consultant, having done a lot of pre-sales in this realm in the past 2 years. I've seen quite a few invitations to tender, and none of them was saying "if you can provide some more expensive operating system software instead of Linux, just deliver some less cluster nodes. We can live with it."
Somebody here was saying "M$ targets this at customers who are running Windows already". This is ridiculous. NONE of the customers I've been working for does NOT run Windows somewhere, either in the datacenter or on the desktop. But ALL of them want the fastest floating point hardware for their money (this is why Opteron boxes sell like sliced bread in some industries), and not spend ANY money for the operating system. Independent of whether it is a public administration customer like a University or a car manufacturer. Mind you, you cannot buy a new German car any more that was not simulated on a Linux cluster at some point. These customers use all these LS-Dynas, Pamcrashes, Nastrans etc. Do you think anybody is going to rewrite all these applications for Windows? Thrash all the existing standard models and replace them by models for other cluster applications? Nobody there is waiting for Windows as a cluster OS. Rather the hell is going to freeze over.
And last, advertising C# as a fast to use programming language is ridiculous too. This great idea simply disregards the billions of lines of existing code written in C or, mostly, Fortran. This is the customers' real value, their own code. Nobody is going to rewrite any of this code in C# just for the heck of it.
But anyway, M$, show what you have, we're going to see your added value. And if you're going to give it away for free, maybe somebody is going to buy it. I for one am going to ask some of my customers what they think about using an apparently crippled Windows cluster edition instead of Unix or Linux. Or rather - no, I'm not going to do M$'s market research.
open (SIG, "</dev/zero"); $sig = <SIG>; close SIG;
Plus they are a convenient way of locking out competing platforms through differential pricing. Though that's not needed, just having another hoop to hop through is often enough. Getting (or giving) that extra sheet of paper can be too much hassle / politics.
Overall, I've had only negative experiences with MS licensing issues, especially the last five years, and say that you must compare apples with apples. Price comparisons don't count for skeletal systems, you have to take into account the costs for a usable setup.
Beta is broken and the link to classic doesn't work. Stop wasting our time or there won't be anybody left here.