Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

A New Approach To Linux Clusters

timothy posted more than 13 years ago | from the but-you-can-still-use-your-imagination dept.

Linux 143

rkischuk writes: "InformationWeek has an article about a group of ex-Cray engineers working on a new architecture for clustering Linux systems. 'It's not easy trying to build scalable systems from commodity hardware designed for assembling desktop computers and small servers.' Per the article, 'As the number of CPUs in a Beowulf-style cluster-a group of PCs linked via Ethernet-increases and memory is distributed instead of shared, the efficiency of each processor drops as more are added,' but 'Unlimited's solution involves tailoring Linux running on each node in a cluster, rather than treating all the nodes as peers.'" Looks like Cray engineers think about clustering even when they're not at Cray.

Sorry! There are no comments related to the filter you selected.

this brings up something.. (3, Interesting)

xtermz (234073) | more than 13 years ago | (#2112329)

i have been thinking about for quite a while now. Beauwould clusters are all nice and well, but what about joe sixpack with some it background like me who wants to get some sort of cluster going on. what methods are available (be it a simplified beouwoulf cluster or whatever...) for the guy with 3 or 4 old machines who wants to waste some electricity and try his hand at clustering some machines. is it possible to do it without being a CS major, or is it just a matter of having enough time/resources...

Re:this brings up something.. (2, Informative)

gnuLNX (410742) | more than 13 years ago | (#2130177)

Yes. Building a cluster is fairly easy if you know a little linux and some programming. Check out http://www.beowulf.org and some of the other sites about information. I am getting ready to build a 20 node cluster with pentium III 1Ghz processors. I am playing the waiting game right now with the University and shipping company however. If you don't mind writing your own distributed applications ( using CORBA or some other libriaries) then you can set up the cluster as four individual machines. Well actually if you have 4 then one will be the rserver node and 3 will be the slave nodes. the server node will need 2 ethernet cards. It will be the only node that connects to the outside world. The other nodes can then be connected by NFS. One peice of advice. Before you build a cluster you should first decide what you are bui;lding it for. Not all software can scale to parallel computing. You must first design your problem then build your cluster. Many cluster are build and run tailored to the problem they are solving. For instance the cluster I am building will be more like a network of Workstations then a beowulf. But for my particular problem it will work in the same way. There are alot of sites out there pertaining to beowulf clusters. You need some inux experiance and some hacker ethics, but it is dooable by anybody for sure. Have fun

Custom software (2)

AdamInParadise (257888) | more than 13 years ago | (#2141543)

What is important to realize is that in order to use these boxes as a cluster, you will have to wrote you own custom software. Yep, it means C and C++, and hours of hacking.

But as mentioned in a previous post, Mosix can do that for you, if and only if your program can use several instances at the same time. Compressing MP3s is a good example.

Re:this brings up something.. (5, Informative)

baptiste (256004) | more than 13 years ago | (#2144648)

Try a MOSIX Cluster [mosix.org] This type of cluster spreads processes out to the machine with the least load. A Beowulf can be done, but to take advantage of it, you have to run custom software that is capable of parallel processing.

Re:this brings up something.. (2, Interesting)

Raging Idiot (457985) | more than 13 years ago | (#2142355)

Normally I just troll, but this is important.

MOSIX works fucking awesome. I used it to compress MP3s. I ripped waves and stored them on my bad-ass machine. Then I ran a at daemon on my slowest machine and ran compression routines in the at q in batch mode. By running on the slowest machine in the group it guaranteed that the jobs would migrate to the faster machines in the group and the slowest machine remained as a "task manager". It would run instances until every machine was busy, then batch would hold jobs until a machine came free, then it would release and on with the show.

It works EXTREMELY well. Try MOSIX for some serious fun.

Re:this brings up something.. (-1, Flamebait)

Anonymous Coward | more than 13 years ago | (#2142130)

God damn I am so sick of your comments. Are you ready? Because here it comes:

FUCK YOU.

Hey, anybody can do this, not just you. You're welcome.

Re:this brings up something.. (-1, Flamebait)

Raging Idiot (457985) | more than 13 years ago | (#2143068)

Hey, anybody can do this, not just you

Wow, you must really be brilliant to have figured that out, you sperm-burping bitch.

LNXI has cool solution to cooling Beowulf clusters (2)

cworley (96911) | more than 13 years ago | (#2112455)

These folks [linuxnetworx.com] are using standard rack mounts, fitting 5 standard ATX motherboards in 8u of rack space (no special motherboard needed). They mount them vertically which makes cooling much more efficient when piling large numbers of CPU's into a small space.

From the last Cray notice (2, Interesting)

HerrGlock (141750) | more than 13 years ago | (#2113200)

There were a few "Because Linux does not scale well with multiple servers" posts about why someone would use a mainframe as opposed to a Beowulf.

Well, it looks like there are people working on the task. But that's not the real point, the right tool for the right job is the point. A whole lot of processes that do not require another process to finish before the next one is where Beowulfs shine, if you want throughput or process with dependancies then a mainframe is your best bet.

But it's still nice to have an alternative for those of us who cannot afford a mainframe.

DanH

Mainframe? (1)

battjt (9342) | more than 13 years ago | (#2139830)

Is mainframe really the right term? I thought that mainframe usually refered to a IT machine like an IBM 390. One of my client's has a "mainframe" that is only 11 400 Mz processors. The Dell 8 way MSSQL server has more processing power. (and we have verified this with benchmarks and working with IBM.)

Isn't there a differnt term for a very fast computer? Maybe something like "super computer"?

Joe

In the words of Seymour Cray: (5, Funny)

LocalYokel (85558) | more than 13 years ago | (#2115939)

If you were plowing a field, which would you rather use?
Two strong oxen or 1024 chickens?

Re:In the words of Seymour Cray: (1, Funny)

Anonymous Coward | more than 13 years ago | (#2113614)

I'd like to see the chickens have a go at it.

That depends.... (1)

nizo (81281) | more than 13 years ago | (#2115145)

If my neighbor just gave me 1024 free chickens
because he upgradeded to two oxen, and I didn't
like to eat chicken, perhaps getting them to
plow a field would be useful?

Re:In the words of Seymour Cray: (1)

Temkin (112574) | more than 13 years ago | (#2122311)

If you were plowing a field, which would you rather use? Two strong oxen or 1024 chickens?

I've also heard this attributed to one of Pyramid's VP's, while drawing comparisons to Sequent systems. Anyone remember Pyramid?

Temkin

Re:In the words of Seymour Cray: (0)

Anonymous Coward | more than 13 years ago | (#2141579)

One Fall day, Bill was out raking leaves when he noticed a hearse slowly drive by. Following the first hearse, was a second hearse which was followed by a man walking solemnly along, followed by a dog, and then about 200 men walking in single file. Intrigued, Bill went up to the man following the second hearse and asked him who was in the first hearse.

"My wife," the man replied.

"I'm sorry," said Bill. "What happened to her?"

"My dog bit her and she died."

Bill then asked the man who was in the second hearse.
The man replied, "My mother-in-law. My dog bit her and she died as well."

Bill thought about this for a while. He finally asked the man, "Can I borrow your dog?" To which the man replied, "Get in line."

Re:In the words of Seymour Cray: (0)

Anonymous Coward | more than 13 years ago | (#2124683)

I believe this is actually a quote from Mike Ess, not Seymour Cray. Or atleast that is what I heard. Seymour only reluctantly embraced more than one oxen.

Re:In the words of Seymour Cray: (3, Funny)

Black Parrot (19622) | more than 13 years ago | (#2137106)

> If you were plowing a field, which would you rather use? Two strong oxen or 1024 chickens?

Either one makes for a fine bar-b-que, once the plowin's done.

Funny, but about your sig.... (0)

Anonymous Coward | more than 13 years ago | (#2142270)

Would that BBQ be roasted on the 'butterfly ballots' whose results were destroyed by the same democrats who tried to run the clock out and got blocked by SCOTUS? The same democrats who cried foul then destroyed the results (recently) when they couldn't manufacture a coup. THANK GOD FOR THE SCOTUS or we would have had 1960 all over again, with some Daley kin ripping off the citizens of the US.

How does may or shall translate via FSC to CANNOT? Idiot.

Re:In the words of Seymour Cray: (0)

Anonymous Coward | more than 13 years ago | (#2143612)

A guy goes to buy a train ticket, and the girl selling tickets has an incredible set of jugs. He says, "Give me two pickets to Titsburgh...umm...I mean, two tickets to Pittsburgh."

He's really embarrassed... The guy in line behind him says, "Relax, pal. We all make Freudian slips like that. Just the other day at the breakfast table I meant to say to my wife, 'Please pass the sugar', but I accidentally said, 'You fucking bitch, you wrecked my life.'"

Re:In the words of Seymour Cray: (0)

Anonymous Coward | more than 13 years ago | (#2137570)

John receives a phone call.
"Hello," he answers.

The voice on the other end says, "This is Susan. We met at a party about 3 months ago."

John: "Hmm... Susan? About 3 months ago?"

Susan: "Yes, it was at Bill's house. After the party you took me home. On the way we parked and got into the back seat. You told me I was a good sport."

John: "Oh, yeah! Susan! How are you?"

Susan: "I'm pregnant and I'm going to kill myself."

John: "Say, you ARE a good sport."

Re:In the words of Seymour Cray: (1)

Beatbyte (163694) | more than 13 years ago | (#2143639)

Neither.
1024 Oxen.

;-)

Re:In the words of Seymour Cray: (2, Funny)

kiwaiti (95197) | more than 13 years ago | (#2145181)

You have successfully converted your field into a mud hole.
What next?

Kiwaiti

Re:In the words of Seymour Cray: (2, Insightful)

phutureboy (70690) | more than 13 years ago | (#2144518)

Somehow I can't see 1024 chickens all agreeing to go in the same direction at the same time.

Re:In the words of Seymour Cray: (1)

nettdata (88196) | more than 13 years ago | (#2144780)


If you were plowing a field, which would you rather use? Two strong oxen or 1024 chickens?

Well, if the chickens were $2 a piece, and the oxen were $25,000 per, and I only had $5,000 to my name, I'd have to say the chickens.

*yawn* (0, Offtopic)

Max Entropy (239730) | more than 13 years ago | (#2116514)

I tried to post an item on this *months* ago and, of course, it was rejected.

People oughta listen to me...

Re:*yawn* (-1)

Trollificus (253741) | more than 13 years ago | (#2131626)

And to add insult to injury, you were modded down for complaining about it. ;p~

RABBIT RAPE (-1, Offtopic)

Anonymous Coward | more than 13 years ago | (#2116515)

Hemos and JonKatz made their way into the lab where the animal experiments were conducted. A cute, fuzzy rabbit had caught their eye...

The evil duo quickly subdued the little lab rabbit. They strapped the now helpless animal's head to the sex table with hot leather. JonKatz had the urge, and removed his pants, which were now buldging. After slipping off his briefs, JonKatz tightly fastened the leather straps and was ready to begin.......

JonKatz began to "grease up". Shoving endless amounts of vaseline and baby oil all around the rabbit's ass, he slid his purple head firmly into the rabbit's tight asshole. Even though the rabbit was slightly unconscious, screams of pain were constanly being emmited. Hemos reached for the chain whip and smacked the rabbit's soft nose until its face was soaked with blood. Now, with the rabbits head drooped over the edge of the table, JonKatz continued his sex hunt. His now tingling cock was pushed deeper and deeper through the thick layers of skin which covered the bowel tract. Five, six, seven, then finally all eight and 3/4 inches were plunged deep within the animal's love canal.

JonKatz's manhood tingled with every slight movement of the now half alive rabbit. He began rhythmically sliding in and out, moaning with pleasure on every thrust. JonKatz worked himself into a hot orgasm. The blood, now coming steadily out of the rabbit's ass with every thrust of JonKatz's pelvis, could be heard dripping on the floor. JonKatz's rate increased and with a final push, he spurted creamy white love gel far up into the rabbit's bleeding ass.

The blood and cum mixed together on the floor, which had now accumulated a large puddle. Unknown to JonKatz, the semen had acted as a powerful enemma for the rabbit and out ushered the contents of its intestine. The stool was loose and soft. It fell to the ground with a soft thud and broke into small pieces. The obnoxious smell caught JonKatz's attention, and no sooner had he fallen to the ground and began licking the large puddle of blood, sperm, and stool. Exited at JonKatz's enthusiasm, Hemos dropped to his knees and also began to slurp the foul mixture.

After cleaning the floor with their tongues, JonKatz and Hemos checked on the battered lab rabbit. It was barely able to hold its head up, as it had lost control of most of its motor fuctions. Feeling no pity for this sexually mistreated animal, they unstrapped it and tossed it across the room, only to make a loud and deep thud against the wall. Its blood soaked fur left spatters of red stains everywhere it touched. Hemos reached for his chain whip, while JonKatz grabbed a pair of rusty hedge clippers (one of the many torture devices carried around for "convenience"). They made their way over to the rabbit. The rabbit was struggling for every last bit of air it could, just gasping and wheezing.

"Awwwww. Poor little thing," Hemos maniacally laughed. He raised his arm and thrust the cold metal whip down, exposing the rabbit's bloody flesh. He kept whacking and whacking at the furry bag of blood. Then, when Hemos stopped to catch his breath, JonKatz stepped over with his rusty hedge clippers. He knelt over the rabbit who was knocking loudly on death's door. JonKatz took a quick glance at the clippers, grinned, and then thrust them deep into the body of the rabbit, obviously hitting many arteries. As the blood squirted into JonKatz's face he moved the clippers around in hopes to find a thick bone to crunch. "Aha! The femur!" he yelled out with excitement. JonKatz wedged the clippers against the bone. He opened them wide......then closed down on them with all his might. The bone could be heard deep inside the rabbit, being mutilated. Death had glazed the bunny's eyes.

The rabbit lay dead, a bloody mess on the floor. Its bodily fluids freely surged across the tiled floor. Then with a look of extreme satisfaction, both JonKatz and Hemos lit up some smokes, gathered their belongings and quietly left the hospital grounds, knowing with confidence that they would strike again, somewhere, soon.

Request for help (5, Interesting)

tbo (35008) | more than 13 years ago | (#2117017)

I'm trying to design a specialized data-fitting program to be used for accelerator-based condensed matter physics (and maybe ultimately other branches of science as well). I need information on adding clustering support to this program. Here's a brief description of what the program does:

The user writes a small chunk of code that calculates the function they're trying to fit the data to. We require the user to code the function him/herself because speed is important, and some of these functions are too difficult for Mathematica or the like to fit. Once the user writes their function, it's linked (dynamically) with the rest of the code. The user then passes in a parameter file, and away it goes.

Many of these fits can take days, and, since they often have to be repeated many times with slight changes to the fitted function or initial parameters, this is a serious concern.

Can this new approach to Linux clusters be used here? We have tons of Linux boxes lying around that are being used for other things, but have lots and lots of spare cycles. We probably couldn't afford a dedicated processing farm, but we could easily live with something like distributed.net where the program transparently takes all the spare cycles.

I know the problem is parallelizable, since each node can calculate the value of the function at a few of the data points, then send back to the "master" the chi-squared contribution of those points. Each iteration of the fitting process, the master sends out the current parameter values, and then the nodes grind away... There's not too much communication required.

One of my big concerns is how to get the user-written function from the "master" computer to all the "slaves". It's unrealistic to expect the user to manually install it on all the machines each time something in the function gets tweaked and it's recompiled. Are there pre-existing standards on how to send code to nodes in a cluster, then have it executed?

Any advice or pointers to good starting places on distributed computing would be much appreciated.

BTW, as a hint to all the other comp sci geeks out there--physics is a great place to find new and challenging computing problems (I'm not claiming this is one). In particular, the particle physics people often have to deal with spectacular data rates, and do extremely complicated event reconstruction. Check it out some time.

Re:Request for help (2, Informative)

laertes (4218) | more than 13 years ago | (#2112458)

The most obvious solution is to use some sort of byte code, but you said that speed was an issue. If you're using Linux, you might want to look into dl_open, a library call. Dl_open lets you load dynamically linkable libraries at run time.

I would imagine you would use this as follows; first, you'd get some data points with which to calculate from a server. Then, you'd also get the name of a shared library which is on a server (NFS mounted probably). This library has a function name 'calc' or some such that does that calculation. You can then call that function, and post the results somewhere.

I would avoid using MPI or PVM, since those are not designed for farming out data the way you are. You should probably use your own job control protocol. Also, you might want to allow for multiple archetectures, naming the library foo-0.0.1.i386.so and foo-0.0.1.alpha.so and so forth,

Re:Request for help (5, Informative)

san (6716) | more than 13 years ago | (#2128822)

Hi

The normal way to operate a cluster is to have a shared (NFS) file system across all the systems, thereby solving the data distribution problem (please note though that this prevents you from doing too much file base IO because it's too slow, you might want to make a local /scratch directory on each node)

Besides the NFS share you'll need some kind of parallel programming library like MPI or pvm, and a job scheduler of some sorts. The libraries you can find on the web (maybe in precompiler RPMS, look for the mpich MPI implementation for a start), and will provide you with a programming framework for doing all the networking and setting up the topology. The scheduler can be as simple as the one provided with MPI/pvm (ie. you name a few hosts and your job gets run on those), or, if there's a number of people accessing the cluster at the same time, you might want to try a real queuer (like gridware [sun.com] ).

The parallellization is something you'll have to do yourself and it's the hardest part of clustering.

Hope this helps :-)

Re:Request for help (1, Informative)

Anonymous Coward | more than 13 years ago | (#2130042)

Check out http://www.cs.wisc.edu/condor/mw/

Re:Request for help (2, Informative)

mj6798 (514047) | more than 13 years ago | (#2139138)

Can this new approach to Linux clusters be used here?

Use PVM or MPI. Both exist prepackaged for most major Linux distributions.

I'm trying to design a specialized data-fitting program to be used for accelerator-based condensed matter physics.

I think this may be a case where a bit more thinking and literature research about the problem would help a great deal. People solve extremely complex data fitting problems on modern PCs without the need for parallel processing, and there are very sophisticated algorithms for doing this. You should probably talk to local experts in statistics, computer science, and pattern recognition.

Re:Request for help (2)

tbo (35008) | more than 13 years ago | (#2115967)

I think this may be a case where a bit more thinking and literature research about the problem would help a great deal.

We're looking at using MINUIT [wwwinfo.cern.ch] , a package written by the computing divsion at CERN [welcome.cern.ch] , as our fitting engine. MINUIT's algorithms are quite advanced, and it's commonly recognized within the physics community as the best general-purpose fitting package out there.

I think you may not realize how complicated the functions we're trying to fit are. Here's the quick and simple version: we study magnetic fields within superconductors and semiconductors on a microscopic level. We do this by using spin-polarized muons or radioactive light ions as a probe, and measuring anisotropy of the emitted decay products. That data then has to be compared against complex models of superconductivity. The computationally expensive part here is calculating the values predicted by the model for a given set of parameters. This has to be done once for each data point to calculate chi-squared, and repeated many times (once in each iteration of the fitting process), each time with different parameters. The models typically contain difficult integrals which must be evaluated numerically thousands of times with very high precision.

Since the function we're trying to fit changes fairly often depending on the sample and measurement techniques used, it's not practical for us to spend huge amounts of time optimizing each individual function to be fitted. The fitting package is already optimized, so the only thing left is to parallelize it.

Re:Request for help (1, Informative)

Anonymous Coward | more than 13 years ago | (#2140461)

Divide the number of data points by nodes on your network. Associate each data point range with IP's of the available machines. Set it up so when the program runs, it will check the IP of the computer that's running it and process the approriate datapoint.

Set up nfs and then write a bash script that will execute whatever gets sent there.

When you wanted to run something, you would just copy it to the server nfs directory and all the nodes would process their respective datapoints, automatically.

Re:Request for help (1, Interesting)

Anonymous Coward | more than 13 years ago | (#2144653)

This problem is trivially easy if you use any of the well developed architechtures for distributed parallel computing. MPI is the most popular, PVM was, but is going out of style. MPI is a cluster based interprocess communication system + remote program invocation. Look at the websites of the major open source implementations of the MPI standard, MPICH (from Argonne Natl. Labs) or LAM/MPI (Notre Dame Uni.) for more information. There's a ton of tutorials and on-line training courses online. -Colin

Some options (2)

truthsearch (249536) | more than 13 years ago | (#2144961)

This article [byte.com] covers three distributed OS options, with some intro explination of the difficulties. I would think the easiest (not necessarily the best) solution could be to use Mosix (listed last in the article) and thread your application to a logical extent. Mosix won't interfere with your current linux boxes, just add it on. The tasks will automatically be load-balanced among the machines.

Dimishing Returns..... (1)

Wiwi Jumbo (105640) | more than 13 years ago | (#2117843)

'As the number of CPUs in a Beowulf-style cluster-a group of PCs linked via Ethernet-increases and memory is distributed instead of shared, the efficiency of each processor drops as more are added,'
Does that mean you could reach a point where adding another node actually slows everything down?

Weird....

Re:Dimishing Returns..... (1)

Chakat (320875) | more than 13 years ago | (#2128951)

Does that mean you could reach a point where adding another node actually slows everything down?

Kind of. You just start blindly adding nodes to a cluster, efficiency drops as the processes are deadlocked more and more, waiting for that relevant network traffic. You may not ever reach negative efficiency, but you will get no gains, therefore, just burning electricity.

Speaking of burning electricity, I wonder if I should start back up implementation of my crazy idea of a PC/Mac/Sun/NeXT/SGI/Alpha/VAX/RS6000 cluster...

*yawn* Already been done (0)

Anonymous Coward | more than 13 years ago | (#2118378)

This idea isn't new at all and has been in practice for a long time in both large machines and in clusters. In clustering, for example, the C-Plant at Sandia uses this type of topology and is on the Top500. I'm pretty sure they have published papers on their topology.

My head hurts! (0, Troll)

Dutchmaan (442553) | more than 13 years ago | (#2118748)

Can you imagine a Beowulf-cluster of beowulf-cluster posts...?

Re:My head hurts! (-1)

Raging Idiot (457985) | more than 13 years ago | (#2113474)

SHUT THE FUCK UP. Seriously. You are the reason your head hurts. It's all that vacum inside your head trying to cave in your skull. Fucking moron.

Can you imagine... (0)

Anonymous Coward | more than 13 years ago | (#2127979)

Can you imagine... wait. I think they already did.

Well, then imagine Natalie Portman Naked & Petrified, then it's ALL good.

Re:My head hurts! (1)

ackthpt (218170) | more than 13 years ago | (#2144675)

I resisted the urge.

However, after reading the article, I suggest you go back and update all the previous "Imagine a Beowulf Cluster of ..." posts, as they're now rendered out of date.

Thanks.

Imagine a Beo... (-1, Troll)

TrollMan 5000 (454685) | more than 13 years ago | (#2118749)

ahhh...never mind.

Re:Imagine a Beo... (-1)

Raging Idiot (457985) | more than 13 years ago | (#2114988)

SHUT UP ya fucking moron!

Plan 9 style architecture? (1, Interesting)

Anonymous Coward | more than 13 years ago | (#2121823)

How in general is this different than the approach taken by Plan 9? (http://plan9.bell-labs.com/sys/doc/9.html)

here's another approach... (-1)

GaylordFucker (465080) | more than 13 years ago | (#2122103)

don't install it! use Windows 2000 instead... face it... it's a stable operating system

(You forgot the elipse.) should read: (-1)

CmdrTaco on (468152) | more than 13 years ago | (#2138658)

use Windows 2000 instead... face it... it's a stable operating system...

... on Bizzaro World!

Re:here's another approach... (-1)

l33t j03 (222209) | more than 13 years ago | (#2144142)

Open Sourcers tend to have difficulty facing reality. Thats why there are so many vaoprware articles on Slashdot, these people whould rather live in the world of make-believe.

They like to delude themselves into thinking that Linux is a serious, enterprise class operating system. They like to think that there is important work being done at Sourceforge. They actually believe the RIAA won't win, that Microsoft will go out of business, that the DMCA will be repealed. Open Sourcers like Star Wars, Anime, and Quake. They like RPGs, Aeon chairs, and Lego Mindstorms.

Why? Anything to escape reality. An Open Sourcer substitutes these synthetic experiences for the real ones that normal people enjoy. Their world is shit and they know it. Building a robot out of Legos (compelte instructions provided) makes them feel smart. Gunning down an electronic foe makes them feel badass. They damn well know that they can't compete in the real world, so they entrench themselves in an electronic substitue where, if they just hit Continue often enough, they will someday be adequate.

Of course the reaction to this kind of truth will be savage. They will posture and babble and thump their chests. Thats what is often called a 'compensatory facade'. Deep down they know they are weak, they just can't admit it.

Re:here's another approach... (0)

Anonymous Coward | more than 13 years ago | (#2133593)

That would have been a really nice troll, if it wasn't so obvious. Try harder.

My company's approach to Linux clustering (-1, Offtopic)

Anonymous Coward | more than 13 years ago | (#2125264)


I put my dick in it.

Imagine.... (-1, Offtopic)

Anonymous Coward | more than 13 years ago | (#2128820)

a beowulf cluster of these.

Yo *Nix Rap Yo (-1, Offtopic)

Anonymous Coward | more than 13 years ago | (#2128821)

I eat meat, I tickle your feet, I ask for slashdot news it's neet,
but today i saw an fbi bird, it tried to eat my honey word.
Red worm ran, into the can, of win doze boxes, then sent some spam,
to see if they could pester the man, who tries to run our nationalized
land.
Read the posts, chase the ghosts, who penetrate our servers and hosts,
and you will come to learn to be, a non-elite computer hacker like me.
if you need help, send me mail, I will gladly flame your tail,
only after youve been inseminated, will my info be disseminated.
That is right, I make light, cuz i dont get none night to night,
but if a girl will come and get me laid, I'll make more funny for all to
read. :)

I can't believe it (-1, Troll)

Anonymous Coward | more than 13 years ago | (#2129601)

I got a FUCKING FIRST POST

Hell-FUCKING-Yeah!

Now This is scalable... (-1, Offtopic)

Anonymous Coward | more than 13 years ago | (#2130067)

A pregnant woman walks into a bank, and lines up at the first available teller. Just at that moment the bank gets robbed and she is shot three times in the stomach. She was rushed to the hospital where she was fixed up. As she leaves she asks the doctor about her baby. The doctor says,

"Oh! You're going to have triplets. They're fine but each one has a bullet lodged in its stomach. Don't worry though the bullets will pass through their system through normal metabolism."

As time goes on the woman has three children, two girls and a boy. Twelve years later, one of the girls comes up to her mother and says "Mommy, I've done a very weird thing!"

Her mother asks her what happened and her daughter replies, "I passed a bullet into the toilet." The woman comforts her and explains all about the accident at the bank.

A few weeks later, her other daughter comes up to her with tears streaming from her eyes. "Mommy, I've done a very bad thing!" The mother says, "Let me guess. You passed a bullet into the toilet, right?"

The daughter looks up from her teary eyes and says, "Yes, how did you know?"
The mother comforts her child and explains about the incident at the bank.

A month later the boy comes up and says, "Mommy, I've done a very bad thing!"
"You passed a bullet into the toilet, right?"
"No, I was masturbating and I shot the dog"

Re:Now This is scalable... (-1)

Raging Idiot (457985) | more than 13 years ago | (#2138959)

BOOO! That was an extremely lame one. And, it's older than me. So fuck you.

From what I can gather, (0)

Anonymous Coward | more than 13 years ago | (#2130571)

They're going to have some nodes in the cluster dedicated to message routing with a specially optimized version of Linux. Which would mean that adding an extra node would increase the load on the router node but not the other nodes in the cluster. Is this correct? And if so, is this revolutionary stuff? Just that it sounds a bit like applying som common sense to me.

I wonder... (1, Funny)

Johnny5000 (451029) | more than 13 years ago | (#2131475)

I'm wondering if the rest of the engineers groan when one of them takes a look at a computer and says:

...

(clears throat)

...

"Imagine a beowulf cluster of these things!"

-J5K

Re:I wonder... (-1)

Raging Idiot (457985) | more than 13 years ago | (#2119821)

I have a special message written by the executives of my company directed at commentors that feel they have a brilliant observation, yet are truly just intellectual midgets trying to prove they are slightly taller than the other midgets around them.

...

(clears throat)

...

FUCK YOU!

Thank you very much.

Cray machines are all about parallel processing (2)

Rosco P. Coltrane (209368) | more than 13 years ago | (#2132906)

"Looks like Cray engineers think about clustering even when they're not at Cray."

Well, duh, Cray machines are massively parallel processing machines, so they're not clusters in the sense that they don't use network cards and separate computers as basic computing units, <OVERSIMPLIFICATION>the processors talk to each other on the same bus and share the same memory</OVERSIMPLIFICATION>, but basically in either case it's about parallel processing. I *hope* Cray engineers think about clusters. I'd hate to see them think about single Athlon supercomputers ...

Re:Cray machines are all about parallel processing (2)

bmajik (96670) | more than 13 years ago | (#2143343)

Not So fast.

The CRAY 1, 2, XMP, etc etc are all VECTOR machines. Some of them happen to be parallel vector machines (multiple VECTOR processors)

The T3 series are the MPP boxes. Cray's bread and butter was VECTOR machines though. MPP came about because some problems aren't easily vectorizable (but can run on MPPs, oddly enough).

No there there (0)

Anonymous Coward | more than 13 years ago | (#2135745)

Why post this article? It says "we're CRAY folks and we're doing cool stuff with LINUX to improve BEOWULF clusters." a) there's absoutely no meat here - just buzz words. b) Almost no one cares about scaling clusters to thousands of nodes for any reason, even fewer for running parallel codes. c) An EFFECTIVE cluster with thousands of nodes running PARALLEL codes isn't a Beowulf. The Beowulf name applies to SINGLE USER clusters assembled from COMMODITY Off-The-Shelf components. Cluster this size spend most of thier time running lots of smaller jobs rather than devoting the whole machine to a single problem (so, not single-user), and you can't scale many (any?) parallel codes to a thousand nodes using commodity hardware.

Gnutella parallel... (2, Interesting)

Saeger (456549) | more than 13 years ago | (#2135746)

Sounds to me like they've rediscovered the concept of a supernode where it's acknowledged that not all peers are created equal.

(I know--not the best analogy)

fcp! (-1, Offtopic)

Anonymous Coward | more than 13 years ago | (#2137247)

first cluster post!

The Real Problem (2)

GrEp (89884) | more than 13 years ago | (#2137588)

The real limitation of Beowolf style computing is RAM. Beowolf is great if you have programs that paralellize with little intercommunication and low RAM usage. The bigger problem is RAM. Big iron like Crays/SUNs/SGIs all have about a Terabyte of RAM in one place. When you are trying to do large physics calculations you usually have a huge data set you need to store for every time series. Supercomputers aren't cool just because they are fast, but because they can hold HUGE amounts of data in RAM for easy acess. Until PCs get a few gigs of RAM per box cluster computing is still going to be Kludgy no matter what kind of message passing scheme you use.

A new light... (0)

snadsnad (451797) | more than 13 years ago | (#2137590)

Seems to shed some new light on the previous post about the Cray SV1 and people dispelling Beowulf [slashdot.org] .

Re:A new light... (0)

snadsnad (451797) | more than 13 years ago | (#2142638)

more exact link to the thread here [slashdot.org] .

Gotta say it... (-1, Redundant)

Anonymous Coward | more than 13 years ago | (#2137591)

how 'bout a beowulf cluster of these clusters?

Duh! (-1)

Raging Idiot (457985) | more than 13 years ago | (#2125898)

Derere, da your pretty funny. Daher,der funny.

SHUT THE FUCK UP! God please, all the stupid fucking jokes here. It's like listening to the conversation in a high-school boys locker-room. Fuck! FUCK FUCK FUCK! I'm not even supposed to be here today!

Re:Duh! (0)

Anonymous Coward | more than 13 years ago | (#2109688)

I don't know if you know this, but cum streaks if you don't clean it up right away.

Re:Duh! (0)

Anonymous Coward | more than 13 years ago | (#2137373)

but if you let it sit for a few months it becomes crispy and is easily flaked away with a fingernail, putty knife, or similar scraper. YMMV, depending on the surface, namely, how porous the surface is.

Re:Duh! (0)

Anonymous Coward | more than 13 years ago | (#2144199)

Wanna go play hockey on the roof? I brought a ball, just one though.

Mixed architectures. (1)

Demon-Xanth (100910) | more than 13 years ago | (#2138663)

Would it be concievably possible to use mixed architectures and assign certain tasks or routines to the architecture best suited for them. Rough example: 200MHz Pentium and 200MHz Cyrix system in the same cluster. Two calculations need to be performed, one interger, one floating point. Send the interger to the Cyrix and the floating point to the Intel. Rather than fight with some platforms being better than others at certain tasks, work WITH that fact.

Re:Mixed architectures. (0)

Anonymous Coward | more than 13 years ago | (#2124129)

Yes, this has been done for a while, usually assignment by hand of the programs that run on which nodes. The hard part is getting an automatic reservation system to figure this out for you. There are some batch schedulers that can schedule this type of stuff for you but you still have to identify which nodes will run what program. In the embedded space this has been an issue for quite a long time. For example an embedded machine may have X number of GPUs (i.e. G4s) and Y number of some DSP (i.e. Sharcs) nodes in the same box and you want the appropriate nodes to do the right things.

fp (-1, Offtopic)

Anonymous Coward | more than 13 years ago | (#2140548)

fp!!!1

Author Stephen King, dead at 54 (-1, Offtopic)

Anonymous Coward | more than 13 years ago | (#2141103)


I just heard some really sad news on talk radio - Horror/fiction writer Stephen King was found dead in his Maine house this morning. I'm sure we'll all miss him - even if you didn't read his books you've probably enjoyed one of his movies. Truly an American icon.

A cheaper alternative (4, Funny)

HRH King Lerxst (79427) | more than 13 years ago | (#2141104)

I like the idea of a furry cluster: furbeowulf [trygve.com] .

Fixed link (2, Funny)

Rimbo (139781) | more than 13 years ago | (#2137946)

Try this:

Furbeowulf [trygve.com]

Funny. :)

French (-1, Offtopic)

Anonymous Coward | more than 13 years ago | (#2141244)

Toast!

can (-1, Offtopic)

Anonymous Coward | more than 13 years ago | (#2141245)

can you imagine a beowulf cluster of those?!?1 wiat type of clustering are they going to call this, it might be a new troll-word for /. :)

Re:can (-1)

l33t j03 (222209) | more than 13 years ago | (#2131917)

Since it uses Linux they'll call it a clusterfuck.

Wow... (-1, Offtopic)

Anonymous Coward | more than 13 years ago | (#2141285)

Imagine a Beowulf cluster of - oh, wait a minute...

From this week's Byte (2)

wiredog (43288) | more than 13 years ago | (#2141541)

SJVN commentary [byte.com] on distributed computing and some interviews [byte.com] with various people in the field.

old ideas come back around, if they are good (2, Informative)

jkorty (86242) | more than 13 years ago | (#2141824)

From the article:
The idea is to free some computers from getting bogged down in processing interrupt requests from peripherals, while letting a second set of machines run the full operating system, furnishing the cluster with networking, job scheduling, input/output, and other capabilities.
The central design theme of the CDC 6400 was exactly this, and it is a product of the mid sixties. In that incarnation, the two central CPUs ran only user applications, while the operating system, with all its interrupts, OS code, and device drivers, would reside nearby in the ten Peripheral CPUs (called PPUs) provided for this purpose. The central CPUs didn't even have an interrupt capability.

Guess who the CDC6400 designer was? Seymour Cray.

Re:old ideas come back around, if they are good (2)

Black Parrot (19622) | more than 13 years ago | (#2118392)

> In that incarnation, the two central CPUs ran only user applications, while the operating system, with all its interrupts, OS code, and device drivers, would reside nearby in the ten Peripheral CPUs (called PPUs) provided for this purpose.

When I heard a CS professor talk about putting multiple CPUs on a single chip, I suggested that one of the CPUs should be dedicated to the OS, which would mean that it wouldn't even need a FP unit. So for (say) 4 or 8 computers on a chip, one would be a "OS server" and the others would be "application servers". Ditching the FP on the "OS server" might allow an extra-high-performance design for it. And the others would only need context switches when the OS demanded it, rather than one for every stinking interrupt that came along.

actually it shows why Cray always does so well.. (3, Insightful)

TechnoVooDooDaddy (470187) | more than 13 years ago | (#2142281)

Cray's engineers seem always willing to consider every possibility, whether it be clusters, p2p, parallel, etc.. showing us that they're considering things well outside of what they're currently offering is also showing us why they're still in the game and even ahead in serious computing power after so many years.. IBM, Sun, etc.. have had their rise and falls, but Cray is always mentioned with reverance...

And yet. (1)

ackthpt (218170) | more than 13 years ago | (#2121482)

These were Ex-Cray, which perhaps says something in and of itself...

Re:actually it shows why Cray always does so well. (-1, Offtopic)

Anonymous Coward | more than 13 years ago | (#2121830)

Mentioned with reverence, but still slowly going bust.

Huge Market for Supercomputers Will Come... (3, Interesting)

Louis Savain (65843) | more than 13 years ago | (#2144612)

Mentioned with reverence, but still slowly going bust.

The reason that high speed computing has not taken off is that there are currently no consumer apps that require it. Only a few scientific, research and governmental organizations have a need for it. However, let's say there is a breakthrough in AI technology, it will require googles of CPUs and memory. And when that happens, the market will explode.

People are going to want their mechanical maids, baby sitters, gardeners, chauffeurs, lawyers, companions, stock market experts, and what not. I predict they are going to crave their mechanical servants to the point of pathological obssession.

Don't be so sure this won't happen in your lifetime. In fact, there is every reason to suppose that it might happen anytime. There is an awful lot of minds thinking about intelligence and an awful lot of money being spent on it right now. IMO, the solution to the intelligence problem is probably simple. As Dr. Rodney Brooks of MIT says, "Maybe this is wishful thinking, but maybe there really is something that we're missing." Any day now.

In conclusion, I would recommend that you don't sell your shares in the supercomputing sector just yet.

Re:actually it shows why Cray always does so well. (1)

Styx (15057) | more than 13 years ago | (#2134403)

Their homepage seems to be http://www.unlimitedscale.com/ [unlimitedscale.com] .
Unfortunately, it contains absolutely no info on what hey are up to.
groups.google has a tiny bit more [google.com] .
And a bit on their funding [localbusiness.com] .

Anybody got any more info?

Re:actually it shows why Cray always does so well. (1)

Styx (15057) | more than 13 years ago | (#2141596)

The portfolio of Quatris Fund [quatrisfund.com] (one of the investors in Unlimited Scale) is small, but interestingly diverse.

Re:actually it shows why Cray always does so well. (3, Informative)

Oestergaard (3005) | more than 13 years ago | (#2141693)

Of the top 500 supercomputers in the world, 47 are vector processor machines - the kind of processors that Cray became famous for.

Not one single of these are made in the U.S.

Cray today is a name. It's a brand. It's not a manufacturer of high performance computers.

Just for the record, IBM produced the two fastest computers currently, Intel the third, IBM the fourth, Hitachi the fifth, SGI, IBM, NEC, IBM, IBM, and Finally, number *11* is a Cray based on the Alpha processor (the T3E).

So, tell me again, who was playing catch-up with who ?

Re:actually it shows why Cray always does so well. (1)

3am (314579) | more than 13 years ago | (#2141581)

and it's not the top of the line, even, if i'm not mistaken. i thought that was the t90.

sigh (-1, Offtopic)

Chundra (189402) | more than 13 years ago | (#2143521)

Ok. Enough with the imagine-a-beowulf-cluster posts. Instead I present you with:

can you imagine a cluster of wolves? Sure you can. First they are shaved, then they're coated in a layer of caramel, then rolled in almonds, and finally dipped in chocolate. Wolf clusters!

(Now available at www.hairyanddavid.com)

Cray rules (0)

Anonymous Coward | more than 13 years ago | (#2144240)

As a Cray developer I can tell you this new clusters are going to kick some serious ass.
Sincerely, Mike Bouma

if I understand correctly... (2, Interesting)

dario_moreno (263767) | more than 13 years ago | (#2144576)

what these guys want to do is to build, say, a cluster of 2 CPU system where one of the CPUs only computes while the other manages I/O and communications. Indeed, the I/O part is really a problem on Beowulves, and dedicating a CPU on it and communication can be cheaper than dedicated network cards like Myrinet (at 1000 $/port) or SCI, and hi-perf I/O like HiPPi. I wonder though if they can beat the price/performance ratio of the latter the way Beowulves beat on raw Flops the ones of traditional supercomputers.

wouldn't life just be easier if... (-1)

GaylordFucker (465080) | more than 13 years ago | (#2144650)

they used RAID... i mean, what's the point of clustering all these boxes? so you could be the coolest kid on the block and say "yeah, i 0wn j00?"... what about power issues? quite honestly, i think this is just stupid... meaningless and a waste of a lot of money... but i'm not surprised... things like this happen everyday... literally

Nakoruru, my friend and commrade (-1, Offtopic)

Anonymous Coward | more than 13 years ago | (#2144899)


Nakoruru, what is that, Indian? Go make me a slurpee, Nakoruru, and give me one of those little "wassup" ligthers, too. I love that shit. Is it true you people eat your own children? I think I'll pass on that hot dog, Nakoruru. I don't want to be muching on little Nakoruruette. Hey, what are you doing? Why are you unzipping your pants? Put your pants back on! Oh ... I get it. "Little Nakoruruette." Ha ha. Cripes, look at that thing. Looks like a fleck of curry. How do you wack off with that, wrap that little dot on your head around it? Okay, I gotta go Nakoruru. See you tomorrow morning when I get my paper and coffee, ya little sand nig you.

Not much information (0)

morbid (4258) | more than 13 years ago | (#2144960)

There wasn't much at all in that article other than what had been said in the caption on /.
Does anyone know what their system does and how it differs from e.g. Beowulf and MOSIX (or GridWare for that matter)?

I don't suppose anyone will reply since I post at 0.
Load More Comments
Slashdot Login

Need an Account?

Forgot your password?