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!

Flattening Out The Linux Cluster Learning Curve

michael posted more than 9 years ago | from the stomp-stomp dept.

Linux Business 89

editingwhiz writes "IT Manager's Journal has a good look at a forthcoming book, The Linux Enterprise Cluster, that explains in clear, concise language how to build a Linux enterprise cluster using open source tools. Writer Elizabeth Ferranini interviews author Karl Kopper in a Q&A. Is this more complicated than it appears to be? (IT Manager's Journal is part of OSTG.)"

cancel ×


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

don't you mean... (3, Insightful)

beckett (27524) | more than 9 years ago | (#10678186)

Re:don't you mean... (1, Insightful)

Anonymous Coward | more than 9 years ago | (#10678627)

Um. all they did was swap the axis used. Just plot time on the other axis. Duh.

if they swapped the axis (1)

beckett (27524) | more than 9 years ago | (#10680432)

then it would be a time curve, not a learning curve. duh.

Re:don't you mean... (4, Funny)

St. Arbirix (218306) | more than 9 years ago | (#10679399)

They were having problems with too many people learning how to cluster linux. Mentions in various forums about "imagine a Beowulf cluster of these" had reached epidemic proportions so they decided something had to be done.

Thanks to this book the learning curve has been flattened down to something more appreciable and amenable to those who have complained about the problem. The curve has been flattened far enough that it takes two years to learn that clustering "will likely require more than one computer to operate correctly" (Chapter 403 pg. 8729). I count this as a big win for society.

Ignore the anonymous coward who replied before me.

Re:don't you mean... (0)

Anonymous Coward | more than 9 years ago | (#10680931)

don't you mean... Steepening the curve?

Well, it depends on what you are graphing. Yes, If you are graphing time on the x-axis and ability on the y-axis, easier things have a "steeper" curve.

But if you are graphing competence on the x-axis, and cumulative effort to get there on the y-axis, eaiser things will have a "flattened" curve.

In my mind, "time" is a lousy thing to graph with learning. Do we count tea breaks? Thinking about the issue in the shower? What about a short period of really intense effort (cram session) versus a steady commitment to learning? In my mind, it is the *effort* required that is important, and I consider effort to be a function of how much I want to learn, rather than the other way 'round. (One has something one wants to learn, and then needs to know how much effort is required. You rarely say "I've got X units of effort, how much can I learn with it?")

Steep prerequisite curve (1)

cyber_rigger (527103) | more than 9 years ago | (#10681164)

A better term might be

"steep prerequisite" curve

i.e. each advancement to the learning process requires a much higher prerequisite.
If step 1. requires a high prerequisite then you would get the "running into a wall" effect.

ya!!! (-1, Offtopic)

Anonymous Coward | more than 9 years ago | (#10678187)

9th post!

9th? (1)

twoslice (457793) | more than 9 years ago | (#10678827)

Dude, you need a cluster.

Fristage Postage! (-1, Offtopic)

Anonymous Coward | more than 9 years ago | (#10678189)

I ownz joo!

This is the kind of book we need... (5, Funny)

Amiga Lover (708890) | more than 9 years ago | (#10678194)

Now it's not just geeks, but also IT Managers who can imagine a beowulf cluster!

Re:This is the kind of book we need... (2, Informative)

Anonymous Coward | more than 9 years ago | (#10678207)

Umm dude.. Enterprise cluster != beowulf cluster

Re:This is the kind of book we need... (1, Interesting)

Anonymous Coward | more than 9 years ago | (#10678510)

> Umm dude.. Enterprise cluster != beowulf cluster

Oh for fuck's sake spare the geeky overliteral bullshit and grow a sense of humor and perspective. Thank fuck it's not GEEKS who are it manager's but true manager's, heaven help us if someone asked a geek to ever look at the big picture in an organisation.

"I fail to see how a examining a large painting would enhance our productivity".

Turn your coder brain off once in a while.

Re:This is the kind of book we need... (2, Interesting)

perlchild (582235) | more than 9 years ago | (#10679293)

You bring an interesting point up, I wish each book on the topic of clusters mentioned which type(s) of clusters it dealt with...

Looking for a good book on High-Availability clusters would be so much simpler

Re:This is the kind of book we need... (2, Insightful)

Green Salad (705185) | more than 9 years ago | (#10678254)

Rather than ridicule to level of expertise, I think it's important for IT management types to have their imagination fired up about clusters.
They're the one's that can get funding and support for you to put one together.

Re:This is the kind of book we need... (1)

Kris_J (10111) | more than 9 years ago | (#10681163)

They're the one's that can get funding and support for you to put one together.

I proposed a minor change to the products we subscribe to from our ISP that would save money and I'm still fighting to prevent it from going to a committee to decide if we should get quotes from other ISPs.

Re:This is the kind of book we need... (1, Funny)

Anonymous Coward | more than 9 years ago | (#10678300)

now just imagine a beowulf cluster of beowulf clusters...

Re:This is the kind of book we need... (2, Interesting)

ocelotbob (173602) | more than 9 years ago | (#10678600)

*Disclaimer: I am tired. It is 6:30 on a sunday morning. I have done the one task I gave myself before I allowed myself to sleep, which was to make pawgloves for my halloween costume. Thus, sanity is overrated right now.

Okay, the classic beowulf cluster is a 4x4 matrix of computers. Now, to have a beowulf of beowulfs, each of those computers on a cluster must be connected to its own 4x4 grid, so you now have a cluster of 256 computers, arranged somewhat suboptimally. Now, in order to communicate with these systems, you are going to need some library functions. Classic beowulfs work well with the industry standard pvm libraries. They can also use openmosix if the application is not natively cluster aware. As we are dealing with clusters of clusters, some applications may not function properly if they were designed to work on just a single cluster. So, most likely, we'll end up needing to use a variety of techniques to beowulf squared an application, such as combining pvm and openmosix

OSTG? (4, Informative)

ricotest (807136) | more than 9 years ago | (#10678199)

I must have missed this, and for anyone else who didn't know, OSTG is the new name for the Open Source Development Network (OSDN) Slashdot is a part of. They're now called the Open Source Technology Group [] .

Re:OSTG? (1)

zerocool^ (112121) | more than 9 years ago | (#10678487)

Ahh, the phases of slashdot.

Slashdot -> VA Linux -> VA Software -> OSDN -> OSTG

Simpler times, those were.

Some thing never change (0)

Anonymous Coward | more than 9 years ago | (#10678748)

Yet still no PT Cruiser? =)

Let me get this straight (3, Insightful)

Timesprout (579035) | more than 9 years ago | (#10678216)

The guy puts a single 10 node cluster together and this qualifies him him to write the 'definitive guidebook called "The Linux Enterprise Cluster"'.

Dont think so.

Re:Let me get this straight (1)

amerei (782437) | more than 9 years ago | (#10678274)

we are individuals.

Re:Let me get this straight (1) (643709) | more than 9 years ago | (#10678421)

no, we are all eris

Re:Let me get this straight (0)

Anonymous Coward | more than 9 years ago | (#10678497)

I'm not

Re:Let me get this straight (1)

cranos (592602) | more than 9 years ago | (#10682112)

I'm not (much whispering of Shut up)

Re:Let me get this straight (0)

Anonymous Coward | more than 9 years ago | (#10687440)

As a new Linux user, I have been looking for help with Open Source projects on numerous occasions. At least somebody had the knowledge to put together a book that will help the rest of us when it comes to stuff like this. Maybe instead of complaining about the verbage in the article, you could put your energy towards something useful, like perhaps contributing constructive ideas. That is of course, if you have any...

Very nice (4, Informative)

a_hofmann (253827) | more than 9 years ago | (#10678257)

Installing and administering the various [] open [] source [] tools [] can be tedious work, especially without documentation of how to put things together.

A quick Google search [] though reveals a lot of free papers and manuals on this very topic.

Re:Very nice (1)

civilizedINTENSITY (45686) | more than 9 years ago | (#10681365)

Papers, yes, but not (singular) paper. The need alledged was for a single source that would hold one's hand through the entire process.

The problem with clustering in Linux... (4, Interesting)

Xpilot (117961) | more than 9 years ago | (#10678262) that there are a gazillion ways to do it, and every cluster vendor comes up with their own way, and there is no agreed-upon standard yet to easily deploy these things (AFAIK). Now the fact that there is no single vendor controlling how clustering works is a good thing, without a lack of a good standard as to what a clustered environment will offer to the application developer, the task of setting up clusters for different types of applications remains a tedious task.

Lars Marowsky-Brée had a paper in the proceedings of OLS 2002 [] describing the problem and a suggeted solution in his paper entitled "The Open Clustering Framework". I'm not sure how far standardized clustering has come since then. Anyone has any insight on the matter?

Re:The problem with clustering in Linux... (4, Interesting)

barks (640793) | more than 9 years ago | (#10678376)

I have yet to meet anyone that's running a homebrew cluster and tell me which distro they're awesome as they appear to be.

What I gathered from my introductory Operating Systems class was that this was the next frontier and exciting market to keep an eye for.......that and creating applications for these setups was not as you said, standarized yet. Can Linux applications that normally run a single box setup migrate relatively easily to a cluster setup yet?

Re:The problem with clustering in Linux... (2, Interesting)

jweage (472545) | more than 9 years ago | (#10678519)

I've personally setup two clusters, both in the 40 CPU range. I've used various versions of Red Hat, I'm now using White Box Enterprise Linux.

I use a PXE boot system with Anaconda kickstarts to get the software installed. A poast install script then configures everything else on the machine. When it reboots, the machine appears in the cluster and is ready to use. I use the Torque batch scheduling system.

You don't need the cluster toolkits to setup a cluster! DHCP, TFTP and a configured kickstart file work just fine with Red Hat.

Re:The problem with clustering in Linux... (2, Interesting)

mindstrm (20013) | more than 9 years ago | (#10678531)

THe answer is "it depends". First, there is no such thing as a generic "cluster". A cluster is just a bunch of machines cooprating to solve a problem (whether that problem is serving a website or computational physics, or the requirement for redundancy)

Some types of applications, it's easy to visualize how to get a dozen or a hundred computers to help with the problem (serving static web pages). Others, it's not (databases)

Re:The problem with clustering in Linux... (1)

ID10T5 (797857) | more than 9 years ago | (#10679876)

Some types of applications, it's easy to visualize how to get a dozen or a hundred computers to help with the problem (serving static web pages). Others, it's not (databases)

Databases may not be easy, but they have been done ( [] ). Not sure if I'd call it a "typical cluster", but I can't say that any cluster is typical. Current Teradata stuff doesn't do Linux, but they're going there [] as I type.

Re:The problem with clustering in Linux... (1)

Forbman (794277) | more than 9 years ago | (#10680178)

Oracle 10g seems to have made an effort to figure out the "grid" cluster database.

I've got a left-handed crescent wrench to help fasten that ID-10T wire...

Re:The problem with clustering in Linux... (1)

ID10T5 (797857) | more than 9 years ago | (#10680250)

I've got a left-handed crescent wrench to help fasten that ID-10T wire...

Still won't help them with they're nuts...

Re:The problem with clustering in Linux... (1, Interesting)

Anonymous Coward | more than 9 years ago | (#10679537)

It depends on the application.

OpenMosix is a clustering technology that allows you to use regular apps and benifit from the cluster.

It works by migrating proccesses from one computer to another. So it's like a SMP machine, the fastest any single thread can be done is limited by the fastest cpu, however the it allows you to do more at once.

For example with a 2 system cluster, you would be compiling the kernel. If you set it up only to use one thread at a time, then you get 100% of the original single machine performance, if you set it up to compile 4 things at the same time, you can get a 160%-180% increase in performacne over a single machine.

All apps can benifit from it, any sort of heavy mutlitasking can benifit from it. No extra programming needed, just a custom kernel that is patched and some services.

Re:The problem with clustering in Linux... (0)

Anonymous Coward | more than 9 years ago | (#10679832)

I've got a two computer "cluster" that took about an hour to set up as a viability test. OpenMosix was simple enough and God only knows why we're using Red Hat 7.2, but it works.

Re:The problem with clustering in Linux... (1)

GreyWolf3000 (468618) | more than 9 years ago | (#10680149)

I read somewhere that both apache and mysql don't run on openmosix.

Re:The problem with clustering in Linux... (1)

sandyb (818932) | more than 9 years ago | (#10684524)


Microsoft is the problem.

Sick of gentoo zealots throwing plugs in completely unrelated topics? Me too! {QUOTE}

This style of comment is the other.


Re:The problem with clustering in Linux... (1)

Mysticalfruit (533341) | more than 9 years ago | (#10684584)

I think you'll want to take a look at openmosix. [] Instead of writing your app to be cluster aware, it hides all that good stuff in the kernel. All you need todo is have an app that'll fork/pthread appropiately and mosix takes care of all the messiness behind the scenes.

Yes But (-1, Troll)

Anonymous Coward | more than 9 years ago | (#10678296)

Does it run Linsux?

Logistics gone digital? (2, Interesting)

egnop (531002) | more than 9 years ago | (#10678339)

End users would often complain about the system's slow response time.
He says, "Because we couldn't print the forms for the warehouse people to select the products to be put on the truck, we'd have dozens of truck drivers sitting in the break room each day for more than 10 minutes.

I actually don't get it, most logistics got wireless for about a decade now...
and the truck driver has no right for a break...

Re:Logistics gone digital? (2, Insightful)

teh_winch (791118) | more than 9 years ago | (#10678707)

If the system is taking a long time to do the work required to print a form how is wireless going to help?

and the truck driver has no right for a break...

What do you propose the driver does? Go drive around the block for 10 min until they are ready to load?

hmmmm (-1, Offtopic)

Anonymous Coward | more than 9 years ago | (#10678345)

my cell phone and computer seem to have different times.....

Publication, standardization, multiplication (3, Insightful)

wombatmobile (623057) | more than 9 years ago | (#10678370)

Publications like this play an important role in establishing best practices and community, two key enablers of standardization.

These in turn will lead to greater adoption, and more publications. A virtuous cycle.

VMS clusters (4, Interesting)

Anonymous Coward | more than 9 years ago | (#10678371)

Want practice with decades-mature enterprise clusters? Why not get a few old VAX or Alpha systems on eBay, and/or fire up a few instances of the simh [] emulator, then join the free OpenVMS hobbyist [] program (I recommend the also-free-to-hobbyists Process Software's Multinet [] TCP/IP stack and server software).

And please, don't be put off by VMS because DCL = your first exposure to a VMS system - feels more awkward than bash (in many ways, it certainly is!). It's in the underlying architecture of the OS where the fruits of tight engineering are really demonstrated.

Re:VMS clusters (2, Informative)

hachete (473378) | more than 9 years ago | (#10678648)

This seems fairly active:

includes a port of bash to VMS. Not sure how good it is.

Having used and programmed DCL, it's not that bad.


Re:VMS clusters (1)

MmmDee (800731) | more than 9 years ago | (#10679480)

As I recall from my Decus days, there were a few alternative command line interpreters available; none however exceeded DCL's presence.

Clustering VMS/VAXen was straight-forward, reliable, fast and exceedingly well-supported by DEC (for a fee anyways).

Re:VMS clusters (0)

Anonymous Coward | more than 9 years ago | (#10679583)

It was interesting 20 years ago. these days, it is better to learn and then move on. I wish that VMS would simply die and allow better systems to take over.

And yes, I use to code on Mumps on pdp's and vax's. It is just that it is time to move on. The company is gone and is being supported by HP and about a half dozen companies who are simply milking it for all that it is worth. But it would be so much cheaper to change over.

Re:VMS clusters (0)

Anonymous Coward | more than 9 years ago | (#10679729)

A few points to your post:
  1. If it were so awful compared to other systems, the generally very large, very talent-filled organisation that choose VMS would happily migrate.
  2. The hobbyist licence is free. We're discussing the technology, not the ridiculous pricing...
(...which is only possible because the biggest customers are government, esp military/intel, where budget is of no consequence. Same goes for the wonderful Open Genera environment.)

Re:VMS clusters (0)

Anonymous Coward | more than 9 years ago | (#10680011)

Well, actually, the migration is occuring, just slowly. Large institions have a nasty habit of taking 10x longer to switch over. But a lot of that is simply companies trying to keep these groups locked. A good example is that IBM's mainframes were dieing slowly. When they quit trying to push MVS/CMS/etc, and instead allowed new competive OSs, such as Linux, to come, then they went started to make sense.

As to the hobbyists license, well, that is simply a way for companies like HP and Parsec (a truely worthless company who can make MS support look good ) to keep money flowing to themselves.

Don't get me wrong. I liked DEC, Vax, and VMS years ago. They had some interesting stuff. But they are gone and bottom feeding suckers are now trying to make as much money as possible to keep alive a nearly dead technology. Personally, I think groups like the VA should move their vax installs running M on over to other cheaper systems. It is way past time to save tax payers money.

VMS is dying .. yeah right (1)

Macka (9388) | more than 9 years ago | (#10683899)

1) It's been ported to Itanium, and will ship on that platform very soon.

2) ISV support for VMS on Itanium is strong and its customers are very loyal.

3) You said you wish it would die and allow "better systems" to take over. What better systems? In the context of clustering (cos that's what this discussion is about) VMS Clustering for High Availability systems is still at the top of the food chain. Nothing exists on Linux to match it. Not yet anyway.

Tru64 Unix clustering is about the next best thing, but there won't be any further development there now until HP port TruCluster onto the next-generation of HP-UX. Unfortunately that's taking way too long, and by the time they get there it just might be irrelevant. may just eat its lunch.

Re:VMS is dying .. yeah right (0)

Anonymous Coward | more than 9 years ago | (#10684226)

Not exactly matching it, but one of the reasons people look at RHEL is because it does support vaguely VMS-like clustering out-of-box via distributed lock managers etc - see []

Unless i read this incorrectly. (2, Informative)

thegoogler (792786) | more than 9 years ago | (#10678401)

And he built a ten node cluster OF ten node clusters, then this is lame. and he is under-qualified to do the book(most likely) as most ACTUAL enterprise clusters are at least 20 nodes, possibly more if its clusters of blade servers.

Re:Unless i read this incorrectly. (1)

markus_baertschi (259069) | more than 9 years ago | (#10679078)

All enterprise clusters I know of are in the 2 to 10 node range. The only reason there is a cluster is because of automated failover in the case of node or site failure. Performance and scalability is of no importance, they just buy a bigger box if necessary.

Some of the sites have hundreds of machines, all clustered in small, manageable units. These are high-end IBM AIX boxes, high-end fiber storage with two sites 50km apart.

Enterprises buy clusters for availability, not for scalability !


Re:Unless i read this incorrectly. (1)

ewilts (121990) | more than 9 years ago | (#10679296)

I was responsible for a 6 node VAX cluster that topped out at over 3300 simultaneous interactive users running All-in-1 (e-mail, word processing) and database applications.

You don't need 20 nodes if 6 can do the job.

Re:Unless i read this incorrectly. (1)

jlehtira (655619) | more than 9 years ago | (#10683843)

Guess what? In clustering environments, the different boxes are usually similiar and run the same software. So adding boxen is very straightforward. He would be totally qualified by testing around a 2-node cluster, because something with more nodes is Very Similiar. That is, if you know how to network 2 computers, adding computers to your switch is not going to be a challenge.

Editor needed (1, Informative)

Bleeblah (602029) | more than 9 years ago | (#10678426)

Who edited that article before it went live? It is a mess!

Re:Editor needed (1)

ID10T5 (797857) | more than 9 years ago | (#10679940)

Yep. Even the measly Google cluster suggests a spelling of "Elizabeth Ferrarini" instead of "Elizabeth Ferranini".

Mandrake CLIC (4, Informative)

bolind (33496) | more than 9 years ago | (#10678509)

I will start by admitting that I am just a dumb university student talking out my ass. I have never set up an enterprise scale cluster.

However, last january we set up a small (six node) cluster with the help of CLIC [] . Once we realized the link between a Mandrake and consective dead CD drives [] , we installed the cluster in little time.

CLIC might focus a little too much on userfriendlyness and a little too little on flexibility, but for our purposes it was great. It sports ganglia, gexec, distcc and MPI (and probably more), and administration and deployment of nodes is a breeze.

I heartily recommend CLIC for student/test/proof-of-concept projects.

Re:Mandrake CLIC (0)

Anonymous Coward | more than 9 years ago | (#10679028)

I am just a dumb university student talking out my ass.

redundant =P

I had to read that twice before I got it (1)

Too many errors, bai (815931) | more than 9 years ago | (#10678571)

I thought at first it said "author Karl Popper" that would've been a trick.

Is it just me... (0, Redundant)

bwilliam13 (736256) | more than 9 years ago | (#10678575)

Or is the editing in that Q&A just horrible? Spelling and grammatical errors abound... Someone should invest some time in Hooked on Phonics before writing an article about something they know nothing about...

Beowulf Newbie Question (2, Interesting)

Phoenix666 (184391) | more than 9 years ago | (#10678589)

I read about setting up a cluster about six months' back, and they said that you can only really run programs that are specifically designed to run on a beowulf cluster. It seems like if you could set up a cluster and be able to run any old app on it without special coding, then you'd have your massive adoption of linux. Plug-n-play supercomputer, using the crappy old boxes gathering dust under the cubicles.

Is there any plans to take beowulf in this direction? Is it already possible, but I was just reading the wrong FAQ?

Re:Beowulf Newbie Question (1)

fossa (212602) | more than 9 years ago | (#10678762)

I'm by no means an expert, but I was under the impression that a cluster of yesterday's computers would easily be outperformed by a single top of the line computer. So, except for fun and learning, clustering with old computers is just a waste of time.

Re:Beowulf Newbie Question (1)

Forbman (794277) | more than 9 years ago | (#10680154)

...It depends. If you had a well-designed database, and reasonably partitioned datasets, a given query could be parcelled out to each server, and get you results far quicker than on a monolithic computer.

If it wasn't so, then it wouldn't be a feature of Oracle, SQL Server, DB2, etc...

Re:Beowulf Newbie Question (3, Informative)

photon317 (208409) | more than 9 years ago | (#10678887)

Inevitably high-performance clusters require software designed to run on high-performance clusters. It is better not to think of such a cluster as a single system, but rather as a network of individual machines with a tight network connection. Some of the clustering add-ons for linux approach and even achieve certain aspects of a "Single system image" type of configuration, but it's never completely like a single system.

Back in 1997 or so I tried to get as close as I could to a true Single System Image by building off of the beowulf patchsets combined with patches for Distributed SysV IPC/SHM and a globally-shared root filesystem using CNFS (cluster-nfs, so that a few essential configfiles can have unique copies per cluster node). It was very daunting work to get those patches integrated together, and the end result was that without some kind of network-interconnect that was as high-speed and low-latency as a processor's FSB, there was always going to be a big performance hit doing things this way. Of course if an application happens to be perfect for simple HPC clusters (all cpu intensive, very little I/O, and the work is easily divisible without tons of IPC between the workers), then it runs fantastically on such a Single System Image cluster, but then again it would have run fantastically on a simple cluster that doesn't look like a Single System too. So what the Single System concept bought me really was a nice abstraction layer that made everything easy to deploy, configure and manage. But it came at a severe initial cost of human labour. It's not worth the trouble.

This is what you were looking for (1)

Macka (9388) | more than 9 years ago | (#10683985)

OpenSSI (Single System Image) Clusters for Linux []

The main features are: single root and single init, cluster filesystems and DLM, single process space and process migration, load leveling, single and shared IPC space, device space and networking space, and single management space

Re:Beowulf Newbie Question (2, Informative)

Junta (36770) | more than 9 years ago | (#10678942)

An openmosix cluster would behave more along the lines of what you are thinking, but ultimately for HPC applications at scale it is generally more efficient to not do openmosix and write the programs explicitly for parallelism mindful of the layout of processing elements (i.e. network topology or balance between SMP connected processing elements and network connections between nodes).

Re:Beowulf Newbie Question (1)

roxtar (795844) | more than 9 years ago | (#10679043)

Okay so I set up my first cluster a few months back (nothing too much just 4 computers running BCCD [] ) Now I did this for an exhibition. I found BCCD easily configurable (but it is like Knoppix.. so you have to configure everything again everytime you reboot). We ran some programs using PVM. Now PVM needs special coding but MOSIX (both PVM and MOSIX come with BCCD) need not (well I havent tried it out for myself but thats what the docs say). It can redistribute the work to other nodes based on the parent node's (which spawns the process) load. Now the question of whether we can have a plug and play computer is very valid one because all the plug and play apps are also CPU intensive and one could use the extra processing power of other idle CPUs. I, personally, would like to see some games running on a cluster (yeah, use the LAN for something else than the deathmatches). I see no reason why it shouldn't be possible.

Now, windows on the other hand has a variety of such applications. But one doesn't have any free software (well we do have PVM..but still) for clustering a set of computers all running windows. Unless Microsoft releases some Kernel source.. any progress in this direction is of no use.

Re:Beowulf Newbie Question (1)

bolind (33496) | more than 9 years ago | (#10680587)

Not really answering your question, but there is a thing called MPI [] (Message Passing Interface) which is a cross-platform standard for parallelized programs. You write your program, and it will run on your Beowolf or that massive 24-way Sun, or even locally on you linux box, if written properly. Of course this will always be slower, in the single CPU case, compared code written the old-fashioned way.

Another very important thing to remember is power consumption and cooling. You might be able to get fifty PII's for free, but powering them, cooling them and maintaining them is not free. Our teeny cluster, consisting of 6 PII-350 nodes, one PIII-450 master and a Cisco switch cost my university $200 to run for a month, and that is not counting cooling. Adjust for power costs in your part of the globe, but still damn expensive for, what in effect, was a ~1200 MHz machine.

SSSShHHHH!!! (1)

Colin Smith (2679) | more than 9 years ago | (#10678768)

Of course it's much more difficult than it appears to be... Ehm, look... Don't tell anyone, OK.

Please stop misusing the term 'learning curve' (4, Informative)

double_h (21284) | more than 9 years ago | (#10679310)

A flat learning curve is a bad thing.

The term "learning curve" was invented by the aerospace industry in the 1930s as a way to quantify improved efficiency from mass production (basically, the more you do a task, the easier it becomes). The term was later adopted by psychology and the social sciences, where most people first encounter it.

In both cases, the horizontal axis of a learning curve represents time or effort, and the vertical axis represents amount learned or productivity. Therefore something that is intuitively obvious in fact has a steep learning curve.

"Learning curve" was a technical term with a specific definition for decades before it was ever a (misused) marketing buzzword.

Thank you for your time :)

Bzzt (1)

slobber (685169) | more than 9 years ago | (#10679440)

The term "learning curve" was invented by the aerospace industry in the 1930s as a way to quantify improved efficiency from mass production

Aren't you confusing "learning curve" with "economy of scales" here?

Re:Bzzt (1)

double_h (21284) | more than 9 years ago | (#10679844)

Aren't you confusing "learning curve" with "economy of scales" here?

Nope. []

Unless... (2, Funny)

freezin fat guy (713417) | more than 9 years ago | (#10679486)

They flatten it vertically. Wohoo! Zero investment, complete knowledge!

Re:Please stop misusing the term 'learning curve' (1, Informative)

Anonymous Coward | more than 9 years ago | (#10679841)

Wrong - the American psychologist E.L. Thorndike was using learning curves in 1911 or before

Re:Please stop misusing the term 'learning curve' (1)

double_h (21284) | more than 9 years ago | (#10682952)

Wrong - the American psychologist E.L. Thorndike was using learning curves in 1911 or before

I did not know that, thanks!

wow, thanks (1)

dougnaka (631080) | more than 9 years ago | (#10682472)

now i don't get how i thought it made sense, what was the substition in axis that made a steep learning curve something hard to learn? I suppose it's the imagining of riding a bike on the curves of a 2d graph and steep sure sounds harder than a nice gradual curve...

I can't wait to beat someone with my new knowledge tomorrow! thanks!

you in5ensitive clod! (-1, Redundant)

Anonymous Coward | more than 9 years ago | (#10679663)

may be hurting the isn't a lemonade Users. This is but with Netcraft Declined in market contributed code ME! It's official Whether you channel #GNAA on

There is a nice cluster solution called OpenMosix (1)

AcidFnTonic (791034) | more than 9 years ago | (#10679670)

Im hearing everyone say how they would like a cluster that doesnt need cluster aware applications... Well check out openmosix. Its a simple kernel patch and userspace utilities that make a cluster that load balances any application.

little advice (1)

zaqattack911 (532040) | more than 9 years ago | (#10681103)

What might I use to cluster together linux servers such that they actually act as a single SMP machine?

I'd want to do more than just loadbalance webservices with it.

It want shell accounts on this cluster that act as one maineframe. People would shell into their home directories (which I suppose would all be from one big NFS), and run processes and whatnot on the entire cluster.

Any ideas?

Love zaq

Re:little advice (1)

Donny Smith (567043) | more than 9 years ago | (#10682353)

>Any ideas?

Yeah - go to Google or some clustering forum/mailing list.

Re:little advice (2, Informative)

dougnaka (631080) | more than 9 years ago | (#10682407)

The first part, act as one big SMP machine is what clustering does.

The second part with shell acounts and home directories are all problems already solved by NIS/NFS. You could setup a pool of machines that all share the same NIS/NFS info so anywhere the user logged in they'd have the same files/passwords, and load balance it via ipvs or dns.

AFAIK the current state of clustering works well for custom code situations, where you write your app to run on the cluster, but doesn't transparently make your 4 boxes act like 1 box with 4X the resources for just any program.

I've used distcc [] with some luck on gentoo, but it only distributes compiling over your nodes.

Single most important thing... cfengine (0)

Anonymous Coward | more than 9 years ago | (#10681496)

Unless you're running a single-system-image cluster (i.e. mosix), and perhaps even then, cfengine is a godsend. It may seem a chore the first time you use it, but it's worth it. Just learn it. Use e.g. a pxe kickstart install that installs cfengine in postinstall, and sets it to run on boot. Make changes to your cfengine configuration, not on the nodes. That way when you inevitably replace something, it's brought right up to speed. []

More Books? (0, Offtopic)

WALoeIII (758807) | more than 9 years ago | (#10682074)

So now I have to buy another book to replace the other 34 books that I bought to put together a simple 4 machine cluster? I hate books.

apps not designed for cluster with lots of state? (2, Interesting)

mikefe (98074) | more than 9 years ago | (#10684013)

I have been looking at network filesystem level clustering and failover and NFS, SMB/CIFS and OpenAFS look like good choices for that. With NFS and CIFS you can have an active/inactive fail-over cluster.

I don't know about NFS, but in the case of CIFS, the protocol spec has provisions for renegotiating locks if a connection is broken, but I don't know if there are bugs in win2k/XP clients with samba 3 servers. OpenAFS can have a sort of active/active setup, but the archatecture is such that there is only one server that handles the writes and the rest are read-only. In all of these you can have a semi active/active failover cluster if you move half of the active volumes to the backup server, but this adds a lot to the complexity of your fail-over system.

Those services have a low to moderate amount of state information kept on the server. In the case of a graphical (VNC) terminal server, I don't know of any open source projects that will allow gnome session to be on one server, have that server go down, another server take over its ethernet MAC and IP address and continue processing where it left off on the backup server. The best I can think of is OpenMosix or maybe OpenSSI which are two single system image type clustering systems. If anyone knows anything, please reply and let me know thanks.

Good idea (1)

techster3599 (824446) | more than 9 years ago | (#10685265)

I think this is a very good idea because people where I live are always talking about "If I had a cluster" when they know almost nothing about Linux

Comments From the Author (2, Interesting)

KarlKopper (827574) | more than 9 years ago | (#10701814)

I'd like to jump in here and make a few comments.

First, about the book being a "definitive" guide. I cannot possibly claim to be an expert on every topic in the book--in fact, no one person can. The book is definitive, however, in that project leaders from each of the open source projects participated in editing and reviewing the material for the book.

It is an over broad statement to say it is the definitive guide for building any and all types of Linux Clusters. The book describes how to build a cluster that can be used to run mission critical applications to support an enterprise (it has little or nothing to do with working on the "Big Problem" as Pfister would call it).

(The book took four years to write by the way.)

I do hope it helps with the learning curve, but this is one of the advantages of building what I'm calling a Linux Enterprise Cluster--the system administrator can leverage his/her knowledge of Linux and add concepts that will allow them to build a cluster capable of supporting the enterprise.

I did not invent anything new for this book, and you CAN already find just about everything on-line that is in this book. I started work on the book in 2000 because, at the time, I wanted to have a guide book like this one that would hold my hand through the process of building a cluster that could support mission critical applications running GNU/Linux.

Finally, let me just agree with the comments about the number of nodes ("You don't need 20 nodes if 6 can do the job"). This book is not about building clusters for scientific applications where thousands of nodes and sophisticated batch job scheduling systems are required. How many nodes does it take to build the ideal cluster for your environment? I think that will depend on a lot of things including your budget, the impact of the failure of a single node in the cluster, how many instances of your application can run concurrently on a single node, performance bottlenecks from your node hardware, and so on. In my opinion, the ideal number of cluster nodes for an enterprise cluster--from the system administrator's standpoint--is about 10 (in a pinch you can log on to every node fairly quickly).

The cluster this book was based on has been in production long enough (over 18 months) to have undergone a complete hardware refresh by the way; so the text is based on actual experience (not just theory) and, as I mentioned earlier, it has been reviewed by subject matter experts to insure its technical accuracy.

Check for New Comments
Slashdot Login

Need an Account?

Forgot your password?

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>