Forgot your password?
typodupeerror
Software Linux

openMosix Is Shutting Down 252

Posted by kdawson
from the who-needs-clusters-anyway dept.
jd writes "Despite having one of the largest user-bases of any clustering system for Linux, openMosix is to be shut down. Top developers have left and they lack the means or motivation to continue. Their official claim of multicore CPUs making clustering redundant is somewhere between highly improbable and totally absurd, as has been pointed out elsewhere. Why is this shutdown so important? Well, from a technical standpoint, the open-source bproc (the Beowulf process migration module) is ancient, MOSIX is very hard to obtain unless you're a student, and kerrighd is (as yet) immature. From a user standpoint, openMosix is the mainstay of the Open Source clustering world and has by far the best management tools of any. The ability of this project to continue will likely have a major impact on the future of Open Source in the high-end markets — if the best of the best couldn't survive, people will be more careful about anything less."
This discussion has been archived. No new comments can be posted.

openMosix Is Shutting Down

Comments Filter:
  • by 42Penguins (861511) on Tuesday July 17, 2007 @10:10PM (#19896139)
    someone else will pick it up.
    Isn't that kind of the point of open source?
    • by ozphx (1061292) on Tuesday July 17, 2007 @10:20PM (#19896207) Homepage
      That is the theory of open-source. In practice the set of core contributors to a project are its foundation. As these people are leaving it will be extremely difficult to find others with the knowledge and motivation to continue its maintainance.

      As with any project requiring something a lot more than a hobbyist the level of expertise required to work on the codebase is rare, and not cheap.

      The only real hope is that a company or university using it is happy to pick up the tab and pay someone.

      Unfortunately the "everyone can see the source code" line doesnt give any comfort when you are talking specialised things like clustering. I probably know a total of one person with the skill to work on such a system, and last I spoke to him he was contracting at 130 an hour - for comparitively easy (and less stressful) .net/c# work.
      • I could maintain it. I have 7 to 10 coworkers who could maintain it. At my previous place there was one guy who could have maintained it. At the place before that, there were over a dozen people who could have maintained it.

        I would in fact maintain it if I cared. I don't care.

        BTW, I have doubts about the .net/c# guy you know. Most people who could maintain Mosix would not tolerate such work. They'd look down on it like a typical C++ developer looks down on HTML or Visual Basic development.
        • They'd look down on it like a typical C++ developer looks down on HTML or Visual Basic development.

          Yes, I'm sure they'd look down on a very well paying job that was far far less stressful.
          • by IWannaBeAnAC (653701) on Wednesday July 18, 2007 @12:38AM (#19897165)
            Since when was writing C++ code stressful? Surely if anything, writing VB code is stressful?!?!
            • Depends on the VB project. A lot of places that actually want it done in VB just don't have someone around who codes and want something worked on. Unless it's a rat's nest, it's usually not so bad, and at $130/hour, I'm sure you could cope.

              Besides, the person I initially replied to was of the opinion that nobody who could do the sort of work that openMosix requires would deign to "dumb himself down" (figuratively speaking) to writing c#/.net code even if it was netting the guy $130/hr. Personally, I call BS. After a while, you learn that you work to live instead of living to work.
            • by dido (9125)

              Writing VB code is not stressful. Maintaining VB code is generally far more stressful than writing and maintaining C++ code put together.

          • by r00t (33219) on Wednesday July 18, 2007 @01:11AM (#19897335) Journal
            The really good hackers:

            a. don't want their minds and skills to rot
            b. get bored by the easy stuff
            c. are not stressed by difficult hacking (stress comes from office politics)
            d. like to be admired for their ability to do the difficult stuff
            e. like to be in the company of peers who can do the difficult stuff

            You might get a great hacker doing lame stuff, but you'd have to pay him much MORE than you'd have to pay him to do the difficult stuff. The extra pay would compensate for the extra boredom. Since you can get a warm body for much less money, you're unlikly to hire the great hacker.

            Since C#/.net is very lame compared to the challenges of something like OpenMosix, we can pretty reliably conclude that the supposed hacker is not really qualified to hack on OpenMosix. (alternate theory: his dad is the CEO and so the pay is quite absurd for the job being done)

            • Let me let you in on a little secret. Even the best people eventually realize that there's more to life than working no matter how "cool" you think what they're working on is. They look at their lives and realize that living to work is a bad idea because life is for actually living.

              For a lot of people, that happens about the time they have their first kid. For others, it happens sooner. Yet others experience it later, to the detriment of their families if they have them.

              I also have to tell you that it's not uncommon for a good independant contractor to be paid more than $130/hour because most consulting companies bill out their contractors at that much or more. Honestly speaking, my top hourly rate thus far has been more than $130/hr.

              You may learn that your ideal of the "great hacker" is rather off the mark some day. The truth is that the really good people often don't care about how great others think they are. They get things done, and move on with what they have to do.
              • by fbjon (692006)
                Though I'm moderately good and enjoy a challenge, I find the idea of working to live much more appealing than living to work. Perhaps it's only those who don't have any life who are the "great hackers".


                And here I am posting on slashdot about it, I must be a great hacker, then...

            • by Seahawk (70898) <tts@i m a g e.dk> on Wednesday July 18, 2007 @02:30AM (#19897717)
              Since C#/.net is very lame compared to the challenges of something like OpenMosix

              Excuse me? So you're saying that the language dictates how "complex" the language is dictates how fun a project in the given language can be?

              I certainly think it is likely that OpenMosix presents a lot of interesting technical challenges that any good developer would love to get his hands on, but a complex business system in c#(or java for that matter) present a DIFFERENT kind of interesting technical challenges!
            • Re: (Score:3, Insightful)

              by Blakey Rat (99501)
              Wow, you have an interesting idea of how the world works.

              a. don't want their minds and skills to rot
              b. get bored by the easy stuff
              c. are not stressed by difficult hacking (stress comes from office politics)
              d. like to be admired for their ability to do the difficult stuff
              e. like to be in the company of peers who can do the difficult stuff


              You're not describing hackers, you're describing anti-social assholes. Specifically the last two points, which sum basically to:

              d. you want the idiot masses to bow before yo
        • by xenocide2 (231786) on Wednesday July 18, 2007 @03:29AM (#19898017) Homepage

          BTW, I have doubts about the .net/c# guy you know. Most people who could maintain Mosix would not tolerate such work. They'd look down on it like a typical C++ developer looks down on HTML or Visual Basic development.

          Most people who could maintain this have chosen not to, but unqualified "I could do this and I know several people who could" claims should be disregarded. I know a guy who rewrote the TCP/IP stack to openMosix for his Master's thesis, and while I think he's a bright person, I don't think he's qualified to maintain openMosix. The big thing is kernel developers what truly look down on is maintaining a 2.4 branch of the kernel as an official stable release. What you're getting into when you maintain openMosix isn't just complicated cluster software, it's a set of inelegant patches with the additional complexity of cluster computing atomicity, that aren't even SMP safe! These aren't reasons for not caring, but rather reasons for actively disliking.

          openMosix was doomed to fail like this at some point. Countless academic projects attempt to improve Linux for their specific needs in the wrong way. They release their work as patches never intended to merge with the kernel, or fork the kernel and never merge again. Over time you can guess what happens -- it becomes impossible to cope with the rate of change that others force on you, and the grant budget never considered ongoing maintenance costs, so the the patches become worthless, or the kernel fork unmaintained. So now Moshe is in deep, and nobody else wants to touch it.
          • by xenocide2 (231786)
            And this is what happens when you miss a / in HTML at 2 in the morning. It's too bad /. doesn't have some better form of markup editing or live preview.
          • Maintaining out-of-tree patches is painful. I was part of a small team doing exactly that, with extremely filthy hacks into the scheduler even. I know of what you speak, from personal experience. Dealing with old kernels is icky too.

            That all comes under desire though, not ability. ("desire" as in "I'd like to do this", not "I'd like somebody else to do this")

            I've known quite a few people with the ability. I expect that any of them, including myself, would actually maintain Mosix if either:

            a. we had strong p
    • someone else will pick it up.
      Isn't that kind of the point of open source?


      It's a nice theory, but it doesn't really work out that way. If the lead devs leave a large project, the task of other people getting up to speed can be huge to impossible. It takes a long time to learn a system, especially if you're just doing it as a hobby.

      Brain drain is a problem in any project, open or closed.
      • Re: (Score:3, Insightful)

        by Frosty Piss (770223)

        It's a nice theory, but it doesn't really work out that way.

        Well, if no one picks it up, than clearly, it's not as popular as we are led to believe. Honestly, it it's that impotent, development will continue, otherwise, maybe it's not that important.

      • by kestasjk (933987)
        This is where comments and documentation become vital. If a project is popular, logically built and well commented maintenance is possible without needing intimate knowledge, and once you have maintainers it's a small step to developers.
        • A large program is difficult to get up to speed on, comments or no comments. Good comments certainly make it a lot easier, but it's still no small task. It takes a long time to get familiar with large systems to the point that you don't have to spend 90% of your time trying to find the place that you're looking for.
    • Having access to the source is one thing. Keeping the best people engaged in those projects is quite another.

      There are many very valuable projects that get very little funding - insufficient to pay the programmers who give that value. If the contributors cannot live by their work then they have to go find payment elsewhere.

      As open source matures, people will come to understand that taking without giving back is not a sustainable model.

    • by goutnet (1129639) on Wednesday July 18, 2007 @06:21AM (#19898633)
      Well, let me precise the announce :

      The project will be shut down in March 2008, not before.
      actually, it's Moshe only who will stop "leading" the project (as a reminder, he didn't really 'lead' many thing in the 2.6 version) ...

      After march, we will see who will get the 'leader' position, but I don't think that is really an important change (call that politics if you want). The fact is for now, oM 2.6 has 3 core devs (me, risc, and g4saa) and we are quite all busy elsewhere. Anyway, if I can make interesting progress this year on the oM2.6 code, I'll take over the project.

      Don't fear, oM project is not yet buried ...

      Anyhow, if any of you guys feel like kernel/user cluster dev, please feel free to contact me (or the list directly, I'll answer it)

      WE NEED MORE DEVS !! (as always anyway).
  • OpenSSI (Score:5, Informative)

    by sonamchauhan (587356) <sonamcNO@SPAMgmail.com> on Tuesday July 17, 2007 @10:13PM (#19896155) Journal
    There's a similar project named 'Open Single System Image'

    http://sourceforge.net/projects/ssic-linux [sourceforge.net]
    • Re: (Score:3, Informative)

      ANd I cant claim that I know what I am talking about, but it seems that OpenMosix was akin to Beowulf clustering... wherein the application needs to be aware (or a library abstraction) that it is working in a cluster.

      OpenSSI, however, works transparently to the userland, at least. Got a program that spawns bunches of processes? OpenSSI.

      But don't get too excited. This is NOT exactly like SMP. Unlike multiple physical processors that can actually have threads of x application running on different procs, O
      • Re:OpenSSI (Score:4, Interesting)

        by jd (1658) <imipak @ y a h o o .com> on Wednesday July 18, 2007 @12:08AM (#19896985) Homepage Journal
        OpenMosix was also fork-and-forget at the PID level. There was an effort to make it fork-and-forget at the level of individual threads, but nobody could figure out how to solve the latency hell that is synchronized shared memory. I believe that it may be partially solvable by using reliable multicasts - only one transmit per update, not one transmit per node - and by using kernel bypass tricks to avoid the 20ms context switch for large updates.

        OpenSSI was part of one-stop solutions, if I remember correctly, the doomed Compaq foray into clustering before HP took them over. Doomed? Well, HP has not exactly been Linux-friendly. Their efforts to be more so by hiring Bruce Perens never panned out and you certainly don't see them porting any of their HPUX security to Linux.

        • Re:OpenSSI (Score:5, Funny)

          by Bazman (4849) on Wednesday July 18, 2007 @02:54AM (#19897849) Journal
          We have an openMosix cluster of ten nodes. Our users can log into any one of them, start a long-running job, and the cluster does its job of balancing and migrating jobs to the best node.

          'fork-and-forget' in this context means our forking users forget which node they started the job on...

  • by Anonymous Coward on Tuesday July 17, 2007 @10:21PM (#19896211)
    FTA: "Moshe Bar, openMosix founder and project leader, has announced plans to end the openMosix Project effective March 1, 2008."

    Wikipedia: Moshe is founder of the company behind the Xen software, XenSource, Inc. Moshe is also founder of the company Qumranet which is behind the development of the KVM virtualization technology in the Linux kernel.

    Looks like Moshe is to busy for that old fashioned mosix stuff...
  • Huh? (Score:3, Funny)

    by wilymage (934907) <wily@bur.COFFEEst minus caffeine> on Tuesday July 17, 2007 @10:22PM (#19896225) Homepage Journal

    "[T]he open-source world progresses with giant steps. It is a world where the sun never sets and where national borders, race and religion have no meaning. What counts is the code. And that comes abundantly, and in high quality." (attributed to Moshe Bar on his site)

    Apparently the code doesn't count, only spurious logic about changing hardware factors. Oh, and apparently the sun does, in fact, set.

    But how cool a name is Moshe Bar?

  • by WIAKywbfatw (307557) on Tuesday July 17, 2007 @10:24PM (#19896245) Journal
    From the summary it seems that the people who've contributed most to the openMosix code have moved on to other things.

    Well, that happens. People's lives don't stand still, they change: they take on other commitments at work, have relationships, travel the world, etc.

    But that doesn't mean that openMosix is dead.

    On the contrary. This is open source software.

    The code isn't lost. Others can pick up the slack and join the effort as they see fit. openMosix can still move forward, perhaps not at the same pace as before, but forward nevertheless.

    It seems to me that the summary misses the point of OSS. If this was a closed source project and the lead developers had walked away then, yes, openMosix would almost certainly be dead and buried.

    But, unless I'm missing something huge this isn't the end of the line for openMosix, precisely because it is open source.

    It hardly seems appropriate to look at this as a failing of OSS development. On the contrary, it's arguably an example of one of its strengths.

    This a baton change not a retirement. At best, the new holder(s) of the baton will soon hit the same stride as the previous holder(s). At worst, the baton has fallen to the ground and it simply needs to be picked up.

    • Yeah, but how likely or realistic is it that the few people in the world who understand, in this case, clustering, to such an extent, will choose to work on this project? The vast majority of software developers want to get paid for their work.

      In theory, you're right. It'll continue. But will reality live up to theory? Only time will tell.
      • by WIAKywbfatw (307557) on Tuesday July 17, 2007 @10:40PM (#19896385) Journal
        I agree, there's a degree of optimism in my argument but the summary is plain flawed.

        Its message and tone is that openMosix = dead, openMosix = OSS, therefore openMosix dying = OSS solutions are bad.

        What it completely fails to address is that the situation would be no better, and in fact would be a lot worse, if this was a CSS tool. Indeed, the ray of light for openMosix users comes from the fact that it is OSS.

        Bashing OSS solutions because one is dead/dying/in limbo/whichever way you want to look at it is patently ridiculous because it's not the openness of the code that's at fault here, or even the open source development model.

        To put it bluntly, CSS projects that lose their core development teams don't exactly fair any better do they?
        • by Telvin_3d (855514)
          Yes and no. CSS at this scale always means commercial. One thing about commercial software is that popular, well used competitive software will not disappear because people got bored and moved onto other things. When the development of a piece of software provides a revenue stream, it is not going anywhere. People will be hired, an interested competitor will buy it out in order to give themselves a leg up, whatever. There are all sorts of survival mechanisms available to commercial software that doesn'
          • by rtb61 (674572) on Tuesday July 17, 2007 @11:48PM (#19896849) Homepage
            Numerous closed source projects are killed all of the time and for all sorts of reasons. For example bought out by a competitor and then just killed regardless of user base desirability and all of it's paid contributors fired on the sport all to eliminate competition, or simply die on the vine, not because of bad code or poor programmers or even a lack of users, just bloated management bleeding a company dry until it fails or killed by a company making use of monopolistic tactics.

            Some utility bits of open source of course do not need a lot of maintaining and reach full maturity pretty early and only require the odd tweak for hardware compatibility, for those projects maintaining a team is difficult, logically speaking those projects get pick up and carried by another open source project that can run them as a side line.

            • by timmarhy (659436)
              Numerous? i seriously doubt it's "Numerous". name me 10 or more seperate projects canned when purchased by a competing software firm. i can think of maybe 5 off the top of my head in the last 10 years.
          • One thing about commercial software is that popular, well used competitive software will not disappear because people got bored and moved onto other things.
            Popular, well-used open source software won't disappear either, because somebody else will take over. If no one steps up, then it wasn't really that popular to begin with. Or if some company really needs the software badly, they can hire someone to work on it.
        • To put it bluntly, CSS projects that lose their core development teams don't exactly fair any better do they?

          On the contrary. A CSS product could be rebadged as openMosix 2008 Horizons(R), given some fancy UI tools and sold for more than double to a bunch of mums and dads who believe they need a cluster of 4 new core duo PCs to run a web browsing platform which fully enables their personal web experience for tomorrow today.

          It's soooo much easier to make money from closed source software.

          • by iamacat (583406)
            You are actually making the opposite point from what you intended. Most families have multiple desktops and notebooks and could realistically benefit from pooling hardware for realtime home video editing, gaming, distributed backups or math/physics educational software. Yet, it takes geeks who only use OSS to actually set up clustering.

            As for money part, we are talking about project abandoned by original developers. With proper legal support though, OSS would be easier to profit from than CSS as other peopl
        • Re: (Score:3, Interesting)

          by drsmithy (35869)

          To put it bluntly, CSS projects that lose their core development teams don't exactly fair any better do they?

          Probably they do. How much of the original development team do you think is still left for things like Windows NT(/Vista), Office, Solaris, NeXTSTEP(/OSX), etc ?

          OSS projects tend to "die" when they aren't popular or "interesting" anymore - and the OSS world can be fickle. CSS projects, tend only to die when they aren't *profitable* any more.

          It's a hell of a lot easier to hire more programmers f

  • by Anonymous Coward
    From a user standpoint, openMosix is the mainstay of the Open Source clustering world and has by far the best management tools of any.

    LOL what?! The poster must be on crack. OpenMosix/Mosix is nothing but an experimental/buggy piece of software used by hobby clusterers, it works with 2.4 kernels but never had good support on 2.6. Real cluster software consists of PBS/Maui or some other queueing/scheduler built in house.
  • by Mag7 (69118) on Tuesday July 17, 2007 @10:36PM (#19896343) Homepage
    What a ghastly overreaction, but hey, this is slashdot.

    Best of the best? I may get flamed for this, but I'd barely heard of OpenMosix.

    When Apache, the Linux kernel, Eclipse and (name a popular GNU project) look like "shutting down", then maybe we can bleat about the failure of open source.

    And as some have said, there's not real reason the baton can't be passed on to interested new parties.
  • by DFDumont (19326) on Tuesday July 17, 2007 @10:45PM (#19896413)
    The pendulum has swung back now. In the days when 10Mbps ethernet came onto the scene and our processors could barely keep up with their floopy drives (which is why a floppy used DMA), we collectively came up with the idea of using several computers to solve a problem by splitting the problem up among them. Since then thanks to Moore's law our processors now spend a lot of time waiting to fetch the next instruction from their on-chip L1 cache - as in when there's a miscalculation in the branch prediction step.
    Our networks however have not kept up to this pace. Right now our very best effort for network speed is infiniband which tops out at 96Gbps theoretical limit. The AMD Opteron page lists a limit of 24GBps, that's 192Gbps, bandwidth using three coherent hypertranport processors. See the problem?
    I see one of two things happening, either we'll find a magic bullet technology to significantly increase our network speeds; or some limit will finally end Moore's law. Otherwise there's simply no reason to tie together multiple processors. Despite Windows best efforts, our CPU's still spend most of their time waiting for something to do.

    Dennis Dumont
    • Re: (Score:2, Informative)

      by 1729 (581437)

      I see one of two things happening, either we'll find a magic bullet technology to significantly increase our network speeds; or some limit will finally end Moore's law. Otherwise there's simply no reason to tie together multiple processors.

      You might not have a need for a cluster, but that doesn't mean that nobody else needs them. We have quite a few of clusters where I work, ranging in size from about 4,000 processors to over 100,000 processors, and these machines aren't sitting idle. Multicore desktops

    • Re: (Score:2, Insightful)

      by David Greene (463)

      The moderators are woefully uninformed.

      We are not at the end of network technology. You're talking about essentially consumer-level stuff. There's a vast amount of network technology out there that goes beyond what Infiniband provides.

      Software that needs very high bandwidth won't work on a cluster and probably won't work very well on a single-socket desktop either. Right tool for the right job and all that. There are plenty of codes out there that want tens or hundreds of thousands of cores. Some can

    • Basically what we (the community) has figured out is that SSI featuresets should not be implemeneted in the OS layer, but below it. Look at the SGI Altix technology. Or large Unisys machines. Or that hyper-transport happy monstrosity that Cray is building. They have special low-level firmwares running on the I/O processors that are doing in low latency, tuned hardware what *Mosix was trying to do from Ring 0 on the nodes.

      Using various ISA interfaces (MPI in the low end, or Hypervisor abstractions like Xen, etc. etc.) you can run many guest OSs in the space as needs require, and localize the shared-memory-ness as required to get maximum threading benefit with the lowest total latency you can tolerate. All this with minimally modified guest OSs in which to run the code. This is a much better situation then heavily modified kernels pretending to be a single system image (and then having to worry about forking/threading/VFS issues and propogation of that stuff).

      On the flip side, grid technology and speciality message-passing libraries fill out the feature set for more embarassingly parallel problems that need lots of CPU and RAM... you have the luxury of spending time and money coding your applications for that environment if you are CPU limited.

      Mosix doesn't have much use anymore as a general purpose product. Either it's too heavy-weight (and drowning in syncro overhead) and we should be relying on firmware/hypervisors that are customized for the hardware, or it's not necessary because we can handle the load balancing at a higher level.
    • no no no.

      if you are dealing with an (embarrassingly) parralelisable problem, clusters are the way to go. take for an example all those pictures in the late 90s of the mandelbrot set. the maths for each location does not rely on any other location, so you can divide the problem up on any number of processors/computers. if you have 1000 processors working on it, you will get the result a thousand times as fast as if you have one processor working on it (plus a fixed cost for initialisation and saving of t
  • by Secret Rabbit (914973) on Tuesday July 17, 2007 @10:57PM (#19896503) Journal
    """
    The direction of computing is clear and key developers are moving into newer virtualization approaches and other projects.
    """

    Translation: The developers have found new shiny objects to play with and are going to drop this to play with something new.

    Remember that OSS is mostly about developers scratching an itch. Once that itch is scratched, if a new shiny object is put in-front of a developer, chances are they'll drop what they're doing to pursue the new thing. As seems to be the case here.

    i.e. New is fun, maintenance is boring, boring sucks, do something new.
    • by nuzak (959558)
      Well, since no one in the small market for clusters was willing to throw significant cash at the problem, what other driver is there but developer interest?

      Keep in mind that clustering in general isn't dead, just that much of it has moved to the language level. Parallelizing individual loops isn't something openMosix or anything else like it can do out of the box.
    • Re: (Score:2, Insightful)

      by 1729 (581437)

      Remember that OSS is mostly about developers scratching an itch.
      Look at the major OSS projects, such as GCC and the Linux kernel. These are not just developers "scratching an itch". On these two projects alone, there are hundreds of full-time OSS developers employed by companies like Red Hat, Intel, Apple, Google, and IBM, as well as by universities and research labs around the world.
      • by jlarocco (851450)

        Look at the major OSS projects, such as GCC and the Linux kernel. These are not just developers "scratching an itch". On these two projects alone, there are hundreds of full-time OSS developers employed by companies like Red Hat, Intel, Apple, Google, and IBM, as well as by universities and research labs around the world.

        Yeah, but even GCC and Linux started out as developers scratching an itch. With few exceptions, almost all OSS starts out as developers scratching an itch. Sometimes companies step in

  • Times like this make me realize that the end result of capitalistic software and open source software is really naught if you are on the losing end. If nobody likes your work, you are not going to be funded, and that's really what seems to be happening here.

    The premise for shutting down the project is correct. Multiple cores all but eliminate the need for the most extreme clusters. Throw PCI-X graphics cards into the mix, and you have even that much more computing power. That's not to say that there aren'
  • by pantherace (165052) on Tuesday July 17, 2007 @11:16PM (#19896631)
    Was a switch to 2.6. I personally was using it in 2.4, however, when 2.6 rolled out, OpenMosix wasn't going to support it for some time. This caused a lot of users to stop using it, because for NOW, there wasn't really a way to justify staying on 2.4, when the responsiveness of 2.6 was so much better.

    I see now that they have an alpha version out for 2.6.

    Note that 2.6.0 was released in 2003.
  • by pavera (320634) on Tuesday July 17, 2007 @11:24PM (#19896675) Homepage Journal
    The article summary was certainly an eye grabber... but, the truth is, I've deployed quite a few linux HA and load balancing clusters. I have also installed a couple openMosix clusters. While it may be sad that openMosix is closing, the vast majority of clustering cannot be handled by openMosix. It is designed as a parallel processing cluster. I would say 99% of clusters are of the HA/load balancing variety. IE, I've got 3 web servers and I want to distribute the load between them. openMosix cannot do this, it isn't designed for it. Or I have 5 DB servers and I want to distribute load/perform replication. again openMosix does not do this. It is a "processing" cluster. IE I have this huge data set, and an application which will split up that data set and do some processing on it. Think SETI@home except, you don't want to send it to people's homes, you just want to run a single process which will send jobs off to other nodes for computing. The only thing I ever successfully used openMosix for was a compile cluster, and for that it was nice, but even for regularly compiling KDE, it wasn't much worth the effort to get the cluster running for the time it saved in compiling.

    At the time I used it it couldn't migrate web server processes or db server processes, so it was useless for what I do most of the time.
    • by dodobh (65811)
      Clustering can be of multiple types. There is a market for highly parallel processing. Think video processing, weather predictions ...
      HA and load balancing is a different type of clustering.
      • by sl3xd (111641) * on Wednesday July 18, 2007 @12:48AM (#19897231) Journal
        I do highly parallel processing. The industry as a whole has moved in a different direction (which is, oddly enough one of the reasons the project is shutting down). We use MPI, which is one of the things that mosix was supposed to let you avoid. There are other ways to maintain a system than the "single system image." Mosix had problems with performance, which is an effective way to ensure it won't be used in high performance applications.

        And it's no fun to develop something you know isn't going to be used, as the supercomputing 'industry' isn't moving in the same direction that Mosix was heading.
      • Wrong and wrong. (Score:3, Insightful)

        by Ayanami Rei (621112) *
        Video processing is not done through multi-processing with shared memory. It's done in batch, in a grid-type environment.
        Weather prediction almost certainly uses special-purpose math libraries (ScaLAPACK, etc.) in a MIMD environment.
    • by sl3xd (111641) * on Wednesday July 18, 2007 @12:41AM (#19897181) Journal
      The big thing I'd add is that all of the high performance clusters I've seen don't use Mosix (open or otherwise). The reason is that while mosix makes some administration tasks easier, it doesn't address the single most important thing for a HPC cluster: Performance.

      The point of mosix is to avoid using a library (such as an MPI implementation) to handle parallel apps, and to make managing a cluster 'easier'.

      The problem is that the performance just isn't there, and that the 'industry' as a whole has overall chosen to use MPI to handle parallelism, and use various other methods to manage the cluster.

      Bottom line: The industry they targeted didn't move in the direction mosix was headed (which is exactly why the developers are shutting it down).
  • by mr_tenor (310787) on Tuesday July 17, 2007 @11:35PM (#19896755)
    As usual, people are posting replies without any clue about the actual situation (or at least the claims of important people involved)

    See http://mulix.livejournal.com/199931.html [livejournal.com]

    "Now the real project can get the credit it deserves. I hate it when people steal credit. It was so annoying to read interviews where it was claimed that behind openMosix are years of research, when all this research was actually behind MOSIX."
  • Imagine a (Score:5, Funny)

    by Tablizer (95088) on Tuesday July 17, 2007 @11:41PM (#19896801) Homepage Journal
    and they lack the means or motivation to continue

    See what happens when you *stop* imagining a Beowulf Cluster?
       
  • This highlights a very real danger with OSS - that the project will collapse under you and you'll be left with 2 choices

    1. a painful migration, and i mean painful in terms of giving birth or passing a kidney stone

    2. maintain the code yourself, which could be even MORE painful and costly.

    yes i know everyone will jump up and down about how this could happen to any project, but folks lets face facts here - In OSS projects where no one is getting paid to write code, you could possibly be hinging a key part o

    • by mudshark (19714)
      And EOL doesn't happen in the world of proprietary software.

      Right.
      • by timmarhy (659436)
        learn to read. i clearly stated MS EOL'd win98 after 9 years. it was in the first sentence. kind of hard to miss.
      • by timmarhy (659436)
        sorry my mistake. i was confusing you with another thread i replied to.

        my point is still valid though. MS has a much much better EOL policy then any OSS project.

    • by dbIII (701233)

      it's often far more expensive to code yourself then to just pay MS and friends for a solution.

      It's clustering - something that's too small a market for Microsoft to put in much effort and requires too many Microsoft licences for anybody else to bother. Micosoft is the new kid on the block in this feild and has not yet produced anything that can be taken seriously - not that there is anything wrong with that since they cannot do everything.

  • use xcpu (Score:2, Informative)

    by warrior_s (881715)
    Guys who used to develop BProc now are focusing their efforts on http://xcpu.org/ [xcpu.org]
  • Look at their versions. The latest release is 2.4.26-based, with a 2.6.15 beta. Clearly it's an invasive patchset, which must be difficult to maintain. Back when the project started, this was probably a worthwhile effort, but the HPC world has changed.

    My guess is that the advent of commodity NUMA hardware (Opteron) motivated more development of MPI applications and libraries, since HPC workloads often perform better on NUMA hardware using MPI between the NUMA nodes. If all your applications are MPI-awar
  • by cmholm (69081) <cmholmNO@SPAMmauiholm.org> on Wednesday July 18, 2007 @12:13AM (#19897015) Homepage Journal
    Geezuus, it's not like OpenMOSIX is unusable as is, or that there aren't alternatives. For that matter, while coding one's own cluster controller isn't trivial, it isn't string theory either. Our shop has released (eg. given away) two schedulers, and we've got another that's stayed in house. When I've strolled the booths at the SuperComputing conference, it seems that every other university is giving away their own cluster controller.

    OpenMOSIX is neat, but it ain't the end all be all, and it's been my experience that any shop that's serious about running a cluster manages to find/attract someone with the chops to get it up and running. Can just any elementary school pull one together for "free"? Maybe not. For them, there's Pooch [daugerresearch.com] or AppleSeed [ucla.edu].
  • I've used a 64 node Beowulf cluster [massey.ac.nz] on occasion. The queue was generally full of single-node jobs and multi-node jobs hardly ever ran. There really is no good way of scheduling in this environment without the ability to suspend a job on one node and later resume it on another. So far as I know, our scheduling software was not capable of this. (Fortunately, I was just submitting single node jobs.)

    Starting with the information in the summary, I spent a few minutes web searching. "bproc" appears not to be capa
    • by r00t (33219)
      Yes, process migration is exactly that.

      It's coming to standard mainline unmodified Linux too, judging by comments made by people supplying the container patches that keep getting accepted.
  • This item probably shouldn't be tagged with Beowulf.

    Most Beowulf clusters run parallel codes written to use the Message_Passing_Interface (MPI) [wikipedia.org]. MPI programs really don't want to be migrated to different nodes while they're running, so load management is achived through schedulers such as Grid Engine [sunsource.net], TORQUE [clusterresources.com], and others. These schedulers avoid the need for process migration by preallocating the resources (compute nodes) in advance, and prevent the load imbalance from happening in the first place. openMosix

  • In summary... (Score:5, Insightful)

    by Rakishi (759894) on Wednesday July 18, 2007 @01:25AM (#19897407)
    Let me explain the reason for their decision in a sane way as I see it.

    *MOSIX was supposed to provide an EASY way of doing clustered worth. Low over head in terms of coding and administration. It was aimed at MODERATE clusters not massive beasts as it lacked performance/efficiency. While two extra machines may be worth the lower overhead two hundred probably are not so the immense clusters used other methods.

    Advanced in computing, multiple cores and so on, have killed this low-to-medium cluster market NOT clustering as a whole.

    Yes there are tons of things that still need clustering, think web data for example for a new one, but they are large and even larger. They need performance and so *MOSIX is not what they are looking for.

    In other words the market for *MOSIX is effectively dead thus the project is joining it.
  • Am I the only one who noticed that Moshe Bar (the leader of the openMosix project) has gone on to found three (!) virtualization companies, including Xensource? http://en.wikipedia.org/wiki/Moshe_Bar [wikipedia.org] It seems his professional interests have moved on as of quite some time ago, and that this is merely "catching up."

    I've looked into attempting an OpenMosix cluster before in my free time but the lack of a 2.6 version made it hard for me to justify the time - as all the work I do from day to day is on a 2.6 sy
  • by steveoc (2661) on Wednesday July 18, 2007 @02:11AM (#19897625)
    You start the project in the first place because you have a unique solution to a given real-world problem.

    Others may have different solutions to the same problem, and you are all free to attack it in your own way. In a totally free environment, you can determine the best solution to the problem using proof-by-mindshare.

    As time moves on, the landscape changes, and some/none/all of your assumptions about the problem domain that drive your solution get challenged.

    If it appears that your solution is no longer relevant, and that other methods work better in the real world, then your project can successfully conclude, and you can move on to the next big thing. In this case, OpenMosix can see that it's solution to the problem is not the ideal way to go, as evidenced by the fact that MPI, load balancers, (insert other solutions), tend to be more applicable to most real world problems ... but that would never have been apparent if it wasnt tried.

    In a way, an open source software development is a test of a hypothesis. You dont measure success just by proving the hypothesis - you can also disprove it (or spawn a new one), and still claim success.

    If this had been a commercial / proprietry project, then everything would be different - there would be egos and money on the line, so the motivations for doing the project in the first place are very very different. If OpenMosix was commercial, higher ups in the company would be moving the goalposts to suit themselves, spending money on advertising and kickbacks, and putting effort into forcing it into sitations where it wasnt the ideal answer. The resultant mindshare and marketshare in a commercially driven enviroment yields sub-optimal solutions - its based on which solution has the best political backing and advertising budget, not the one that best fits the problem.

    See, its like this - to an opensource mindset, the hottest person in da club is the one that gets _given_ the most phone numbers. To a non-opensource mindset, the hottest person in da club is the one who can _buy_ the most phone numbers. Someone thought that the flouro lime green shirt might be a good idea .. but at da club, its not working out that way. Thankfully, we can toss the lime green shirt and try something different, because we are non-commercial.

    The sort of people who read the headline of the story and see it as a bad thing, a negative thing, an anti-FLOSS thing .. are looking at the story with their commerically-oriented-hat on. If that is you, then you shouldnt be working in science or computers - you should be out selling mobile phone ringtones, Celine Dion records, yo-yo's, insurance, timeshare condo plans, roller skates, lottery tickets, etc, etc, etc. If that is you, then you deserve to end up with the fat'n'ugly chick in the lime green shirt, simply because the advertising banners plastered all over the wall TOLD you she was the best choice.

    Thank goodness open source allows a project to go from conception to conclusion for all the right reasons.
  • but if this is useful and actually used by any companies, then it's a great way of getting yourself a job offer to carry on.
  • ... so it might as well be me:

    "openMosix is dying and Netcraft confirms it!"

    Forgive me.. just trying to keep the memes alive m'am!
  • hmmm.. (Score:3, Insightful)

    by pjr.cc (760528) on Wednesday July 18, 2007 @05:44AM (#19898513)
    Having read the comments I think people didn't actually read had been put on the announcement page, mostly about SSI losing some of its value in the wake of faster and bigger machines.

    To proclaim this is an object of example for the failure of OSS projects - my god, what a leap of stupidity that is. In reality, i'd be claiming the exact opposite in that it was one of the few SSI's to get into real world situations and be used quite heavily - which means it was actually very successful. It's a project that made it through a complete life cycle, birth, success and death. I would say its probably dying slightly before its time, but the authors reasons are quite sound in reality.

    This is something you just don't often see in the CSS world - companies make something and want/need to make money off it (indefinitely if possible), so not only do they bring a new version with more bells and whistles every year (even when the prior version only had 10% of its bells and whistles used) they're continuously pushing to continue making money off the product, and that often means "never expire the product, morph it if we must, but every coder hour is less profit - sales are dropping, NEW VERSION TIME!". Wow, that was even less cynical than I normally am!
  • by Ktistec Machine (159201) on Wednesday July 18, 2007 @09:23AM (#19899803)
    We used Mosix (and then OpenMosix) for several years, with much success. Around, oh, I don't remember but say 2002-2003 we started to see stability problems with it, though, and eventually dropped it. This may have been a problem with our local configuration, or hardware, or who knows what (we never got to the bottom of it).

    By that time, though, I'd already come to be uncomfortable with OpenMosix for two reasons:

    • The develpers seemed to be completely uninterested in security issues. This is something that was less of a concern in The Good Old Days, but really should be on the frontest of burners now.
    • The OpenMosix kernel code was so large and stuck its tentacles into so many places, there was no way it was ever going to make it into the mainstream kernel. This meant that, if any changes were necessary, we were either at the mercy of the OpenMosix developers or we were going to have to maintain them ourselves.
    All of that being said, I loved OpenMosix when it worked. It's a great idea. I came out of a VAX/VMS cluster background, and OpenMosix was a serious step in the direction of resurrecting that functionality in open source. I'd like to see someone take over OpenMosix, make security a priority, and work to break it into small, digestible lumps that could slowly be merged into the mainline kernel.
  • Ever heard of ROCKS? (Score:3, Informative)

    by mauriceh (3721) <[maurice] [at] [harddata.com]> on Wednesday July 18, 2007 @02:04PM (#19904251) Homepage
    The main reason projects like this are floundering is that the ROCKS project is becoming the defacto standard for cluster setups.

    Also, companies like IBM and HP love to push their own proprietary setups.

    As well, there are some good commercial products that add lots of well supported tools.
    For example MOAB

"Floggings will continue until morale improves." -- anonymous flyer being distributed at Exxon USA

Working...