This is a read-only archive. Find the latest Linux articles, documentation, and answers at the new!

If openMosix simpler and updated

Posted by: Anonymous Coward on April 11, 2006 11:25 PM
It would be great. It should be simpler to set up an openMosix cluster, like apt-get install, change a few configuration options in<nobr> <wbr></nobr>/etc/openmosix, start the additional nodes and you are done. Moving, recreating, setting up, duplicating<nobr> <wbr></nobr>/home, insistance on using dhcp instead of static ips, and other set up procedures turns off those who would be considered casual users. But give those "casual users" the ability to simply add older boxes into a mini-cluster without too many steps or steps that endanger<nobr> <wbr></nobr>/home or require complicated setups and you will see a much larger number of users using openMosix.

I'd like to use openMosix. I finally saw a file or two appear in debian Stable. Each time I see some news on openMosix, or if I see something hit Debian stable, I take another look at the project, hoping. Always disappointed. Hasn't become ubiquitous for distros, hasn't turned into a project that is just "there" or is simply bundled with the distro itself.

Another problem with openMosix is the slowness in updating the project. Where's the 2.6 kernel solutions? Will I see openMosix supporting 2.6 kernel versions in Debian that have AMD flags (k-7, k-8, etc) or are compatible, or are we talking custom kernels, another barrier to "just running it". Where are the user tools for 2.6? Last time I checked (about a week ago) there were supposedly alpha 2.6 openMosix kernels in cvs, and either then or just a bit earlier, people posting about the lack of user tools with no responses. Which brings up another issue, time to update the site. If no one's paying attention to these issues, is this project still on track? Or are the developers making too much money installing and running openMosix on a few large customers' clusters and don't have time to bother with the FOSS project?

Developers and fans of openMosix, don't take this too critically or personally. Look at it as constructive criticism at worst. I'm just telling you from my non-guru, non-kernel-compiling-weekly seat, from a layman's perspective not a programmer's perspective. I've got some desktops that would benefit tremendously from openMosix. A cluster that works with migrated processes is exactly what I need, and others with older systems need, not PVM or Beowulf or other clusters. The project isn't aimed at us, but we could benefit just as the LTSP project benefits from its cluster setup.


Return to Building a Linux supercomputer using SSH and PVM