Baslinux mailing list

[James Miller <jamtat AT mailsnare.net>]

On Sun, 27 Jul 2003 qwms-avib AT dea.spamcon.org wrote:

> Today I ran openMosix on two computers with BL2 (ramdisk).
> This enabled the computers to share jobs.  So, when I gave
> the slower computer a big gzip to do, I could see it shift
> that job to the faster computer.
>
> It's not that difficult to set up.  You simply replace the
> BL2 kernel with the openMosix kernel (which is available
> for download at basiclinux.com.ru), edit BOOT.BAT, list
> the addresses of the computers you want in the cluster
> (in /etc/hpc.map) and execute the start program.  Of course,
> you have to configure your network first (insmod, ifconfig)
> in the usual way.
>
> If people are really interested in this, I'll provide detailed
> instructions.  I suppose I could even do a special BL2 package
> with openMosix built in.
>
This sounds like a fascinating discovery, Steven.  Let me see whether the
way it strikes me makes sense to you or anyone else.  What Openmosix does,
as I've underastood it (I'm also sub'd to the K12LTSP list, where's it's
been discussed several times) is to harness the computing power of all
machines hooked to a given network such that this power can be used from
any of the "nodes" (correct terminology?) on the network: is that
approximately correct?  If so, then BL2 + Openmosix = a way of utilizing
older (maybe throwaway) systems to get more up-to-date computing power,
right?  A person could salvage say, 3 or 4 older machines and, with a bit
of networking setup, have the equivalent of a much better machine than any
of the individual machines on the network.  Strikes me as a great way of
keeping obsolete equipment out of the landfill, and of giving those with
more limited financial resources (if they have the tech saavy) access to
better computing power.  I really like this idea, if it's what it seems to
me to be.  Of course the downside to an Openmosix cluster like this from
an economic point of view is that the cost of running it will be
substantially higher than that of a single, more powerful machine (several
power supplies running, instead of only one).  But, in certain
circumstances I can envision, it could work really well.  Is my
understanding of the potential of this on-track?

Keep up the good work, Steven.  This seems like a real positive
development in BL to me.  As we say in Americaneze - go for it!

James