Re: MOSIX

[Dariush Pietrzak <eyck@forumakad.pl>]

> As long as processes aren't too large or too small, it's going to work :)
Medium-sized and small are the ones I expect on my systems.
mosix installation i've seen is overloaded with BIG processes and it works
like a charm ( fortran programs that use GIGs of RAM - all machines are
equipped with 128M up to 512M of ram with 2Gigs of swap - swap divided
into eee, two swaps, it's sth MOSIX-specific )


> Process migration works for processes that a single node can
> process. :)
I'd be intereset in how well this handles handles - file handles and
sockets


> you have up to 15-20 machines, it might not be visible. I might be
I've heard of 2000 machines MOSIX in israel and it was unusable - too much
network traffic even using best switches and 100Mbit networ
( i think gigabit ethernet ain't the best thing for parallel computing due
to larger delays , and myrinet cards are way too expensive )

> 1000s of boxen of course. :)
it's been said that it can support up to 6500 boxes, but I think that it
would be way cheeper and faster to buy parallel machine from SGI


> can usually pass messages in systems like Mach or Amoeba in a convenient
Amoeba is quite strange thing, although i think i like it's filesystem
very much. and i don't like it's licence.
there is linux version built on Mach microkernel, do you think this would
be any better? 

> for scientific computing. Linear algebra, mostly. blas, scalapack, etc.
blacs. yes. but I ain't going to do much scientific computing, am thinking
about some more general solutions.

> People also have tried automatic parallelization of sequential code, but that
> doesn't work. :)
Hmm? and what about modern processors? don't they do this and do this
quite nicely ?


> to do some really neat work, I suggest you to have a look at HPF (High Performance
> Fortran), this seems to be the only serious data-parallel language around. Not that
never learned fortran, there is physics hmm division/catedra( pardon my
english ) near by, they teach fortran, but they do it bad or fortran is a
dirty language cause i didn't like how their code looks and works.

> be sure that it is going to be viable for at least a couple of decades. :)
so are assemblers, but I ain't going to do much coding with asm either.


> in potato and woody distributions. LAM can also handle heterogeneous networks,
that's great, I'll take a look at it, thanks.


> will distract you from the problem. If the available code doesn't give you much
> leverage, the rest is black magic.
thanks, I'll remember that.

> Some physicists like Charm++ also, but I don't find that very efficient.
what is Charm++?