[BioC] openMosix and R
mtmorgan at fhcrc.org
Thu Jan 12 21:50:46 CET 2006
You'll benefit with openMosix because your R session can migrate to
less-used nodes in the cluster.
Extra benefit might come if you use or develop some of the parallel
processing tools available through R. For instance, snow, Rmpi, and
rpvm can be used to 'spawn' and communicate with new processes,
including new R processes. I think (no direct experience, though) that
openMosix will allow these processes to migrate to under-used nodes,
resulting in efficient computation.
R processes are relatively large, and computations likely to benefit
from parallelization may often involve very large data sets. For these
situations (large processes, large data) migration between nodes is
likely to be 'costly'. Whether costs outweigh benefits likely depends
on the details of the problem being solved.
It would be great to hear from people with direct experience using
Claudio Isella <claudio.isella at ircc.it> writes:
> Dear Bioc,
> in my lab we are evaluating the possibility to aquire a linux farm based
> on openMosix. In order to do this, we have to evaluate if the
> application we usually run, are going to improve their performance with
> this solution.
> Therefore I want to ask you if R, and in particular BioC packages can
> fork in this openMosix enviroment, and if so how to do it.
> Claudio Isella
> Bioconductor mailing list
> Bioconductor at stat.math.ethz.ch
More information about the Bioconductor