[Bioclusters] Newbie question: simple low-admin non-threaded Debian-based cluster solution?

elijah wright elw at stderr.org
Fri Jan 21 12:51:03 EST 2005


> Getting R to work seamlessly on a cluster is not trivial, unless the 
> users are using R in batch mode.  Getting R to work interactively and 
> still have the graphical parts of it work correctly is less easy.  X 
> authentication starts to be a problem.  It's unfortunate that R doesn't 
> have some sort of client-server architecture which would allow the hard 
> work to occur on a cluster node, and the interactive stuff be handled 
> locally by a client.

look into Rserv - http://stats.math.uni-augsburg.de/Rserve/

R has some of the neatest toys :)

also investigate RScaLAPACK and other Parallel-R packages.


>> The cluster must require the absolute minimum of configuration and 
>> maintenance, because Ive got to do it and Im hardly ever around these 
>> days.
>
> cfengine is good for this, as you've already suggested.  We use cfengine 
> for managing configuration information on our Linux desktops, although 
> not on our cluster nodes.

i've used jablicate here for initial workstation setups, along with a few 
hand-rolled scripts to tweak things on newly constructed systems (moving 
our kerberos, ldap, automounter configurations into place, for example).

we have been meaning to try out PFARS as a management tool - i hear it is 
quite useful.  your situation may vary, depending on the amount of 
stability you expect in your nodes.  if you change things frequently, that 
may affect what works well for you.


> GridEngine is pretty good.  I think the lack of Debian support is probably a 
> licence issue - I'm not sure SGE is DFSG-compliant.  As others have said,

pretty sure this is correct.  [there's also the fact that it is very 
large, complex software... almost as bad as Globus and friends.]


--elijah


More information about the Bioclusters mailing list