[Bioclusters] Cluster ideas/suggestions

[Micha Bayer]

Nick,

if you have dedicated machines then Condor and BLAST can work reasonably
well together because you can keep target databases preinstalled on all
your machines. This gets you around the i/o issues.

We run BLAST on Condor that way and it seems pretty reasonable. There is
also a very large Condor Pool at Wisconsin Uni which is used for BLAST
and it does a hell of a lot of useful work. 

Micha


On Thu, 2005-01-13 at 15:34, Nick D'Angelo wrote:
> All great ideas, thank you for them so far.
> 
> I should have mentioned, that the cluster is required to run Blast, CLusta1W
> and RNAfold.
> 
> Currently I have three Fedora machines, kind of all doing independent work
> in isolation of each other and we manually setup the jobs to run until
> completed.
> 
> Nick 
> 
> -----Original Message-----
> From: Micha Bayer [mailto:michab at dcs.gla.ac.uk]
> Sent: Thursday, January 13, 2005 10:01 AM
> To: Clustering, compute " farming & distributed computing in life
> science informatics
> Subject: Re: [Bioclusters] Cluster ideas/suggestions
> 
> 
> Hi,
> 
> this sounds like you might want to look at Condor. Condor is an
> excellent tool for doing just that sort of thing (desktop cycle
> harvesting). 
> 
> It can be installed on Linux or Windows machines, and it is highly
> configurable. One can set machines up so that jobs never run when the
> user is working, so that users don't even know a job is lurking in the
> background on their machine.  
> 
> This would save you the trouble of having to reboot the machines, and
> you would get extra cycles during the day when users are in their coffee
> break etc. 
> 
> Very nice package, free , very mature and great documentation. We run a
> Condor pool here and we think it is excellent. There is also a large
> user community already with mailing lists etc and good support
> otherwise.
> 
> http://www.cs.wisc.edu/condor/
> 
> If you have a pool of users who trust you to run jobs on their machines
> then this is just the ticket.
> 
> cheers
> Micha
> 
> 
> On Thu, 2005-01-13 at 14:34, Nick D'Angelo wrote:
> > In speaking to our R and D managers, they posed a good question.
> > 
> > What about their desktop machines (relatively New Dell PCs), have them
> > automatically shutdown and reboot, say at 8:00 pm and then join the
> cluster
> > until 05:00 am.
> > 
> > Then at 5:00 am, initiate another reboot that will present the Windows
> Login
> > for the 'normal business day'.
> > 
> > This would make great use of the hundreds of computers that are mostly
> > sitting idle during the off hours 'normal business day'.
> > 
> > Thoughts, suggestions always appreciated, thanks.
> > 
> > Nick
> > 
> > In case you need to know,  I am likely going to install the BioBrew v3.x
> > which has just been pre-leased in Beta I believe.
> > _______________________________________________
> > Bioclusters maillist  -  Bioclusters at bioinformatics.org
> > https://bioinformatics.org/mailman/listinfo/bioclusters
-- 
--------------------------------------------------
Dr Micha M Bayer
Grid Developer, BRIDGES Project
National e-Science Centre, Glasgow Hub
246c Kelvin Building
University of Glasgow
Glasgow G12 8QQ
Scotland, UK
Email: michab at dcs.gla.ac.uk
Project home page: http://www.brc.dcs.gla.ac.uk/projects/bridges/
Personal Homepage: http://www.brc.dcs.gla.ac.uk/~michab/
Tel.: +44 (0)141 330 2958