Re: [Condor-users] rsh error

["Diego Bello" <dbello@xxxxxxxxx>]

On 11/11/06, Christopher Jon Jursa <cjursa@xxxxxxxxxxxx> wrote:
> Hi,
>
> I am attempting to run an MPI executable and submit it through Condor.  I am
> using Fedore Core 5, mpich 1.2.4 and Condor 6.7.21.
>
> However, I am getting an rsh error when Condor executes.
>
> The errror message is at
> http://gis.sis.pitt.edu/temp/chris/mpi2/mpiTest.error
>
> The job submission file I am using is at
> http://gis.sis.pitt.edu/temp/chris/mpi/mpi_job
>
> Finally, the script file used in the job file is at
> http://gis.sis.pitt.edu/temp/chris/mpi2/jobfile.sh
>
> How is rsh used by Condor and MPI?  How do I fix the rsh error?  I think I
> have dropped all the firewalls.  What are common reasons for this error?
>
> Cheers,
>
> Chris
>
> Sincerely,
>
> Christopher Jon Jursa
> Geoinformatics Laboratory
> School of Information Sciences
> University of Pittsburgh
> web: http://gis.sis.pitt.edu
> email: cjursa@xxxxxxxxxxxx
> phone: 412-624-8858

You have to configure RSH, by default, it is disabled in Linux.
Check the /etc/xinetd.d/rsh and /etc/xinetd.d/rlogin and make sure
they say disable=no.

In /etc/hosts.allow you need an entry like this:
in.rshd: 192.168.1.0/255.255.255.0
in.rlogind: 192.168.1.0/255.255.255.0

Also, you have to add every mpi host in the /etc/hosts.equiv file so
you can freely use rsh between them.

Be carefull, rsh is a plain text comunication service, so if you are
not in a closed cluster, try using ssh instead rsh.

I hope this helps.

Bye!
--
Diego Bello Carreño
Estudiante Memorista de Ingeniería Civil Informática
UTFSM, Valparaíso, Chile
Usuario #294897 counter.li.org