[GE users] Yet anaother MPICH tight-integration problem

David S. dgs at gs.washington.edu
Tue Sep 7 16:17:41 BST 2004


> What are you using as allocation_rule with the 'mpich' PE? Does
> it forsee more than two tasks be running when it breaks with
> 
>    error: executing task of job 27 failed:
> 
> error message?

I'm using the "$round_robin" rule, as specified in the "mpich.template"
that comes with the SGE distribution.  I'm not quite sure what you mean
by "forsee more than two tasks be running".  It seems to break when it
tries to start a second slave process on the node already running the 
master and one slave.  That's with the 'mpi/rsh' wrapper around 'qrsh'.
With '/usr/bin/rsh', it seems to work as expected.

David S.

> 

---------------------------------------------------------------------
To unsubscribe, e-mail: users-unsubscribe at gridengine.sunsource.net
For additional commands, e-mail: users-help at gridengine.sunsource.net




More information about the gridengine-users mailing list