[mpich-discuss] SGE & Hydra Problem

Pavan Balaji balaji at mcs.anl.gov
Wed Sep 15 03:54:25 CDT 2010


Did it not give any output before failing?

--
Pavan Balaji
http://www.mcs.anl.gov/~balaji

----- "Ursula Winkler" <ursula.winkler at uni-graz.at> wrote:

> Pavan Balaji schrieb:
> > I'm assuming the application still hung at this point and you had to
> kill it?
> >   
> No, I didn't have to kill it. It finished (or timed out) by itself.
> >
> > Are you not running this command within an SGE job script? The qrsh
> command should be run from b79, not from b00.
> >
> >  
> 
> Ok, everything clear :-)
> 
> But the command "/installadmin/sge/bin/lx24-amd64/qrsh -inherit -V
> b56
> /installadmin/mpich2/test/intel/bin/hydra_pmi_proxy --control-port 
> b73:52298
> --debug --demux poll --pgid 0 --enable-stdin 1 --proxy-id 1" run in a
> 
> SGE job
> script from b46 gives the same error: "error: executing task of job 
> 158279 failed:"
> 
> Ursula


More information about the mpich-discuss mailing list