[GE users] Tight Integration of MPICH with SGE
Waseem Ahmad
Waseem.Ahmad.1 at Sun.COM
Tue Jul 27 16:46:06 BST 2004
Reuti!
All of the required environment variables are set on slave nodes
too.Yes, i am using ch_p4 device. The broken pipe error is corrected
now. It was reported by SGE .e* files. Instead i get the following error.
Cannot read /tmp/machines.
Looked for files with extension solaris in
directory /gridware/sge/mpich-1.2.5.2/util/machines
This is reported in the Programme output.
Note that i am able to run the sample script for testing tight
integration provided in the mpi directory. But when i try to run my perl
script which spawns mpi jobs through mpirun, i get above mentioned problem.
Thanks.
Reuti wrote:
> Hi,
>
> some programs need some environment variables set up also on the slave
> nodes in the correct way. So I added -V to the qrsh command in the rsh
> wrapper in the mpi directory (man qsub to get the explanation of -V).
> Are you using ch_p4 device? Some programs using MPI have built in to use
> ssh instead. This you can adjust with:
>
> export P4_RSHCOMMAND=rsh
>
> to get rsh again.
>
> Do you get the broken pipe error in any of the output files of SGE or in
> the output of your program?
>
> Reuti
>
>
> Waseem Ahmad wrote:
>
>> Reuti!
>> - I am running SGE on Solaris 9.
>> - I did use catch_rsh in the PE startup
>> - Job is first task is set to false too.
>> - I dont know about -V for qrsh. Can you please exaplin it a little.
>>
>> Thanks.
>>
>>
>> Reuti wrote:
>>
>>>> I am able to run MPI Jobs through SGE while MPICH is loosely
>>>> integrated with SGE. But when i try to run jobs thorugh tight
>>>> integration configured according to the README in the mpi directory,
>>>> i am get broken pipe errors.
>>>
>>>
>>>
>>>
>>> Some more infos about your setup would be useful:
>>>
>>> - which platform?
>>> - did you use -catch_rsh in the prolog of the PE?
>>> - set job is first task to false?
>>> - do you need any environment variables in the program (-V for qrsh
>>> in the rsh-wrapper may be necessary)?
>>>
>>> Cheers - Reuti
>>>
>>> ---------------------------------------------------------------------
>>> To unsubscribe, e-mail: users-unsubscribe at gridengine.sunsource.net
>>> For additional commands, e-mail: users-help at gridengine.sunsource.net
>>>
>>>
>>
>>
>>
>> ---------------------------------------------------------------------
>> To unsubscribe, e-mail: users-unsubscribe at gridengine.sunsource.net
>> For additional commands, e-mail: users-help at gridengine.sunsource.net
>
>
>
>
> ---------------------------------------------------------------------
> To unsubscribe, e-mail: users-unsubscribe at gridengine.sunsource.net
> For additional commands, e-mail: users-help at gridengine.sunsource.net
>
>
---------------------------------------------------------------------
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