[mpich-discuss] SGE & Hydra Problem

Pavan Balaji balaji at mcs.anl.gov
Wed Sep 15 02:03:31 CDT 2010


Hmm.. That's unexpected. Can you try a simpler program such as 
"/bin/true", and just use two nodes for testing?

% mpiexec -verbose /bin/true

(and)

% /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

Can you send me the output for both commands?

Thanks,

  -- Pavan

On 09/15/2010 01:57 AM, Ursula Winkler wrote:
> Pavan Balaji schrieb:
>> The below output seems incomplete. Did the launch hang, and had to be
>> killed?
>>
> The launch hang some minutes then obviously timed out (with the error
> message
> I quoted in my first message).
>> Can you try the below command?
>>
>> % /installadmin/sge/bin/lx24-amd64/qrsh -inherit -V b56
>> /installadmin/mpich2/test/intel/bin/hydra_pmi_proxy
>>
>> It should launch and error out, but not hang.
> It doesn't hang
>

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


More information about the mpich-discuss mailing list