[mpich-discuss] Hydra process manager on Condor
Savita Shrivastava
savita.shrivastava at gmail.com
Mon Mar 19 12:40:16 CDT 2012
I am able to run the mpich2 outside the condor as well as inside the
condor. For condor, I needed to add -wdir to the execute command. It was
not finding the condor's scratch directory.
Thanks for following up.
Savita
On Fri, Mar 16, 2012 at 4:32 PM, Pavan Balaji <balaji at mcs.anl.gov> wrote:
>
> Are you able to use MPICH2 outside the condor environment? It's better to
> make sure you are able to do that first.
>
> -- Pavan
>
>
> On 01/24/2012 03:01 PM, Savita Shrivastava wrote:
>
>>
>> I am struggling to run an MPI job on our RedHat MRG which has condor and
>> MPICH2 (1.4.1) with hydra process manager installed. If some one has
>> used hydra on condor please let me know how to run a job successfully.
>>
>> Thanks
>> Savita
>>
>>
>>
>> On Tue, Dec 27, 2011 at 9:30 PM, Pavan Balaji <balaji at mcs.anl.gov
>> <mailto:balaji at mcs.anl.gov>> wrote:
>>
>> Savita,
>>
>> [please keep mpich-discuss cc'ed]
>>
>> These files should be written to the same location that your mpiexec
>> was launched from. If you want to write it to a different location,
>> you can provide the full path to the files.
>>
>> -- Pavan
>>
>> On 12/27/2011 03:28 PM, Shrivastava, Savita wrote:
>>
>> Hi Pavan, Thanks for your response.
>>
>> After adding the -outfile-pattern ho.out -errfile-pattern he.err
>> in the
>> mpiexec command, the output file and error files were not
>> written to the
>> directory. I also tried adding -wdir. Another point I want to
>> mention
>> here is that the output file created by my script is not written
>> to the
>> output directory I mentioned in my script.
>>
>> I suspect there may be some parameters or settings may be needed
>> to run
>> mpiexec successfully on condor.
>>
>> Please advise.
>>
>> Thanks
>> Savita
>>
>>
>>
>>
>> -----Original Message-----
>> From: Pavan Balaji [mailto:balaji at mcs.anl.gov
>> <mailto:balaji at mcs.anl.gov>]
>> Sent: Tuesday, December 27, 2011 12:01 AM
>> To: mpich-discuss at mcs.anl.gov <mailto:mpich-discuss at mcs.anl.**gov<mpich-discuss at mcs.anl.gov>
>> >
>> Cc: Shrivastava, Savita
>> Subject: Re: [mpich-discuss] Hydra process manager on Condor
>>
>>
>> Hydra does not understand Condor's parameters. But you can
>> emulate the
>> behavior you want by setting these options for mpiexec:
>>
>> -outfile-pattern ho.out -errfile-pattern he.err
>>
>> You can also do more fancy things like:
>>
>> -outfile-pattern ho.%r.out -errfile-pattern he.%r.err
>>
>> which uses different files for each rank.
>>
>> See mpiexec -outfile-pattern -help for more information on other
>> patterns.
>>
>> -- Pavan
>>
>> On 12/19/2011 12:27 PM, Shrivastava, Savita wrote:
>>
>> Hi,
>>
>> We have installed MPICH2 with Hydra process manager on our
>> Condor
>> cluster. When I submit an mpi job to condor, the job is
>> transferred to
>> the execute node and executed properly (as I looked in the
>> condor log
>>
>> on
>>
>> execute node where the job was executing) but it does not
>> write the
>> standard output from script to condor output file mentioned
>> in job
>> description file. Please guide me here how to run the mpi job
>> successfully on condor using hydra process manager.
>>
>> My job description as below. The perl script has standard
>> output
>>
>> "Hello".
>>
>>
>> universe = parallel
>>
>> executable = /usr/lib64/mpich2/bin/mpiexec
>>
>> arguments = -n 2 -machinefile machinefile test2.pl
>> <http://test2.pl>
>>
>>
>> getenv=true
>>
>> machine_count = 1
>>
>> should_transfer_files = yes
>>
>> when_to_transfer_output = on_exit
>>
>> transfer_input_files = test2.pl <http://test2.pl>
>>
>>
>> output = ho.out
>>
>> error = he.err
>>
>> log = hl.log
>>
>> Requirements = Memory>= 1024&& Cpus>=2
>>
>>
>> request_cpus = 2
>>
>> request_memory = 1024
>>
>> queue
>>
>> Thanks
>>
>> Savita
>>
>>
>>
>> ______________________________**___________________
>> mpich-discuss mailing list mpich-discuss at mcs.anl.gov
>> <mailto:mpich-discuss at mcs.anl.**gov<mpich-discuss at mcs.anl.gov>
>> >
>>
>> To manage subscription options or unsubscribe:
>> https://lists.mcs.anl.gov/__**mailman/listinfo/mpich-discuss<https://lists.mcs.anl.gov/__mailman/listinfo/mpich-discuss>
>>
>> <https://lists.mcs.anl.gov/**mailman/listinfo/mpich-discuss<https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss>
>> **>
>>
>>
>>
>> --
>> Pavan Balaji
>> http://www.mcs.anl.gov/~balaji <http://www.mcs.anl.gov/%**7Ebalaji<http://www.mcs.anl.gov/%7Ebalaji>
>> >
>> ______________________________**___________________
>> mpich-discuss mailing list mpich-discuss at mcs.anl.gov
>> <mailto:mpich-discuss at mcs.anl.**gov <mpich-discuss at mcs.anl.gov>>
>>
>> To manage subscription options or unsubscribe:
>> https://lists.mcs.anl.gov/__**mailman/listinfo/mpich-discuss<https://lists.mcs.anl.gov/__mailman/listinfo/mpich-discuss>
>> <https://lists.mcs.anl.gov/**mailman/listinfo/mpich-discuss<https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss>
>> **>
>>
>>
>>
>>
>>
>> ______________________________**_________________
>> mpich-discuss mailing list mpich-discuss at mcs.anl.gov
>> To manage subscription options or unsubscribe:
>> https://lists.mcs.anl.gov/**mailman/listinfo/mpich-discuss<https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss>
>>
>
> --
> Pavan Balaji
> http://www.mcs.anl.gov/~balaji
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/mpich-discuss/attachments/20120319/7be7ea06/attachment.htm>
More information about the mpich-discuss
mailing list