<meta http-equiv="Content-Type" content="text/html; charset=utf-8"><div dir="ltr">The system is a micro-OS running in an embedded processor. There will be multiple of these processors, each one with a single mpi rank. I'm starting to think that I will have to do what Hydra does myself. Is there any documentation about what a mpi job expects from hydra?<div><br></div><div>Eduardo</div></div><div class="gmail_extra"><br><div class="gmail_quote">On Sat, Jan 17, 2015 at 5:58 PM, Jeff Hammond <span dir="ltr"><<a href="mailto:jeff.science@gmail.com" target="_blank">jeff.science@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">How do you create processes on this system? If you are using an MPI<br>
implementation that has a 1:1 mapping between MPI processes and OS<br>
processes, you've got to be able to create multiple processes somehow.<br>
<br>
Do you have any platform details you can share?<br>
<br>
Jeff<br>
<div class="HOEnZb"><div class="h5"><br>
On Sat, Jan 17, 2015 at 11:46 AM, Eduardo <<a href="mailto:erocha.ssa@gmail.com">erocha.ssa@gmail.com</a>> wrote:<br>
> I tried to use a newer MPICH, but, as you said, Hydra forks as part of<br>
> mpiexec. Is it possible to launch a job without mpiexec/mpirun ? That should<br>
> probably work in my environment (assuming that there is no listener as a<br>
> heavy process as it is the case in the default mpich-1.2.7p1).<br>
><br>
> The problem is not that the fork symbol is missing. The problem is that it<br>
> is been called. My environment actually has a dummy fork, but that only<br>
> causes the program to abort if it is called.<br>
><br>
> So in summary, the problem is that I cannot use mpiexec to launch a program,<br>
> because it calls fork. In mpich-1.2.7p1 , I can launch myself the program as<br>
> if I was launching a debug (as in section 3.5.6 of the CH_P4 manual). In<br>
> addition, the mpich cannot issue a fork for a listener like task, only<br>
> threads.<br>
><br>
> Eduardo<br>
><br>
> On Sat, Jan 17, 2015 at 4:23 PM, Jeff Hammond <<a href="mailto:jeff.science@gmail.com">jeff.science@gmail.com</a>><br>
> wrote:<br>
>><br>
>> MPICH shouldn't fork. Hydra probably uses fork to launch processes as part<br>
>> of mpiexec.<br>
>><br>
>> Blue Gene doesn't support fork either and MPICH runs there, but the<br>
>> process launcher is not Hydra. Same for Cray last time I checked. So I'm<br>
>> sure that fork isn't required to use MPICH, at least if dynamic processes<br>
>> are not used.<br>
>><br>
>> Is the issue that you cannot link an MPI program because the fork symbol<br>
>> is missing or that you cannot launch jobs with a Hydra?<br>
>><br>
>> All mainstream MPI implementations use OS processes to implement MPI<br>
>> processes, but the standard doesn't require this. FG-MPI uses threads to<br>
>> implement MPI processes, but as it still uses Hydra (AFAIK), it may or may<br>
>> not work for you.<br>
>><br>
>> Can you describe in detail what happens when you try to build and run<br>
>> MPICH-latest on your system?<br>
>><br>
>> Jeff<br>
>><br>
>> Sent from my iPhone<br>
>><br>
>> On Jan 17, 2015, at 9:41 AM, Eduardo <<a href="mailto:erocha.ssa@gmail.com">erocha.ssa@gmail.com</a>> wrote:<br>
>><br>
>> I would use a newer version if I could. However, I cannot issue a fork in<br>
>> my embedded environment. I can create threads though.<br>
>><br>
>> So, is there any newer versions of mpich that does not create heavy<br>
>> processes? I can live without MPI_Spawn and the like.<br>
>><br>
>> Regards,<br>
>><br>
>> Eduardo<br>
>><br>
>> On Jan 16, 2015 5:42 PM, "Wesley Bland" <<a href="mailto:wbland@anl.gov">wbland@anl.gov</a>> wrote:<br>
>>><br>
>>> Can you try using a more recent version of MPICH. The version you are<br>
>>> using is years old and we don't support it anymore. Our latest version is<br>
>>> 3.1.3. You might see if the issue is still present there.<br>
>>><br>
>>> Thanks,<br>
>>> Wesley<br>
>>><br>
>>> On Fri, Jan 16, 2015 at 10:54 AM, Eduardo <<a href="mailto:erocha.ssa@gmail.com">erocha.ssa@gmail.com</a>> wrote:<br>
>>>><br>
>>>> Hi,<br>
>>>><br>
>>>> I am trying to compile and use mpich-1.2.7p1 with threaded listener<br>
>>>> (i.e. configured with --enable-threaded-listener). However, I cannot even<br>
>>>> run a simple mpi example with the resulting mpich.<br>
>>>><br>
>>>> I need to use threaded listener because the environment I am compiling<br>
>>>> for (kind of embedded environment) does not have fork (no heavy processes).<br>
>>>><br>
>>>> The error I get with the mpich with threaded listener is:<br>
>>>><br>
>>>> rm_2889: 1103279872: p4_error: listener select: -1<br>
>>>> p4_error: latest msg from perror: Bad file descriptor<br>
>>>> p0_2710: (2.097656) net_recv failed for fd = 5<br>
>>>> p0_2710: 3778266880: p4_error: net_recv read, errno = : 104<br>
>>>><br>
>>>> Has anyone experienced a similar problem?<br>
>>>><br>
>>>> Thanks in advance,<br>
>>>> Eduardo<br>
>>><br>
>>><br>
>>><br>
>>> _______________________________________________<br>
>>> discuss mailing list <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
>>> To manage subscription options or unsubscribe:<br>
>>> <a href="https://lists.mpich.org/mailman/listinfo/discuss" target="_blank">https://lists.mpich.org/mailman/listinfo/discuss</a><br>
>><br>
>> _______________________________________________<br>
>> discuss mailing list <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
>> To manage subscription options or unsubscribe:<br>
>> <a href="https://lists.mpich.org/mailman/listinfo/discuss" target="_blank">https://lists.mpich.org/mailman/listinfo/discuss</a><br>
>><br>
>><br>
>> _______________________________________________<br>
>> discuss mailing list <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
>> To manage subscription options or unsubscribe:<br>
>> <a href="https://lists.mpich.org/mailman/listinfo/discuss" target="_blank">https://lists.mpich.org/mailman/listinfo/discuss</a><br>
><br>
><br>
><br>
> _______________________________________________<br>
> discuss mailing list <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
> To manage subscription options or unsubscribe:<br>
> <a href="https://lists.mpich.org/mailman/listinfo/discuss" target="_blank">https://lists.mpich.org/mailman/listinfo/discuss</a><br>
<br>
<br>
<br>
</div></div><span class="HOEnZb"><font color="#888888">--<br>
Jeff Hammond<br>
<a href="mailto:jeff.science@gmail.com">jeff.science@gmail.com</a><br>
<a href="http://jeffhammond.github.io/" target="_blank">http://jeffhammond.github.io/</a><br>
</font></span><div class="HOEnZb"><div class="h5">_______________________________________________<br>
discuss mailing list <a href="mailto:discuss@mpich.org">discuss@mpich.org</a><br>
To manage subscription options or unsubscribe:<br>
<a href="https://lists.mpich.org/mailman/listinfo/discuss" target="_blank">https://lists.mpich.org/mailman/listinfo/discuss</a><br>
</div></div></blockquote></div><br></div>