Open MPI logo

Open MPI Development Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Development mailing list

Subject: Re: [OMPI devel] XML request
From: Greg Watson (g.watson_at_[hidden])
Date: 2009-08-19 10:48:01


Ralph,

Looks like it's working now.

Thanks,
Greg

On Aug 18, 2009, at 5:21 PM, Ralph Castain wrote:

> Give r21836 a try and see if it still gets out of order.
>
> Ralph
>
>
> On Aug 18, 2009, at 2:18 PM, Greg Watson wrote:
>
>> Ralph,
>>
>> Not sure that's it because all XML output should be via stdout.
>>
>> Greg
>>
>> On Aug 18, 2009, at 3:53 PM, Ralph Castain wrote:
>>
>>> Hmmm....let me try adding a fflush after the <mpirun> output to
>>> force it out. Best guess is that you are seeing a little race
>>> condition - the map output is coming over stderr, while the
>>> <mpirun> tag is coming over stdout.
>>>
>>>
>>>
>>> On Tue, Aug 18, 2009 at 12:53 PM, Greg Watson
>>> <g.watson_at_[hidden]> wrote:
>>> Hi Ralph,
>>>
>>> I'm seeing something strange. When I run "mpirun -mca
>>> orte_show_resolved_nodenames 1 -xml -display-map...", I see:
>>>
>>> <mpirun>
>>> <map>
>>> <host name="Jarrah.local" slots="1" max_slots="0">
>>> <process rank="0"/>
>>> <process rank="1"/>
>>> <process rank="2"/>
>>> <process rank="3"/>
>>> </host>
>>> </map>
>>> ...
>>> </mpirun>
>>>
>>> but when I run " ssh localhost mpirun -mca
>>> orte_show_resolved_nodenames 1 -xml -display-map...", I see:
>>>
>>> <map>
>>> <host name="Jarrah.local" slots="1" max_slots="0">
>>> <process rank="0"/>
>>> <process rank="1"/>
>>> <process rank="2"/>
>>> <process rank="3"/>
>>> </host>
>>> </map>
>>> <mpirun>
>>> ...
>>> </mpirun>
>>>
>>> Any ideas?
>>>
>>> Thanks,
>>> Greg
>>>
>>>
>>> On Aug 17, 2009, at 11:16 PM, Ralph Castain wrote:
>>>
>>> Should be done on trunk with r21826 - would you please give it a
>>> try and let me know if that meets requirements? If so, I'll move
>>> it to 1.3.4.
>>>
>>> Thanks
>>> Ralph
>>>
>>> On Aug 17, 2009, at 6:42 AM, Greg Watson wrote:
>>>
>>> Hi Ralph,
>>>
>>> Yes, you'd just need issue the start tag prior to any other XML
>>> output, then the end tag when it's guaranteed all XML other output
>>> has been sent.
>>>
>>> Greg
>>>
>>> On Aug 17, 2009, at 7:44 AM, Ralph Castain wrote:
>>>
>>> All things are possible - some just a tad more painful than others.
>>>
>>> It looks like you want the mpirun tags to flow around all output
>>> during the run - i.e., there is only one pair of mpirun tags that
>>> surround anything that might come out of the job. True?
>>>
>>> If so, that would be trivial.
>>>
>>> On Aug 14, 2009, at 9:25 AM, Greg Watson wrote:
>>>
>>> Ralph,
>>>
>>> Would it be possible to get mpirun to issue start and end tags if
>>> the -xml option is used? Currently there is no way to determine
>>> when the output starts and finishes, which makes parsing the XML
>>> tricky, particularly if something else generates output (e.g. the
>>> shell). Something like this would be ideal:
>>>
>>> <mpirun>
>>> <map>
>>> ...
>>> </map>
>>> <stdout>...</stdout>
>>> <stderr>...</stderr>
>>> </mpirun>
>>>
>>> If we could get it in 1.3.4 even better. :-)
>>>
>>> Thanks,
>>> Greg
>>> _______________________________________________
>>> devel mailing list
>>> devel_at_[hidden]
>>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>>>
>>> _______________________________________________
>>> devel mailing list
>>> devel_at_[hidden]
>>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>>>
>>> _______________________________________________
>>> devel mailing list
>>> devel_at_[hidden]
>>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>>>
>>> _______________________________________________
>>> devel mailing list
>>> devel_at_[hidden]
>>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>>>
>>> _______________________________________________
>>> devel mailing list
>>> devel_at_[hidden]
>>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>>>
>>> _______________________________________________
>>> devel mailing list
>>> devel_at_[hidden]
>>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>>
>> _______________________________________________
>> devel mailing list
>> devel_at_[hidden]
>> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>
> _______________________________________________
> devel mailing list
> devel_at_[hidden]
> http://www.open-mpi.org/mailman/listinfo.cgi/devel