In general, yes, OPAL_PREFIX should be enough.
However, it is certainly easier to configure properly if you have the same
prefix on all nodes, even if it's actually different one one node.
Check out this FAQ entry for more details:
http://www.open-mpi.org/faq/?category=building#where-to-install
On Nov 9, 2011, at 3:13 AM, Christophe Peyret wrote:
>
> • Few Additionnal Informations about my Network configuration
>
> /opt is a share point it uses NFS
>
> /Network/opt
>
> is the point where /opt can be found accross the Network
>
> I declared OPAL_PREFIX because openmpi was built with prefix /opt and runs it
> directory /Network/opt
>
>
> • If a copy the directory /opt/openmpi-1.4.4 on all my nodes
>
> scp -r /opt/openmpi-1.4.4 root@node2:/opt/.
> scp -r /opt/openmpi-1.4.4 root@node3:/opt/.
> scp -r /opt/openmpi-1.4.4 root@node4:/opt/.
> ....
>
> This time my program runs.
>
> • A Question : is OPAL_PREFIX declaration enought to use /Network/opt rather
> than /opt ?
>
>
> Christophe
>
>
>> The problem is that the prefix you configured with doesn't match the prefix
>> you are providing:
>>
>> configure: prefix = /opt/openmpi-1.4.4
>>
>> running: prefix = /Network/opt/openmpi-1.4.4
>>
>> The two have to match in order for the libraries to be found.
>>
>>
>> On Nov 8, 2011, at 6:01 AM, Christophe Peyret wrote:
>>
>> > Hello,
>> >
>> >
>> > I am trying to run a program on a cluster composed with Apple Xserve
>> > running 10.5.8 (Leopard).
>> >
>> >
>> > 1) I am using openmpi-1.4.4 compiled with Intel ifort and icc (V12)
>> > (/opt is a share point mounted in /Network/opt with NFS)
>> >
>> > ./configure --prefix=/opt/openmpi-1.4.4 \
>> > F77=/Network/opt/intel/composerxe/bin/ifort F77FLAGS="-arch x86_64" \
>> > FC=/Network/opt/intel/composerxe/bin/ifort FCFLAGS="-arch x86_64" \
>> > CC=/Network/opt/intel/composerxe/bin/icc CFLAGS="-arch x86_64" \
>> > CXX=/Network/opt/intel/composerxe/bin/icpc CXXFLAGS="-arch x86_64"
>> >
>> > make
>> > sudo make install
>> >
>> >
>> > Each /etc/profile of my nodes contains :
>> >
>> > export COMP_HOME=/Network/opt/intel/composerxe
>> > export PATH=$COMP_HOME/bin:$COMP_HOME/man:$PATH
>> > export DYLD_LIBRARY_PATH=$COMP_HOME/lib/:$DYLD_LIBRARY_PATH
>> >
>> > export MPI_HOME=/Network/opt/openmpi-1.4.4
>> > export OPAL_PREFIX=/Network/opt/openmpi-1.4.4
>> >
>> > export PATH=${MPI_HOME}/bin:${MPI_HOME}/man:$PATH
>> > export DYLD_LIBRARY_PATH=$MPI_HOME/lib/:$DYLD_LIBRARY_PATH
>> > export LD_LIBRARY_PATH=$MPI_HOME/lib/:$LD_LIBRARY_PATH
>> >
>> > 2) when I lauch mpirun on several nodes, the MPI connections fails and I
>> > have the error message :
>> >
>> > mpirun --prefix /Network/opt/openmpi-1.4.4/ -H node1,node2 -n 2 space64 -f
>> > Test/Euler/eulerRigid.def
>> > dyld: lazy symbol binding failed: Symbol not found: _orte_daemon
>> > Referenced from: /Network/opt/openmpi-1.4.4/bin/orted
>> > Expected in: /usr/lib/libopen-rte.0.dylib
>> >
>> > dyld: Symbol not found: _orte_daemon
>> > Referenced from: /Network/opt/openmpi-1.4.4/bin/orted
>> > Expected in: /usr/lib/libopen-rte.0.dylib
>> >
>> > bash: line 1: 2973 Trace/BPT trap /Network/opt/openmpi-1.4.4/bin/orted
>> > --daemonize -mca ess env -mca orte_ess_jobid 1644560384 -mca orte_ess_vpid
>> > 1 -mca orte_ess_num_procs 2 --hnp-uri
>> > "1644560384.0;tcp://10.0.0.1:50782;tcp://125.1.4.55:50782"
>> > --------------------------------------------------------------------------
>> > A daemon (pid 41667) died unexpectedly with status 133 while attempting
>> > to launch so we are aborting.
>> >
>> > There may be more information reported by the environment (see above).
>> >
>> > This may be because the daemon was unable to find all the needed shared
>> > libraries on the remote node. You may set your LD_LIBRARY_PATH to have the
>> > location of the shared libraries on the remote nodes and this will
>> > automatically be forwarded to the remote nodes.
>> > --------------------------------------------------------------------------
>> > --------------------------------------------------------------------------
>> > mpirun noticed that the job aborted, but has no info as to the process
>> > that caused that situation.
>> > --------------------------------------------------------------------------
>> > mpirun: clean termination accomplished
>> >
>> >
>> > 3) Does anyone have an idea ?
>> >
>> >
>> > --
>> > Christophe Peyret
>> > ONERA - DSNA - PS3A
>> > 29 ave de la Division Leclerc
>> > F92320 Chatillon
>> > Tel. : +331 4673 4778
>> > Fax : +331 4673 4166
>> >
>> > http://www.onera.fr/dsna/couplage-methodes-aeroacoustiques
>> >
>>
>>
> --
> Christophe Peyret
> ONERA - DSNA - PS3A
> 29 ave de la Division Leclerc
> F92320 Chatillon
> Tel. : +331 4673 4778
> Fax : +331 4673 4166
>
> http://www.onera.fr/dsna/couplage-methodes-aeroacoustiques
>
>
>
>
>
> _______________________________________________
> users mailing list
> us...@open-mpi.org
> http://www.open-mpi.org/mailman/listinfo.cgi/users
--
Jeff Squyres
jsquy...@cisco.com
For corporate legal information go to:
http://www.cisco.com/web/about/doing_business/legal/cri/
