[OMPI devel] OFED 1.1 compile problems on trunk

2008-01-23 Thread Jeff Squyres
We recently brought some code over to the openib btl in the trunk that accidentally broke builds on OFED 1.1 and 1.0. Attached is a patch that fixes the problem. I'll commit the patch tonight because it involves changes to configure. -- Jeff Squyres Cisco Systems openib-ofed1.1.patch Desc

Re: [OMPI devel] dropping a pls module into an Open MPI build

2008-01-23 Thread Ralph H Castain
Hi Dean Had to ponder this for awhile. I'm not entirely sure of the source of the problem, but one suspicion has to do with the name of the module. Open MPI ships with a module named "rsh" in the PLS framework. The MCA uses the module name in its loading process. If you insert another module with

Re: [OMPI devel] [OMPI svn] svn:open-mpi r17177

2008-01-23 Thread Aurélien Bouteiller
Undefined symbols: "_opal_carto_base_components_opened", referenced from: _opal_carto_base_components_opened$non_lazy_ptr in components.o "_opal_carto_base_open", referenced from: ompi_info::open_components() in components.o "_opal_carto_base_close", referenced from: o

[OMPI devel] trunk breakage

2008-01-23 Thread Jeff Squyres
The vprotocol pml does not compile for me. make[4]: Entering directory `/home/jsquyres/svn/ompi2/ompi/mca/pml/v/ vprotocol/pessimist' /bin/sh ../../../../../../libtool --tag=CC --mode=compile gcc - DHAVE_CONFIG_H -I. -I../../../../../../opal/include - I../../../../../../orte/include -I../..

Re: [OMPI devel] trunk breakage

2008-01-23 Thread Aurélien Bouteiller
Should be fixed with r17184. Thanks for the quick bug report ! Aurelien Le 23 janv. 08 à 14:08, Jeff Squyres a écrit : The vprotocol pml does not compile for me. make[4]: Entering directory `/home/jsquyres/svn/ompi2/ompi/mca/pml/v/ vprotocol/pessimist' /bin/sh ../../../../../../libtool --tag

Re: [OMPI devel] OMPI/ORTE and tools

2008-01-23 Thread Jeff Squyres
Gotcha; thanks for the explanation. The capabilities you added sounds good for the moment; I'm sure we'll think of more over time... On Jan 22, 2008, at 10:19 AM, Ralph H Castain wrote: On 1/19/08 6:31 AM, "Jeff Squyres" wrote: Ralph -- I'm a little confused as to what you're provid

Re: [OMPI devel] [OMPI svn] svn:open-mpi r17177

2008-01-23 Thread George Bosilca
Or the visibility attribute in the .h file. Please add OPAL_DECLSPEC to all functions that are visible from outside the carto component. Thanks, George. On Jan 23, 2008, at 1:25 PM, Aurélien Bouteiller wrote: Undefined symbols: "_opal_carto_base_components_opened", referenced from:

Re: [OMPI devel] trunk breakage

2008-01-23 Thread Ralph H Castain
Still no joy... pn1180961:~/openmpi/trunk rhc$ make install > /dev/null vprotocol_pessimist_sender_based.c: In function 'sb_mmap_file_open': vprotocol_pessimist_sender_based.c:43: error: 'errno' undeclared (first use in this function) vprotocol_pessimist_sender_based.c:43: error: (Each undeclared

[OMPI devel] v pml question

2008-01-23 Thread Jeff Squyres
Just curious: what are the "mca" and "vprotocol" symlinks to "." for in the v/vprotocol directory for? If they're necessary, can they be committed to svn? If they're not necessary, can they be removed? -- Jeff Squyres Cisco Systems

[OMPI devel] RES: v pml question

2008-01-23 Thread Leonardo Fialho
I'm testing the v protocol just now. Anybody have plans to do a message wrapper mixing crcpw and v_protocol? Leonardo Fialho University Autonoma of Barcelona -Mensagem original- De: devel-boun...@open-mpi.org [mailto:devel-boun...@open-mpi.org] Em nome de Jeff Squyres Enviada em: miércol

Re: [OMPI devel] RES: v pml question

2008-01-23 Thread Aurélien Bouteiller
Hi, Actually it might already work. We never tried yet but nothing should prevent it. The symlinks are necessary to trick the autogen and configure stages. This is required to avoid code replication from autogen.sh. If you look carefully you will see that the simlinks are created only ins

Re: [OMPI devel] dropping a pls module into an Open MPI build

2008-01-23 Thread Dean Dauger, Ph. D.
Hi All, I think I have a possible explanation for this problem. Previously orterun was jumping to 0x: [Rotarran-X-5:04475] Failing at address: 0x0 [ 1] [0xb828, 0x] (-P-) On a hunch I tried changing the number of bool's in the orte_pls_rsh_component_t data structure

Re: [OMPI devel] dropping a pls module into an Open MPI build

2008-01-23 Thread Ralph Castain
I'm sorry, but now I am totally confused. Are you saying that you are having problems with the default rsh component in the distributed 1.2.3 code?? Or are you having a problem with your customized version? What compiler are you using? If it's your customized version, did you make sure to change th