1
1
openmpi/ompi
Jeff Squyres 57a3dce9ba LANL noticed that calling MPI_ABORT invokes opal_output(0, ...)
unconditionally, which can result in a flood of messages to the user
if all MPI processes invoke abort.  Additionally, some users were
confused because they saw the MPI_ABORT opal_output() messages from
''some'' MPI processes, but not ''all'' of them (despite the fact that
every MPI process supposedly invoked MPI_ABORT).  The reason is that
calling MPI_ABORT triggers ORTE to kill all MPI processes, so it's a
race condition as to whether a) all MPI processes actually invoke
MPI_ABORT, and/or b) whether every process is able to opal_output()
before they are killed.

This commit does two simple things:
 * Now use orte_show_help() for the MPI_ABORT message, so they are
   aggregated. 
 * Add a note in the message that calling MPI_ABORT kills all
   processes, so you might not see all output, yadda yadda yadda.

This commit was SVN r19735.
2008-10-14 19:23:03 +00:00
..
attribute Repair the MPI-2 dynamic operations. This includes: 2008-07-03 17:53:37 +00:00
class Small fix for including unistd.h header file. 2008-06-27 16:25:31 +00:00
communicator Ensure that the mutex is properly constructed/destructed. 2008-09-09 12:57:45 +00:00
contrib/vt Removed - This file will be created by autotools 2008-09-19 15:09:46 +00:00
datatype Remove the protection around computing the remote size. This has to be done 2008-09-26 23:11:53 +00:00
debuggers Disable global ID resolution when sparse groups are used. Tested by 2008-09-23 16:27:01 +00:00
errhandler Based on a review by Ralph, no need to call getpid() or gethostname(); 2008-09-23 20:04:34 +00:00
etc Many thanks to Ralf W. for finding a subtle bug in these Makefile.am's 2008-06-04 01:28:03 +00:00
file - Destruct the file->f_io_requests_lock as well. 2008-10-14 15:23:45 +00:00
group Fix 2 derefenced NULL variables (Coverty fix 474 & 476). 2008-08-06 15:50:54 +00:00
include Increase the size of MPI_MAX_PORT_NAME from 256 to 1024. 2008-09-25 16:47:17 +00:00
info Effectively revert the orte_output system and return to direct use of opal_output at all levels. Retain the orte_show_help subsystem to allow aggregation of show_help messages at the HNP. 2008-06-09 14:53:58 +00:00
mca Fix warnings (thanks Jeff) from previous fix. This is extra 2008-10-10 14:35:52 +00:00
mpi LANL noticed that calling MPI_ABORT invokes opal_output(0, ...) 2008-10-14 19:23:03 +00:00
op - double declaration of extern "C" make MS compiler complain. Change them to *_C_DECLS. 2008-08-27 15:49:40 +00:00
peruse - Move the OMPI_DECLSPEC from .c to .h 2008-09-11 12:26:33 +00:00
proc Fix CID 839: minor memory leak on error 2008-08-11 20:46:27 +00:00
request - As shown in ticket #1349, the status is not copied 2008-09-02 15:36:10 +00:00
runtime Sometimes we don't have a valid error code, so don't segv if 2008-10-01 21:42:08 +00:00
tools Very tiny modification of the output when displaying mca param values to clarify that ones found in the environment could have also been set on the cmd line - we don't have a way to distinguish them internally. 2008-09-25 13:08:17 +00:00
win Replace the ompi_pointer_array with opal_pointer_array. The next step 2007-12-21 06:02:00 +00:00
Makefile.am Some more work on the man pages: 2008-08-07 19:20:40 +00:00