1
1
Граф коммитов

365 Коммитов

Автор SHA1 Сообщение Дата
Jeff Squyres
16d8e9216b Ran across this comment about i18n support, so I figured I'd update
it.  :-)

This commit was SVN r24631.
2011-04-22 12:14:20 +00:00
George Bosilca
eb8383802e ret might have been used uninitialized. Not anymore.
This commit was SVN r24452.
2011-02-24 03:02:48 +00:00
Shiqing Fan
baad4e1844 fix a non if-controlled brace.
This commit was SVN r24428.
2011-02-22 11:45:43 +00:00
Ralph Castain
e22262602e Extend the opal output code to support systems that cannot allow stdout/err to be output to console or files. This occurs in some embedded environments where file systems are in flash and consoles are redirected to NULL.
Add three new envars (not MCA params!) that control this behavior (see output.h for explanation).

This commit was SVN r24422.
2011-02-21 21:42:59 +00:00
Ralph Castain
bf1cff3711 Plug a couple of additional memory leaks - try to highlight a little better that strings returned from reg_string_name must be freed by caller
This commit was SVN r24383.
2011-02-14 20:58:22 +00:00
Ralph Castain
b5de068533 Clean up an error in r24371 - can't use a const parameter as target in asprintf as it changes the value of the address.
Add some new proc/job states

Rename a constant to reflect coming change - remove the arbitrary difference between restarting a proc locally and relocating it to another node in terms of the number of restarts allowed.

Add pretty-print of signals for "proc aborted due to signal" reports.

This commit was SVN r24378.

The following SVN revision numbers were found above:
  r24371 --> open-mpi/ompi@93d28a5792
2011-02-14 19:29:09 +00:00
Abhishek Kulkarni
93d28a5792 Change opal_err2str_fn_t to return the error string as an argument.
This means that the converters (opal_err2str, orte_err2str) can now
return NULL as a "silent error". The return value of opal_err2str_fn_t
is the status of the operation (OPAL_SUCCESS or OPAL_ERROR).

This fixes the "Unknown error" message issues on the trunk.

This commit was SVN r24371.
2011-02-13 16:09:17 +00:00
Nysal Jan
92e06b0a1f Missed this change suggested by Terry
This commit was SVN r24364.
2011-02-08 04:06:52 +00:00
Nysal Jan
a31025bb48 Fix pty setup code on AIX
This commit was SVN r24363.
2011-02-08 02:54:47 +00:00
Abhishek Kulkarni
d711c5a4b1 SOS fix for the Studio compilers (Thanks to Terry for spotting this).
This commit was SVN r24355.
2011-02-03 22:36:28 +00:00
Abhishek Kulkarni
3243b16bb3 Decode SOS error code before checking it with the native error code.
This commit was SVN r24281.
2011-01-20 23:21:38 +00:00
Ralph Castain
ac1853b5d8 Took me a couple of days, but finally tracked this one down. Some compilers/glibc's don't like composite test statements in a return and just randomly pick one of the two options.
So....don't do that!!!

This commit was SVN r24212.
2011-01-10 16:29:42 +00:00
Jeff Squyres
a525e70f46 Convert "opal_show_help" to be a global variable pointer.
It is statically initialized to the real back-end OPAL show_help
function.  During orte_show_help_init(), the variable is re-assigned
with the value of the back-end ORTE show_help function (the one that
does error message aggregation).  

Therefore, anything that calls opal_show_help() after a certain point
in orte_init() will have their show_help messages be aggregated.
w00t!  Even code down in OPAL -- that has no knowledge of ORTE -- will
have their messages aggregated.  '''Double w00t!'''

During orte_show_help_finalize(), we restore the original pointer
value so that it something calls opal_show_help() after
orte_finalize(), it'll still work properly (but it won't be
aggregated).  

This commit was SVN r24185.
2010-12-16 23:00:25 +00:00
Terry Dontje
b3f2ac8d46 removed direct include of stdbool.h from event.h that was causing studio C++ issues. Also removed include of stdbool.h in a couple other places since it was already being pulled in via opal_config_bottom.h.
This commit was SVN r23963.
2010-10-27 20:47:42 +00:00
Ralph Castain
bab990d812 Revert r23928 as being the incorrect fix. The correct fix is not to include ipv6 interfaces when ipv6 support was not requested.
This commit was SVN r23930.

The following SVN revision numbers were found above:
  r23928 --> open-mpi/ompi@7394f6d167
2010-10-25 14:31:18 +00:00
Ralph Castain
7394f6d167 Silence warnings about IPV6 sa_family not known when ipv6 support is not enabled in configure
This commit was SVN r23928.
2010-10-25 13:56:23 +00:00
Jeff Squyres
73bcc4a36b Fix mistake that came in via the ompi-agen tree in r23764. The mistake wasn't part of the core autogen upgrade; it was an additional 'bonus' cleanup. Oops. The mistake will always create a set of directories under installdir, even if you do not --with-devel-headers. The set of directories will be empty, but still -- they should not be there at all. This commit fixes that -- the directories are not created at all if you do not --with-devel-headers
This commit was SVN r23801.

The following SVN revision numbers were found above:
  r23764 --> open-mpi/ompi@40a2bfa238
2010-09-24 22:53:28 +00:00
Ralph Castain
3631e4e936 Revert remaining svn kruft from r23764
This commit was SVN r23786.

The following SVN revision numbers were found above:
  r23764 --> open-mpi/ompi@40a2bfa238
2010-09-22 01:11:40 +00:00
Ralph Castain
40a2bfa238 WARNING: Work on the temp branch being merged here encountered problems with bugs in subversion. Considerable effort has gone into validating the branch. However, not all conditions can be checked, so users are cautioned that it may be advisable to not update from the trunk for a few days to allow MTT to identify platform-specific issues.
This merges the branch containing the revamped build system based around converting autogen from a bash script to a Perl program. Jeff has provided emails explaining the features contained in the change.

Please note that configure requirements on components HAVE CHANGED. For example. a configure.params file is no longer required in each component directory. See Jeff's emails for an explanation.

This commit was SVN r23764.
2010-09-17 23:04:06 +00:00
Ralph Castain
e96b5f486f Reorganize the opal interface code in opal/util/if.c per prior emails and telecon discussions. Move the interface discovery code into a framework so that configuration logic can separate it out (instead of the prior #if-#else confusion).
All interface APIs for accessing the info remain unchanged in opal/util/if.c.

This has been tested on Mac, Linux, and NetBSD. Nobody else seemed interested in testing it, so there may be some future problems revealed as people try it on other OSs.

This commit was SVN r23743.
2010-09-13 01:58:51 +00:00
Rainer Keller
5eb571c458 - As suggested in CMR #2558, attribute-macros should be
be tested on function pointers and assigned accordingly,
   instead of using the pre-processor in the header files.

   A functional change is (re-) specifying __opal_attribute_noreturn__
   on orte_errmgr_base_abort(): All modules in the errmgr framework
   either use this function, or define their own abort function,
   which sets __opal_attribute_noreturn__.
   This attributes was taken out with the errmgr overhaul in r22872.

This commit was SVN r23689.

The following SVN revision numbers were found above:
  r22872 --> open-mpi/ompi@e4f2d03d28
2010-08-31 10:28:51 +00:00
Brad Benton
09c4f4d95c Added copyright notices for the files modified in r23669.
This commit was SVN r23687.

The following SVN revision numbers were found above:
  r23669 --> open-mpi/ompi@271cfa8c9a
2010-08-30 17:46:47 +00:00
Nysal Jan
271cfa8c9a Fix the the opal_path_nfs test for GPFS. Reported by Paul H. Hargrove
This commit was SVN r23669.
2010-08-26 10:10:16 +00:00
Jeff Squyres
a5ce58f098 Define that we return OPAL_ERR_TIMEOUT if the other end of the socket
closes in an opal_fd_read().

This commit was SVN r23650.
2010-08-24 19:07:04 +00:00
Ralph Castain
51833bfe6c Not -everyone- wants to ignore loopback devices. Give us a choice.
This commit was SVN r23637.
2010-08-24 02:37:05 +00:00
Rainer Keller
14aad075eb - On Jaguar, we don't have pretty printed stackframe, aka no opal_stackframe_output*
This commit was SVN r23602.
2010-08-12 14:44:56 +00:00
Rolf vandeVaart
3d9b05ba2b Fix bug introduced by r23463. We now handle positive
error codes correctly again.  Also fix a typo.
Reviewed by Jeff Squyres. 

This commit was SVN r23531.

The following SVN revision numbers were found above:
  r23463 --> open-mpi/ompi@2af3e6e5ae
2010-07-28 19:19:27 +00:00
Jeff Squyres
245dc1a86d Add a cast to avoid a compiler warnings on BSD.
This commit was SVN r23502.
2010-07-27 14:14:37 +00:00
Jeff Squyres
0ce1a82cde This commit looks much bigger than it is. There are only 2
substantive changes in this commit; the rest are minor style changes:

 1. Change an OBJ_NEW(opal_list_item_t) to OBJ_NEW(opal_if_t).  This
    was causing memory corruption in the BSD code paths.
 1. Move some local variables from the top of opal_if_init() to inside
    the non-BSD code paths so that we avoid bunches of warnings about
    unused variables when compiling on BSD.  In doing so, I indented
    the whole non-BSD section one level deeper, making the commit look
    huge. 

I also added a few {} around 1-line blocks, added some spaces, broke a
few lines, re-formatted a few comments, ...etc.  Trivial stuff.

This commit was SVN r23501.
2010-07-27 13:46:55 +00:00
Shiqing Fan
71d2749b6b Fix a header problem on Windows.
This commit was SVN r23483.
2010-07-23 07:52:34 +00:00
Jeff Squyres
29c1ad4196 Forgot BEGIN/END C_DECLS.
This commit was SVN r23453.
2010-07-21 11:05:08 +00:00
Jeff Squyres
b3952e4f07 Use const for the opal_fd_write() function, just to be nice.
This commit was SVN r23452.
2010-07-21 11:01:16 +00:00
Jeff Squyres
ab5fc1b570 Add trivial functions to loop over read()'ing and write()'ing with a
file descriptor (i.e., read and write complete messages, transparently
handling partial reads/writes, EAGAIN, and EINTR).

This code effectively already exists in a few places in the code base;
this is mainly a consolidation.

This commit was SVN r23450.
2010-07-20 19:53:49 +00:00
Ralph Castain
f325ac030a Add a function to prepend a string to the beginning of an argv array - useful when building app_contexts from user input
This commit was SVN r23303.
2010-06-24 15:52:36 +00:00
Shiqing Fan
43bd92272a Remove an unnecessary inline definition, in order to solve the conflict of function exporting on Windows.
This commit was SVN r23230.
2010-06-01 15:44:46 +00:00
Shiqing Fan
857f1669e2 Solve a few compilation problems on Windows.
This commit was SVN r23193.
2010-05-21 14:30:15 +00:00
Abhishek Kulkarni
0b3e5f5d79 Silence a opal_sos compiler warning.
This commit was SVN r23163.
2010-05-17 23:14:44 +00:00
Abhishek Kulkarni
afbe3e99c6 * Wrap all the direct error-code checks of the form (OMPI_ERR_* == ret) with
(OMPI_ERR_* = OPAL_SOS_GET_ERR_CODE(ret)), since the return value could be a
 SOS-encoded error. The OPAL_SOS_GET_ERR_CODE() takes in a SOS error and returns
 back the native error code.

* Since OPAL_SUCCESS is preserved by SOS, also change all calls of the form
  (OPAL_ERROR == ret) to (OPAL_SUCCESS != ret). We thus avoid having to
  decode 'ret' to get the native error code.

This commit was SVN r23162.
2010-05-17 23:08:56 +00:00
Abhishek Kulkarni
b0e963299a Adding a new function to return the stack trace (not including the call to the function itself)
as a string (which must be freed by the caller).

This commit was SVN r23160.
2010-05-17 22:57:42 +00:00
Abhishek Kulkarni
5e05546194 Adding SOS headers and package data to the Makefile.
This commit was SVN r23159.
2010-05-17 22:53:33 +00:00
Abhishek Kulkarni
4e33e6aeaa Merge OPAL SOS into the trunk.
The OPAL SOS framework tries to meet the following objectives:

 * reduce the cascading error messages and the amount of code needed to print an error message.
 * build and aggregate stacks of encountered errors and associate related individual errors with each other.
 * allow registration of custom callbacks to intercept error events.

For more information, refer to
https://svn.open-mpi.org/trac/ompi/wiki/ErrorMessages

This commit was SVN r23158.
2010-05-17 22:51:52 +00:00
Jeff Squyres
8a85c4617f Fixes trac:2366: dragonboy noticed that the PGI compiler is picky about
#if directives -- had to change a pair of #if conditionals in
opal/util/stacktrace.c to make the PGI compiler accept it.

This commit was SVN r22923.

The following Trac tickets were found above:
  Ticket 2366 --> https://svn.open-mpi.org/trac/ompi/ticket/2366
2010-04-01 17:04:06 +00:00
Jeff Squyres
c26dae01ce Update the if.c code to properly use the OBJ_* system.
This commit was SVN r22869.
2010-03-23 20:37:06 +00:00
Rainer Keller
814fb9399f - Further patches for support on NetBSD (and DragonFly) by
Aleksej Saushev.
   Dont use bash or bashism in shell scripts
   We should use Posix' setpgid(0,0), which is equivalent to setpgrp().

This commit was SVN r22829.
2010-03-15 05:33:42 +00:00
Josh Hursey
e9b5162d79 Fix the configure logic for --with-ft so that it properly takes a comma separated list.
Many of the OPAL_ENABLE_FT should be OPAL_ENABLE_FT_CR, so fix those.

The OPAL Layer INC should call opal_output on restart so that it can refresh the string it prints to reflect the current pid/hostname which may have changed.

This commit was SVN r22824.
2010-03-12 23:57:50 +00:00
Ralph Castain
8c7f3a0c44 Silence warnings by correctly identifying when we are on a Mac
This commit was SVN r22724.
2010-02-27 08:15:49 +00:00
Iain Bason
7445b23e0d Fixed a minor typo.
This commit was SVN r22706.
2010-02-24 19:05:19 +00:00
Terry Dontje
cfe37fb5a1 Fixed issue with detecting root dir and used appropriate defines for solaris detection
This commit was SVN r22686.
2010-02-23 15:58:49 +00:00
Rainer Keller
a46cecf4f2 - Use strrchr instead of loop for '/' as Nysal suggests.
This commit was SVN r22649.
2010-02-17 23:40:08 +00:00
Jeff Squyres
17f0885f12 Add proper BSD interface detection code. Fixes a long-standing
discussion on the users list (see
http://www.open-mpi.org/community/lists/users/2009/12/11526.php). 

Many thanks to Kevin Buckley who did most of the coding work, and to
Aleksej Saushev for his extreme patience in waiting for me to review
and commit this stuff.

This commit was SVN r22640.
2010-02-17 19:43:57 +00:00