1
1
Граф коммитов

4654 Коммитов

Автор SHA1 Сообщение Дата
Jeff Squyres
97fa83d24f Fix a compiler warning: string::size_type is unsigned, so checking for
>=0 is meaniningless.

This commit was SVN r21313.
2009-05-28 15:44:11 +00:00
Jeff Squyres
f960f2d944 Fix compiler warning
This commit was SVN r21312.
2009-05-28 13:34:48 +00:00
Jeff Squyres
1834fc4ac6 Nysal noticed some repeated header files; removed.
This commit was SVN r21310.
2009-05-28 12:05:42 +00:00
George Bosilca
2f9765926e This is the real commit, the previous one was just a test ... to make
sure Jeff is reading all commits ;)

This commit was SVN r21308.
2009-05-28 00:49:40 +00:00
George Bosilca
63118c9beb Do not allow redefinition of MPI_MAX_DATAREP_STRING.
This commit was SVN r21307.
2009-05-28 00:37:19 +00:00
George Bosilca
be320ca959 Don't add the offset to all segments, only the first one should be affected. Thanks
to Roberto Ammendola for this bug report and patch.

This commit was SVN r21300.
2009-05-27 16:12:18 +00:00
Edgar Gabriel
d93def71ea second part of the 'running out of cids problem', this time focusing on what
happens when hierarch is used. . Two major items:
 - modify the comm_activate step to take an additional argument, indicating
 whether the new communicatio has to go through the collective selection
 step. This is not required sometimes (e.g. when a process calls
 MPI_COMM_SPLIT with color=MPI_UNDEFINED), and contributed significantly to
 the exhaustion of cids.
 - when freeing a communicator, check whether we can reuse the block of cids
 assigned to that comm. This only works if the current front of the cid
 assignment (cid_block_start) is right ater the block of cids assigned to this
 comm.

Fixes trac:1904
Fixes trac:1926

This commit was SVN r21296.

The following Trac tickets were found above:
  Ticket 1904 --> https://svn.open-mpi.org/trac/ompi/ticket/1904
  Ticket 1926 --> https://svn.open-mpi.org/trac/ompi/ticket/1926
2009-05-27 15:21:07 +00:00
Shiqing Fan
b3c077e112 Microsoft doesn't provide inet_pton and inet_ntop APIs on Windows XP, but only on Windows Vista and 2008. So add a stand alone version of inet_pton and inet_ntop functions from ISC.
This commit was SVN r21295.
2009-05-27 14:32:30 +00:00
Josh Hursey
1c58367f8b Fix for makedistcheck. Make sure that distclean removes the mpi-ext.h file that is automaticly generated at configure time.
This commit was SVN r21293.
2009-05-27 14:05:04 +00:00
Rainer Keller
51e2b5dcef - Make the maximum length user strings configurable... Namely
MPI_MAX_PROCESSOR_NAME
      MPI_MAX_ERROR_STRING
      MPI_MAX_OBJECT_NAME
      MPI_MAX_INFO_KEY
      MPI_MAX_INFO_VAL
      MPI_MAX_PORT_NAME
      MPI_MAX_DATAREP_STRING

   Defaults stay as theyr currently are -- and now give an explanation on the
   min/max values being used in a central place...
   m4-macro _OPAL_WITH_OPTION_MIN_MAX_VALUE may be benefical in other parts
   of the configure system.

 - We need some of these in the lower level OPAL for an upcoming commit!
   All other levels base their values on them.

This commit was SVN r21292.
2009-05-27 12:54:40 +00:00
Rainer Keller
88390b0d7c - Just remove white-space at end of lines
This commit was SVN r21291.
2009-05-27 12:46:04 +00:00
Shiqing Fan
7a495e936c Add the generated mpi_portable_platform.h into the install file list.
This commit was SVN r21290.
2009-05-27 12:16:36 +00:00
Rainer Keller
4b9aecb188 - Fix a few buglet's, "suppported", ": ", and
stay below 63 characters  in length...

This commit was SVN r21286.
2009-05-27 02:04:54 +00:00
Rainer Keller
653656f012 - Hey, as of r19461, we're officially endorse MPI-2.1
... even in Fortran ;-)

This commit was SVN r21284.

The following SVN revision numbers were found above:
  r19461 --> open-mpi/ompi@008fa8c5cc
2009-05-27 00:32:23 +00:00
Josh Hursey
3e847c19f0 Per RFC: MPI Interface Extensions Infrastructure
Add infrastructure for MPI Interface Extensions. This allows a developer to create new MPI interfaces that are non-standard.

The following email thread describes the functionality proposed in the RFC:
  http://www.open-mpi.org/community/lists/devel/2009/05/5997.php

The following wiki page describes how to use and enable the extensions:
  https://svn.open-mpi.org/trac/ompi/wiki/MPIExtensions

This commit was SVN r21272.
2009-05-26 20:49:35 +00:00
Shiqing Fan
19ecbfa324 A quick and simple fix for Windows supporting deprecated functionality warnings, let MTT run again first. MS compiler attributes check has to be accomplished in order to fully enable this feature on Windows.
This commit was SVN r21267.
2009-05-23 22:12:54 +00:00
Rainer Keller
fbb2834977 - Missed string.h to get rid of warnings...
This commit was SVN r21265.
2009-05-22 23:47:49 +00:00
Rainer Keller
916eb1fb1e - As proposed in RFC and telcon, warn the user about deprecated
functionality (per MPI-2.1). This warning can be toggled using
   --enable-mpi-interface-warning (default OFF), but can be
   selectively turned on passing
       mpicc -DOMPI_WANT_MPI_INTERFACE_WARNING

   Using icc, gcc < 4.5, warnings (such as in mpi2basic_tests) show:
     type_vector.c:83: warning: ‘MPI_Type_hvector’ is deprecated
     (declared at /home/../usr/include/mpi.h:1379)

   Using gcc-4.5 (gcc-svn) these show up as:
     type_vector.c:83: warning: ‘MPI_Type_hvector’ is deprecated
     (declared at /home/../usr/include/mpi.h:1379):
     MPI_Type_hvector is superseded by MPI_Type_create_hvector in MPI-2.0


   Jeff and I propose to turn such warnings on with Open MPI-1.7 by default.


 - Detection of user-level compiler is handled using the preprocessor
   checks of GASnet's other/portable_platform.h (thanks to Paul Hargrove
   and Dan Bonachea) adapted into ompi/include/mpi_portable_platform.h
   (see comments).

   The OMPI-build time detection is output (Familyname and Version)
   with ompi_info.

   This functionality (actually any upcoming __attribute__) are turned
   off, if a different compiler (and version) is being detected.


 - Note, that any warnings regarding (user-compiler!=build-compiler)
   as discussed in the RFC are _not_ included for now.


 - Tested on Linux with --enable-mpi-interface-warning on
   Linux, gcc-4.5 (deprecated w/ specific msg)
   Linux, gcc-4.3 (deprecated w/o specific msg)
   Linux, pathscale 3.1 (deprecated w/o specific msg)
   Linux, icc-11.0 (deprecated w/o specific msg)

   Linux, PGI-8.0.6 accepts __deprecated__ but does not issue a warning,
   further investigation needed...

This commit was SVN r21262.
2009-05-22 04:39:43 +00:00
Rainer Keller
225a1d6d8e - For memcpy and memset need string.h
This commit was SVN r21259.
2009-05-21 22:36:06 +00:00
George Bosilca
26342508de It is supposed not to be set until we detect our local rank ...
This commit was SVN r21256.
2009-05-20 17:41:13 +00:00
George Bosilca
7bd97ac17b Try to deal with the ticket #1831. I think we might reach a case where the
shm_fifos values are only partially updated, and this leads to wrong values
for the offset. Moving the write barrier at the right place, plus forcing
some read barriers might help.

In addition I get rid of the sm_offset array which is completely useless.

This commit was SVN r21253.
2009-05-19 22:50:44 +00:00
Abhishek Kulkarni
b48f13cda4 Minor fix in the man page for MPI_Comm_remote_size
This commit was SVN r21252.
2009-05-19 15:23:44 +00:00
Jeff Squyres
8dc83b0865 Use the newer ORTE_NAME_PRINT instead of ORTE_NAME_ARGS
This commit was SVN r21250.
2009-05-18 14:38:13 +00:00
Jeff Squyres
17761f60b9 Clean up a few compiler warnings
This commit was SVN r21243.
2009-05-14 15:40:38 +00:00
Jeff Squyres
efd229b56b Clean up bunches of compiler warnings
This commit was SVN r21242.
2009-05-14 15:39:53 +00:00
Rainer Keller
b2f8095ba7 - Update to fix in r21234: as discussed on devel@,
for printing size_t use "%lu" and cast to (unsigned long).

This commit was SVN r21238.

The following SVN revision numbers were found above:
  r21234 --> open-mpi/ompi@22b6177fb9
2009-05-14 14:10:22 +00:00
Rainer Keller
d5cb1b4f97 - Shown by __opal_attribute_format__, probably macro
was converted from opal_output_verbose

This commit was SVN r21237.
2009-05-14 13:57:37 +00:00
Pavel Shamis
14eb11c18a Removing unused and duplicated XRC code.
I just found that we have 2 place where we call for XRC domain
creation. First one in init_one_device() and second one prepare_device_for_use().
They have absolutely identical code, but the call in init_one_device() is useless
because on this stage we don't know about QP configuration and we don't know if we need 
XRC at all. So I removing the duplicated code from init_one_device().

This commit was SVN r21235.
2009-05-14 13:15:00 +00:00
Rainer Keller
22b6177fb9 - Use the "z" length modifier for size_t arguments for printf.
This commit was SVN r21234.
2009-05-14 00:52:20 +00:00
Rainer Keller
73fd329cbd - Add the proper __opal_attribute_format__(__printf__...) to
declarations.

This commit was SVN r21226.
2009-05-14 00:10:59 +00:00
Iain Bason
a282cf062c Roll back Jeff's roll back (r21028) of Iain's changes (r20926, r20941, r20950).
It turns out that the "Intel" interpretation of the MPI spec violates
the Fortran standard (section 14.6.1.1 of the Fortran 95 standard).

This commit was SVN r21225.

The following SVN revision numbers were found above:
  r20926 --> open-mpi/ompi@0a24eadaad
  r20941 --> open-mpi/ompi@045b0e8871
  r20950 --> open-mpi/ompi@73af921c22
  r21028 --> open-mpi/ompi@25249c9843
2009-05-13 18:32:13 +00:00
Jeff Squyres
424d9ed0c8 Fix "reorder" parameter to be logical, per MPI spec.
This commit was SVN r21215.
2009-05-12 14:08:14 +00:00
Ralph Castain
d396f0a6fc Per the discussion on the devel list, move the binding of processes to processors from MPI_Init to process start. This involves:
1. replacing mpi_paffinity_alone with opal_paffinity_alone - for back-compatibility, I have aliased mpi_paffinity_alone to the new param name. This caus
es a mild abstraction break in the opal/mca/paffinity framework - per the devel discussion...live with it. :-) I also moved the ompi_xxx global variable
 that tracked maffinity setup so it could be properly closed in MPI_Finalize to the opal/mca/maffinity framework to avoid an abstraction break.

2. Added code to the odls/default module to perform paffinity binding and maffinity init between process fork and exec. This has been tested on IU's odi
n cluster and works for both MPI and non-MPI apps.

3. Revise MPI_Init to detect if affinity has already been set, and to attempt to set it if not already done. I have *not* tested this as I haven't yet f
igured out a way to do so - I couldn't get slurm to perform cpu bindings, even though it supposedly does do so.

This has only been lightly tested and would definitely benefit from a wider range of evaluation...

This commit was SVN r21209.
2009-05-12 02:18:35 +00:00
Jeff Squyres
f7f5603d5c * No need for warning aggregation here; orte_show_help() does that
for us already.
 * Slightly clarify the error message strings; now they match the new
   error strings for btl_openib_ipaddr_in|exclude

This commit was SVN r21197.
2009-05-09 12:29:06 +00:00
Jeff Squyres
cd6c6e6206 Add some error checking into the btl_openib_ipaddr_in|exclude
calculations, and fix a few small memory leaks in that same logic.

This commit was SVN r21196.
2009-05-09 12:28:09 +00:00
Edgar Gabriel
0bc8164a11 fix the group_compare operation which failed to recognize unequal groups in
case the first process of the group was not represented at all in the second
group. Also added some cleanup of the code w.r.t. booleans vs. ints.
 
Thanks for Geoffrey Irving for reporting the bug and providing the initial
solution. 

This commit was SVN r21192.
2009-05-08 13:51:28 +00:00
Jeff Squyres
c166678cf2 Gah -- forgot to test the case where btl_tcp_if_include wasn't
specified.  :-(

This commit was SVN r21191.
2009-05-07 21:50:02 +00:00
Jeff Squyres
97c9610b7f Note to self: test error messages before committing.
This commit was SVN r21190.
2009-05-07 20:31:26 +00:00
Jeff Squyres
4779520787 Add the ability to btl_tcp_if_include and btl_tcp_if_exclude based on
subnet specifications (in addition to interface names).  These
parameters now take a comma-delimited list of interfaces names and/or
a.b.c.d/x specifications (only IPv4 currently supported for subnet
specifications).  For example:

  mpirun --mca btl_tcp_if_include 10.10.30.0/8,eth0

This commit was SVN r21189.
2009-05-07 18:53:33 +00:00
Shiqing Fan
537b8cd8b1 Get rid of improper use of SET_SOURCE_FILES_PROPERTIES. When using the latest CMake (2.6 patch 4), we get many errors, which didn't show in previous version.
This commit was SVN r21188.
2009-05-07 17:41:05 +00:00
Rainer Keller
c868ec21b0 - Fix Coverity CID 30;
If there is no errhandler, can't reference it...
   Return early.

This commit was SVN r21187.
2009-05-07 17:05:15 +00:00
Rainer Keller
2941cb1494 - Fix Coverity CID 525 and 526 --- and some more;
- due to the <= with we could overrun the array
   - we didn't correctly test at _all_, since we never marked the
     ranks already excluded / included...
   - when returning in error, we should free (elements_int_list)...

This commit was SVN r21186.
2009-05-07 16:45:18 +00:00
Jeff Squyres
af8f0438ef Make a better error message when the TCP BTL fails to connect
This commit was SVN r21184.
2009-05-07 14:09:35 +00:00
Jeff Squyres
04f3b23f1b Fix one tiny name change that was missed.
This commit was SVN r21183.
2009-05-06 21:41:59 +00:00
Jeff Squyres
93ed8cf78f Remove this very, very outdated file.
This commit was SVN r21182.
2009-05-06 21:03:34 +00:00
Greg Koenig
60485ff95f This is a very large change to rename several #define values from
OMPI_* to OPAL_*.  This allows opal layer to be used more independent
from the whole of ompi.

NOTE: 9 "svn mv" operations immediately follow this commit.

This commit was SVN r21180.
2009-05-06 20:11:28 +00:00
Matthias Jurenz
fb3bbb8021 Updated version number to 5.4.9
This commit was SVN r21178.
2009-05-06 10:54:43 +00:00
Matthias Jurenz
3f83c94328 Fixed faulty searching for matching filter directive
This commit was SVN r21177.
2009-05-06 10:54:27 +00:00
Rainer Keller
4ff860db1f - Fix Coverity CID 477:
In _correct_ programs only when (group->grp_proc_count - n) > 0,
   we may fill ranks_included (callers of ompi_group_excl make sure)...
   Therefore move the ranks_included loop into the true
   block of the if (which is changed from "!= 0" to ">0").

   Otherwise, the initilization of k=0 and ranks_included=NULL is good
   for the ompi_group_incl (and submethods ompi_group_*).

   Tested on Linux w/ mpi_test_suite and MPIch testsuite:
     4 grouptest_coll
     4 groupcreate
     4 grouptest

This commit was SVN r21172.
2009-05-05 22:30:08 +00:00
Shiqing Fan
cd565923d3 Completely remove ltdl support for Windows build.
This commit was SVN r21170.
2009-05-05 18:59:13 +00:00
Jeff Squyres
4e4d3b2ec1 Patch from Number Cruncher/Simon to shut up gcc 4.1's complaints about
type punning.  A description of the issue is in the comment included
in this commit.

This commit was SVN r21166.
2009-05-05 16:41:26 +00:00
Ralph Castain
f6b95c4ee0 Remove unused var
This commit was SVN r21164.
2009-05-05 15:12:10 +00:00
George Bosilca
039fed1973 Fix Coverity CID #264.
This commit was SVN r21162.
2009-05-05 13:54:55 +00:00
Shiqing Fan
387ee0ad29 fix a type cast
This commit was SVN r21161.
2009-05-05 13:51:02 +00:00
George Bosilca
db096d7d3a Fix Coverity CID #304.
This commit was SVN r21159.
2009-05-05 13:47:47 +00:00
George Bosilca
b4334cff2e Cleanup.
This commit was SVN r21158.
2009-05-05 13:42:28 +00:00
George Bosilca
271eb11f28 Remove an unused statically defined function.
This commit was SVN r21157.
2009-05-05 13:23:49 +00:00
Rainer Keller
4a7e078dae - Compiling with --enable-picky plus -Wextra, we get
several errors on unused parameters -- as this header
   is included in several files, this shows up too often.

This commit was SVN r21156.
2009-05-05 13:10:54 +00:00
Rainer Keller
9bcc47b05c - Similar to the previous commit, pass ONE character less into
ompi_info_get, to not stand the chance to overwrite any of the
   buffers (on the stack).

This commit was SVN r21155.
2009-05-05 13:06:28 +00:00
Rainer Keller
250c3d0ddd - Fix Coverity CID 527
malloc buffer for ompi_info_get one character larger for the NUL-termination
   See comment in ompi/mpi/c/info_get.c or MPI-2.1 p289

This commit was SVN r21154.
2009-05-05 13:05:20 +00:00
Rainer Keller
9736af1191 - Fix Coverity CID 182:
Well, well, just do not "call" ompi_comm_rank twice but rather
   reuse variable...

 - Fix Coverity CID 1262:
   Using uninitialized value "(statuses[err_index]).MPI_ERROR"
   Sure, these statuses are only initialized after ompi_request_wait_all,
   so introduce a short-circuit label to jump to...

This commit was SVN r21153.
2009-05-05 12:28:51 +00:00
Ralph Castain
4be24521aa Modify the orte_process_info structure to handle a broader range of process types by replacing the individual booleans with a 32-bit bitmap. Use a set of #define's to define the individual bits, and a set of matching macros to test for them. Update the orte code base to use the macros instead of the booleans.
Minor mod to the ompi layer to use the new #define's - just one-line name replacements.

This commit was SVN r21144.
2009-05-04 11:07:40 +00:00
Edgar Gabriel
338b136c28 adding a feature which tries to reuse a block of cids assigned to a
communicator. This works, if all processes agree that all communicators
utilizing the cids in the block have been freed. If they don't, they assign a
new block of cid's.

This fixes the application scenario reported in the week, in fact the test
succefully creates 100,000 communicators without exceeding a cid of 20. The
fix also keeps the main property of the algorithm (namely using a single
Allreduce operation to get a new block) and did not modify the communicator
structure.

This commit was SVN r21142.
2009-05-02 18:03:57 +00:00
Brian Barrett
77cf736f48 Make max_contextid field match same type as cid in communicator.
Refs trac:1904

This commit was SVN r21141.

The following Trac tickets were found above:
  Ticket 1904 --> https://svn.open-mpi.org/trac/ompi/ticket/1904
2009-05-01 21:11:59 +00:00
Ralph Castain
f6da7d86a2 Propagate Brian's change so we abort if we run out of CIDs to the csum module
This commit was SVN r21137.
2009-05-01 15:09:44 +00:00
Brian Barrett
7f898d4e2b * Make rdma the default. Somehow, the code didn't match what was supposed
to happen
* Properly error out (rather than cause buffer overflow) in case where
  the datatype packed description is larger than our control fragments.
  This still isn't standards conforming, but at least we know what
  happened.
* Expose win_set_name to external libraries (like the osc modules)
* Set default window name to the CID of the communcator it's using
  for communication

Refs trac:1905

This commit was SVN r21134.

The following Trac tickets were found above:
  Ticket 1905 --> https://svn.open-mpi.org/trac/ompi/ticket/1905
2009-04-30 22:36:09 +00:00
Brian Barrett
736debcffc Check during communicator creation that we didn't get assigned a CID we can't handle, so that the code aborts instead of hange.
Refs trac:1904

This commit was SVN r21133.

The following Trac tickets were found above:
  Ticket 1904 --> https://svn.open-mpi.org/trac/ompi/ticket/1904
2009-04-30 19:23:57 +00:00
Josh Hursey
13a3453e35 more copyright fixes - sorry
This commit was SVN r21129.
2009-04-30 16:41:50 +00:00
Josh Hursey
1f42065950 Make sure the CRCPW wrapper does not try to reference a NULL value in MPI_Finalize(), due to the ordering of pml_finalize and comm_del.
Some of the PML interfaces are noops in BKMRK. Allow the CRCPW to detect and skip the call to these functions.

This commit was SVN r21126.
2009-04-30 16:36:50 +00:00
Jeff Squyres
c01079e1f3 Fix some handling in error cases (avoid uninitialized variables,
etc.).  Yay compiler warnings for noticing these.  :-)

This commit was SVN r21114.
2009-04-29 14:40:12 +00:00
Ralph Castain
e7b5cfa259 Replace missing include file
This commit was SVN r21107.
2009-04-29 13:19:46 +00:00
Rainer Keller
1ef32928fd - get MTL up and running:
Nothing notable, except mtl_base_datatype.h -- Undo change from r21096:
   Yes, we should not include datatype_internal.h, but we did and we have to:
   we derefence desc, and get an incomplete type, otherwise.

This commit was SVN r21103.

The following SVN revision numbers were found above:
  r21096 --> open-mpi/ompi@221fb9dbca
2009-04-29 08:04:16 +00:00
Rainer Keller
be008f2215 - In case of OPAL_ENABLE_FT == 1, we need to
#include "opal/runtime/opal_cr.h"

   Thanks to Caciano Machado for reporting.

This commit was SVN r21101.
2009-04-29 06:57:49 +00:00
Rainer Keller
221fb9dbca ... Delayed due to notifier commits earlier this day ...
- Delete unnecessary header files using
   contrib/check_unnecessary_headers.sh after applying
   patches, that include headers, being "lost" due to
   inclusion in one of the now deleted headers...

   In total 817 files are touched.
   In ompi/mpi/c/ header files are moved up into the actual c-file,
   where necessary (these are the only additional #include),
   otherwise it is only deletions of #include (apart from the above
   additions required due to notifier...)

 - To get different MCAs (OpenIB, TM, ALPS), an earlier version was
   successfully compiled (yesterday) on:
   Linux locally using intel-11, gcc-4.3.2 and gcc-SVN + warnings enabled
   Smoky cluster (x86-64 running Linux) using PGI-8.0.2 + warnings enabled
   Lens cluster (x86-64 running Linux) using Pathscale-3.2 + warnings enabled

This commit was SVN r21096.
2009-04-29 01:32:14 +00:00
Rainer Keller
6c1cce8761 - For the upcoming header cleanup commit,
several header files (previously included by header-files)
   now have to be moved "upward".
   This is mainly system headers such as string.h, stdio.h and for
   networking, but also some orte headers.

This commit was SVN r21095.
2009-04-29 00:49:23 +00:00
Josh Hursey
aae5d3c825 Switch up the conditional statement, add OPAL_LIKELY.
Thanks to Jeff for the suggestion.

This commit was SVN r21082.
2009-04-27 19:08:05 +00:00
Josh Hursey
2e1fbc4c75 Fix a copy problem when using a drained message that has a NULL buffer. This often happens when draining a Barrier message which are sometimes point-to-point messages with count=0 and a NULL buffer.
This fixes a bug that can happen when checkpointing while one process is in such a routine. Previously a warning was thrown.

This commit was SVN r21080.
2009-04-27 18:39:45 +00:00
Jeff Squyres
537579ad5d Add some notifier messages during MPI_INIT and MPI_FINALIZE (which
only show up if a notifier component is selected, of course).  These
can be disabled by setting the MCA parameter mpi_notify_init_finalize
to 0.

These messages are both intended as "hey, does the community like
this?" and as a way to get some real-world testing of the notify
system.  The default is currently to send these messages if a notify
component is selected; we can change the default later if desired.

This commit was SVN r21078.
2009-04-27 14:15:33 +00:00
Shiqing Fan
3d4e0472d6 Add windows support files into the tarball, including .windows, CMakeLists.txt files, and CMake modules. Thanks to Jeff for testing it on Linux.
This commit was SVN r21069.
2009-04-24 16:39:33 +00:00
Matthias Jurenz
9bd95d04e0 Install header files to 'PREFIX/include/vampirtrace' to avoid compile error due to conflicts with newer "stand-alone" VT versions
This commit was SVN r21065.
2009-04-24 11:36:38 +00:00
Jeff Squyres
8704d33f4e Revamp one of the credits system checks and make it smaller, simpler,
and mo'bettah.  Put in lengthy comments explaining what's going on.
We might still want to tweak this some more, but we can no longer get
IMB-EXT to hang with this new code anymore (e.g., even without eager
RDMA -- we discovered after the fact that the code in the v1.3.2
release will hang if eager RDMA is disabled).

Fixes trac:1890.  Really.

This commit was SVN r21061.

The following Trac tickets were found above:
  Ticket 1890 --> https://svn.open-mpi.org/trac/ompi/ticket/1890
2009-04-23 20:04:39 +00:00
Shiqing Fan
0037f55424 Correctly set the compile flags of 'mpicc' for static version.
This commit was SVN r21055.
2009-04-22 13:17:25 +00:00
Ethan Mallove
0f4c18472c Remove unused {{{malloc.h}}} include.
(see http://www.open-mpi.org/community/lists/devel/2009/04/5845.php)

This commit was SVN r21049.
2009-04-21 17:35:58 +00:00
Jeff Squyres
9d94fa2308 Fixes trac:1890: we weren't checking the return status of
_endpoint_post_send(), which could result in an infinite loop (see the
comment in the code).

This is part one of a proper fix; it's suitable for the v1.3 tree and
for an immediate release.  Pasha and I plan to spend a little more
time and clean up this stuff properly, but it does not need to be
included in v1.3.2.

This commit was SVN r21047.

The following Trac tickets were found above:
  Ticket 1890 --> https://svn.open-mpi.org/trac/ompi/ticket/1890
2009-04-21 16:57:17 +00:00
Nysal Jan
5353236a53 Reduce the size of FIN header by 8 bytes. This is done by rearranging the fields to reduce the amount of compiler padding
This commit was SVN r21046.
2009-04-21 14:41:51 +00:00
Jeff Squyres
c4b307d57e Fix an incorrect comment.
This commit was SVN r21045.
2009-04-21 13:38:43 +00:00
Jeff Squyres
6f78420900 Correctly check for the case where we didn't find the mpool that we
were looking for.  This makes the openib btl fail a little more
gracefully (for example) if you specify a bogus value to
btl_openib_mpool.

Thanks to Roberto Ammendola for identifying the exact issue.

This commit was SVN r21044.
2009-04-21 12:40:50 +00:00
Jeff Squyres
25249c9843 Roll back r20926, r20941, r20950: Iain's changes from last week.
This has turned into an MPI spec interpretation issue.  :-(

Open MPI has intrepreted the spec one way for the past several years;
these commits reflect a different interpretation that changes how we
treat the EXTRA_STATE parameter to the Fortran attribute copy and
delete callbacks.  This new way breaks our internal copy of the Intel
Fortran attribute tests.  So after talking with Terry/Sun, we're going
to back out these changes (both here and on the v1.3 branch) until we
get further clarification from the Forum.

This commit was SVN r21028.

The following SVN revision numbers were found above:
  r20926 --> open-mpi/ompi@0a24eadaad
  r20941 --> open-mpi/ompi@045b0e8871
  r20950 --> open-mpi/ompi@73af921c22
2009-04-16 14:29:32 +00:00
Ralph Castain
2b0b9dd227 Sync to change in a tmp branch
This commit was SVN r21015.
2009-04-15 13:09:51 +00:00
Shiqing Fan
e8f5ad04d4 Don't collect files recursively.
This commit was SVN r21013.
2009-04-15 09:47:14 +00:00
Ralph Castain
46d6c6d516 Sync the csum module with the recent ob1 changes
This commit was SVN r21002.
2009-04-14 18:40:54 +00:00
Nysal Jan
221447ef17 Fix checksum mismatch on Big-endian systems when heterogeneous mode is enabled
This commit was SVN r21001.
2009-04-14 17:21:38 +00:00
Ralph Castain
9c39a3edd7 Enable the passing of MCA params to dynamically spawned jobs. This creates a new info_key "ompi_param" that allows a user to specify MCA params for a dynamically spawned job.
We currently apply all of the MCA params in the parent job to the child. This commit allows a user to specify additional params for the child job, and to override any pre-existing params with the new value so they can better control behavior of the child job.

This commit was SVN r20989.
2009-04-14 14:15:49 +00:00
Shiqing Fan
339948928d Only include unistd.h, if we have it.
This commit was SVN r20988.
2009-04-14 13:39:06 +00:00
Nysal Jan
697f1837f4 Move fix for ticket #1875 to csum PML
This commit was SVN r20986.
2009-04-14 10:44:29 +00:00
George Bosilca
05ee4c280e Mismatch between the reported subversion and the one in the mpi.h.
Thanks to Rob Egan for the report.

This commit was SVN r20985.
2009-04-14 05:29:07 +00:00
Jeff Squyres
778c8c86d2 Make mpool fail-to-unregister-freed-memory errors be fatal. Try to
make that routine a bit more safe, too (ensure to not call malloc and
friends if from_alloc==true).

This commit was SVN r20984.
2009-04-14 00:54:20 +00:00
George Bosilca
b5deb228f3 Allow the BTL to release the descriptor. In fact the only thing the PML
needs is to be involved in the RMA completion process, which is insured
by the MCA_BTL_DES_SEND_ALWAYS_CALLBACK flag. Fixes trac:1875.

This commit was SVN r20983.

The following Trac tickets were found above:
  Ticket 1875 --> https://svn.open-mpi.org/trac/ompi/ticket/1875
2009-04-13 23:41:50 +00:00
Jeff Squyres
8de80e9297 mca_mpool_base_mem_cb_array is no longer used anywhere in the code
base.  Remove it.

This commit was SVN r20982.
2009-04-13 23:41:45 +00:00
George Bosilca
64075cd54d Get rid of the bitmap header file.
This commit was SVN r20972.
2009-04-10 16:44:37 +00:00
George Bosilca
527540aeb1 Rename req_bytes_delivered to req_bytes_expected for the receive
requests to really reflect what this field means.

This commit was SVN r20971.
2009-04-10 16:36:20 +00:00
George Bosilca
c148d33eb5 Play nicely with the reference count on the ompi_proc structure.
This commit was SVN r20970.
2009-04-10 16:32:02 +00:00
Nysal Jan
1decf8bf36 Move ob1 FIN/ACK fixes to csum PML
This commit was SVN r20954.
2009-04-08 10:43:35 +00:00
George Bosilca
dfc7cea329 Fix the deadlock issues on the osu_bw. The problem is that the PML is
event driver, and if there are no event generated by the BTLs ... well
nothing happens (i.e there is no progress at the PML level and all
pending fragments remain pending). By forcing the BTL to trigger the
callbacks for all ACK and FIN, we give more opportunities to the PML
to do real progress, but we pay this in terms of performance.

This commit was SVN r20953.
2009-04-07 16:56:37 +00:00
George Bosilca
44ce610b8b Add a comment to highlight the fact that this function reappend the
FIN message to the pending list when the send fails. Therefore, any
upper level function is not required to add it.
Make sure we don't send the FIN twice.

This commit was SVN r20952.
2009-04-07 16:48:58 +00:00
Iain Bason
73af921c22 Update keyval_create functions.
The fix for #1864 in r20926 caused gcc to emit some warnings. Also,
Jeff Squyres pointed out parallel bugs in mpi_type_create_keyval and
mpi_win_create_keyval.

This commit was SVN r20950.

The following SVN revision numbers were found above:
  r20926 --> open-mpi/ompi@0a24eadaad
2009-04-07 13:47:52 +00:00
George Bosilca
ccb79b963f This is the other half of the commit r20946 as I mess them up between
two of my testing machines. The fix require both commits!

This commit was SVN r20947.

The following SVN revision numbers were found above:
  r20946 --> open-mpi/ompi@e2bb4c9b8f
2009-04-06 21:49:52 +00:00
George Bosilca
e2bb4c9b8f Correct the handling of the pckt_pending list. The problem was that
we returned the pck before coping the values out. With this change
it seems to work at least on two architectures (even with the 
mpool size set back to 0).

This commit was SVN r20946.
2009-04-06 21:45:08 +00:00
Eugene Loh
c4adfd1806 Increase mpool_sm_min_size default to 64M so osu_bw will run.
This commit was SVN r20944.
2009-04-06 18:37:00 +00:00
Ralph Castain
547fd635d1 Update the Makefile for ortetools so the trunk can compile
This commit was SVN r20943.
2009-04-06 14:04:00 +00:00
George Bosilca
045b0e8871 Remove two warnings about "cast from pointer to integer of different size".
This commit was SVN r20941.
2009-04-05 21:02:36 +00:00
Nysal Jan
5032f59edf Fix checksum computation in the buffered send code
This commit was SVN r20935.
2009-04-03 07:09:24 +00:00
Nysal Jan
4e001fb10a Fix a compiler warning
This commit was SVN r20931.
2009-04-02 14:48:27 +00:00
Ralph Castain
ba1a98c398 Fix a warning message by pointing to the correct header
This commit was SVN r20930.
2009-04-02 13:54:59 +00:00
Nysal Jan
e561a6c43a Add missing checksum calculation. This fixes a checksum mismatch failure while using TCP BTL
This commit was SVN r20927.
2009-04-01 20:48:35 +00:00
Iain Bason
0a24eadaad Fix Fortran bindings for MPI_KEYVAL_CREATE and MPI_COMM_CREATE_KEYVAL.
The EXTRA_STATE parameter is passed by reference, and thus should be
dereferenced before it is stored.  Similarly, the stored value should
be passed by reference to the copy and delete routines.

This fixes trac:1864.

This commit was SVN r20926.

The following Trac tickets were found above:
  Ticket 1864 --> https://svn.open-mpi.org/trac/ompi/ticket/1864
2009-04-01 19:31:46 +00:00
Jeff Squyres
fc8993ba87 mpool name is the first show_help param, not the last.
This commit was SVN r20925.
2009-04-01 18:42:01 +00:00
Jeff Squyres
0d52271cd6 Per http://www.open-mpi.org/community/lists/announce/2009/03/0029.php
and https://svn.open-mpi.org/trac/ompi/ticket/1853, mallopt() hints do
not always work -- it is possible for memory to be returned to the OS
and therefore OMPI's registration cache becomes invalid.

This commit removes all use of mallopt() and uses a different way to
integrate ptmalloc2 than we have done in the past.  In particular, we
use almost exactly the same technique as MX:

 * Remove all uses of mallopt, to include the opal/memory mallopt
   component.
 * Name-shift all of OMPI's internal ptmalloc2 public symbols (e.g.,
   malloc -> opal_memory_ptmalloc2_malloc).
 * At run-time, use the existing glibc allocator malloc hook function
   pointers to fully hijack the glibc allocator with our own
   name-shifted ptmalloc2.
 * Make the decision whether to hijack the glibc allocator ''at run
   time'' (vs. at link time, as previous ptmalloc2 integration
   attempts have done).  Look at the OMPI_MCA_mpi_leave_pinned
   and OMPI_MCA_mpi_leave_pinned_pipeline environment variables and
   the existence of /sys/class/infiniband to determine if we should
   install the hooks or not.
 * As an added bonus, we can now tell if libopen-pal is linked
   statically or dynamically, and if we're linked statically, we
   assume that munmap intercept support doesn't work.

See the opal/mca/memory/ptmalloc2/README-open-mpi.txt file for all the
gory details about the implementation.

Fixes trac:1853.

This commit was SVN r20921.

The following Trac tickets were found above:
  Ticket 1853 --> https://svn.open-mpi.org/trac/ompi/ticket/1853
2009-04-01 17:52:16 +00:00
George Bosilca
b7c1ae4f76 Nothing important, just an identation.
This commit was SVN r20919.
2009-04-01 15:27:16 +00:00
George Bosilca
8221975490 We don't need the opal_bitmap definitions here.
This commit was SVN r20918.
2009-04-01 15:25:10 +00:00
Terry Dontje
4b43911c6a Remove superfluous spaces in manpages that were causing catman to
generate mangled windex files.  Made ompi-top.1 and ompi-iof.1 build
by default.  Also, added the orte-top synonym to the ompi-top manpage.

This commit was SVN r20915.
2009-04-01 14:40:27 +00:00
Nysal Jan
aff903f39c Don't print this message by default
This commit was SVN r20914.
2009-04-01 14:31:21 +00:00
Matthias Jurenz
e66e5104e7 Added check whether the trace environment already closed before create a new event (avoids potential segfault)
This commit was SVN r20913.
2009-04-01 07:53:30 +00:00
Matthias Jurenz
fa3cf2d2ba Added MPI wrapper function for 'MPI_Init_thread'
This commit was SVN r20912.
2009-04-01 07:52:14 +00:00
George Bosilca
c5b1bdd57c Correctly deal with the error case. The problem is tricky: the MPI standard doesn't allow
MPI_ERR_IN_STATUS to be returned from any functions that return only one completed request
(few exception here: wait_some and wait_all and the test versions). As we use an wait_all
in these send_receive functions we should convert the MPI_ERR_IN_STATUS to the real
error, i.e. the one comming from the MPI_ERROR field in the status corresponding to the
failed request.

This commit was SVN r20907.
2009-03-31 23:44:59 +00:00
George Bosilca
12ce14ec8c A possible patch for the SM problems. I moved the synchronization
after each process create it's FIFOs but before they access the
peer's FIFOs. Second, replace a one way synchronization by a real
barrier, so we know that every process is really where we expect
them to be.

This commit was SVN r20906.
2009-03-31 21:46:27 +00:00
Patrick Geoffray
278d508fa4 Missing send immediate function (NULL) in btl module definition.
Fixes trac:1859.

This commit was SVN r20905.

The following Trac tickets were found above:
  Ticket 1859 --> https://svn.open-mpi.org/trac/ompi/ticket/1859
2009-03-31 18:44:10 +00:00
George Bosilca
2b1804b0f4 Remove useless header files.
This commit was SVN r20897.
2009-03-30 23:09:18 +00:00
Jeff Squyres
b95a3d0eb9 * Remove an extraneous OBJ_CONSTRUCT
* Ensure we don't try to do opal_list_get_next() on an item we just
   deleted
 * set myaddrs = NULL when we're done with it, just for good measure

Once this is ported to OMPI v1.3 branch, it fixes
https://bugs.openfabrics.org/show_bug.cgi?id=1579.

This commit was SVN r20896.
2009-03-30 20:24:31 +00:00
Ralph Castain
cba3708893 Cleanup debugging output, remove an unnecessary re-compute of the checksum
This commit was SVN r20895.
2009-03-30 17:09:32 +00:00
Ralph Castain
d5e6104035 Continue to cleanup the csum pml module. Some minor corrections and debug output added.
This commit was SVN r20894.
2009-03-29 23:27:06 +00:00
Jeff Squyres
bf8defc475 Shaun Jackson noted that MPI_STATUS_IGNORE is actually (effectively)
NULL, so testing for NULL as a bad status parameter here is a bad
idea.

This commit was SVN r20891.
2009-03-28 01:24:41 +00:00
Donald Kerr
47dc1bd493 fix #1828; rework the private data connection establishment process; reviewed by terry d.
This commit was SVN r20889.
2009-03-26 17:54:44 +00:00
Donald Kerr
27ed29a0a1 wrap linux specific steps in __linux__ define
This commit was SVN r20888.
2009-03-26 15:09:01 +00:00
Rainer Keller
6ad07dbffa - First have the _config.h header,
then include system headers based on what's defined.

This commit was SVN r20886.
2009-03-26 12:56:22 +00:00
George Bosilca
25d457e3d4 The "missing" header ompi_config.h should not be added here. This file will
get installed for external tools, and they don't need any dependency on our
internal ompi_config.h file. Moreover, this file is crafted in such a way
that there is no need for ompi_config.h.

This commit was SVN r20884.
2009-03-25 21:09:13 +00:00
Donald Kerr
a1ba2e2164 add Sun vendor_id to Tavor Infinihost settings
This commit was SVN r20883.
2009-03-25 19:13:55 +00:00
Donald Kerr
cd7940e208 add vendor_id
This commit was SVN r20882.
2009-03-25 17:57:24 +00:00
Pavel Shamis
d25b7203a2 Adding send_immediate (sendi) implementation to openib btl.
This commit was SVN r20881.
2009-03-25 16:53:26 +00:00
Matthias Jurenz
c2d8fae9a0 Replaced usage of PATH_MAX by VT_PATH_MAX to avoid compile errors on some platforms (i.e. by using Intel compiler version 10.1.021)
This commit was SVN r20873.
2009-03-25 14:40:49 +00:00
Pavel Shamis
8888c9831c Prevent segfault for case when we release SRQ before srq_create.
This commit was SVN r20872.
2009-03-25 14:18:05 +00:00
Ralph Castain
f72e3ba9f9 Update the PML base send init macro to take a converter_flag field (discussed with George).
Update the csum pml module - still not quite right, but closer.

Modify the LANL platform files to keep pace.

This commit was SVN r20859.
2009-03-24 19:12:53 +00:00
Shiqing Fan
8bb6bb97a4 Make the compiler wrapper find the correct version of libraries, i.e. debug or release version based on build type.
This commit was SVN r20852.
2009-03-24 10:42:37 +00:00
Ralph Castain
d88df53a86 A touch more cleanup. Also, bring over the peruse cleanups from r20844
This commit was SVN r20849.

The following SVN revision numbers were found above:
  r20844 --> open-mpi/ompi@daba352af4
2009-03-24 01:36:31 +00:00
Ralph Castain
78323fd6b2 Minor cleanups to compile without warnings
This commit was SVN r20848.
2009-03-24 00:54:16 +00:00
Ralph Castain
75ca19d1d1 Turn off a function that hasn't been added to the code base yet...
This commit was SVN r20847.
2009-03-23 23:56:11 +00:00
Ralph Castain
17f51a0389 Add a new PML module that acts as a "mini-dr" - when requested, it performs a dr-like checksum on messages for BTL's that require it, as specified by MCA params.
Add two new configure options that specify:

1. when to add padding to the openib control header - this *only* happens when the configure option is specified

2. when to use the dr-like checksum as opposed to the memcpy checksum. Not selectable at runtime - to eliminate performance impacts, this is a configure-only option

Also removed an unused checksum version from opal/util/crc.h.

The new component still needs a little cleanup and some sync with recent ob1 bug fixes. It was created as a separate module to avoid performance hits in ob1 itself, though most of the code is duplicative. The component is only selectable by either specifying it directly, or configuring with the dr-like checksum -and- setting -mca pml_csum_enable_checksum 1.

Modify the LANL platform files to take advantage of the new module.

This commit was SVN r20846.
2009-03-23 23:52:05 +00:00
Ralph Castain
fb2b41d40a Give up on the pcie BTL and blow it away. The drivers for this initial implementation have been too customized by IBM - too hard to re-integrate the code.
Maybe someday, someone with enough interest/time can start over...

This commit was SVN r20845.
2009-03-23 23:27:57 +00:00
George Bosilca
daba352af4 As the request is not yet updated (i.e. _MATCHED cannot be called as we don't yet know the
expected length of the message) we should use the source and tag from the message header
instead of the value from the status structure attached to the request.
-This line, and those below, will be ignored--

M    pml_ob1_recvreq.c

This commit was SVN r20844.
2009-03-23 20:25:53 +00:00
Rainer Keller
a3c3babe01 - Ewww, r20817 messed up PGI on Jaguar big time!
Now, while #include "ompi_config.h" is good and fine in order
   to have OMPI_DECLSPEC,
   here it led to stdint.h (with the uint8_t) being included early
   but INSIDE a namespace "MPI" {}.
   Of course it was included anymore (thinkg #define _STDINT_H), when
   it was required in opal/class/opal_hash_list.h
   NOT good.

 - opal/class/opal_object.h: Yeah, one can have nested extern "C" {}
   but it's not necessary. Instead just have the outer *_C_DECLS.

This commit was SVN r20837.

The following SVN revision numbers were found above:
  r20817 --> open-mpi/ompi@6f808d9b05
2009-03-21 01:37:38 +00:00
Rainer Keller
353e489be8 - We're using opal_list_t, so better include it here...
- ompi/contrib/vt/vt/acinclude.m4: The missing escape \` messed up output on Jaguar
   Mailed to Matthias Jurenz

This commit was SVN r20836.
2009-03-21 01:28:31 +00:00
Jeff Squyres
804eb94f5f Fix the MCA param name to use the non-deprecated name.
This commit was SVN r20832.
2009-03-20 01:44:40 +00:00
Shiqing Fan
22b5c536af Clean up some unnecessary compiler flags.
This commit was SVN r20827.
2009-03-18 16:55:34 +00:00
Aurelien Bouteiller
fa9b6e729b Fix missing file in Makefile.am and the "CREATE FAILURE".
This commit was SVN r20821.
2009-03-18 13:42:48 +00:00
Rainer Keller
bff1b2a22b - Finally add the missing opal/util/output.h
for the OPAL_OUTPUT_VERBOSE macro.
 - ompi/errhandler/errhandler_predefined.h:
   Well, just the missing fwd declarations...

This commit was SVN r20820.
2009-03-17 22:37:15 +00:00
Rainer Keller
6f808d9b05 Preparation work for another commit (after RFC):
- This patch solely _adds_ required headers and is rather localized
   The next patch (after RFC) heavily removes headers (based on script)
 - ompi/communicator/communicator.h: For sources that use
   ompi_mpi_comm_world, don't require them to include "mpi.h"
 - ompi/debuggers/ompi_common_dll.c: mca_topo_base_comm_1_0_0_t needs
   #include "ompi/mca/topo/topo.h"
 - ompi/errhandler/errhandler_predefined.h:
   ompi/communicator/communicator.h depends on this header file!
   To prevent recursion just have fwd declarations.
   #include "ompi/types.h" for fwd declarations of the main structs.
 - ompi/mca/btl/btl.h: #include "opal/types.h" for ompi_ptr_t 
 - ompi/mca/mpool/base/mpool_base_tree.c: We use ompi_free_list_t and
   ompi_rb_tree_t, so have the proper classes
 - ompi/mca/op/op.h:
   Op is pretty self-contained: Nobody up to now has done
   #include "opal/class/opal_object.h"
 - ompi/mca/osc/pt2pt/osc_pt2pt_replyreq.h:
   #include "opal/types.h" for ompi_ptr_t 
 - ompi/mca/pml/base/base.h:
   We use opal_lists  
 - ompi/mca/pml/dr/pml_dr_vfrag.h:
   #include "opal/types.h" for ompi_ptr_t
 - ompi/mca/pml/ob1/pml_ob1_hdr.h:
   #include "ompi/mca/btl/btl.h" for mca_btl_base_segment_t
 - opal/dss/dss_unpack.c:
   #include "opal/types.h"
 - opal/mca/base/base.h:
   #include "opal/util/cmd_line.h" for opal_cmd_line_t
 - orte/mca/oob/tcp/oob_tcp.c:
   #include "opal/types.h" for opal_socklen_t
 - orte/mca/oob/tcp/oob_tcp.h:
   #include "opal/threads/threads.h" for opal_thread_t
 - orte/mca/oob/tcp/oob_tcp_msg.c:
   #include "opal/types.h" 
 - orte/mca/oob/tcp/oob_tcp_peer.c:
   #include "opal/types.h"  for opal_socklen_t
 - orte/mca/oob/tcp/oob_tcp_send.c:
   #include "opal/types.h" 
 - orte/mca/plm/base/plm_base_proxy.c:
   #include "orte/util/name_fns.h" for ORTE_NAME_PRINT
 - orte/mca/rml/base/rml_base_receive.c:
   #include "opal/util/output.h" for OPAL_OUTPUT_VERBOSE
 - orte/mca/rml/oob/rml_oob_recv.c:
   #include "opal/types.h" for ompi_iov_base_ptr_t
 - orte/mca/rml/oob/rml_oob_send.c:
   #include "opal/types.h" for ompi_iov_base_ptr_t
 - orte/runtime/orte_data_server.c
   #include "opal/util/output.h" for OPAL_OUTPUT_VERBOSE
 - orte/runtime/orte_globals.h:
   #include "orte/util/name_fns.h" for ORTE_NAME_PRINT

 Tested on Linux/x86-64

This commit was SVN r20817.
2009-03-17 21:34:30 +00:00
Rainer Keller
b9b84a9c29 - ompi/mca/mpool/rdma/mpool_rdma_module.c: At this level
without mpi.h we have no notion of MPI_SUCCESS...
 - ompi/mca/btl/sm/btl_sm.h: ptrdiff_t needs stddef.h 
 - ompi/mca/mpool/base/: If we use opal_pointer_array_t,
   better include the class header.

This commit was SVN r20816.
2009-03-17 20:21:36 +00:00
Aurelien Bouteiller
3cd5a0d833 Support for the MPI event logger improving event logging perfs.
This commit was SVN r20804.
2009-03-17 17:35:28 +00:00
Pavel Shamis
c6d038a8e8 Adding vendor_error code to error report.
This commit was SVN r20803.
2009-03-17 15:47:34 +00:00
Pavel Shamis
5afa2988f1 Updating RNR/IB timeout for openib btl
This commit was SVN r20801.
2009-03-17 15:03:06 +00:00
Rainer Keller
f5b4e250cb - By include "mpi.h" tell the compiler to look in local include dirs,
first.

This commit was SVN r20800.
2009-03-17 14:44:04 +00:00
Rainer Keller
7390b3476e - If we collect a return value, let the caller at least know about it...
This commit was SVN r20797.
2009-03-17 13:52:59 +00:00
Rainer Keller
6a72c0f4d1 - As long as a header declares _DECLSPEC functionality
it should include the corresponding _config.h header file.

   Tested on Linux/x86-64

This commit was SVN r20795.
2009-03-17 01:45:19 +00:00
Donald Kerr
d29a5e57c1 remove superfluous define
This commit was SVN r20785.
2009-03-16 02:24:01 +00:00
George Bosilca
a9be1b1dde Set the mem_node to a more meaningful value, as suggested by Ake Sandgren.
This commit was SVN r20780.
2009-03-14 22:08:26 +00:00
Eugene Loh
64f52b0168 Clean up in response to code review on CMR 1825:
minor changes in comments and edge-case handling.

This commit was SVN r20774.
2009-03-13 18:11:41 +00:00
Rainer Keller
d8cf4c0fec - Get pgcc on XT to complain less:
In case we use memcmp, strlen, strup and friends include <string.h>
   Also several constants.h are not included directly
 - Let's have mca_topo_base_cart_create  return ompi-errors in
   ompi/mca/topo/base/topo_base_cart_create.c

This commit was SVN r20773.
2009-03-13 02:10:32 +00:00
Donald Kerr
ef55aae401 fix #1829 : udapl btl support for relaxed ordering
This commit was SVN r20772.
2009-03-13 01:01:00 +00:00
Rainer Keller
04585ed8e3 - Explicit mark dependency
This commit was SVN r20771.
2009-03-12 22:48:41 +00:00
Rainer Keller
6fca443a71 - No, we don't want to have a notion of an MPI_Comm in this layer
We want ompi_communicator_t instead, rrrrrr.

This commit was SVN r20770.
2009-03-12 22:38:14 +00:00
George Bosilca
b29da4744f Amazing that there is only one compiler complaining about this ...
This commit was SVN r20768.
2009-03-12 21:30:08 +00:00
Rainer Keller
74b3acd4bd - No need to declare struct mca_mpool_base_resources_t;
Already in
   #include "ompi/mca/mpool/mpool.h"

This commit was SVN r20767.
2009-03-12 20:27:16 +00:00
Rainer Keller
296a6fb275 - So much fun along the way:
we normally don't do opal/include/opal/...
   Just use the std. opal/...

This commit was SVN r20766.
2009-03-12 19:21:11 +00:00
Rainer Keller
29b1b205fd - Remove two headers (and actually include rml.h) prior to test of
removal script...

This commit was SVN r20765.
2009-03-12 17:58:39 +00:00
Jeff Squyres
14ee1b7ba2 Refs trac:1826: remove barriers before all non-rooted collective ops.
This commit was SVN r20763.

The following Trac tickets were found above:
  Ticket 1826 --> https://svn.open-mpi.org/trac/ompi/ticket/1826
2009-03-12 02:23:08 +00:00
Ralph Castain
a8002c0f04 Remove missing files from Makefile.am so make dist will succeed
This commit was SVN r20743.
2009-03-06 02:57:51 +00:00
Rainer Keller
ec0ed48718 - Revert r20739
This commit was SVN r20742.

The following SVN revision numbers were found above:
  r20739 --> open-mpi/ompi@781caee0b6
2009-03-05 21:56:03 +00:00
Rainer Keller
a94438343b - Revert r20740
This commit was SVN r20741.

The following SVN revision numbers were found above:
  r20740 --> open-mpi/ompi@2a70618a77
2009-03-05 21:50:47 +00:00
Rainer Keller
2a70618a77 - Second patch, as discussed in Louisville.
Replace short macros in orte/util/name_fns.h
   to the actual fct. call.

 - Compiles on linux/x86-64

This commit was SVN r20740.
2009-03-05 21:14:18 +00:00
Rainer Keller
781caee0b6 - First of two or three patches, in orte/util/proc_info.h:
Adapt orte_process_info to orte_proc_info, and
   change orte_proc_info() to orte_proc_info_init().
 - Compiled on linux-x86-64
 - Discussed with Ralph

This commit was SVN r20739.
2009-03-05 20:36:44 +00:00
Shiqing Fan
99b415a7e0 On windows, the mca_common_* libraries should be installed in bin, otherwise the libraries that are dependent on them, e.g. shared build of mca_btl_sm, couldn't be loaded at runtime. This commit fixes the problem.
This commit was SVN r20735.
2009-03-05 14:57:35 +00:00
Ralph Castain
20b81ff634 Add the PCIE BTL. This won't actually work yet - still need to work through issues with system header files, generalize specification of resources, etc. - but it won't build unless specifically directed to do so. Meantime, any more changes that impact these areas of the code base can be reflected here rather than having to be dealt with later.
This commit was SVN r20734.
2009-03-05 02:40:25 +00:00
Terry Dontje
9215100ac4 Increase communicator padding to accomodate ppc larger lock structures.
This commit was SVN r20728.
2009-03-04 19:54:58 +00:00
Rainer Keller
9dea63d63a - Last of intrusive commits (promised)... err for now.
Anyway, this is blocking the move: do not include pml.h
   if not really needed, aka none of the following used:
     mca_pml
     MCA_PML_CALL
     OMPI_ANY_TAG
     OMPI_ANY_SOURCE
     OMPI_PROC_NULL

 - Notable exceptions (deleting in one header->adding):
   - ompi/mca/mtl/psm/
   - ompi/mca/osc/rdma/
   - ompi/mca/btl/openib/btl_openib_endpoint.c depended on
     pml_base_sendreq.h

 - Tested on Linux/x86-64, this time including make check
   (thanks Jeff and Ralph)

This commit was SVN r20725.
2009-03-04 17:06:51 +00:00
Josh Hursey
b62bc63f76 Fix some compiler warnings. I was using the ompi_predefined_* types instead of the base classes.
This commit was SVN r20722.
2009-03-04 16:16:13 +00:00
Rainer Keller
fd28b392bf - An intrusive commit yet again (sorry): with the separation we
get bitten by header depending on having already included
   the corresponding [opal|orte|ompi]_config.h header.
   When separating, things like [OPAL|ORTE|OMPI]_DECLSPEC
   are missed.

   Script to add the corresponding header in front of all following
   (taking care of possible #ifdef HAVE_...)

 - Including some minor cleanups to
   - ompi/group/group.h -- include _after_ #ifndef OMPI_GROUP_H
   - ompi/mca/btl/btl.h -- nclude _after_ #ifndef MCA_BTL_H
   - ompi/mca/crcp/bkmrk/crcp_bkmrk_btl.c -- still no need for
     orte/util/output.h
   - ompi/mca/pml/dr/pml_dr_recvreq.c -- no need for mpool.h
   - ompi/mca/btl/btl.h -- reorder to fit
   - ompi/mca/bml/bml.h -- reorder to fit
   - ompi/runtime/ompi_mpi_finalize.c -- reorder to fit
   - ompi/request/request.h -- additionally need ompi/constants.h

 - Tested on linux/x86-64

This commit was SVN r20720.
2009-03-04 15:35:54 +00:00
Eugene Loh
efe8c3a283 Initialize reuse_old_request properly at the beginning of each loop iteration in pml_ob1_start.c.
This commit was SVN r20712.
2009-03-04 06:58:36 +00:00
Rainer Keller
8123363357 - Dough. Makefile.am was missing in r20710
This commit was SVN r20711.

The following SVN revision numbers were found above:
  r20710 --> open-mpi/ompi@d68a8a1904
2009-03-04 00:30:28 +00:00
Rainer Keller
d68a8a1904 - Now that we don't need it anymore, blast away
ompi/class/ompi_bitmap.[ch] -- may always be restored from svn
   again...

This commit was SVN r20710.
2009-03-04 00:28:58 +00:00
Rainer Keller
811f2bd9b4 - As discussed on RFC, move the ompi_bitmap to the
opal layer.
   Add a check against a maximum (actually get rid of ifs internally to
   opal_bitmap.c) -- the functionality to set the current maximum size
   opal_bitmap_set_max_size() is currently only used in attribute.c
   to set the maximum OMPI_FORTRAN_HANDLE_MAX...

   Tested on linux/x86-64 with intel-tests with all_tests_no_perf_f
   run with 6 procs.
   Let's look into MTT as well...

This commit was SVN r20708.
2009-03-03 22:25:13 +00:00
Shiqing Fan
317db0fe62 Fix up the compiler flags again.
This commit was SVN r20702.
2009-03-03 17:32:08 +00:00
Jeff Squyres
a8456b27d7 Update the code to match the latest proposal:
https://svn.mpi-forum.org/trac/mpi-forum-web/wiki/MPI3Tools/dllapi

This commit was SVN r20681.
2009-03-02 21:29:52 +00:00
George Bosilca
8078bac53c Correct a case where the added datatype is considered as contiguous but
has gaps in the beginning. Thanks to Markus Blatt for the bug report.

This commit was SVN r20674.
2009-03-02 17:33:13 +00:00
Rich Graham
7ef1550267 add an index to indicate which socket group I belong to.
This commit was SVN r20672.
2009-03-02 14:39:54 +00:00
Rich Graham
daf7673aff gather socket information - not debugged.`
This commit was SVN r20670.
2009-03-02 10:58:12 +00:00
Jeff Squyres
fd979b2278 Add support for the notifier framework into ompi_info
This commit was SVN r20664.
2009-03-01 01:01:39 +00:00
Rainer Keller
02416033ad - Get rid of warning on function declarations:
First "static inline", then the type

This commit was SVN r20657.
2009-02-28 14:15:34 +00:00
Jeff Squyres
2002c576fe Add a lengthy comment about correctness and features of MPI_FINALIZE,
per a lengthy discussion at the Louisville, Feb 2009 OMPI meeting.

This commit was SVN r20656.
2009-02-28 12:58:12 +00:00
Tim Mattox
57be80c983 First pass at integrating the CIFTS/FTB support as
a notifier module.
The Notifier framework was extended slightly to
convey more information about each event notice.
This works with the FTB v0.5 API.

To compile with FTB support, use --with-ftb=/path/to/ftb/install

CIFTS == Coordinated Infrastructure for Fault Tolerant Systems
FTB == Fault Tolerance Backplane
see http://wiki.mcs.anl.gov/cifts/index.php

This commit was SVN r20655.
2009-02-27 22:53:43 +00:00
Matthias Jurenz
dfb95c0cd7 Added missing header include of 'cctypes.h' for function 'tolower()'
This commit was SVN r20653.
2009-02-27 14:47:46 +00:00