1
1
Граф коммитов

13107 Коммитов

Автор SHA1 Сообщение Дата
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
Nysal Jan
8e2b6a8b3c There is no need to set epevin.data.fd as we have already set epevin.data.ptr to 5 earlier
This commit was SVN r20949.
2009-04-07 12:45:19 +00:00
Nysal Jan
2e1d14cafe Add a comment explaining the change made
This commit was SVN r20948.
2009-04-07 03:59:32 +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
Nysal Jan
fbba533874 Fix broken epoll detection. Add the write only fd of the pipe to the epoll set and check if the fd is ready for writing. The earlier test works with older linux distros but fails with newer ones.
This commit was SVN r20945.
2009-04-06 21:44:10 +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
Jeff Squyres
a13dfb2140 Add in a proper test for munmap.
This commit was SVN r20936.
2009-04-04 00:43:17 +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
Jeff Squyres
52a0e5fe69 Add some checks for more network driver types.
This commit was SVN r20934.
2009-04-02 19:17:21 +00:00
Nysal Jan
ab18a3629f Change the return type to handle the case where an invalid interface name is passed to this function.
This commit was SVN r20933.
2009-04-02 18:35:09 +00:00
Rainer Keller
9b7ab92de9 - Per mail and diff from Ken Matney:
Allow multiple retries to open file as well, for ALPS to supply the file.

This commit was SVN r20932.
2009-04-02 17:46:08 +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
Jeff Squyres
3bf8c7025a Remove compiler warning about function not being prototyped.
This commit was SVN r20929.
2009-04-02 13:06:47 +00:00
Shiqing Fan
7a7c4bcb4b fix a type cast for windows.
This commit was SVN r20928.
2009-04-02 08:45:48 +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
0f517c3d3f Gah; some non-final code got merged in by accident. Remove debugging
printf and put in the final test code for malloc.

This commit was SVN r20924.
2009-04-01 18:20:23 +00:00
Jeff Squyres
bf17ce1d3f Doh; forgot to add the OPAL_DECLSPEC to munmap().
This commit was SVN r20923.
2009-04-01 18:09:25 +00:00
Jeff Squyres
7aa431882c Remove the mallopt component (accidentally missed in r20921); refs
#1853.

This commit was SVN r20922.

The following SVN revision numbers were found above:
  r20921 --> open-mpi/ompi@0d52271cd6
2009-04-01 18:02:08 +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
Jeff Squyres
b7a052a81d Fix r20917 -- some systems require <unistd.h> for !_SC_PAGESIZE.
This commit was SVN r20920.

The following SVN revision numbers were found above:
  r20917 --> open-mpi/ompi@d10393a925
2009-04-01 16:41:12 +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
George Bosilca
d10393a925 A more optimized version of the set function. It only touch the first byte on
each page. Anyway, this function is _NEVER_ called as we use bind instead of set.
So please don't rely on the first touch memory affinity to do the right thing.

This commit was SVN r20917.
2009-04-01 15:24:03 +00:00
George Bosilca
6ca6cfaafc Mark the address with the correct type.
This commit was SVN r20916.
2009-04-01 15:18:08 +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
7ed4e4f9e8 Using absolute addresses leads to getting the data from strange places
if the opal_buffer_t get reallocated (and it gets). As in all cases
the data in the beginning of the buffer is the one we need, using
relative addresses fixes the problem.

This commit was SVN r20904.
2009-03-31 16:23:27 +00:00
Aurelien Bouteiller
ccc8aa5784 Fix a segfault caused by making copies of the pointer to an array that is realloced meanwhile. The base pointer can change its address while the copy still tries to access pages that are not ours anymore.
As a safeguard, good coding style should never access directly opal_pointer_array_t->addr or opal_value_array_t->bytes_array. I found another instance of the same bug somewhere else and will commit a separate patch for it. 

This commit fixes ticket #1858 and solves user case http://www.open-mpi.org/community/lists/devel/2009/03/5731.php .

Aurelien

This commit was SVN r20903.
2009-03-31 15:41:55 +00:00
Terry Dontje
b92bec7c85 Put in a check for visibility attribute support so we don't add the visibility
linker option when there is no visibility attribute support thus no visible 
external variables.  This is to get around a Sun Studio compiler version that
doesn't recognize the visibility attribute but recognizes the -xldscope option.

This commit was SVN r20902.
2009-03-31 14:31:00 +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
5498f93a50 Gaah -- get the bug reporter's name right!
This commit was SVN r20893.
2009-03-28 01:29:01 +00:00
Jeff Squyres
1be70da78c Add note about fix for MPI_REQUEST_GET_STATUS. Tentatively marking
this for 1.3.3 -- I don't know if the door for 1.3.2 is still open or
not...

This commit was SVN r20892.
2009-03-28 01:28:09 +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