1
1
Граф коммитов

10565 Коммитов

Автор SHA1 Сообщение Дата
Shiqing Fan
3c38c9c020 - Add extern "C" to resolve linkage specification problems.
This commit was SVN r16577.
2007-10-26 09:54:42 +00:00
Jeff Squyres
86824ffb7b Remove some mVAPI verbiage.
This commit was SVN r16576.
2007-10-26 03:22:43 +00:00
George Bosilca
e724ca0a1f Remodel the ompi_free_list a little. The free_list_memory is in
fact a free_list_item so instead of having a struct, use typedef
to make them equivalent. Modify the parallel debuggers support
in order to allow them access to the internal types even when
we have an optimized build.

This commit was SVN r16567.
2007-10-25 16:47:54 +00:00
Jeff Squyres
1085336cfc Add note about fixing fd leak in altix timer code.
This commit was SVN r16565.
2007-10-25 16:06:05 +00:00
Jeff Squyres
dd27622814 Fix fd leak noted by Paul Hargrove.
http://www.open-mpi.org/community/lists/devel/2007/10/2493.php

This commit was SVN r16564.
2007-10-25 16:03:21 +00:00
Ethan Mallove
2b363f8afb Sanity check for SVK workspace in autogen.sh.
This commit was SVN r16563.
2007-10-25 14:12:52 +00:00
Sven Stork
29b2f8ce97 - fix broken build target, we have to use the files in the RPM build
environment.

This commit was SVN r16561.
2007-10-24 17:48:30 +00:00
George Bosilca
682f110658 Correctly test the finalize condition. Thanks to Ake Sandgren for bringing this
issue to our attention.

This commit was SVN r16560.
2007-10-24 13:34:27 +00:00
Ralph Castain
a791ce2299 The processor affinity must be set on a per-process basis, not per-app-context.
This commit was SVN r16559.
2007-10-23 20:46:16 +00:00
Gleb Natapov
3a63eb6c17 Cleanup macro definitions.
This commit was SVN r16554.
2007-10-23 13:33:19 +00:00
Gleb Natapov
d836f3dbbe Remove unused macro.
This commit was SVN r16552.
2007-10-23 13:18:10 +00:00
Gleb Natapov
18ed60edeb Revert previous commit. There was no memory leak, the pointer is saved inside
free list for future use. This patch moves BTL initialization into separate
function too.

This commit was SVN r16551.
2007-10-23 12:57:45 +00:00
Gleb Natapov
657e544e02 Fix memory leak. Define init_data on a stack instead of allocation it each time.
This commit was SVN r16550.
2007-10-23 11:10:52 +00:00
Gleb Natapov
9e2d5acf8e Remove unused filed from openib fragment structure.
This commit was SVN r16549.
2007-10-23 07:38:29 +00:00
George Bosilca
95c9fbdf45 Make sure the MX MTL component is shared between all files.
This commit was SVN r16545.
2007-10-22 18:06:52 +00:00
George Bosilca
7a63f9b730 I somehow mess up my last commit. Sorry.
This commit was SVN r16543.
2007-10-22 15:08:17 +00:00
George Bosilca
b93f72bdfd Remove 2 warnings about uninitialized i and quit_flags.
This commit was SVN r16542.
2007-10-22 15:01:15 +00:00
Jeff Squyres
5637c7a5a0 In addition to r16513, this commit fixes trac:1170.
If we cannot resolve the route to the peer that we're trying to send
to, don't queue up the message in the TCP OOB -- instead, return it to
the upper layer (e.g., the RML) and let it decide what to do.

In the case of the routed RML, the tree component will queue it up for
later transmission.  Hence, we don't want the message queued up both
here in the TCP OOB and the tree routed.  Also see some more
discussion / explanation in #1171.

This commit was SVN r16540.

The following SVN revision numbers were found above:
  r16513 --> open-mpi/ompi@7ae9589d70

The following Trac tickets were found above:
  Ticket 1170 --> https://svn.open-mpi.org/trac/ompi/ticket/1170
2007-10-22 13:46:57 +00:00
Gleb Natapov
63dde87076 If SM BTL cannot send fragment because the cyclic buffer is full put the
fragment on the pending list and send it later instead of spinning on
opal_progress().

This commit was SVN r16537.
2007-10-22 12:07:22 +00:00
Rainer Keller
42d6cf27c3 - In ompi_request_init():
Change order of initialization as in the declaration
   Add missing initialization of req_persistent and req_mpi_object
   to ompi_request_empty and ompi_request_null.

This commit was SVN r16536.
2007-10-22 11:28:49 +00:00
Rich Graham
0de9bd9fa0 when attaching an md for posted receive, generate a start event, so that
PtlMDUpdate will pick up all incoming events.

This commit was SVN r16517.
2007-10-19 19:09:40 +00:00
Jeff Squyres
7ae9589d70 The header is at the address of the buffer pointed to by the iov, not
the address of the iov.

This commit was SVN r16513.
2007-10-19 12:40:14 +00:00
Jeff Squyres
abf1b728b9 Minor code maintenance fix -- put the THREAD_UNLOCK outside the if
statement so that you only have to have it once.

This commit was SVN r16512.
2007-10-19 12:36:26 +00:00
Ralph Castain
73eeb7f0d2 Fix a bug in the way we handled buffer releases and the conditioned wait that held us in the xcast until completed.
This commit was SVN r16504.
2007-10-19 01:17:01 +00:00
Gleb Natapov
52c6160252 MCA_PML_BASE_REQUEST_MPI_COMPLETE() macro does nothing except call to
ompi_request_complete(). Remove the macro and call the function directly.

This commit was SVN r16498.
2007-10-18 14:20:24 +00:00
George Bosilca
aa20a94b6f Remove warning about an unused variable.
This commit was SVN r16497.
2007-10-18 13:48:56 +00:00
Gleb Natapov
4f865e22e8 We have two different version of ompi_request_complete. One as a function
another as a macro. Make it one inline function.

This commit was SVN r16495.
2007-10-18 13:02:27 +00:00
Gleb Natapov
e0a3a7e53e Move duplicated code all over the code to a single function ompi_request_wait_completion().
This commit was SVN r16494.
2007-10-18 12:33:21 +00:00
Gleb Natapov
807f49ed7f If there are more then one BTL present we may divide payload between them in
such a way that converter will not be able to pack some of it. This commit adds
handling of such cases. If converter can't pack any data for a BTL the data is
sent over another BTL that has data to send.

This commit was SVN r16493.
2007-10-18 12:07:37 +00:00
George Bosilca
df80d21e04 Get rid of the recv_context field. Instead we can rely on the unique_id,
which is shared between the DLL and the parallel debugger.

This commit was SVN r16492.
2007-10-17 22:07:38 +00:00
George Bosilca
938be44f07 Complete the removal of the mvapi BTL.
This commit was SVN r16491.
2007-10-17 22:02:52 +00:00
Jeff Squyres
b7eeae0a74 Remove the mvapi BTL. Woo hoo!
This commit was SVN r16483.
2007-10-17 14:08:03 +00:00
Josh Hursey
0bf61a1b84 Move in some accumulated small features and minor bug fixes for C/R support.
{{{
svn merge -r 16447:16475 https://svn.open-mpi.org/svn/ompi/tmp/jjh-fgs .
}}}

This commit was SVN r16478.
2007-10-17 13:47:36 +00:00
Jeff Squyres
c143858998 Various updates to the not-yet-released stuff.
This commit was SVN r16463.
2007-10-16 16:57:30 +00:00
Ralph Castain
6f498c0964 Since we no longer set the APP_NUM attribute in the case of a singleton, protect the code so we don't crash in that case.
This commit was SVN r16461.
2007-10-16 16:17:48 +00:00
Ralph Castain
ec5fe78876 When in the unity message routing mode, we have to update the RML contact info in the parent procs so that they know how to talk to the children. Ideally, this would be done in the MPI layer since that layer knows which procs are actively involved in the comm_spawn. However, it isn't being done there, which causes comm_spawn to fail, so do it explicitly in the RTE.
Note that this means ALL procs in the parent job are updated, even though they may not be participating in the comm_spawn. This doesn't really hurt anything - just unnecessary.

Comm_spawn still has a problem when a child process shares a node with a parent, so this doesn't fix everything. It only fixes the bug of ensuring all procs know how to talk to each other.

This commit was SVN r16460.
2007-10-16 16:09:41 +00:00
Ralph Castain
713b6e13a5 Improve diagnostic output messages when errors are hit
This commit was SVN r16457.
2007-10-16 14:51:52 +00:00
Josh Hursey
ea0652d20f If we are going to pretend to do filem, then we should always pretend.
No one should be using this feature except for me. :)

This commit was SVN r16454.
2007-10-15 20:04:35 +00:00
Ralph Castain
b6196e8a39 When we can detect that a daemon has failed, then we would like to terminate the system without having it lock up. The "hang" is currently caused by the system attempting to send messages to the daemons (specifically, ordering them to kill their local procs and then terminate). Unfortunately, without some idea of which daemon has died, the system hangs while attempting to send a message to someone who is no longer alive.
This commit introduces the necessary logic to avoid that conflict. If a PLS component can identify that a daemon has failed, then we will set a flag indicating that fact. The xcast system will subsequently check that flag and, if it is set, will send all messages direct to the recipient. In the case of "kill local procs" and "terminate", the messages will go directly to each orted, thus bypassing any orted that has failed.

In addition, the xcast system will -not- wait for the messages to complete, but will return immediately (i.e., operate in non-blocking mode). Orterun will wait (via an event timer) for a period of time based on the number of daemons in the system to allow the messages to attempt to be delivered - at the end of that time, orterun will simply exit, alerting the user to the problem and -strongly- recommending they run orte-clean.

I could only test this on slurm for the case where all daemons unexpectedly died - srun apparently only executes its waitpid callback when all launched functions terminate. I have asked that Jeff integrate this capability into the OOB as he is working on it so that we execute it whenever a socket to an orted is unexpectedly closed. Meantime, the functionality will rarely get called, but at least the logic is available for anyone whose environment can support it.

This commit was SVN r16451.
2007-10-15 18:00:30 +00:00
Jeff Squyres
94b1e9cff9 Update to use BTL_VERBOSE and BTL_ERROR instead of opal_output'ing to
the mca_btl_base_output stream directly (and relying on it to be -1 if
we didn't want any output).

This commit was SVN r16449.
2007-10-15 17:53:02 +00:00
Jeff Squyres
423f23eb6a Fixes trac:1160. There is still some other problem in the OOB, but we
wanted to commit this to get wider testing.

This commit was SVN r16445.

The following Trac tickets were found above:
  Ticket 1160 --> https://svn.open-mpi.org/trac/ompi/ticket/1160
2007-10-15 15:41:36 +00:00
Josh Hursey
f16a42947a Change some default MCA parameters:
- Global snapshot directory = $HOME
 - FileM 'rsh' = 'ssh'
 - FileM 'rcp' = 'scp'

This commit was SVN r16444.
2007-10-15 15:21:17 +00:00
Rolf vandeVaart
3dd5196338 Remove the --mca btl_base_debug flag and clean up
the use of the --mca btl_base_verbose flag.  The
btl framework now matches all the other frameworks.
Slightly modify error messages for clarity.

This commit was SVN r16443.
2007-10-15 13:10:20 +00:00
Gleb Natapov
1330974e5e eager_limit is no longer needed in OB1 PML. Remove it.
This commit was SVN r16442.
2007-10-15 09:26:42 +00:00
George Bosilca
436b0f2a5b Way to many numbers in this uint32_t.
This commit was SVN r16437.
2007-10-12 13:11:55 +00:00
Tim Prins
12d3ad4c5c remove unused and outdated opal message buffer code
This commit was SVN r16436.
2007-10-11 22:09:01 +00:00
George Bosilca
e9aa15f9d5 On behalf of Ralf Wildenhues:
config/ompi_check_visibility.m4 (OMPI_CHECK_VISIBILITY):
Rename ompi_vc_cc_fvisibility to ompi_cv_cc_fvisibility, so
that it will be cached.

This commit was SVN r16435.
2007-10-11 22:06:39 +00:00
Josh Hursey
520c27ac94 If the HNP is acting as the orted for local launch then the gpr_replica
variable is not defined. Make sure to set it to something reasonable 
so that file preloading still works (instead of seg faulting :)

Thanks to Hiep Bui Hoang for reporting this bug.

This commit was SVN r16433.
2007-10-11 19:47:04 +00:00
Josh Hursey
e483c36cea Remove a big of debug in filem/rsh that should have never been committed.
A guesture towards overlapping file removal with metadata update.

This commit was SVN r16432.
2007-10-11 19:37:33 +00:00
Josh Hursey
31e9369e8b Fix orterun so it does not get influenced by an application's argv set.
For example, if I have an application that, internal to the application, takes
the argument '-mca foo bar' we do not want orterun to pick up this argument and
pass it through the system.

So the following
{{{
 shell$ mpirun -np 2 -mca btl tcp,self ./myapp -mca foo bar
}}}

orterun should pick up {{{-mca btl tcp,self}}} but not {{{-mca foo bar}}} which
it was previous to this commit.

I tested command line runs and runs with app files to confirm this patch works.

This commit was SVN r16431.
2007-10-11 18:33:40 +00:00