1
1
Граф коммитов

12181 Коммитов

Автор SHA1 Сообщение Дата
Dan Lacher
0ef83a558e minor tweak to header line for ompi_crcp.7
This commit was SVN r19150.
2008-08-04 19:48:10 +00:00
Tim Mattox
ef610bea0e Resync the trunk NEWS file with the 1.2 branch.
This commit was SVN r19149.
2008-08-04 18:32:52 +00:00
Ralph Castain
5a2053ade2 Per July technical meeting:
Revise the scope precedence in the MPI_Publish, Unpublish, and Lookup functions. If a global server was specified and is available, then default to using it for all three functions. If not, then default to using local scope.

If an info_key was provided, then it takes preference. We always follow the user's direction - this change only impacts the scope ordering if the user -doesn't- tell us the order to use.

This commit was SVN r19146.
2008-08-04 16:43:12 +00:00
George Bosilca
e6f700bf04 Reenable the ddt_test as #1242 is now closed.
This commit was SVN r19145.
2008-08-04 15:57:02 +00:00
Jeff Squyres
b83ee7d82a * Fix a problem with VPATH builds if the destination directory didn't
already exist  
 * s/top_srcdir/top_builddir/ in a bunch of places; left over from the
   previous man page generation system

This commit was SVN r19141.
2008-08-04 15:17:50 +00:00
Jeff Squyres
8d5bcf9257 Fix a bunch of double quote issues
This commit was SVN r19140.
2008-08-04 15:13:29 +00:00
Edgar Gabriel
1adb3a6cda Fixes trac:1408
The optimization that was introduced a year ago for saving a collective
synchronization  step for certain communicator creation functions has to be
disabled for now. The bug has been exposed by the hierarch module, but could
appear as well for inter-communicator creations. The problem is, that within a
communicator creation step we invoke a comm_dup (for intercomm_create) or
other collective operations (in case of hierarch) before all processes have
been synchronized. This lead to the "Dropped message for non-existant
communicators" error. This commit disables the optimization without removing
it from the code base. In theory, it can be enabled again as soon as we have
the unexpected message queues for unknown cid's, which were required if I
remember right anyway for the multi-threaded scenarios and potentially for
fault tolerance.

Before moving the patch to 1.3 I would like to let it soak for a couple of
days on trunk. Please note, taht my 2nd comment on ticket #1408 was
semi-correct, since the order of activation of the communicator and quering
the collective module have already been changed earlier.

This commit was SVN r19139.

The following Trac tickets were found above:
  Ticket 1408 --> https://svn.open-mpi.org/trac/ompi/ticket/1408
2008-08-04 14:55:09 +00:00
Rainer Keller
4712a73db5 - Help the compiler, by noting that errors are unlikely.
This commit was SVN r19138.
2008-08-04 14:50:27 +00:00
Ralph Castain
381d10833a Remove comments in documentation about the "-nw" option to mpirun as this option doesn't exist, and probably never will
This commit was SVN r19137.
2008-08-04 14:38:37 +00:00
Jeff Squyres
35f721a706 Suggestion from Ralf W. to clean up sub-make's properly.
This commit was SVN r19136.
2008-08-04 14:35:40 +00:00
Ralph Castain
35a86b3347 Establish an MCA param "orte_allocation_required" so that a system can require the user have an RM-provided allocation in order to run. This helps prevent the problem where a user forgets to get an allocation on an RM-managed cluster, and then executes mpirun on the head node - thus causing all of their mpi procs to launch on the head node, usually bringing it to its knees.
Since OMPI allows mpirun to default to the local node, and since users want to retain the option to co-locate procs with mpirun, we needed another param to block this error case.

This commit was SVN r19135.
2008-08-04 14:25:19 +00:00
Rainer Keller
0d08866786 - Declare functions in lex-files as extern "C" {} to get
rid of warnings.

This commit was SVN r19132.
2008-08-04 11:49:01 +00:00
Jeff Squyres
7d1f6d42ab Case-sensitive filesystem fix for OS X / Xgrid
This commit was SVN r19130.
2008-08-02 14:07:48 +00:00
Ralph Castain
fdde3de903 Combination of some changes by both Jeff and I. Few minor cleanups to the code (e.g., allow options to show-mca-params to be either case), and an enhancement that allows the user to specify multiple options separated by commas (e.g., "env,api").
This commit was SVN r19124.
2008-08-02 00:43:27 +00:00
Ralph Castain
5b2f53a069 One more quick fix - ensure we are looking at the value and not its pointer
This commit was SVN r19123.
2008-08-01 23:39:55 +00:00
Ralph Castain
21ba1b2ec0 Modify the configure system in the paffinity framework so that only one component is built. Cleanout variable name conflicts that on some systems prevented building
This commit was SVN r19122.
2008-08-01 22:54:24 +00:00
Jeff Squyres
26c7daf16a Fix typo
This commit was SVN r19121.
2008-08-01 21:30:53 +00:00
Dan Lacher
9175da1e02 Putback for all changes to automate man page updates to strings of
versions, dates and build names.

Fixes trac:1387

Big thanks to Jeff and Brian for help and oversight.

This commit was SVN r19120.

The following Trac tickets were found above:
  Ticket 1387 --> https://svn.open-mpi.org/trac/ompi/ticket/1387
2008-08-01 21:14:37 +00:00
Ralph Castain
21cd4b9df8 Add pls_rsh_agent synonym to the PLM rsh component
This commit was SVN r19119.
2008-08-01 20:15:42 +00:00
Jeff Squyres
1a3045ff81 * Remove some extraneous AC_MSG_RESULT's
* Make the results of the top-level configure.ac test for
   _SC_NPROCESSORS_ONLN be cached so that we can check for it
   elsewhere (e.g., opal/mca/paffinity/posix/configure.m4)
 * Update top-level configure.ac test for _SC_NPROCESSORS_ONLN: stamp
   out another AC_TRY_COMPILE
 * Ensure paffinity:posix doesn't even try to compile if we don't
   have _SC_NPROCESSORS_ONLN
 * Minor style updates

This commit was SVN r19118.
2008-08-01 11:41:08 +00:00
Ralph Castain
e1501f2c9c Add darwin paffinity component to handle the difference between Tiger and Leopard. Although both are POSIX compatible, Tiger is a tad different in this regard and requires a different interface to get the #processor data.
This commit was SVN r19117.
2008-08-01 00:15:10 +00:00
Jeff Squyres
4bdc093746 Fixes trac:1361: mainly add new internal MCA parameter that orterun will
set when it launches under debuggers using the --debug option.

This commit was SVN r19116.

The following Trac tickets were found above:
  Ticket 1361 --> https://svn.open-mpi.org/trac/ompi/ticket/1361
2008-07-31 22:11:46 +00:00
Jeff Squyres
b45d59ea2e Adjust API usage for new parameter in mca_base_param_lookup_source()
This commit was SVN r19115.
2008-07-31 21:56:20 +00:00
Jeff Squyres
9fda668edf Clarify the comment that the caller should not modify or free the
filename.

This commit was SVN r19114.
2008-07-31 21:53:59 +00:00
Jeff Squyres
5818eca234 Also make sure that the new INTERNAL channel doesn't close the
endpoint and/or the real stderr fd in the HNP.

This commit was SVN r19113.
2008-07-31 21:26:58 +00:00
Ralph Castain
164c1ebba7 Ensure output of new source dat is in the parseable output of ompi_info too
This commit was SVN r19112.
2008-07-31 20:35:42 +00:00
Ralph Castain
f7d1c2d229 Extend the mca param display capability to allow independent output of the params based on where they were last set (default, enviro, file, or API), and to out
put the name of the file that set them if they were set by file. This is of great assistance to support personnel trying to understand why a user is having pro
blems.

Coordinated with Jeff.

This commit was SVN r19111.
2008-07-31 20:00:45 +00:00
Rainer Keller
dbafe83999 - Update the warn_unused result from allocating functions
- Set __opal_attribute_nonnull__ where an argument *must* not be null
 - Mark unused functions

This commit was SVN r19107.
2008-07-31 15:46:09 +00:00
Ralph Castain
2ee493c3f9 Fix some FT code to reflect change in session_dir interface
This commit was SVN r19106.
2008-07-31 14:53:18 +00:00
Jeff Squyres
5ac6a4387c Fix MPI_CART_GET to take an array of logicals for the periods argument
(not integers)

This commit was SVN r19099.
2008-07-30 20:29:23 +00:00
Ralph Castain
a62b2a0150 Per the July technical meeting:
Standardize the handling of the orte launch agent option across PLMs. This has been a consistent complaint I have received - each PLM would register its own MCA param to get input on the launch agent for remote nodes (in fact, one or two didn't, but most did). This would then get handled in various and contradictory ways.

Some PLMs would accept only a one-word input. Others accepted multi-word args such as "valgrind orted", but then some would error by putting any prefix specified on the cmd line in front of the incorrect argument.

For example, while using the rsh launcher, if you specified "valgrind orted" as your launch agent and had "--prefix foo" on you cmd line, you would attempt to execute "ssh foo/valgrind orted" - which obviously wouldn't work.

This was all -very- confusing to users, who had to know which PLM was being used so they could even set the right mca param in the first place! And since we don't warn about non-recognized or non-used mca params, half of the time they would wind up not doing what they thought they were telling us to do.

To solve this problem, we did the following:

1. removed all mca params from the individual plms for the launch agent

2. added a new mca param "orte_launch_agent" for this purpose. To further simplify for users, this comes with a new cmd line option "--launch-agent" that can take a multi-word string argument. The value of the param defaults to "orted".

3. added a PLM base function that processes the orte_launch_agent value and adds the contents to a provided argv array. This can subsequently be harvested at-will to handle multi-word values

4. modified the PLMs to use this new function. All the PLMs except for the rsh PLM required very minor change - just called the function and moved on. The rsh PLM required much larger changes as - because of the rsh/ssh cmd line limitations - we had to correctly prepend any provided prefix to the correct argv entry.

5. added a new opal_argv_join_range function that allows the caller to "join" argv entries between two specified indices

Please let me know of any problems. I tried to make this as clean as possible, but cannot compile all PLMs to ensure all is correct.

This commit was SVN r19097.
2008-07-30 18:26:24 +00:00
Lenny Verkhovsky
90a784dfca Making paffinity_base_slot_list invisible for the user
This commit was SVN r19096.
2008-07-30 14:52:45 +00:00
George Bosilca
7f01be2830 Remove useless defines. The MCA was bumped to 2.0, there is no reason to keep
these defines around.

This commit was SVN r19091.
2008-07-30 10:40:18 +00:00
Terry Dontje
0ff11f7523 Added initialization and proper increment of the value of num_processors
pointer.  This commit fixes trac:1420.

This commit was SVN r19089.

The following Trac tickets were found above:
  Ticket 1420 --> https://svn.open-mpi.org/trac/ompi/ticket/1420
2008-07-30 10:29:05 +00:00
Jeff Squyres
fc7c58ede6 Missed updating the topo base check to look for v2.0.0, causing all
topology-related MPI tests to fail.

This commit was SVN r19088.
2008-07-30 00:50:42 +00:00
Donald Kerr
2899f64146 moving vendor_id info to top of file
This commit was SVN r19087.
2008-07-29 22:33:17 +00:00
Donald Kerr
513225c9f3 add Sun Microsystems, Inc. vendor_id
This commit was SVN r19085.
2008-07-29 19:31:41 +00:00
Ralph Castain
01a7259a7d This fixes ticket #1426 - mpirun is cleaning up ALL session dirs
Mpirun - and the orteds - were doing their best to whack all session dirs on their nodes just in case there was something lingering due to an abnormal termination. Unfortunately, they were -too- good at it. They were whacking all session directories under the user's name, even those from other mpiruns!

This adds another layer to the session dir tree so that we can denote which jobs come from our own job family, and restricts the cleanup operation to only session dirs from within our own job family. So we'll still cleanup anything due to our own mpirun, but won't whack any other mpirun from this user.

Call it being polite...

This commit was SVN r19083.
2008-07-29 18:58:35 +00:00
Jeff Squyres
49d9f614d0 Remove errant debugging printf
This commit was SVN r19082.
2008-07-29 18:53:40 +00:00
George Bosilca
2d8cbc6ade Allow other BTL to work even if they collide with regard to the exclusivity. The problem was
that by decreasing the btl_inuse if there was already a registered BTL we basically reset
the changes for this new BTL to register it's progress function, even if it was supposed to
handle another peer.

This commit was SVN r19080.
2008-07-29 18:38:11 +00:00
Ralph Castain
d45d728e8e Allow debuggers to attach to a running mpirun by -always- setting up the MPIR_Proctable. Only wait for MPIR_Breakpoint and hold MPI proc
s if we are launching under a debugger.

This commit was SVN r19079.
2008-07-29 17:39:16 +00:00
George Bosilca
a4d905db4a Allow xgrid to compile.
This commit was SVN r19076.
2008-07-29 13:24:08 +00:00
Ralph Castain
1210a96d82 Ensure a value gets defined before used...thanks Jeff
This commit was SVN r19075.
2008-07-29 13:08:45 +00:00
Jeff Squyres
388c047579 Ensure to actually register the proper synonym index
This commit was SVN r19074.
2008-07-29 13:05:39 +00:00
Jeff Squyres
0af7ac53f2 Fixes trac:1392, #1400
* add "register" function to mca_base_component_t
   * converted coll:basic and paffinity:linux and paffinity:solaris to
     use this function
   * we'll convert the rest over time (I'll file a ticket once all
     this is committed)
 * add 32 bytes of "reserved" space to the end of mca_base_component_t
   and mca_base_component_data_2_0_0_t to make future upgrades
   [slightly] easier
   * new mca_base_component_t size: 196 bytes
   * new mca_base_component_data_2_0_0_t size: 36 bytes
 * MCA base version bumped to v2.0
   * '''We now refuse to load components that are not MCA v2.0.x'''
 * all MCA frameworks versions bumped to v2.0
 * be a little more explicit about version numbers in the MCA base
   * add big comment in mca.h about versioning philosophy

This commit was SVN r19073.

The following Trac tickets were found above:
  Ticket 1392 --> https://svn.open-mpi.org/trac/ompi/ticket/1392
2008-07-28 22:40:57 +00:00
Jeff Squyres
a7c79558ad Remove an errant printf that was causing non-fatal errors to be
displayed (e.g., when deleting files that should have been silently
ignored if they didn't exist).

This commit was SVN r19071.
2008-07-28 22:11:31 +00:00
Jeff Squyres
c93f1d8c5e Fixes trac:1419: got a patch from upstream to fix the "OS X doesn't
have/need lseek64" issue.  This fix is also included in MPICH2 after
v1.0.7.

This commit was SVN r19070.

The following Trac tickets were found above:
  Ticket 1419 --> https://svn.open-mpi.org/trac/ompi/ticket/1419
2008-07-28 17:02:53 +00:00
Ralph Castain
96c6262abd Update LANL platform files
This commit was SVN r19069.
2008-07-28 16:40:31 +00:00
Ralph Castain
a0ae63f19e Ensure we call close_port after comm_spawn[_multiple]. Cleanout the port name in close_port
This commit was SVN r19068.
2008-07-28 16:40:11 +00:00
Ralph Castain
1a77b15523 Modify the handling of hostfiles to allow them to subdivide allocations. Utilize the "slots_alloc" field of the orte_node_t object - which had previously been unused - to track the #slots allocated to a given app_context. Let the hostfile filtering action utilize the #slots field to modify the allocated slots for each app_context.
This commit was SVN r19066.
2008-07-28 15:10:40 +00:00