1
1
Граф коммитов

18 Коммитов

Автор SHA1 Сообщение Дата
Ralph Castain
884fb7fcf2 Update the PMIx2 support to include the latest shared memory optimizations
Update ORTE support for dynamic PMIx operations e.g., PMIx_Spawn
Update to track master
Ensure that --disable-pmix-dstore actually disables the dstore. Sync to a few debugger updates

Signed-off-by: Ralph Castain <rhc@open-mpi.org>
2016-12-14 15:00:10 -08:00
Ralph Castain
527b5c692a Update to include extended tool support, new datatypes 2016-08-08 13:39:46 -07:00
Jeff Squyres
72f41d4490 pmix: replace all tabs with spaces
No code or logic changes

Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
2016-07-17 15:08:33 -04:00
Ralph Castain
4a55fba414 Fix registration of error handlers thru the pmix120 component. A thread-shift operation was hanging on the sync_event_base, which made it dependent on someone calling opal_progress. Unfortunately, a process in "sleep" or spinning outside the MPI library won't do that, and so we never complete errhandler registration. 2016-03-02 15:01:01 -08:00
Ralph Castain
3a56f0d34b Create the pmix external component. Fix a few places where opal/util/argv.h were required when building with an external pmix (go figure).
NOTE: Building with external pmix *requires* that you also build with external libevent and hwloc libraries. Detect this at configure and error out with large message if this requirement is violated.

Closes #1204  (replaces it)
Fixes #1064
2015-12-15 15:26:13 -08:00
Ralph Castain
267ca8fcd3 Cleanup the PMIx direct modex support. Add an MCA parameter pmix_base_async_modex that will cause the async modex to be used when set to 1. Default it to 0 for now
to continue current default behavior.

Also add an MCA param pmix_base_collect_data to direct that the blocking fence shall return all data to each process. Obviously, this param has no effect if async_
modex is used.
2015-10-27 17:31:56 -07:00
Ralph Castain
37c3ed68e7 Cleanup connect/disconnect and bring comm_spawn back online! 2015-09-06 10:27:39 -07:00
Ralph Castain
a772b46c15 Bring the MPI_Publish and friends online 2015-09-02 12:04:07 -07:00
Ralph Castain
cf6137b530 Integrate PMIx 1.0 with OMPI.
Bring Slurm PMI-1 component online
Bring the s2 component online

Little cleanup - let the various PMIx modules set the process name during init, and then just raise it up to the ORTE level. Required as the different PMI environments all pass the jobid in different ways.

Bring the OMPI pubsub/pmi component online

Get comm_spawn working again

Ensure we always provide a cpuset, even if it is NULL

pmix/cray: adjust cray pmix component for pmix

Make changes so cray pmix can work within the integrated
ompi/pmix framework.

Bring singletons back online. Implement the comm_spawn operation using pmix - not tested yet

Cleanup comm_spawn - procs now starting, error in connect_accept

Complete integration
2015-08-29 16:04:10 -07:00
Ralph Castain
869041f770 Purge whitespace from the repo 2015-06-23 20:59:57 -07:00
Jeff Squyres
0dbbffb753 pmix_base_frame: use the "= { 0 }" initializer
Per open-mpi/ompi#381, convert the specific intialization of opal_pmix
to use the generic "= { 0 }" initializer.  This form can be used to
initialize any type when the intent is just to zero out / assign
*some* value.
2015-02-05 17:51:06 -05:00
Jeff Squyres
621af3aa07 pmix_base: fix global opal_pmix symbol for static linking on OS X
OS X has weirdness when static linking.  If a symbol is not
initialized, it is put into the common block section, and Weird Things
happen (linking when trying to using that global symbol will fail).
If you initialize the variable, it goes into a different section (and
linking to it will work).

This link (that might go stale someday) has some information about OS
X linker scope and treatment of symbol definitions:
https://developer.apple.com/library/mac/documentation/DeveloperTools/Conceptual/MachOTopics/1-Articles/executing_files.html#//apple_ref/doc/uid/TP40001829-98432-TPXREF120

Fixes #375.
2015-02-04 12:12:31 -05:00
Ralph Castain
ba25e8a0ce Fix singletons 2015-01-27 09:29:42 -06:00
Nadezhda Kogteva
2bce929330 MTL MXM cleanup: unnecessary OMPI_MTL_MXM_CONNECT_ON_FIRST_COMM variable removed 2014-10-20 10:29:47 +03:00
Elena
c905fe9b78 pmix: removed pmix_base_direct modex mca parameter, renamed orte_full_modex_cutoff and ompi_hostname_cutoff to direct_modex_cutoff 2014-10-09 06:15:31 +02:00
Ralph Castain
6323b226c7 Bring over some updates from the PMIx branch - mostly just minor cleanups. Make the direct grpcomm component no longer be the default. For now, we seem to be having problems with non-blocking fence operations, so make them not be the default under any scenario (e.g., when sm is the only btl in operation).
This commit was SVN r32673.
2014-09-06 19:19:44 +00:00
Ralph Castain
41c6058153 Bring over changes to MXM from pmix branch:
MTL MXM: establish endpoint connection on the first communication when direct_modex used

This commit was SVN r32668.
2014-09-03 18:22:11 +00:00
Ralph Castain
aec5cd08bd Per the PMIx RFC:
WHAT:    Merge the PMIx branch into the devel repo, creating a new
               OPAL “lmix” framework to abstract PMI support for all RTEs.
               Replace the ORTE daemon-level collectives with a new PMIx
               server and update the ORTE grpcomm framework to support
               server-to-server collectives

WHY:      We’ve had problems dealing with variations in PMI implementations,
               and need to extend the existing PMI definitions to meet exascale
               requirements.

WHEN:   Mon, Aug 25

WHERE:  https://github.com/rhc54/ompi-svn-mirror.git

Several community members have been working on a refactoring of the current PMI support within OMPI. Although the APIs are common, Slurm and Cray implement a different range of capabilities, and package them differently. For example, Cray provides an integrated PMI-1/2 library, while Slurm separates the two and requires the user to specify the one to be used at runtime. In addition, several bugs in the Slurm implementations have caused problems requiring extra coding.

All this has led to a slew of #if’s in the PMI code and bugs when the corner-case logic for one implementation accidentally traps the other. Extending this support to other implementations would have increased this complexity to an unacceptable level.

Accordingly, we have:

* created a new OPAL “pmix” framework to abstract the PMI support, with separate components for Cray, Slurm PMI-1, and Slurm PMI-2 implementations.

* Replaced the current ORTE grpcomm daemon-based collective operation with an integrated PMIx server, and updated the grpcomm APIs to provide more flexible, multi-algorithm support for collective operations. At this time, only the xcast and allgather operations are supported.

* Replaced the current global collective id with a signature based on the names of the participating procs. The allows an unlimited number of collectives to be executed by any group of processes, subject to the requirement that only one collective can be active at a time for a unique combination of procs. Note that a proc can be involved in any number of simultaneous collectives - it is the specific combination of procs that is subject to the constraint

* removed the prior OMPI/OPAL modex code

* added new macros for executing modex send/recv to simplify use of the new APIs. The send macros allow the caller to specify whether or not the BTL supports async modex operations - if so, then the non-blocking “fence” operation is used, if the active PMIx component supports it. Otherwise, the default is a full blocking modex exchange as we currently perform.

* retained the current flag that directs us to use a blocking fence operation, but only to retrieve data upon demand

This commit was SVN r32570.
2014-08-21 18:56:47 +00:00