ports/openmpi
ports/openmpi
1
1
Форкнуть 0
Код Релизы Активность
17 325 коммитов 3 Ветки 0 Теги 130 MiB
e497894c4d
Граф коммитов

2764 Коммитов

Автор SHA1 Сообщение Дата
Ralph Castain
35fef87202 Make the "no virtual machine" selection more intuitive by providing a --novm option to mpirun. 
This commit was SVN r27048.
 2012-08-15 14:55:03 +00:00
Nathan Hjelm
8e03f77004 update alps configure scripts 
This commit was SVN r27026.
 2012-08-13 22:57:55 +00:00
Ralph Castain
589acf550c Improve the new MPI_INFO_ENV to better handle Java applications and to correctly report the info for singletons. 
This commit was SVN r27025.
 2012-08-13 22:13:49 +00:00
Ralph Castain
49a757e0bd Silly me - now that all daemons are stripping their prefix on the backend, we no longer need to do it as they report 
This commit was SVN r27023.
 2012-08-13 20:48:13 +00:00
Ralph Castain
b9b41d8662 For cases where the alpha+non-zero prefix must be removed from a node name, be sure to do it everywhere we access node names - otherwise, modex methods such as pmi will fail to correctly identify procs on the same node 
This commit was SVN r27022.
 2012-08-13 20:44:56 +00:00
Ralph Castain
cb48fd52d4 Implement the MPI_Info part of MPI-3 Ticket 313. Add an MPI_info object MPI_INFO_GET_ENV that contains a number of run-time related pieces of info. This includes all the required ones in the ticket, plus a few that specifically address recent user questions: 
"num_app_ctx" - the number of app_contexts in the job
"first_rank" - the MPI rank of the first process in each app_context
"np" - the number of procs in each app_context

Still need clarification on the MPI_Init portion of the ticket. Specifically, does the ticket call for returning an error is someone calls MPI_Init more than once in a program? We set a flag to tell us that we have been initialized, but currently never check it.

This commit was SVN r27005.
 2012-08-12 01:28:23 +00:00
Ralph Castain
c4ee297a60 Cleanup the pmi grpcomm module so it passes non-btl modex data correctly. 
This commit was SVN r26992.
 2012-08-10 20:35:50 +00:00
Ralph Castain
e3e9b7345d First cut at updating the ccp launcher to use the state machine 
This commit was SVN r26986.
 2012-08-10 17:09:33 +00:00
Shiqing Fan
e304c19920 This is also used on Windows. 
This commit was SVN r26975.
 2012-08-08 16:44:00 +00:00
George Bosilca
ba879c2c51 Remove the unused map. 
This commit was SVN r26960.
 2012-08-07 12:06:13 +00:00
Shiqing Fan
2f442799f8 fix several typecasts 
This commit was SVN r26957.
 2012-08-07 10:41:53 +00:00
Ralph Castain
53b1a1c976 Cleanly error out when someone asks to map-to <object> if that object doesn't exist on a node. 
This commit was SVN r26950.
 2012-08-04 21:52:36 +00:00
Ralph Castain
61b09a132b Fix bynode mapping of multiple app-contexts 
This commit was SVN r26949.
 2012-08-03 21:45:40 +00:00
Ralph Castain
96f6f94c24 Ensure we don't get trapped in an infinite loop when ranking bynode if something isn't right 
This commit was SVN r26948.
 2012-08-03 21:45:10 +00:00
Ralph Castain
0d878937fe If a callback is set in the state machine, and the state doesn't yet exist, create it 
This commit was SVN r26947.
 2012-08-03 21:43:36 +00:00
Ralph Castain
431d5361ed For those who really preferred our prior mode of operation that mapped procs and only launched daemons on the nodes that had procs on them, introduce the "novm" state machine component. This recreates the old mode of operation by re-ordering the launch sequence so that we allocate, then map, and then launch daemons only on the reqd nodes (instead of across the entire allocation). 
This commit was SVN r26946.
 2012-08-03 16:30:05 +00:00
Ralph Castain
dc22ea5cde A little cleaner on the message about repeated ctrl-c, and re-enable the event so we can abort if we see multiple ctrl-c's that don't meet the time requirement 
This commit was SVN r26945.
 2012-08-03 01:26:18 +00:00
Ralph Castain
e6c72bfd53 Ensure we can forcibly exit even when we are stuck inside of an event by replacing the libevent signal handler with a POSIX one that (a) attempts to trip a libevent termination event and (b) if anothe ctrl-c hits within 5 seconds, just calls exit. 
This commit was SVN r26943.
 2012-08-02 21:15:35 +00:00
Ralph Castain
d818c9d407 Includes a patch from Jeff and Josh: update the simulator module to allow specification of multiple slot and max_slot counts for each node group (but don't require it). Remove the requirement that each node group provide its own topology. Adjust verbosities to allow showing some light debug output to see what nodes have been added without getting a bunch of other stuff. 
This commit was SVN r26936.
 2012-08-02 04:57:13 +00:00
Jeff Squyres
62c2ff7ee7 It's actually ''not'' an error to exit if all routes and children are 
gone.  So exit with 0, not ORTE_ERROR_DEFAULT_EXIT_CODE (which is 1).

This fixes a race condition in the rsh launcher upon termination,
where ORTE would sometimes think that a daemon failed to launch.

This commit was SVN r26935.
 2012-08-01 19:49:19 +00:00
Nathan Hjelm
4557e15c18 oob/ud fix compile error 
This commit was SVN r26933.
 2012-07-31 21:50:34 +00:00
Ralph Castain
6ee35e4977 Add num_local_peers to orte_process_info so we don't keep re-computing it, ensure it is available for direct launch via pmi as well 
This commit was SVN r26931.
 2012-07-31 21:21:50 +00:00
Jeff Squyres
88cbe9c780 .ompi_ignore this component until it can be fixed. 
This commit was SVN r26930.
 2012-07-31 21:02:06 +00:00
Nathan Hjelm
980692804d oob/ud: don't start listening for ud requests unless we have one usable port 
This commit was SVN r26929.
 2012-07-31 19:00:18 +00:00
Ralph Castain
23c2a315a9 Add missing line to set flag indicating at least one port found 
This commit was SVN r26914.
 2012-07-30 17:54:38 +00:00
Ralph Castain
6285f7d8c0 Per request of Shiqing, restore the ccp components 
This commit was SVN r26904.
 2012-07-29 23:49:59 +00:00
Ralph Castain
94d11e04fd Add an intermediate state when the VM is ready so that third party tools can take action prior to mapping/launching apps 
This commit was SVN r26902.
 2012-07-28 15:33:09 +00:00
Ralph Castain
8bc6694a62 Ensure the daemons don't incorrectly declare a failed launch 
This commit was SVN r26875.
 2012-07-26 19:05:06 +00:00
Ralph Castain
07846f12ae Reconnect the rsh/ssh error reporting code for remote spawns to report failure to launch. Ensure the HNP correctly reports non-zero exit status when ssh encounters a problem. 
Thanks to Terry for spotting it!

This commit was SVN r26868.
 2012-07-25 21:46:45 +00:00
Jeff Squyres
e5cfad0c1a This variable is only used in FT builds. 
This commit was SVN r26854.
 2012-07-24 12:48:47 +00:00
Shiqing Fan
12d99a9ebb Update the hwloc build on Windows and related files. 
This commit was SVN r26818.
 2012-07-20 12:14:28 +00:00
Abhishek Kulkarni
1ce378b5c6 Make C/R work with nodes > 1. This fix makes sure that the app coordinators send 
the "ready-to-checkpoint" signal to the global coordinator only after ORTE has
initialized.

This commit was SVN r26795.
 2012-07-13 23:37:29 +00:00
Abhishek Kulkarni
1878f276cd Replace the pattern while(flag) { opal_progress() }; in the C/R code 
with the ORTE_WAIT_FOR_COMPLETION macro.

This commit was SVN r26794.
 2012-07-13 23:31:56 +00:00
George Bosilca
772ec212eb Fix another compiler warning. 
This commit was SVN r26775.
 2012-07-10 15:57:42 +00:00
Abhishek Kulkarni
eec5a28aa4 More C/R fixes. 
* Fix a typo introduced by the removal of the notifier framework
* Fix to flush the modex cached data correctly using the orte DB API.

This commit was SVN r26773.
 2012-07-10 01:19:46 +00:00
Abhishek Kulkarni
5c58a1c9c1 Fix C/R support in the trunk. 
Among other things, this patch deals with the following issues:
* fix ompi-checkpoint argument parsing
* ompi-restart -showme prints an extraneous "Restarted child with PID" 
  message. Move around the debug statement to avoid this.
* fixes for the state machine changes

This commit was SVN r26770.
 2012-07-09 23:34:13 +00:00
George Bosilca
ec760454a6 Cleaning ... 
This commit was SVN r26747.
 2012-07-04 21:22:13 +00:00
Ralph Castain
6ae5776904 Cleanup IPV6 build 
This commit was SVN r26738.
 2012-07-04 00:03:50 +00:00
Ralph Castain
1a90471374 Drat - missed the other one 
This commit was SVN r26718.
 2012-07-02 22:18:31 +00:00
Ralph Castain
9a6a969f60 Remove debug 
This commit was SVN r26717.
 2012-07-02 22:18:08 +00:00
Ralph Castain
b83fc41d54 Add a state that allows mpirun or other tools to be notified of a job completion prior to terminating so that alternative actions can be performed. 
This commit was SVN r26716.
 2012-07-02 22:16:32 +00:00
Ralph Castain
8bebf2fa47 Ensure we don't build the MR iof components unless hadoop support is enabled 
This commit was SVN r26694.
 2012-06-28 18:20:15 +00:00
Ralph Castain
9aa821d8b4 Add missing file to tarball 
This commit was SVN r26688.
 2012-06-28 02:57:10 +00:00
Ralph Castain
0dfe29b1a6 Roll in the rest of the modex change. Eliminate all non-modex API access of RTE info from the MPI layer - in some cases, the info was already present (either in the ompi_proc_t or in the orte_process_info struct) and no call was necessary. This removes all calls to orte_ess from the MPI layer. Calls to orte_grpcomm remain required. 
Update all the orte ess components to remove their associated APIs for retrieving proc data. Update the grpcomm API to reflect transfer of set/get modex info to the db framework.

Note that this doesn't recreate the old GPR. This is strictly a local db storage that may (at some point) obtain any missing data from the local daemon as part of an async methodology. The framework allows us to experiment with such methods without perturbing the default one.

This commit was SVN r26678.
 2012-06-27 14:53:55 +00:00
Brian Barrett
b22faedd9d Remove the Portals4 SHMEM reference implementation runtime support, as we're 
no longer using the runtime provided by the reference implementation.

Remove the Catamount support from ORTE, since we're no longer supporting
Catamount.  Left the Catamount timer component, because I'm not sure whether
it's used on the XTs running CNL.

This commit was SVN r26677.
 2012-06-27 14:17:43 +00:00
Josh Hursey
28681deffa Backout the ORCA commit. :( 
There is a linking issue on Mac OSX that needs to be addressed before this is able to come back into the trunk.

This commit was SVN r26676.
 2012-06-27 01:28:28 +00:00
Josh Hursey
542330e3a7 Commit of ORCA: Open MPI Runtime Collaborative Abstraction 
This is a runtime interposition project that sits between the OMPI and ORTE layers in Open MPI.

The project is described on the wiki:
  https://svn.open-mpi.org/trac/ompi/wiki/Runtime_Interposition

And on this email thread:
  http://www.open-mpi.org/community/lists/devel/2012/06/11109.php

This commit was SVN r26670.
 2012-06-26 21:42:16 +00:00
Ralph Castain
a34f09e67a Ensure common port is off when not being used 
This commit was SVN r26666.
 2012-06-26 16:09:58 +00:00
Ralph Castain
92527da4e3 Remove unused component 
This commit was SVN r26660.
 2012-06-26 00:49:28 +00:00
Ralph Castain
0103f82918 Turn off the common port for slurm for now 
This commit was SVN r26656.
 2012-06-25 21:55:51 +00:00