1
1
Граф коммитов

2897 Коммитов

Автор SHA1 Сообщение Дата
Ralph Castain
2504da1ac9 Remove stale code - message arrival time doesn't really mean much anymore.
This commit was SVN r27905.
2013-01-24 23:02:02 +00:00
Ralph Castain
9bfb2b989b Silence warning
This commit was SVN r27901.
2013-01-24 19:38:51 +00:00
Ralph Castain
4b310473a1 Correct the computation of the daemon vpid
cmr:v1.7

This commit was SVN r27899.
2013-01-24 18:04:53 +00:00
Ralph Castain
b403ca5bd8 Silence warning
This commit was SVN r27897.
2013-01-23 22:17:08 +00:00
Ralph Castain
4d34d30a97 Silence warning
This commit was SVN r27896.
2013-01-23 22:16:48 +00:00
Ralph Castain
a591fbf06f Add initial support for dynamic allocations. At this time, only Slurm supports the new capability, which will be included in an upcoming release.
Add hooks for supporting dynamic allocation and deallocation to support application-driven requests and fault recovery operations.

This commit was SVN r27879.
2013-01-20 00:33:42 +00:00
Ralph Castain
e4673f3283 Add new job state
This commit was SVN r27878.
2013-01-20 00:30:27 +00:00
Ralph Castain
73387e50e2 Add missing variable def - thanks to Paul Hargrove for spotting.
This commit was SVN r27865.
2013-01-18 14:32:53 +00:00
Ralph Castain
54266837e9 Remove use of param_find function as that function will be disappearing
This commit was SVN r27831.
2013-01-15 19:50:38 +00:00
Ralph Castain
aea6787918 Add new routed component with self-healing connections - based on radix component - for use in monitoring system
This commit was SVN r27757.
2013-01-08 04:40:35 +00:00
Ralph Castain
c9a596b487 Remove unused var
This commit was SVN r27756.
2013-01-08 04:39:30 +00:00
Ralph Castain
beddf3b379 Add required rml tag
This commit was SVN r27751.
2013-01-05 06:32:20 +00:00
Ralph Castain
bee8bf5d8f Update the sensor framework to report stats back to the HNP if requested by including the data in heartbeats.
This commit was SVN r27748.
2013-01-05 06:30:20 +00:00
Ralph Castain
c71e119bbb Extend the db framework to add support for logging data to databases without duplicating all the modex-related storage.
This commit was SVN r27746.
2013-01-05 06:28:09 +00:00
George Bosilca
34eecb8956 Be more explicit about the operation (store or update). complain loudly
if something goes wrong.

This commit was SVN r27743.
2013-01-04 20:47:25 +00:00
Ralph Castain
cc29f8ff95 Attempt to fix the stupid Cray PMI problem
This commit was SVN r27742.
2013-01-04 02:53:42 +00:00
Nathan Hjelm
6a9ab9b221 Change orte_startup_timeout to be in seconds and remove the 10 second maximum
This commit was SVN r27741.
2013-01-03 23:56:34 +00:00
Ralph Castain
c65de32218 Cleanup the PMI subsystems to support Sam's "rml-less" shared memory wireup. Only retrieve keys that are specifically requested, and only when they are requested. Let string values be segmented across multiple keys, but don't do it for anything else.
This commit was SVN r27737.
2013-01-03 02:16:10 +00:00
Ralph Castain
d1163ebbf2 Ensure we cleanup DFS worker threads during finalize to avoid segfaulting in MCA param cleanup
This commit was SVN r27723.
2012-12-25 21:17:35 +00:00
Ralph Castain
c5ba59ba67 Remove stale component
This commit was SVN r27684.
2012-12-18 04:01:16 +00:00
Ralph Castain
0427a478b2 Remove stale component
This commit was SVN r27683.
2012-12-18 04:00:51 +00:00
Ralph Castain
82f1ba0ea8 Fix static port usage, ensure that both ipv4 and ipv6 are given if ipv6 was enabled
This commit was SVN r27682.
2012-12-18 03:59:49 +00:00
Ralph Castain
2fdd367aa9 Refs trac:3429
Fix bug reported by FreyGuy19713: in cases where HNP node has multiple entries in a hostfile or other allocation, we need to track the total slots allocated to that node.

This commit was SVN r27673.

The following Trac tickets were found above:
  Ticket 3429 --> https://svn.open-mpi.org/trac/ompi/ticket/3429
2012-12-14 17:00:44 +00:00
Ralph Castain
1e92aa2b66 Enable multiple worker threads for processing DFS requests
This commit was SVN r27659.
2012-12-09 02:54:19 +00:00
Ralph Castain
c26ed7dcdd Fix comm_spawn when ORTE progress thread is enabled by ensuring that all operations on the global list of active collectives are done in events to avoid conflicts.
This commit was SVN r27658.
2012-12-09 02:53:20 +00:00
Nathan Hjelm
3e1b13b13a Re-add support for old flex (2.5.4a and earlier) while still cleaning up properly in new flex.
This commit was SVN r27657.
2012-12-07 00:12:43 +00:00
Ralph Castain
1237f8db57 Extend the ras module interface to include the orte_job_t being allocated so that dynamic allocations can be supported
This commit was SVN r27627.
2012-11-23 13:50:10 +00:00
George Bosilca
994d1aba50 Nothing.
This commit was SVN r27626.
2012-11-21 20:07:20 +00:00
Ralph Castain
43f883cb42 Add some more detailed error output to the db_hash component and nidmap code. Ensure the local nodename is included in the HNP's aliases
This commit was SVN r27622.
2012-11-18 17:57:19 +00:00
Ralph Castain
f2ec35536e Fix a bug that prevented MCA params from being forwarded to daemons upon launch
cmr:v1.7

This commit was SVN r27621.
2012-11-18 17:55:26 +00:00
Ralph Castain
e11f32038a Add an MCA param to retain all aliases based on IP addrs for node names so that procs can look them up by interface, if desired. If the param is set, pass aliases around to all daemons and procs for local use
This commit was SVN r27619.
2012-11-16 04:04:29 +00:00
Ralph Castain
3cecc1569b Fix segfault if no file_maps were pushed
This commit was SVN r27612.
2012-11-15 15:39:17 +00:00
Ralph Castain
fe6dfad625 Update DFS to support multi-node operations
This commit was SVN r27594.
2012-11-12 02:54:53 +00:00
Ralph Castain
a6325e4546 Silence compiler warning
This commit was SVN r27590.
2012-11-12 02:51:29 +00:00
Ralph Castain
26f1cd0909 Fix compiler warnings
This commit was SVN r27588.
2012-11-12 02:50:45 +00:00
Ralph Castain
bd887f7f56 Add a new "test" component to the DFS that treats all files as remote in order to test the app-to-daemon interactions on a single machine. Set a global param to indicate we are using staged execution. Add a param to indicate it is okay for non-MPI processes to execute without finalizing. Cleanup file map load and fetch operations.
This commit was SVN r27587.
2012-11-10 14:09:12 +00:00
Ralph Castain
615cc66b44 Protect the HNP cleanup in cases where no session dirs are created
This commit was SVN r27585.
2012-11-10 14:03:07 +00:00
Nathan Hjelm
e0f5137e46 add prototypes for lex destroy functions
This commit was SVN r27580.
2012-11-09 22:00:27 +00:00
Nathan Hjelm
8658bbc902 instead of relying on yyterminate to clean up the lex context call the destroy functions directly (after closing the file)
This commit was SVN r27577.
2012-11-09 16:10:55 +00:00
Ralph Castain
9b729794f2 A prior commit apparently broke the trunk when something was inadvertently left behind - so remove a reference to a no-longer-existing function
This commit was SVN r27574.
2012-11-07 11:11:05 +00:00
Nathan Hjelm
7fb5caea92 Remove the finish_parsing function from various .l files. The function is incomplete (doesn't clean up the lex state) and should be replaced by *_yylex_destroy which correctly cleans up the state.
Checked with the flex 2.5.35. Verified with valgrind that this fixes several "still reachable" leaks.

cmr:v1.7

This commit was SVN r27571.
2012-11-06 19:26:14 +00:00
Nathan Hjelm
bdedd8b0d3 Per RFC modify the behavior of mca_base_components_close to NOT close the output. Modify frameworks to always close their output and set to -1.
Reasoning: The old behavior was a little confusing. mca_base_components_open does not open an output stream so it is a little unexpected that mca_base_components_close does. To add to this several frameworks (that don't use mca_base_components_close) failed to close their output in the framework close function and others closed their output a second time. This change is an improvement to the symantics of mca_base_components_open/close as they are now symetric in their functionality.

This commit was SVN r27570.
2012-11-06 19:09:26 +00:00
Brian Barrett
e61c00212d Add files found in svn but not tarball
This commit was SVN r27549.
2012-11-01 02:27:03 +00:00
Nathan Hjelm
2acd0f83de Revert "Revert r27451 and r27456 - the cmd line parser is incorrectly marking the application as an MCA parameter".
It appears the problem was not with the command line parser but the rsh plm. I don't know why this problem was not occuring before the command line parser changes but it appears to be resolved now.

This commit was SVN r27527.

The following SVN revision numbers were found above:
  r27451 --> open-mpi/ompi@d59034e6ef
  r27456 --> open-mpi/ompi@ecdbf34937
2012-10-30 19:45:18 +00:00
Nathan Hjelm
df9bd0ed59 fix bug in plm/rsh that could add extraneous mca options to the orted argv
cmr:v1.7

This commit was SVN r27526.
2012-10-30 19:40:04 +00:00
Ralph Castain
a080de188f Enable orterun to directly support staged execution, treating each app as a separate job. Support transfer of file maps when support exists.
This commit was SVN r27516.
2012-10-29 23:11:30 +00:00
Ralph Castain
e5e72c3137 Expand the dfs API to support retrieval, loading and purging of file maps.
This commit was SVN r27515.
2012-10-29 23:05:45 +00:00
Ralph Castain
4e52a15e70 Provide for sync on seek and close DFS operations. Eliminate an unnecessary wake-up timer when using ORTE progress thread
This commit was SVN r27500.
2012-10-26 15:49:04 +00:00
Ralph Castain
4ef30c016b Remove stale windows references
This commit was SVN r27491.
2012-10-26 01:19:14 +00:00
Ralph Castain
df642f1508 Add an API to get a remote file's size. Separate dfs cmds from returned data messages so daemons don't get confused.
This commit was SVN r27487.
2012-10-25 22:23:08 +00:00