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
45fee2b491 Resolve the case where only the HNP is in the system (i.e., single-node operation) 
This commit was SVN r26382.
 2012-05-03 18:00:01 +00:00
Ralph Castain
c352ca36c2 Minor cleanup 
This commit was SVN r26381.
 2012-05-02 21:23:37 +00:00
Ralph Castain
b2f77bf08f Extend the iof by adding two new components to support map-reduce IO chaining. Add a mapreduce tool for running such applications. 
Fix the state machine to support multiple jobs being simultaneously launched as this is not only required for mapreduce, but can happen under comm-spawn applications as well.

This commit was SVN r26380.
 2012-05-02 21:00:22 +00:00
Ralph Castain
c5da4f24d7 Fix stupid singletons - get the pidmap message correct 
This commit was SVN r26378.
 2012-05-02 17:48:02 +00:00
Ralph Castain
9f724db182 Remove duplicate event assignment 
This commit was SVN r26360.
 2012-04-30 16:06:20 +00:00
Ralph Castain
289f9f41ec From long-term discussions, have the daemons use the node_t and proc_t structs and arrays instead of the pidmap and nidmap arrays. Sets the stage for future work. 
This commit was SVN r26359.
 2012-04-29 00:10:01 +00:00
Ralph Castain
f3e3704c9e Per request from Brian, enable mapping of stddiag output (output from opal_output calls) to stderr of the local process. This allows you to obtain that output in a local window (for example, when using xterm for each process) instead of having it automatically forwarded to mpirun. Turn this on automatically whenever someone uses the -xterm option, and to be set manually using the orte_map_stddiag_to_stderr mca param. 
This commit was SVN r26352.
 2012-04-27 14:39:34 +00:00
Jeff Squyres
46f47e08b6 Remove typo/extra brackets and parens. 
This commit was SVN r26351.
 2012-04-27 13:48:43 +00:00
Jeff Squyres
9d0df5a9a6 Update configury in the new oob ud component: actually check to see if 
it succeeds and run $1 or $2, accordingly.  This allows "make dist" to
run properly on machines that do not have OpenFabrics stuff installed
(e.g., the nightly tarball build machine).

There's still more to be done here -- it doesn't check for non-uniform
directories where the OpenFabrics headers/libraries might be
installed.  We might need to re-tool/combine
ompi/config/ompi_check_openib.m4 (which checks for way more than
oob/ud needs) and move it up to config/ompi_check_ofa.m4, or
something...?

This commit was SVN r26350.
 2012-04-27 11:32:56 +00:00
Jeff Squyres
9829d2279f System-level includes should be at the top of the file, before most 
OPAL/ORTE/OMPI includes.

This commit was SVN r26349.
 2012-04-27 11:29:22 +00:00
Ralph Castain
38af7db183 Ensure the progress message comes out right away. Otherwise, on a large system where proc state messages are arriving frequently, the message doesn't get printed until the launch is done! 
This commit was SVN r26346.
 2012-04-26 23:41:03 +00:00
Nathan Hjelm
e1e0d466e5 Merge ssh://ct-fe1/usr/projects/hpctools/hjelmn/ompi-trunk-git into HEAD 
This commit was SVN r26344.
 2012-04-26 22:06:12 +00:00
Ralph Castain
3461809341 Fix reporting of launch progress so the numbers are correct and appear when they should 
This commit was SVN r26342.
 2012-04-26 00:10:09 +00:00
Ralph Castain
71805bf7e4 Clearout the startup_timeout event if the job did in fact start. Have ORTE_TERMINATE use the job state macro so debug will show where it was called 
This commit was SVN r26334.
 2012-04-25 01:05:17 +00:00
Jeff Squyres
708b497968 Ensure to unset the iof "active" flag after the libevent read callback 
fires (it's already reset once we queue up the read event again).  Failure
to unset the active flag would cause other logic to not queue up the
read event again, because it thought the read event was still active).

This commit was SVN r26311.
 2012-04-23 15:58:12 +00:00
Ralph Castain
7999266f99 Silence warning by removing unused var 
This commit was SVN r26275.
 2012-04-17 22:34:48 +00:00
Ralph Castain
f68487016c Add test code from Terry. Properly terminate if we don't abort on non-zero exit 
This commit was SVN r26271.
 2012-04-16 16:44:23 +00:00
Ralph Castain
ddfbde587f Change the default to "abort" the job when any process exits with a non-zero status. Add the required code to ensure the orted tells the HNP about the problem. 
This commit was SVN r26270.
 2012-04-13 21:19:46 +00:00
Ralph Castain
7741ba47be Fix comm_spawn that spans multiple nodes 
This commit was SVN r26268.
 2012-04-13 01:59:07 +00:00
Ralph Castain
4d16790836 Fix collectives for jobs running across partial allocations 
This commit was SVN r26267.
 2012-04-13 00:38:47 +00:00
Ralph Castain
5d14fa7546 Fix mpi_abort, minimize error output. 
This commit was SVN r26266.
 2012-04-11 14:37:08 +00:00
Ralph Castain
d3dfba3872 Fix the scenario where an MPI error handler causes a proc to exit after finalize, but with non-zero status to indicate an error occurred. 
This commit was SVN r26265.
 2012-04-11 02:23:46 +00:00
Ralph Castain
9cd4c06488 Get things to build and run when --disable-orte is specified 
This commit was SVN r26263.
 2012-04-10 21:50:01 +00:00
Ralph Castain
14d5525fb1 Some minor cleanups. Get singletons working. Cleanup abort handling so it gets properly identified. 
This commit was SVN r26261.
 2012-04-10 19:08:54 +00:00
Ralph Castain
53bbcf4b5b Plug slot allocation leak 
This commit was SVN r26260.
 2012-04-10 14:56:24 +00:00
Ralph Castain
f5cd996b91 Fix the case where n=1 
This commit was SVN r26258.
 2012-04-09 22:44:56 +00:00
Ralph Castain
a34be856aa Now that we have PMI support, this is no longer needed 
This commit was SVN r26254.
 2012-04-07 13:36:24 +00:00
Ralph Castain
71f9e69c62 Remove stale code 
This commit was SVN r26253.
 2012-04-07 13:34:12 +00:00
Ralph Castain
19630ca28d Remove stale code 
This commit was SVN r26252.
 2012-04-07 13:33:40 +00:00
Ralph Castain
93bbeabc55 Remove stale code 
This commit was SVN r26251.
 2012-04-07 13:33:30 +00:00
Ralph Castain
b6cde9a8d1 Remove stale code 
This commit was SVN r26250.
 2012-04-07 13:33:18 +00:00
George Bosilca
319f76d66a Low hanging fruit. Remove a declared but not defined function. 
This commit was SVN r26245.
 2012-04-06 15:43:28 +00:00
Ralph Castain
ed197acaa2 Eliminate stale code 
This commit was SVN r26244.
 2012-04-06 15:31:13 +00:00
Ralph Castain
bd8b4f7f1e Sorry for mid-day commit, but I had promised on the call to do this upon my return. 
Roll in the ORTE state machine. Remove last traces of opal_sos. Remove UTK epoch code.

Please see the various emails about the state machine change for details. I'll send something out later with more info on the new arch.

This commit was SVN r26242.
 2012-04-06 14:23:13 +00:00
Ralph Castain
ca3ff58c76 Ensure we get a non-zero exit status when we can't find the specified fork agent. Output a better error message, and ensure we don't multiply report the problem. 
This commit was SVN r26191.
 2012-03-24 00:49:38 +00:00
Ralph Castain
46b040c79f Fix typo 
This commit was SVN r26189.
 2012-03-24 00:31:05 +00:00
Ralph Castain
2bd75ec7e3 Fix Cray XE builds - the priority here needs to equal that of the HNP component so that both build. Otherwise, mpirun tries to use PMI for its basis, and that doesn't work! 
This commit was SVN r26188.
 2012-03-23 20:06:34 +00:00
Ralph Castain
811413e9bc Correctly handle multiple cpu-set ranges. Correctly support optional binding directives combined with cpu-set. 
This commit was SVN r26187.
 2012-03-23 14:50:41 +00:00
Ralph Castain
ce0caf7567 Support -cpu-set by binding to the specified cpus in the absence of any other binding directive. Allows users to subdivide nodes for multiple parallel mpirun invocations. 
This commit was SVN r26186.
 2012-03-23 14:05:52 +00:00
Ralph Castain
33ed3cda07 Update the gridengine allocator to support data from multiple queues by checking for duplicate node entries 
This commit was SVN r26148.
 2012-03-15 17:45:50 +00:00
Josh Hursey
4dd9f89a99 Create an MCA parameter (ess_base_stream_buffering) that allows the user to override the system default for buffering of stdout/stderr streams. See 'man setvbuf' for more information. 
Note: I am working on a system that buffered all output until the application fishished due to a default of 'fully buffered.' This makes debugging painful. This switch fixed the problem by allowing me to adjust the buffering.

This commit was SVN r26119.
 2012-03-08 22:02:28 +00:00
Ralph Castain
e71e871bae Initialize sink location when stdin is forwarded to all ranks 
This commit was SVN r26107.
 2012-03-06 15:47:04 +00:00
Ralph Castain
366f9d1518 Add some missing localities to the hwloc pretty-print, fix pmi modex 
This commit was SVN r26105.
 2012-03-06 06:21:10 +00:00
Ralph Castain
834a86420b Ensure we use the slurm module for slurm environments, and correct init order in pmi module when used by daemons 
This commit was SVN r26089.
 2012-03-02 23:10:48 +00:00
Ralph Castain
ceb34ed0c9 Fix typo 
This commit was SVN r26079.
 2012-03-02 09:58:09 +00:00
Ralph Castain
b2f1bade37 Fix the -H localhost issue 
This commit was SVN r26071.
 2012-02-29 16:56:00 +00:00
Jeff Squyres
81dc6a11ee Fix typo in copyright notice, found by Paul Hargrove 
This commit was SVN r26070.
 2012-02-29 02:02:54 +00:00
Ralph Castain
a83da303c5 When using PMI, we know the ranks that share our node and their relative local/node ranks. Save that info in the pidmap array so that BTLs that require early knowledge of local ranks can access it. 
This commit was SVN r25992.
 2012-02-21 16:43:17 +00:00
Jeff Squyres
b6a90434e4 Fix some include file header ordering issues for some BSDs, suggested 
by Paul Hargrove.

This commit was SVN r25984.
 2012-02-21 13:32:14 +00:00
Jeff Squyres
b295a01d8e Fix another configury error found by Paul Hargrove. Thanks, Paul! 
This commit was SVN r25971.
 2012-02-20 21:38:27 +00:00
Jeff Squyres
cdc783925e (Re-)Add oob_tcp_if_(in|ex)clude functionality to allow CIDR notation, 
just like the btl_tcp_if_(in|ex)clude MCA param.

This commit was SVN r25953.
 2012-02-17 15:38:42 +00:00
Jeff Squyres
3e22450345 Fix the oob_tcp_verbose MCA param; make it actually apply to the OOB 
TCP verbose handle (not the generic/0 handle).

This commit was SVN r25942.
 2012-02-16 22:28:11 +00:00
Ralph Castain
b3aabf1565 Cleanup the --without-hwloc build. Thanks to Paul Hargrove for reporting it broken. 
This commit was SVN r25931.
 2012-02-15 11:08:57 +00:00
Ralph Castain
91977444af Silence warnings 
This commit was SVN r25929.
 2012-02-15 03:42:27 +00:00
Ralph Castain
bba6508b4b Handle the default hostfile case a little better... 
This commit was SVN r25928.
 2012-02-15 03:33:49 +00:00
Ralph Castain
f14c4be580 Correct the ordering logic so the list gets correctly built in daemon vpid order 
This commit was SVN r25818.
 2012-01-30 16:25:07 +00:00
Shiqing Fan
bfbd3c67a5 Add a windows file into the tarball. 
This commit was SVN r25811.
 2012-01-29 10:12:02 +00:00
Ralph Castain
a0edae52f2 Ensure the wrapper flags get entered in the right order, with -lpmi coming before the alps util libs 
This commit was SVN r25809.
 2012-01-27 20:56:21 +00:00
Ralph Castain
3f31feee6f Handle the case where a user's rankfile specifies only cpus, and not socket:cpu pairs. 
This commit was SVN r25803.
 2012-01-27 12:21:45 +00:00
Ralph Castain
07f3a91075 Okay, get srun to play nice. Problem was that everything worked fine so long as the user did "salloc" with an argument requesting a specific number of nodes. However, if the user specified instead a number of processes, then we launched that number of daemons - resulting in multiple daemons/node. Not good. 
So force things to behave correctly either way.

This commit was SVN r25792.
 2012-01-26 19:58:57 +00:00
Ralph Castain
ef94e606c7 Add some debug 
This commit was SVN r25791.
 2012-01-26 19:23:32 +00:00
Ralph Castain
1449b27e9f Ensure that slurm only launches one orted/node, regardless of how the allocation was obtained. 
This commit was SVN r25790.
 2012-01-26 19:23:15 +00:00
Jeff Squyres
64165ce758 r25775 removed the .windows from this directory, but left it in the 
Makefile.am. 

This commit was SVN r25782.

The following SVN revision numbers were found above:
  r25775 --> open-mpi/ompi@2c9a4beffd
 2012-01-26 10:45:06 +00:00
Jeff Squyres
3751495443 Add missing arguments for the new DYLD_LIBRARY_PATH stuff. 
This commit was SVN r25780.
 2012-01-26 00:35:48 +00:00
Ralph Castain
079e4d9156 Per George's comment, just duplicate the lib path envars to provide both Linux and Mac compatible values 
This commit was SVN r25776.
 2012-01-25 14:37:36 +00:00
Shiqing Fan
2c9a4beffd Add and remove a few components for windows build. 
This commit was SVN r25775.
 2012-01-25 09:01:27 +00:00
Ralph Castain
8b115754e6 Fix typo 
This commit was SVN r25763.
 2012-01-21 23:50:39 +00:00
Ralph Castain
469e40ace2 Expand the coverage a little when looking at remote shells for rsh. Prior patch (r25758) works only if both ends of the rsh/ssh connection are Mac. What we really want is to use the Mac version of ld_library_path when the remote end is Mac, regardless of the OS where mpirun is executing. So add a test for system type to the remote_shell test, and set the ld_library_path name to match the remote system type. 
This commit was SVN r25762.

The following SVN revision numbers were found above:
  r25758 --> open-mpi/ompi@1afb77e603
 2012-01-21 23:48:42 +00:00
Ralph Castain
1afb77e603 Mac requires setting DYLD_LIBRARY_PATH instead of the Linux standard LD_LIBRARY_PATH, so ensure we set that when using rsh to launch in Mac environments. 
Thanks to Teng Lin for the patch!

This commit was SVN r25758.
 2012-01-20 19:14:32 +00:00
Ralph Castain
be3dfb6a1a Ensure that we only add -lpmi once to the wrapper compilers, no matter how many components might use it. 
This commit was SVN r25753.
 2012-01-20 04:56:38 +00:00
Ralph Castain
d7fe1615b6 Add missing dollar sign on variable 
This commit was SVN r25745.
 2012-01-19 20:45:22 +00:00
Ralph Castain
0d20f745e2 Remove stale function def 
This commit was SVN r25744.
 2012-01-19 20:40:48 +00:00
Nathan Hjelm
6d0e7a0a0e don't enable ess/alps unless cnos is available 
This commit was SVN r25743.
 2012-01-19 19:36:00 +00:00
Ralph Castain
9d556e2f17 Allow daemons to use PMI to get their name where PMI support is available while using the standard grpcomm and other capabilities. Remove the GNI code from the alps ess component as that component should only be for alps/cnos installations. 
This commit was SVN r25737.
 2012-01-18 20:56:53 +00:00
Ralph Castain
6235a355de Correctly handle co-spawning of daemons when attaching to a running job. We cannot use the general process mappers as we only want debugger daemons spawned on nodes where application procs already exist. So custom build the map for the debugger daemon job, and have the plm just launch that job without doing its usual vm-spawn step. 
This commit was SVN r25736.
 2012-01-18 00:19:49 +00:00
Nathan Hjelm
a2437feba7 removed debug message 
This commit was SVN r25722.
 2012-01-12 20:23:59 +00:00
Nathan Hjelm
5ab1674138 fixed de bruijn copyrights 
This commit was SVN r25720.
 2012-01-12 17:18:08 +00:00
Nathan Hjelm
c57f18999d added Debruijn routed component 
This commit was SVN r25717.
 2012-01-12 17:11:03 +00:00
Ralph Castain
477582abef Grrrr....fix ALL the cases where the membind warning occurs. 
This commit was SVN r25715.
 2012-01-11 23:51:18 +00:00
Ralph Castain
bf103de66c My apologies for doing this outside of the usual time restrictions, but we need to get this in so we can make progress. 
Move the ORTE-level debugger code back into orterun and out of the ORTE library to resolve symbol conflicts.

This commit was SVN r25713.
 2012-01-11 15:53:09 +00:00
Ralph Castain
167ad944c4 Surprise, surprise - hwloc treats memory binding as at the thread, not process, level. Thus, hwloc always sets the membind proc-level support flag to false, and indicates actual memory binding support via the thread-level flag. So...just to be safe, test -both- flags and issue the "no support" warning ONLY if both are false. 
This commit was SVN r25709.
 2012-01-11 01:12:57 +00:00
Shiqing Fan
e3dfc49ced make correct use of the newly updated structures in the Windows module. 
This commit was SVN r25699.
 2012-01-09 11:08:34 +00:00
Ralph Castain
840841bb8f Missed a couple 
This commit was SVN r25686.
 2011-12-29 23:30:19 +00:00
Ralph Castain
af7fb68cfb If we forward envars in rsh, then we have to be very careful about both duplicate entries and disallowed characters on the cmd line. To aid with detecting duplicates, make all cmd line options be given in their mca variant. Check anything we might add for semi-colons and protect those values with quotes. 
This commit was SVN r25685.
 2011-12-29 23:25:25 +00:00
Jeff Squyres
a4c8bb27fa Pull in the MPIR_Breakpoint symbol via a dummy function in 
debuggers_base_fns.c: orte_debugger_base_pull_mpir_breakpoint().

This commit was SVN r25660.
 2011-12-15 18:39:34 +00:00
Ralph Castain
2dd2694f25 Fix comm_spawn in oversubscribed conditions. IF oversubscription is allowed, let nodes flow into the mapper even if they are oversubscribed, constrained by the slots_max absolute ceiling. Cleanup error messages when comm_spawn fails so it correctly and succintly reports the ereror. 
This commit was SVN r25659.
 2011-12-15 18:04:48 +00:00
Ralph Castain
1adefcc176 When routing is not enabled, all routes must go direct 
This commit was SVN r25656.
 2011-12-15 15:32:09 +00:00
Ralph Castain
e683b2f9c7 Minor touchup - reset the pointer to the end of the list each time to ensure we get the nodes in correct daemon order 
This commit was SVN r25651.
 2011-12-14 22:16:52 +00:00
Ralph Castain
912abe8a6c Catch one more use-case 
This commit was SVN r25649.
 2011-12-14 21:03:19 +00:00
Ralph Castain
f531b09a8d Correctly handle -host and -hostfile options. Ensure the initial vm launch constrains itself to the union of specified hosts if those options are given. Get oversubscribe set correctly for that case. 
This commit was SVN r25648.
 2011-12-14 20:01:15 +00:00
George Bosilca
ac26f58bd7 I guess this wasn't yet ready for prime time. 
This commit was SVN r25624.
 2011-12-12 23:55:11 +00:00
Nathan Hjelm
885d5cbcf8 enable ptmalloc with using uGNI 
This commit was SVN r25621.
 2011-12-12 20:52:51 +00:00
Nathan Hjelm
be11acf727 bug fix. don't add node to allocated_nodes twice 
This commit was SVN r25619.
 2011-12-12 19:14:41 +00:00
Ralph Castain
3f1ae5d89b No longer need this include 
This commit was SVN r25606.
 2011-12-09 00:40:07 +00:00
Ralph Castain
44094cd5b3 Remove compiler warning 
This commit was SVN r25601.
 2011-12-08 16:35:41 +00:00
Samuel Gutierrez
0a922dcb3e fixes XE6 build. 
This commit was SVN r25600.
 2011-12-08 16:13:58 +00:00
Samuel Gutierrez
0588e9ba36 add Cray XK6 support to ras alps. the configuration file is a different format and is in a different place. 
This commit was SVN r25599.
 2011-12-08 14:05:02 +00:00
Ralph Castain
7180ad40ad Fix a copule of minor buglets 
This commit was SVN r25589.
 2011-12-07 21:08:35 +00:00
Ralph Castain
3e7ab1212a Since this has come up a number of times, have the rsh launcher add MCA params from the environment by default. If it finds that the cmd line is too long, error out with a message directing the user to set a param to ignore the environmental MCA params. 
This commit was SVN r25581.
 2011-12-07 01:24:36 +00:00
Ralph Castain
7510339725 Remove stale orte_vm_launch param. Add a param that allows users to specify envars to forward/set so they can do it in the MCA param file instead of only via mpirun cmd line. 
This commit was SVN r25580.
 2011-12-06 21:31:22 +00:00
Ralph Castain
15facc4ba6 Fix comm_spawn yet again...add another test 
This commit was SVN r25579.
 2011-12-06 20:15:40 +00:00
Ralph Castain
90b7f2a7bf The rest of the multi app_context fix. Remove the restriction on number of app_contexts that can have zero np specified as multiple mappers now support that use-case. Update the ranking algorithms to respect and track bookmarks. Ensure we properly set the oversubscribed flag on a per-node basis. 
This commit was SVN r25578.
 2011-12-06 17:28:29 +00:00
Ralph Castain
d9c7764e9b Remove some debug 
This commit was SVN r25575.
 2011-12-05 22:04:50 +00:00
Ralph Castain
df2f594aa8 Some cleanup associated with multiple app_contexts. Ensure nodes only get entered once into the map. Correctly handle bookmarks. Cleanup tracking of slots_inuse and correct detection of oversubscription. 
Still need to resolve the ranking issue so it starts at the bookmark, but that will come next.

This commit was SVN r25574.
 2011-12-05 22:01:08 +00:00
Abhishek Kulkarni
0b7c51fae2 Correct an invalid reference to a missing help file. 
This commit was SVN r25573.
 2011-12-05 21:29:07 +00:00
Josh Hursey
b5ac320826 * If not able to checkpoint at this time (say because we are already checkpointing or restarting) then make sure to re-set the listener so that we can checkpoint later. 
* Work around duplicate node names in the map. It should not happen normally, but if the rmaps component gets this wrong provide a work around. Ralph is working on a rmaps fix for this, so we will likely remove/comment out the fix later.

This commit was SVN r25572.
 2011-12-05 19:29:26 +00:00
Josh Hursey
cc57840b53 Fix ess/tool so that it does not segv when using the rsh PLM. Just have it use the base function directly to avoid similar problems with finalizing other components. 
This commit was SVN r25571.
 2011-12-05 15:40:46 +00:00
Ralph Castain
6cbd8fa6c9 Keep everyone in sync with new job state 
This commit was SVN r25563.
 2011-12-02 14:12:40 +00:00
Ralph Castain
07655e2945 Handle the case where the allocator "fibs" to us about the node names. In some cases (ahem...you know who you are!), the allocator will tell us a node number (e.g., "16"). However, the daemon will return a node name (e.g., "nid0016") - leaving us not recognizing its location. 
So provide a new parameter (can't have too many!) that handles this situation by stripping the prefix from the returned node name. Also do a little cleanup to ensure we cleanly exit from errors, without generating too many annoying messages.

This commit was SVN r25562.
 2011-12-02 14:10:08 +00:00
Jeff Squyres
ecf6ba910c Silence a few icc warnings and about mixing enums with other types. 
This commit was SVN r25560.
 2011-12-02 13:18:54 +00:00
Ralph Castain
641e17f26c A better way of handling fqdn allocations. Prior method was wrong as it equated "node1" with "node10", which definitely caused problems. 
Detect the addition of fqdn nodes in the allocation. If not found, then strip all incoming hostnames from daemons of any domain info when matching those names against the names in the node pool.

Leave some protection and "live" diagnostic output in place so we can continue to detect problems across all environments.

This commit was SVN r25557.
 2011-12-01 14:24:43 +00:00
Ralph Castain
512aea79bc Print the right nodename value, fix the strange case 
This commit was SVN r25556.
 2011-12-01 02:31:56 +00:00
Ralph Castain
44394c6b34 Add a little more protection 
This commit was SVN r25555.
 2011-12-01 00:30:56 +00:00
Ralph Castain
c4ea7a252a Add a little protection against badly formed node names so we don't segfault if they are encountered 
This commit was SVN r25554.
 2011-11-30 23:33:59 +00:00
Ralph Castain
fa9e99454a Don't divide by cpus-per-task - we'll deal with that at binding time. 
This commit was SVN r25552.
 2011-11-30 21:35:25 +00:00
Ralph Castain
c56acf60ca Although we never really thought about it, we made an unconscious assumption in the mapper system - we assumed that the daemons would be placed on nodes in the order that the nodes appear in the allocation. In other words, we assumed that the launch environment would map processes in node order. 
Turns out, this isn't necessarily true. The Cray, for example, launches processes in a toroidal pattern, thus causing the daemons to wind up somewhere other than what we thought. Other environments (e.g., slurm) are also capable of such behavior, depending upon the default mapping algorithm they are told to use.

Resolve this problem by making the daemon-to-node assignment in the affected environments when the daemon calls back and tells us what node it is on. Order the nodes in the mapping list so they are in daemon-vpid order as opposed to the order in which they show in the allocation. For environments that don't exhibit this mapping behavior (e.g., rsh), this won't have any impact.

Also, clean up the vm launch procedure a little bit so it more closely aligns with the state machine implementation that is coming, and remove some lingering "slave" code.

This commit was SVN r25551.
 2011-11-30 19:58:24 +00:00
George Bosilca
7a238933b6 Silence a compiler warning. 
This commit was SVN r25543.
 2011-11-29 20:53:08 +00:00
Terry Dontje
b1bb339d23 fix r25507 rationalization of rsh support by removing include of plm_base_rsh_support.h from tm module 
This commit was SVN r25519.

The following SVN revision numbers were found above:
  r25507 --> open-mpi/ompi@b475421c16
 2011-11-29 11:49:41 +00:00
Ralph Castain
0d55a3d739 Missed one spot... 
This commit was SVN r25517.
 2011-11-28 22:30:53 +00:00
Ralph Castain
237c79b6d7 Fix daemon collectives - missed the one spot where returning orte_routed_tree_t was required. Sigh. Change the routed components to return that type on the list of children when get_routing_tree is called. 
This commit was SVN r25516.
 2011-11-28 22:24:49 +00:00
Ralph Castain
89e5bd27a2 Fix copyright date 
This commit was SVN r25512.
 2011-11-28 15:54:04 +00:00
Ralph Castain
70ab8422b1 Per the internal comments, the delay between ssh invocations is not there for debugging purposes, but rather to allow for NIS authetication times. We have seen that problem in the past, so don't just do the delay when we are debugging - use the delay for the intended purpose. Also, allow for shorter than second-level delays as it doesn't always have to be so long. 
This commit was SVN r25510.
 2011-11-27 01:49:42 +00:00
Ralph Castain
b173316b74 Dont induce a delay between spawns unless specifically asked to do so 
This commit was SVN r25509.
 2011-11-26 16:50:31 +00:00
Ralph Castain
b475421c16 As promised, rationalize the rsh support. Remove rshbase and the base rsh support, centralizing all rsh support into the rsh component. Remove the "slave" launch support as that experiment is complete. Fix tree spawn and make that the default method for rsh launch, turning it "off" for qrsh as that system does not support tree spawn. 
This commit was SVN r25507.
 2011-11-26 02:33:05 +00:00
Ralph Castain
9b59d8de6f This is actually a much smaller commit than it appears at first glance - it just touches a lot of files. The --without-rte-support configuration option has never really been implemented completely. The option caused various objects not to be defined and conditionally compiled some base functions, but did nothing to prevent build of the component libraries. Unfortunately, since many of those components use objects covered by the option, it caused builds to break if those components were allowed to build. 
Brian dealt with this in the past by creating platform files and using "no-build" to block the components. This was clunky, but acceptable when only one organization was using that option. However, that number has now expanded to at least two more locations.

Accordingly, make --without-rte-support actually work by adding appropriate configury to prevent components from building when they shouldn't. While doing so, remove two frameworks (db and rmcast) that are no longer used as ORCM comes to a close (besides, they belonged in ORCM now anyway). Do some minor cleanups along the way.

This commit was SVN r25497.
 2011-11-22 21:24:35 +00:00
George Bosilca
1000af1c48 No need to abort there, returning an error trigger the 
abort at the upper level.

This commit was SVN r25494.
 2011-11-18 19:07:26 +00:00
Ralph Castain
866edf6a89 Now that George has found his problem, we no longer need the bozo check. Interesting how these platform-specific issues surface... 
This commit was SVN r25493.
 2011-11-18 17:43:14 +00:00
George Bosilca
b613c7eacb Fix the issue with the round robin mapper. When mixing 
different precisions, one should manually promote the
participants to the expected type. In this particular
example as opal_list_get_size returns an unsigned long,
the computation on the left side is translated to an
unsigned. If the hostfile contains more nodes that what
required (via the -np), this leads to a gigantic value 
for the balance, and breaks the round robin algorithm.

This commit was SVN r25492.
 2011-11-18 17:03:35 +00:00
Ralph Castain
1e5e9bde77 Add protection against a bozo case where we could end up in an infinite loop while calculating ranks 
This commit was SVN r25491.
 2011-11-18 15:35:55 +00:00
George Bosilca
61f273b987 Do not tolerate uninitialized variables. 
This commit was SVN r25489.
 2011-11-18 10:19:24 +00:00
Ralph Castain
b34acd0476 Grrr....get the correct number too! 
This commit was SVN r25478.
 2011-11-15 11:11:47 +00:00
Ralph Castain
593fc388a9 Make it a little more obvious as to which nodes are from each topology by labeling them with a letter. 
This commit was SVN r25477.
 2011-11-15 11:10:39 +00:00
Ralph Castain
6310361532 At long last, the fabled revision to the affinity system has arrived. A more detailed explanation of how this all works will be presented here: 
https://svn.open-mpi.org/trac/ompi/wiki/ProcessPlacement

The wiki page is incomplete at the moment, but I hope to complete it over the next few days. I will provide updates on the devel list. As the wiki page states, the default and most commonly used options remain unchanged (except as noted below). New, esoteric and complex options have been added, but unless you are a true masochist, you are unlikely to use many of them beyond perhaps an initial curiosity-motivated experimentation.

In a nutshell, this commit revamps the map/rank/bind procedure to take into account topology info on the compute nodes. I have, for the most part, preserved the default behaviors, with three notable exceptions:

1. I have at long last bowed my head in submission to the system admin's of managed clusters. For years, they have complained about our default of allowing users to oversubscribe nodes - i.e., to run more processes on a node than allocated slots. Accordingly, I have modified the default behavior: if you are running off of hostfile/dash-host allocated nodes, then the default is to allow oversubscription. If you are running off of RM-allocated nodes, then the default is to NOT allow oversubscription. Flags to override these behaviors are provided, so this only affects the default behavior.

2. both cpus/rank and stride have been removed. The latter was demanded by those who didn't understand the purpose behind it - and I agreed as the users who requested it are no longer using it. The former was removed temporarily pending implementation.

3. vm launch is now the sole method for starting OMPI. It was just too darned hard to maintain multiple launch procedures - maybe someday, provided someone can demonstrate a reason to do so.

As Jeff stated, it is impossible to fully test a change of this size. I have tested it on Linux and Mac, covering all the default and simple options, singletons, and comm_spawn. That said, I'm sure others will find problems, so I'll be watching MTT results until this stabilizes.

This commit was SVN r25476.
 2011-11-15 03:40:11 +00:00
Ralph Castain
c8e105bd8c Remove stale code 
This commit was SVN r25475.
 2011-11-14 23:39:23 +00:00
Ralph Castain
793f4c688f Extend capability to support heterogeneous clusters with multiple topologies 
This commit was SVN r25474.
 2011-11-13 23:23:09 +00:00
Ralph Castain
6b5e1b89cf Turn off tree spawn as it doesn't currently work - will fix shortly. Add topology collection 
This commit was SVN r25472.
 2011-11-11 23:42:36 +00:00
Ralph Castain
d008aeb531 Silence debug 
This commit was SVN r25471.
 2011-11-11 16:42:45 +00:00
George Bosilca
3d318a4c26 Put the interface of our MPIR support in sync with the document accepted by the MPI 
Forum (http://www.mpi-forum.org/docs/mpir-specification-10-11-2010.pdf).

This commit was SVN r25456.
 2011-11-08 01:24:16 +00:00
George Bosilca
85a18dab74 MPIR_partial_attach_ok is not a volatile, but a constant. 
This commit was SVN r25455.
 2011-11-08 01:00:38 +00:00
Ralph Castain
a3ce355a60 Revert r25453 and r25450 until we can fix the libevent2013 configure code - still not getting the includedir to eval correctly. 
This commit was SVN r25454.

The following SVN revision numbers were found above:
  r25450 --> open-mpi/ompi@7f7d5c4f1f
  r25453 --> open-mpi/ompi@c9fe8c32e2
 2011-11-07 16:23:44 +00:00
Samuel Gutierrez
e03bc93fb7 only use pmi grpcomm and pubsub during the direct launch case. use PMI environment variable to setup vpid in ess alps on cray xe systems. add pmi test code. 
This commit was SVN r25447.
 2011-11-06 17:28:40 +00:00
Ralph Castain
fcee46b063 Add an option for printing a diffable process map for testing mappers 
This commit was SVN r25428.
 2011-11-03 14:22:07 +00:00
Samuel Gutierrez
3fe7b3ee54 add PMI support to ess alps module. xt system guys: please yell at me if i missed something in cnos. 
This commit was SVN r25423.
 2011-11-03 04:04:32 +00:00
Samuel Gutierrez
27b9bcfafd update ess alps configuration file to include CNOS and PMI checks. some of the features committed here aren't being used, but they will be. also update orte_check_pmi.m4 to include missing call to action-if-not-found if --with-pmi is not specified or is disabled. 
This commit was SVN r25422.
 2011-11-03 02:14:47 +00:00
Jeff Squyres
7f6f7bd0eb Remove this component; twitter long ago switched to the oauth 
authentication, and no one has ever updated this component to match.
It can be revived out of history if anyone cares.

This commit was SVN r25421.
 2011-11-02 21:04:49 +00:00
Ralph Castain
b2e2d24726 As in the rsh module, report failed daemons to the errmgr for proper cleanup 
This commit was SVN r25419.
 2011-11-02 18:30:22 +00:00
Ralph Castain
3e4165fd8d Cleanup includes 
This commit was SVN r25418.
 2011-11-02 18:28:28 +00:00
Ralph Castain
b77552c45d Cleanup some include files, return a silent error in open/select as the complaining component already output a message 
This commit was SVN r25416.
 2011-11-02 17:42:06 +00:00
Ralph Castain
55b996678e Minor indentation changes 
This commit was SVN r25414.
 2011-11-02 15:56:56 +00:00
Ralph Castain
f00753881e Handle the case where mpirun -is- of the same topology as the compute nodes. 
This commit was SVN r25412.
 2011-11-01 22:26:03 +00:00