ports/openmpi
ports/openmpi
1
1
Форкнуть 0
Код Релизы Активность
16 805 коммитов 3 Ветки 0 Теги 130 MiB
b6ae288a59
Граф коммитов

3492 Коммитов

Автор SHA1 Сообщение Дата
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
25476c7e54 buffer is not yet initialized, so there is no reason to release it. 
This commit was SVN r25549.
 2011-11-29 23:50:18 +00:00
Jeff Squyres
6fbbfd0f7a Gah! r25545 acidentally included ''waaaay'' more stuff than it was 
supposed to.  I.e., half-baked/not complete stuff.

This commit backs out all of r25545.  Sorry folks!

This commit was SVN r25546.

The following SVN revision numbers were found above:
  r25545 --> open-mpi/ompi@7f9ae11faf
 2011-11-29 23:24:52 +00:00
Jeff Squyres
7f9ae11faf Per http://www.open-mpi.org/community/lists/users/2011/11/17862.php, 
to make MPI_IN_PLACE (and other sentinel Fortran constants) work on OS
X, we need to use the following compiler (linker) flag:

    -Wl,-commons,use_dylibs 

So if we're compiling on OS X, test to see if that flag works with the
compiler.  If so, add it to the wrapper FFLAGS and FCFLAGS (note that
per a future update, we'll only have one Fortran compiler anyway).

Fixes trac:1982.  

This commit was SVN r25545.

The following Trac tickets were found above:
  Ticket 1982 --> https://svn.open-mpi.org/trac/ompi/ticket/1982
 2011-11-29 23:05:54 +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
88d32312d6 The bind_level should be initialized to zero or weird things happens. I'm 
not yet sure how and why, but packing a uint8_t with opal_dss lead to
weird values during unpack (except if the original value is already
set to zero).

This commit was SVN r25490.
 2011-11-18 10:22:58 +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
3ea59cce96 minor cleanup to getenv_pmi.c. 
This commit was SVN r25449.
 2011-11-07 03:18:07 +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
34f0a27cb6 Initialize the locality info - at time of pmap creation, we at least know node locality 
This commit was SVN r25446.
 2011-11-06 17:06:41 +00:00
Ralph Castain
729935dffb Minor cleanups, mirroring what Jeff did to ompi_info 
This commit was SVN r25438.
 2011-11-05 00:42:49 +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
891027c10d Cleanup error reports 
This commit was SVN r25420.
 2011-11-02 18:34:19 +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
198e001554 Add another test 
This commit was SVN r25415.
 2011-11-02 15:59:16 +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
Ralph Castain
d28dd55d33 Minimize the amount of topology info returned by the daemons. Most clusters, especially at scale, use the same node topology on every node, so there is no re 
ason to return the topology from every daemon. Borrow a page from the --hetero-apps page and let users indicate that the node topology differs by adding a --
hetero-nodes option to mpirun. If the option is set, then every daemon returns topology info. If not set, then only daemon vpid=1 returns it.

We always want one daemon to return the topology as the head node is often different from the compute nodes. Having one daemon return the compute node topolo
gy allows us to detect any such difference. All compute nodes are then set to the same topology.

This commit was SVN r25408.
 2011-11-01 18:43:10 +00:00
Ralph Castain
14966e0f8f Cleanup PMI startup - if a component isn't selected, it should finalize PMI IFF it started it. Otherwise, components that aren't selected can finalize PMI when it is in use by other parts of the system. 
This commit was SVN r25407.
 2011-11-01 16:25:12 +00:00
Ralph Castain
71ed8e3cd3 Bring back the local node's binding capabilities along with its topology. Clean up indentation. 
This commit was SVN r25399.
 2011-10-30 13:20:16 +00:00
Ralph Castain
d492b20975 Bozo check for topology info 
This commit was SVN r25398.
 2011-10-30 11:49:38 +00:00
Ralph Castain
4232115a98 Ensure pruning remains within the current job/app being mapped. 
This commit was SVN r25397.
 2011-10-30 00:02:20 +00:00
Ralph Castain
648c85b41b Add a simple pattern mapper as an example of how to use the topology info to create desired mappings. Let the user specify a pattern based on resource types, and map that pattern across all available nodes as resources permit. 
Don't automatically display the topology for each node when --display-devel-map is set as it can overwhelm the reader. Use a separate flag --display-topo to get it.

This commit was SVN r25396.
 2011-10-29 15:12:45 +00:00
Ralph Castain
12a589130a Add some debug 
This commit was SVN r25395.
 2011-10-29 15:07:58 +00:00
Ralph Castain
965b04d1a5 Use the new utilities to get a topology that reflects available cpus 
This commit was SVN r25394.
 2011-10-29 15:07:36 +00:00
Ralph Castain
e50bcbf028 Add the ability to specify a topology-containing xml file to describe the simulated nodes to support mapping tests against arbitrary topologies 
This commit was SVN r25388.
 2011-10-29 02:01:11 +00:00
Ralph Castain
7fa5f82d70 Add simulator component to support testing of large scale mapping methods. Automatically sets do-not-resolve and do-not-launch, and creates however many nodes the user wants to simulate in the system. 
This commit was SVN r25386.
 2011-10-28 23:48:53 +00:00
Ralph Castain
e2eb8d5f78 Remove bad param registration - that param was already registered as an int_name in another location. 
This commit was SVN r25381.
 2011-10-28 19:14:43 +00:00
Josh Hursey
6726590b1c Remove the 'ess_node_rank' accessor from here. This caused running under 'tm' to segv at the orteds. 
It just looks like this part of the component was not updated during r25331. It was removed from the 'env' and 'slurm' environments in that patch. It looks like 'tm' was updated, but did not get this particular piece.

This commit was SVN r25380.

The following SVN revision numbers were found above:
  r25331 --> open-mpi/ompi@b44f8d4b28
 2011-10-28 17:41:35 +00:00
Josh Hursey
59ff1dbbfb Fix indentation problem that caused a segv when running without regex. 
This was introduced in r25063.

This commit was SVN r25379.

The following SVN revision numbers were found above:
  r25063 --> open-mpi/ompi@e58623cd5b
 2011-10-28 13:39:32 +00:00
Samuel Gutierrez
922e41a318 fix typo. use PMI_Initialized for init status instead of PMI_Init. 
This commit was SVN r25377.
 2011-10-27 22:27:30 +00:00
Ralph Castain
951d72692c Reverse the #if direction so we report daemon failure to the errmgr - otherwise, we just hang if a daemon fails to start. 
Reviewed with Josh.

This commit was SVN r25366.
 2011-10-25 19:09:52 +00:00
Ralph Castain
c55cba55a7 Totally trivial spelling fix 
This commit was SVN r25361.
 2011-10-24 14:06:33 +00:00
Ralph Castain
955d8e7d46 Allow apps to use pmi when launched by mpirun, if desired, without affecting daemons 
This commit was SVN r25359.
 2011-10-23 15:57:13 +00:00
Nathan Hjelm
e8af0d8589 don't use alps paffinity 
This commit was SVN r25358.
 2011-10-21 22:52:03 +00:00
Abhishek Kulkarni
46952e9008 Fix C/R functionality in trunk. Intra-node checkpointing of a job now works as expected. 
Signed-off-by: Abhishek Kulkarni <adkulkar@osl.iu.edu>

This commit was SVN r25357.
 2011-10-21 22:07:35 +00:00
Nathan Hjelm
7b1172b346 need a terminating character in the decoded string 
This commit was SVN r25355.
 2011-10-21 16:46:28 +00:00
Nathan Hjelm
cd257ac707 fixed typo in pmi grpcomm 
This commit was SVN r25353.
 2011-10-21 16:28:36 +00:00
Shiqing Fan
5711414eb7 Fix Windows build 
This commit was SVN r25351.
 2011-10-21 14:46:58 +00:00
Ralph Castain
53ef085567 Fix a minor issue seen by Jeff in specific failure pathway 
This commit was SVN r25350.
 2011-10-21 14:44:48 +00:00
Ralph Castain
3e72fccacf Cray's PMI implementation is quite different from slurm's - they extended PMI-1 by adding some, but not all, of the PMI-2 APIs. So you can't just switch to using PMI-2 functions as it isn't a complete implementation. Instead, you have to selectively figure out which ones they have in PMI-2, and use any missing ones from PMI-1. What fun. 
Modify the configure logic and the PMI components to accommodate Cray's approach. Refactor the PMI error reporting code so it resides in only one place. Cray actually decided -not- to define the PMI-2 error codes, so we have to use the PMI-1 codes instead. More fun.

This commit was SVN r25348.
 2011-10-21 04:54:38 +00:00
Nathan Hjelm
beb8d8ce32 pmi return code wtf 
This commit was SVN r25336.
 2011-10-20 17:51:24 +00:00
Ralph Castain
84713d5a84 Fix singletons again - must have been broken for a very long time, which only shows how little anyone cares about this capability. 
This commit was SVN r25332.
 2011-10-19 20:19:08 +00:00
Ralph Castain
b44f8d4b28 Complete implementation of the ess.proc_get_locality API. Up to this point, the API was only capable of telling if the specified proc was sharing a node with you. However, the returned value was capable of telling you much more detailed info - e.g., if the proc shares a socket, a cache, or numa node. We just didn't have the data to provide that detail. 
Use hwloc to obtain the cpuset for each process during mpi_init, and share that info in the modex. As it arrives, use a new opal_hwloc_base utility function to parse the value against the local proc's cpuset and determine where they overlap. Cache the value in the pmap object as it may be referenced multiple times.

Thus, the return value from orte_ess.proc_get_locality is a 16-bit bitmask that describes the resources being shared with you. This bitmask can be tested using the macros in opal/mca/paffinity/paffinity.h

Locality is available for all procs, whether launched via mpirun or directly with an external launcher such as slurm or aprun.

This commit was SVN r25331.
 2011-10-19 20:18:14 +00:00
Ralph Castain
2958f3de34 Add some clarifying comments and a small efficiency improvement 
This commit was SVN r25322.
 2011-10-18 18:30:43 +00:00
Ralph Castain
b771114086 Fix the fix :-) 
If the errmgr is going to try and hold the orted until all routes and children are gone, then the exit cmd must do the same. Otherwise, the orted exits immediately without waiting for routes to be dismantled, which is why we don't see the connections close.

Also cleanup some diagnostics and add some debug to more clearly see what's going on.

This commit was SVN r25321.
 2011-10-18 17:56:37 +00:00
Ralph Castain
ae8e556d14 Okay, once again let's fix the vpid calculator. Identified problem with prior commit (some rmaps components already place their procs in the jdata->procs array, and others don't), so account for those variations. 
This commit was SVN r25315.
 2011-10-18 15:50:11 +00:00
George Bosilca
749b63c09d Provide a generic fix for the termination issue instead of r25248. The 
termination condition is to be checked at the daemon/HNP level not down
in the routing.

This commit was SVN r25313.

The following SVN revision numbers were found above:
  r25248 --> open-mpi/ompi@b42ccc89b8
 2011-10-18 03:07:37 +00:00
George Bosilca
f28890fbb7 Revert r25302 as it break the --bynode option. 
This commit was SVN r25311.

The following SVN revision numbers were found above:
  r25302 --> open-mpi/ompi@d7a8553179
 2011-10-18 02:48:17 +00:00
Ralph Castain
2fdd9c6dea Ensure mpirun doesn't pick this component 
This commit was SVN r25307.
 2011-10-17 22:28:28 +00:00
Ralph Castain
8f0ef54130 Complete implementation of pmi support. Ensure we support both mpirun and direct launch within same configuration to avoid requiring separate builds. Add support for generic pmi, not just under slurm. Add publish/subscribe support, although slurm's pmi implementation will just return an error as it hasn't been done yet. 
This commit was SVN r25303.
 2011-10-17 20:51:22 +00:00
Ralph Castain
d7a8553179 Fix the mapping algo for computing vpids - it was borked for bynode operations when using nperxxx directives 
This commit was SVN r25302.
 2011-10-17 19:49:04 +00:00
Ralph Castain
f1a5a26ba0 Minor cleanups 
This commit was SVN r25289.
 2011-10-14 18:46:03 +00:00
Ralph Castain
89a20de474 Remove unused includes. Ensure that the error log is at least always available as we otherwise segfault when reporting errors that occur prior to opening the errmgr framework 
This commit was SVN r25288.
 2011-10-14 18:45:11 +00:00
Ralph Castain
07dbbc6513 Sorry for mid-day correction - but folks are trying to test this, and we didn't realize it was still ignored :-( 
This commit was SVN r25287.
 2011-10-14 16:19:20 +00:00
Ralph Castain
7bb294f917 Fix debug flags - thanks Terry! 
This commit was SVN r25286.
 2011-10-14 16:10:21 +00:00
Ralph Castain
054c485dcf Cleanup a race condition and an unreliable method that caused us to not properly handle procs that trapped sigterm for cleanup purposes while ORTE was trying to kill them. Thanks to Rick Payne and Ian Wells of Cisco for spending weeks chasing this down. 
Fix a termination issue that caused procs local to mpirun to not be killed if they weren't calling into the library. Thanks to Terry Dontje for spending countless hours chasing his tail on this one! :-(

This commit was SVN r25285.
 2011-10-14 15:39:54 +00:00
Ralph Castain
08fa9e1c6a Correct include path 
This commit was SVN r25282.
 2011-10-13 23:46:52 +00:00
Ralph Castain
b96ef2161d Complete the PMI support. Generalize PMI operations to support both slurm and non-slurm environments. Correct some configuration issues - we really only want the PMI integration at the individual component level. Ensure that the pmi grpcomm component doesn't get selected when launching via mpirun by setting its priority below the bad component. 
Only verified in a slurm environment as that's all I have access to...

This commit was SVN r25275.
 2011-10-12 20:59:25 +00:00
Ralph Castain
634f83fc52 Fix the routed components. All had errors, some completely broken. You cannot test 
0 == ORTE_EPOCH_CMP(target->epoch,ORTE_EPOCH_INVALID)

when epoch is not configured as this will always return true. This caused get_route to return an error in all non-binomial routed modules, and caused all components to return an error when delete_route was called.

So protect the checks with ORTE_ENABLE_EPOCH so we get the correct behavior.

This commit was SVN r25274.
 2011-10-12 20:18:57 +00:00
Ralph Castain
24a46f2acb These were missed by prior commit - need to remove lingering references to OPAL_HWLOC_HAVE_XML 
This commit was SVN r25272.
 2011-10-12 16:54:03 +00:00
George Bosilca
872d377021 Tell what the update status is. 
This commit was SVN r25259.
 2011-10-11 19:49:12 +00:00
Brian Barrett
98e98ce2c5 * opal_atomic_trylock is documented to return 0 if the lock was acquired, 
1 otherwise.  It was doing the opposite, so this patch fixes the
  return values.  All uses (all in ORTE) used the actual return values,
  not the documented values, so fix them as well.

This commit was SVN r25257.
 2011-10-11 18:43:45 +00:00
Ralph Castain
2f38ff5e54 Ensure we don't try to build this module unless pmi is specifically requested 
This commit was SVN r25252.
 2011-10-11 06:12:04 +00:00
Ralph Castain
baefdabd98 Add some debug. Now confirmed to work correctly (prior problem was with odin tcp connection, not code). 
This commit was SVN r25249.
 2011-10-11 02:15:17 +00:00
Ralph Castain
b42ccc89b8 Although this didn't solve the earlier termination problem, the code will be required once we get connection terminations properly detected. If a daemon (or HNP) is trying to terminate, then we need to check for termination conditions whenever a route is lost - when all child connections are gone, then we are free to finalize. 
This commit was SVN r25248.
 2011-10-10 21:41:49 +00:00
Ralph Castain
1aa1c2e9b4 Get the slurm pmi support working. Cannot use infiniband, of course, as the oob can't make the connection - may try other existing methods. Modex may not quite be working right yet 
as odin was having trouble making TCP connections, but at least the configure now works so things build, so save that for now

This commit was SVN r25247.
 2011-10-10 21:39:10 +00:00
Swen Boehm
08b4322a1a patched the lex files to not issue the following compiler warning: 
'yyunput' defined but not used

This commit was SVN r25246.
 2011-10-10 18:13:04 +00:00
Ralph Castain
f1a3a35fcd Cannot rely on detection of connection terminations for deciding when to exit as they don't always go away immediately. There is no info coming back anyway, so it's okay to just exit once the relay has been sent. The relay is sent via a blocking API, so just go ahead and quit. 
This commit was SVN r25245.
 2011-10-10 16:38:46 +00:00
George Bosilca
649af6c925 Enumerated mixed with another type (int) is tolerated but 
easily fixable.

This commit was SVN r25241.
 2011-10-09 03:54:52 +00:00
Terry Dontje
c6691b4122 clean up local procs when abort or abort signal happens 
This commit was SVN r25237.
 2011-10-06 19:19:55 +00:00
Nathan Hjelm
79b14fc3b1 removed licensing warning 
This commit was SVN r25235.
 2011-10-05 20:31:27 +00:00
Nathan Hjelm
34afb5a0fa first cut at general pmi check 
This commit was SVN r25234.
 2011-10-05 17:14:24 +00:00
George Bosilca
80c02647c8 Each level (OPAL/ORTE/OMPI) should only return it's own constants, 
instead of the current mismatch.

This commit was SVN r25230.
 2011-10-04 14:50:31 +00:00
George Bosilca
c6d6c9aece Remove some #if by using the correct macro (aka. ORTE_EPOCH_CMP). 
This commit was SVN r25229.
 2011-10-04 14:42:40 +00:00
Samuel Gutierrez
25cbf79592 modifications to ras alps. this commit allows users to mpirun without having to set id environment variables (BASIL_RESERVATION_ID, OMPI_ALPS_RESID). note, however, that we preserved the old behavior. if an id environment variable is set, it will be obeyed and our new code path is essentially bypassed. if we missed something, please yell at us. with this commit, the use of ras-alps-command.sh is no longer needed... at least that is our hope. 
This commit was SVN r25181.
 2011-09-26 21:31:08 +00:00
Ralph Castain
8347385630 Fix the radix routed component. 
This commit was SVN r25175.
 2011-09-22 09:32:53 +00:00
Jeff Squyres
ecd603256a * Rename opal_hwloc_components to opal_hwloc_base_components 
* Fix some comments

This commit was SVN r25150.
 2011-09-17 11:54:36 +00:00
Ralph Castain
1cd7b02df3 Add a set of default errmgr components that support solely the default "everything dies on error" behavior. Set their priority to be selected by default, but provide params to adjust those priorities to allow other component selection. 
This commit was SVN r25139.
 2011-09-13 22:03:45 +00:00
Ralph Castain
3c4f04f4d9 Ensure opal_hwloc_topology is NULL after being destroyed 
This commit was SVN r25138.
 2011-09-13 19:21:10 +00:00
Nathan Hjelm
079ccdf8b1 fix debugger co-location launching 
This commit was SVN r25136.
 2011-09-13 15:08:03 +00:00
Ralph Castain
ca7638553f Remove stale code 
This commit was SVN r25133.
 2011-09-12 23:00:41 +00:00
Ralph Castain
556a05566e Silence warning 
This commit was SVN r25130.
 2011-09-12 16:21:51 +00:00
Shiqing Fan
0aea775837 Set the compiler flags in a better way. 
This commit was SVN r25125.
 2011-09-12 08:24:27 +00:00
Ralph Castain
92c7372e20 Per the RFC from Jeff, move hwloc from opal/mca/common to its own static framework ala libevent. Have ORTE daemons collect the topology info at startup and, if --enable-hwloc-xml is set, send that info back to the HNP for later use. The HNP only retains unique topology "templates" to reduce memory footprint. Have the daemon include the local topology info in the nidmap buffer sent to each app so the apps don't all hammer the local system to discover it for themselves. 
Remove the sysinfo framework as hwloc replaces that functionality.

This commit was SVN r25124.
 2011-09-11 19:02:24 +00:00
Ralph Castain
2091e39bee Record the file descriptor on the read event when building optimized 
This commit was SVN r25123.
 2011-09-11 18:57:14 +00:00
Rainer Keller
9d5afc58c6 - Fix breakage of the epoch changes with PGI: 
Don't juse include pre-processor macros between two strins ("s1" #if 0 ... "s2")...
   Rather print out the epoch as 0 always...

This commit was SVN r25110.
 2011-08-31 08:40:31 +00:00
Wesley Bland
f8740e5478 Correct a typo reported by Pasha. 
This commit was SVN r25109.
 2011-08-30 18:44:52 +00:00
Ralph Castain
03ddf8520b Resolve not-used warnings 
This commit was SVN r25101.
 2011-08-27 14:27:15 +00:00
Ralph Castain
56ebfa23cc ORTE configure options belong in orte/config, not opal. 
This commit was SVN r25100.
 2011-08-27 14:23:49 +00:00
Wesley Bland
f542ecd578 Fix a couple of problems with the resil code not compiling. 
This commit was SVN r25099.
 2011-08-27 03:21:00 +00:00
George Bosilca
a4245b8d63 Remove some warnings related to the resilience patch. 
This commit was SVN r25097.
 2011-08-27 00:15:34 +00:00
George Bosilca
67ec5a0556 While doing cleanup remove pending warnings. 
This commit was SVN r25095.
 2011-08-26 23:38:06 +00:00
George Bosilca
fc1184c41f Remove a warnings introduced by the epoch commit. 
This commit was SVN r25094.
 2011-08-26 23:36:52 +00:00
Wesley Bland
4e7ff0bd5e By popular demand the epoch code is now disabled by default. 
To enable the epochs and the resilient orte code, use the configure flag:

--enable-resilient-orte

This will define both:

ORTE_ENABLE_EPOCH
ORTE_RESIL_ORTE

This commit was SVN r25093.
 2011-08-26 22:16:14 +00:00
Ralph Castain
1c08a4006c Refactor some code to remove a few API handles from errmgr. Reviewed/tested by Wes. 
This commit was SVN r25064.
 2011-08-18 16:24:45 +00:00
Ralph Castain
e58623cd5b Bring alps back to full operations by correctly computing daemon names. Unfortunately, alps doesn't assign cnos rank in node-based order - i.e., cnos rank=0 isn't necessarily on the first node of the execution. So adjust when using static ports. 
Add some debug to nidmap

Ensure that the HNP's node name is not included in the regex when launching via rshbase as that node is automatically included in the daemon map.

This commit was SVN r25063.
 2011-08-18 14:59:18 +00:00
Wesley Bland
a2a20c3766 I believe this should fix the race condition that Terry is seeing in the MTT 
tests. It appears that nothing in the errmgr was using the mutexes to protect
the odls child list.

This commit was SVN r25062.
 2011-08-18 14:52:30 +00:00
Shiqing Fan
6d0ab9bd6c One library was missing for linking orterun on Windows. 
This commit was SVN r25057.
 2011-08-18 09:33:41 +00:00
Ralph Castain
23f47295a8 Add even more debug 
This commit was SVN r25053.
 2011-08-16 16:41:33 +00:00
Ralph Castain
d624d43f69 Add more debug 
This commit was SVN r25052.
 2011-08-16 15:47:37 +00:00
Ralph Castain
3d96497581 Add debug 
This commit was SVN r25050.
 2011-08-16 12:22:05 +00:00
Shiqing Fan
7292ee2387 One .windows file is missing in the tarball. 
This commit was SVN r25049.
 2011-08-15 10:21:25 +00:00
Shiqing Fan
3af7c9f7bb Complete the MinGW build support on Windows. 
This commit was SVN r25048.
 2011-08-15 09:47:23 +00:00
Shiqing Fan
627f1dd351 Correct several export declarations. 
This commit was SVN r25047.
 2011-08-15 09:45:51 +00:00
Ralph Castain
ca3d29a1e6 Extend regex support to a bigger audience 
This commit was SVN r25046.
 2011-08-12 21:02:48 +00:00
Ralph Castain
ea4e2c2db4 Unused variables 
This commit was SVN r25045.
 2011-08-12 21:02:09 +00:00
Jeff Squyres
1cbfb53801 r24976 wasn't quite right -- you now actually get a warning if you 
specify btl_tcp_if_include because btl_tcp_if_exclude is defaulted to
the loopback devices.

This commit does a few things:

 * Introduce a new OPAL MCA base function:
   mca_base_param_check_exclusive_string().  It checks to see that the
   ''user'' does not set two MCA parameters that are mutually
   exclusive by checking the source of those MCS param values.
 * Use the above function in many BTLs (and the OOB TCP) to ensure
   that <foo>_if_include and <foo>_if_exclude are not both specified
   ''by the user''.
 * Re-arrange many of these BTLs to move their MCA registration code
   into a separate component_register() function (vs. the
   component_open() function).

This code has been nominally reviewed and checked by Ralph, George,
Terry, and Shiqing.

This commit was SVN r25043.

The following SVN revision numbers were found above:
  r24976 --> open-mpi/ompi@8f4ac54336
 2011-08-10 17:24:36 +00:00
Ralph Castain
b360c98afd Per request from Pasha, revert r25004 - but modified a touch to reflect fact that opal_argv_append copies the provided string, so we don't need to print it and then free it. 
This commit was SVN r25037.

The following SVN revision numbers were found above:
  r25004 --> open-mpi/ompi@2418831bea
 2011-08-09 22:42:27 +00:00
Nathan Hjelm
aa3d302a05 use persistent rml_recv in iof 
This commit was SVN r25035.
 2011-08-09 21:30:12 +00:00
Ralph Castain
f1951e7ccd If we are abnormally terminating, then don't wait for orteds to report back. Send them a "halt_vm" command, which instructs them to kill their local procs and immediately terminate, doing their best to cleanup on the way out. 
Also do a little cleanup on debug output in rshbase.

This commit was SVN r25033.
 2011-08-09 17:42:19 +00:00
Wesley Bland
67feeb6aca Move the errmgr code back. This shouldn't cause the svn problems that I 
apparently caused last time. Sorry about that. This one will just be a big
changelog.  

This commit was SVN r25016.
 2011-08-08 16:01:08 +00:00
Wesley Bland
09274cd047 Make sure that the epoch is initialized everywhere so we don't get weird output 
during valgrind. This shouldn't have caused any problems with any actual
execution. Just extra warnings in valgrind.

This commit was SVN r25015.
 2011-08-08 15:11:55 +00:00
Ralph Castain
8014e3429e Don't double-count procs as they are launched 
This commit was SVN r25011.
 2011-08-08 06:05:23 +00:00
Ralph Castain
7b9f958dcf Add some missing error strings. Update test to show silent errors 
This commit was SVN r25010.
 2011-08-08 04:21:02 +00:00
Ralph Castain
4083dc617f Fix computation of number of required files and file descriptors - it only depends on the total number of local procs, not on the number of procs in the entire job! 
This commit was SVN r25008.
 2011-08-08 04:09:40 +00:00
Ralph Castain
590ac70e88 Add a simple test program for error string output 
This commit was SVN r25007.
 2011-08-07 21:32:25 +00:00
Ralph Castain
8b3c562b84 Adjust verbosity levels to make it easier to debug at scale 
This commit was SVN r25006.
 2011-08-07 21:14:21 +00:00
Ralph Castain
2418831bea Pass the nodelist to the aprun command even when using all nodes 
This commit was SVN r25004.
 2011-08-06 04:19:41 +00:00
Ralph Castain
bd8e43a2de Correct debug output so it doesn't falsely report the module 
This commit was SVN r25003.
 2011-08-05 20:30:34 +00:00
Ralph Castain
d603c79ab4 Fix the FAILED_TO_START scenario so orted doesn't segfault 
This commit was SVN r25002.
 2011-08-05 20:29:50 +00:00
Ralph Castain
c86bfb4e90 Need to copy the string 
This commit was SVN r25001.
 2011-08-05 19:03:28 +00:00
Ralph Castain
7b307d5bf0 Cleanup handling of all-numerical node names 
This commit was SVN r25000.
 2011-08-05 14:59:14 +00:00
Ralph Castain
157bad5435 If we can't compress the name, that's fine - but still have to move to next posn 
This commit was SVN r24999.
 2011-08-05 14:43:36 +00:00
Ralph Castain
3199663613 Correctly handle the case of mixes of character-based names and all-number names 
This commit was SVN r24998.
 2011-08-05 14:37:36 +00:00
Ralph Castain
066022126e Sort the nodes to be in numerically increasing order so the regex has a chance of working right. 
This commit was SVN r24993.
 2011-08-05 03:37:13 +00:00
Ralph Castain
5a634caad9 Cleanly handle the case where the node "name" is just a number, and avoid the N-N output when the number is not part of a sequence. 
This commit was SVN r24992.
 2011-08-05 03:36:30 +00:00
Jeff Squyres
294e1f50cd Remove compiler warning about nested comment 
This commit was SVN r24984.
 2011-08-03 18:30:56 +00:00
Wesley Bland
87a96da99c Should fix some of the shutdown woes of the errmgr. 
Correctly checks that the orted's job is completed.
Correctly tests to make sure that there is shutdown going on (doesn't rely on orte_orteds_term_ordered).
Adds a patch from Ralph to correctdly check the status of processes.

This commit was SVN r24962.
 2011-08-01 14:00:41 +00:00
Ralph Castain
42b125ef35 Move the debug so it more accurately reports 
This commit was SVN r24961.
 2011-07-29 20:48:46 +00:00
Ralph Castain
70bca4691f Add a new "sensor" module that supports fault tolerance tests - randomly kills local procs and/or the daemon itself 
This commit was SVN r24960.
 2011-07-29 20:48:22 +00:00
Wesley Bland
5fde3e0e00 Move the resilient orte errmgr code into a seperate errmgr for now while it's 
still unstable. Reverted errmgr modules back to the original errmgr (with the
updates since the resilient code was brought into the trunk).

This commit was SVN r24958.
 2011-07-28 21:24:34 +00:00
Ralph Castain
6c879f87fb Add a new param "orte_remote_tmpdir_base" for those situations where the compute nodes require a different session directory head than the head node. 
This commit was SVN r24956.
 2011-07-27 19:37:17 +00:00
Ralph Castain
decab98fb2 Do a little better job of catching up on missed mcast messages, and provide a way out of scenarios where catch-up is impossible. 
This commit was SVN r24955.
 2011-07-27 14:58:30 +00:00
Ralph Castain
c3bc33b3fb Don't be so restrictive - accept "slots" as well as "slot" in rank file 
This commit was SVN r24954.
 2011-07-27 00:45:30 +00:00
Wesley Bland
b972fd84e1 No longer sends extra FAILED_NOTIFICATION messages in the non-failure case. 
Should reduce finalize complexity and avoid a race condition that has been
detected by a few users.

This commit was SVN r24952.
 2011-07-26 20:47:44 +00:00
Ralph Castain
715f871605 Ignore the daemon job when reporting parseable output 
This commit was SVN r24944.
 2011-07-25 20:44:08 +00:00
Ralph Castain
db193555c2 Use non-blocking sends for recovering from lost multicast messages 
This commit was SVN r24943.
 2011-07-25 18:49:47 +00:00
Ralph Castain
199804fc35 complete implementation of parseable output 
This commit was SVN r24929.
 2011-07-23 22:23:24 +00:00
Ralph Castain
ffe6f5f40e Fix map pack/unpack so they match 
This commit was SVN r24928.
 2011-07-23 22:23:05 +00:00
Ralph Castain
00647fa342 Update orte-ps to add parseable output - not fully tested because I couldn't get other parts of the system to work. 
This commit was SVN r24927.
 2011-07-23 20:20:31 +00:00
Ralph Castain
869024f1c6 You have to initialize th daemon param -before- using it to get epoch!! 
This commit was SVN r24926.
 2011-07-23 20:19:43 +00:00
Ralph Castain
361bcef253 Close multicast before rml 
This commit was SVN r24925.
 2011-07-23 20:19:15 +00:00
Shiqing Fan
cc4403a863 Remove two unused windows files. 
This commit was SVN r24913.
 2011-07-21 12:53:32 +00:00
Brian Barrett
3bd66a5932 * Remove unused Portals3.3 reference implementation support 
This commit was SVN r24906.
 2011-07-20 23:30:29 +00:00
Eugene Loh
921852e1e5 Clean up the computations of num_procs_alive. Do some code 
refactoring to improve readability and to compute num_procs_alive
correctly and to remove the use of loop iteration variables for
two loops nested one inside another (causing MPI_Comm_spawn_multiple
to fail).

This commit was SVN r24903.
 2011-07-14 20:10:48 +00:00
Ralph Castain
8853e0e80a Fix regular expression analyzer for slurmd - use a slurm-specific version 
Fix multi-node routing for daemon startup when static ports are not set

This commit was SVN r24898.
 2011-07-13 22:49:56 +00:00
Ralph Castain
8d1b31b887 Don't know how we got away with this for so long, but we really shouldn't be referencing pointer array objects directly. 
Also, fix an error in mpirx debugger module - the pointer array object is the pointer to the object itself, not the object "super" like in an opal_list.

This commit was SVN r24894.
 2011-07-13 20:11:14 +00:00
Ralph Castain
1405bacd85 Ensure we dont segfault if we report an error 
This commit was SVN r24890.
 2011-07-13 15:00:22 +00:00
Jeff Squyres
3893a5a1de Fix compile error introduced in r24888. 
This commit was SVN r24889.

The following SVN revision numbers were found above:
  r24888 --> open-mpi/ompi@e5253647ea
 2011-07-13 14:18:00 +00:00
Shiqing Fan
e5253647ea Fix a type cast. 
This commit was SVN r24888.
 2011-07-13 09:00:17 +00:00
Ralph Castain
1ad110d2e9 After a nice, calm, rational discussion between Brian, Jeff, and myself, we decided to revert r24864 and r24862 to restore the reference counters in opal_init/finalize. The rationale was that we should instead change orte_init/finalize to also use reference counters to support multi-embedded libraries. Jeff and Brian will discuss proposing a similar change to mpi_init/finalize to the MPI Forum so that all three libraries will behave in similar manners. 
It was agreed that opal_init_util had wound up being used in unintended ways, which raised the problem of getting reference counts to work right. However, fixing it would involve more pain than it was worth - and so long as the other layers are made to behave similarly, I have no preference either way.

Complete implementation will follow - for now, this just reverts the prior changes.

This commit was SVN r24886.

The following SVN revision numbers were found above:
  r24862 --> open-mpi/ompi@aa92e0c4eb
  r24864 --> open-mpi/ompi@a5062385c2
 2011-07-12 17:07:41 +00:00
Nathan Hjelm
3f4e5d7dd6 add missing thread lock/unlock around condition_broadcast 
This commit was SVN r24885.
 2011-07-12 15:43:56 +00:00
Nathan Hjelm
c3ec2e2614 fix a potential race condition in rml 
This commit was SVN r24884.
 2011-07-12 15:43:12 +00:00
Abhishek Kulkarni
6bf02d1344 Fixes (after the new ORTE resiliency layer was merged) to make the trunk build with C/R flags turned on. 
This commit was SVN r24872.
 2011-07-10 23:36:26 +00:00
Ralph Castain
a5062385c2 Fix singletons 
This commit was SVN r24864.
 2011-07-08 14:38:33 +00:00
Jeff Squyres
3affb8403e Remove extra output 
This commit was SVN r24863.
 2011-07-08 13:01:30 +00:00
Ralph Castain
aa92e0c4eb Replace a useless counter with a boolean check to see if we have already passed thru opal_finalize so we don't call finalize, and then don't pass thru it (as was happening on several tools) 
This commit was SVN r24862.
 2011-07-08 06:43:19 +00:00
Ralph Castain
05f4926bfe Remove some remaining cruft re regular expressions - caused the trunk to fail if regex wasn't being used 
This commit was SVN r24861.
 2011-07-08 06:42:12 +00:00
Ralph Castain
1ee7c39982 Fix some major bit-rot on scalable launch. If static ports are provided, then daemons can connect back to the HNP via the routed connection tree instead of doing so directly. In order to do that at scale, the node list must be passed as a regular expression - otherwise, the orted command line gets too long. 
Over the course of time, usage of static ports got corrupted in several places, the "parent" info got incorrectly reset, etc. So correct all that and get the regex-based wireup going again.

Also, don't pass node lists if static ports aren't enabled - they are of no value to the orted and just create the possibility of overly-long cmd lines.

This commit was SVN r24860.
 2011-07-07 18:54:30 +00:00
Ralph Castain
6496b2f845 Ensure we terminate properly on non-zero exit status 
This commit was SVN r24859.
 2011-07-07 14:33:49 +00:00
Wesley Bland
0628963506 Fix a return code when a process isn't found. 
This commit was SVN r24845.
 2011-06-30 15:22:54 +00:00
Brian Barrett
e52fef28ca Do something rational for the disable full support case 
This commit was SVN r24844.
 2011-06-30 14:48:19 +00:00
Ralph Castain
8ac35a8496 Fully enable the monitoring of memory usage and automatic termination of memory hogs when limits are reached. Improve the efficiency of the sensor system so we don't multiply sample the resource usage if multiple modules are active. Ensure we output the proc error summary when we abnormally terminate. 
This commit was SVN r24843.
 2011-06-30 14:11:56 +00:00
Ralph Castain
c449871ade Add an mca param to set the "fork agent" - i.e., a program to be run when forking off a process (e.g., valgrind). While you could specify this by "mpirun -n N fork_agent ./my_app", not everyone launches procs with ORTE from mpirun. 
Provide the ability to store recent stat histories using the ring_buffer class

This commit was SVN r24842.
 2011-06-30 03:12:38 +00:00
Ralph Castain
2e1fa3e08e Don't error out if the recv.cancel comes back not found as this is just a race condition 
This commit was SVN r24841.
 2011-06-30 01:19:50 +00:00
Ralph Castain
418229c71c Define a new error constant 
This commit was SVN r24833.
 2011-06-28 19:47:16 +00:00
Wesley Bland
84be81df95 Standardize the initialization of the EPOCH's. 
Everyone will be starting at MIN anyway (until we implement restart of course)
so there's no reason to set the epoch to INVALID and then immediately reset them
to MIN. This way there's less room to make mistakes later.

This commit was SVN r24829.
 2011-06-28 14:20:33 +00:00
Ralph Castain
c203eee223 Since process names now have three fields, be sure to initialize all three of them 
This commit was SVN r24828.
 2011-06-27 20:50:08 +00:00
Ralph Castain
d316701d3c Remove unnecessary mcast channel 
This commit was SVN r24816.
 2011-06-23 20:44:22 +00:00
Wesley Bland
e1ba09ad51 Add a resilience to ORTE. Allows the runtime to continue after a process (or 
ORTED) failure. Note that more work will be necessary to allow the MPI layer to
take advantage of this.

Per RFC:
http://www.open-mpi.org/community/lists/devel/2011/06/9299.php

This commit was SVN r24815.
 2011-06-23 20:38:02 +00:00