Ralph Castain
6039e385cd
Per request from Terry, make -host and -hostfile respect order when used as filters. In other words, if you specify -host host1,host3,host2, then we should use the hosts in that order. Previously, we used them in whatever order they were found in the allocation - all the -host did was tell us which nodes to use, not what order to use them in.
...
Relative node syntax remains supported. Also, if you specify empty nodes, but have a specific empty node called out later, we will not include that node in the empties we add. I'll provide examples in the manpage.
This commit was SVN r19402.
2008-08-26 02:56:10 +00:00
Shiqing Fan
94a2147e3d
- make sure that the system has the header files.
...
This commit was SVN r19400.
2008-08-25 13:56:10 +00:00
Jeff Squyres
7bcd285e98
Don't save the old .hgignore file
...
This commit was SVN r19399.
2008-08-25 12:55:07 +00:00
Ralph Castain
f722f134f7
Check the return code from opal_paffinity before continuing to set maffinity as it can only be done if the map_to_socket_core function succeeds.
...
This commit was SVN r19396.
2008-08-23 03:13:29 +00:00
Ralph Castain
b45029fd0e
Application processes should not open/close the IOF framework - there is nothing in that framework for application procs to do.
...
Fix a bug in iof_base_close where we destruct a thread lock prior to unlocking it.
This commit was SVN r19392.
2008-08-22 01:28:19 +00:00
Ralph Castain
4ef9d15d97
Revamp the opal mca paffinity interface. We ran into a problem when we encountered machines that had "holes" in their physical processor layout - e.g., machines that supported "hotplugging", or that had unpopulated sockets. To solve that problem, we had to clarify at the API level where we were describing physical vs logical processor info, and then translate accordingly in the underlying implementation.
...
See opal/mca/paffinity/paffinity.h for explanation as to the physical vs logical nature of the params used in the API.
Fixes trac:1435
This commit was SVN r19391.
The following Trac tickets were found above:
Ticket 1435 --> https://svn.open-mpi.org/trac/ompi/ticket/1435
2008-08-21 19:21:28 +00:00
Matthias Jurenz
7b61e02841
Fixed Coverity warnings
...
CIDs: 815,867,879,880,881,909,910,918,919,936
This commit was SVN r19386.
2008-08-21 15:01:32 +00:00
Matthias Jurenz
ea55900971
Corrected last checkin: potential buffer overflow
...
This commit was SVN r19385.
2008-08-21 15:00:44 +00:00
Matthias Jurenz
1bac115f7c
Added check for empty environment variables
...
This commit was SVN r19384.
2008-08-21 15:00:14 +00:00
Matthias Jurenz
67f1e35eb0
Fixed Coverity warnings
...
CIDs: 737,739,740,741,742,743,744,756,907,1110,1111
This commit was SVN r19376.
2008-08-20 15:50:15 +00:00
Ralph Castain
04fe1e1875
Avoid using the "access" function for security reasons as per its documentation. Also, check to ensure it is a file (and not something else) when we are looking for a file
...
Fixes trac:1272
This commit was SVN r19373.
The following Trac tickets were found above:
Ticket 1272 --> https://svn.open-mpi.org/trac/ompi/ticket/1272
2008-08-20 15:30:25 +00:00
Ralph Castain
43f8bcfe54
Update slurm plm to respect leave_session_attached
...
This commit was SVN r19370.
2008-08-19 18:30:30 +00:00
Ralph Castain
4e0f34a062
When we hit an error prior to actually launching daemons, it would be nice if orterun didn't bark about daemons failing to launch, mpirun detecting a job failed, etc.
...
Add a new job state to indicate that we never attempted to launch. Flag such a scenario and avoid hitting all the other error messages.
This commit was SVN r19366.
2008-08-19 15:19:30 +00:00
Ralph Castain
9447334749
Some comments relating to relative indexing
...
This commit was SVN r19365.
2008-08-19 15:17:40 +00:00
Ralph Castain
6d82efba21
Add relative indexing capabilities for hostfile and -host - we can now reference hosts using a relative syntax.
...
See the orte_hosts manpage for an explanation
This commit was SVN r19364.
2008-08-19 15:16:27 +00:00
Edgar Gabriel
ef2bb46e45
no need to create and free the groups. We just want to translate the ranks and we can use the internal group structures right away for that operation. Fixes an issue with groups that have not been freed previously, due to the fact that ompi_group_free was not visible here (I know, this could have been solved also by setting OMPI_DECLSPEC on ompi_group_free, but this solution should be faster.)
...
This commit was SVN r19362.
2008-08-19 13:59:58 +00:00
Edgar Gabriel
149ecb8d7d
1. debug the four new algorithms
...
2. fix a bug in the initial communicator creation of llcomm
3. fix a bug which showed up as the result of fixing issue number 2: we have
to check now whether llcomm has really be created before freeing the
according llcomm in hierarch_destruct.
This commit was SVN r19361.
2008-08-18 21:54:35 +00:00
Edgar Gabriel
7cbc4a4077
adding four different algorithms for a hierarchical bcast which try to
...
generate an overlap between the different layers. Why four versions? Because
there is right now always the trade-off between using non-blocking operations
on a layer with a trivial, linear algorithm and using the more sophisticaed
algorithms in a blocking manner.
- bcast_intra_seg used the bcast of lcomm and llcomm, similarly
to original algorithm in hierarch. However, it can segment
the message, such that we might get an overlap between the two
layers. This overlap is based on the assumption, that a process
might be done early with a bcast and can start the next one.
- bcast_intra_seg1: replaces the llcomm->bcast by isend/irecvs
to increase the overlap, keeps the lcomm->bcast however
- bcast_intra_seg2: replaced lcomm->bcast by isend/irecvs
to increase the overlap, keeps however llcomm->bcast
- bcast_intra_seg3: replaced both lcomm->bcast and llcomm->bcast
by isend/irecvs
The code is lightly tested, more testing to follow right now.
This commit was SVN r19358.
2008-08-18 16:05:44 +00:00
Matthias Jurenz
19514f4df6
Fixed Coverity warnings
...
CIDs: 865,866,896,897,974,975,976
This commit was SVN r19356.
2008-08-18 14:24:41 +00:00
Matthias Jurenz
0f9693d8af
Fixed Coverity warnings
...
CIDs: 714,781,782,825,872,917
This commit was SVN r19354.
2008-08-18 14:24:06 +00:00
Matthias Jurenz
c65e8a6882
Fixed Coverity warnings
...
CIDs: 794,882,908,934,962
This commit was SVN r19352.
2008-08-18 14:23:25 +00:00
Matthias Jurenz
63d84e2626
Fixed Coverity warnings
...
CIDs: 977
This commit was SVN r19350.
2008-08-18 14:22:48 +00:00
Matthias Jurenz
aa05fba21f
Fixed Coverity warnings
...
CIDs: 823,824,905,906
This commit was SVN r19348.
2008-08-18 14:22:15 +00:00
Matthias Jurenz
406a61f599
Fixed Coverity warnings
...
CIDs: 821,822,903,904
This commit was SVN r19346.
2008-08-18 14:21:37 +00:00
Matthias Jurenz
7364bc9691
Fixed Coverity warnings
...
CIDs: 957,1109
This commit was SVN r19344.
2008-08-18 14:20:50 +00:00
Matthias Jurenz
33434d49fb
Fixed Coverity warnings
...
CIDs: 1105
This commit was SVN r19342.
2008-08-18 14:19:30 +00:00
Matthias Jurenz
daa8119dd0
Corrected provious checkin (Coverity warning CID: 875)
...
This commit was SVN r19340.
2008-08-18 14:18:48 +00:00
Matthias Jurenz
9fc72120b7
Fixed Coverity warnings
...
CIDs: 1104
This commit was SVN r19338.
2008-08-18 14:17:39 +00:00
Matthias Jurenz
a4491e1b4c
Fixed Coverity warnings
...
CIDs: 918,919
This commit was SVN r19336.
2008-08-18 14:16:23 +00:00
Matthias Jurenz
1555a8843f
Renamed 'args' to 'argv' to avoid Coverity warnings (TAINTED_STRING)
...
CIDs: 1106,1107,1108
This commit was SVN r19334.
2008-08-18 14:15:39 +00:00
Matthias Jurenz
5081fd0da6
Fixed Coverity warnings
...
CIDs: 727
This commit was SVN r19332.
2008-08-18 14:13:45 +00:00
George Bosilca
6982e8ecbc
Don't forget to release the temporary arrays used for converting
...
the datatypes from Fortran to C.
This commit was SVN r19314.
2008-08-17 21:57:59 +00:00
George Bosilca
2499112d1c
Fix indentation.
...
This commit was SVN r19313.
2008-08-17 20:10:54 +00:00
George Bosilca
a6e3a47102
Fix typo.
...
This commit was SVN r19312.
2008-08-17 20:08:38 +00:00
George Bosilca
a41dcbbc44
Play nicely with the PML. If the data is in the pending send queue, then
...
tell the PML we're still in charge of sending it.
This commit was SVN r19311.
2008-08-17 20:07:53 +00:00
George Bosilca
f3568a271a
Replace tabs with spaces.
...
This commit was SVN r19310.
2008-08-17 20:06:48 +00:00
George Bosilca
10612bef8a
Bring back the SM pending queue, to avoid deadlocks.
...
This commit fixes trac:1378.
This commit was SVN r19309.
The following Trac tickets were found above:
Ticket 1378 --> https://svn.open-mpi.org/trac/ompi/ticket/1378
2008-08-17 19:00:50 +00:00
Ethan Mallove
cb927614c7
Fixes trac:1448 (''Need configure workaround for Sun Studio compiles on Sparc Solaris'')
...
This commit was SVN r19307.
The following Trac tickets were found above:
Ticket 1448 --> https://svn.open-mpi.org/trac/ompi/ticket/1448
2008-08-16 00:47:33 +00:00
Matthias Jurenz
c7ac98dd62
Fixed several Coverity-Warnings
...
This commit was SVN r19304.
2008-08-15 15:15:21 +00:00
Jeff Squyres
c1abc108af
Fix the make_dist_tarball script: check for the successful completion
...
of the actual command, not the $? from tee (which will always be 0).
This commit was SVN r19300.
2008-08-14 21:23:25 +00:00
Jeff Squyres
80d11dba8f
Bring in PLPA v1.2b4
...
This commit was SVN r19299.
2008-08-14 21:04:28 +00:00
Ralph Castain
a81dfa0aea
When using a platform file, allow the system to automatically pickup an associated default MCA param file for that platform. This change will first look for a file named "platform.conf" (where platform = the name of the platform you specified) in the directory where the platform file itself resides. If that isn't found, it then looks for our default mca param file name in that same location. If neither of those are found, we just use the good old standby default param file that ships with the openmpi code.
...
I tested this with both conventional and VPATH builds without problem. Please let me know if you hit an issue.
This commit was SVN r19296.
2008-08-14 20:26:17 +00:00
Ralph Castain
49745c5f40
Provide a new option that allows a user to leave an ssh session open without getting deluged by ORTE debug output. The new option is --leave-session-attached, with a corresponding MCA param of orte_leave_session_attached.
...
Theoretically, any PLM could use this - but in reality, all of them except rsh/ssh already leave the session attached anyway.
This fixes trac:656 - a REALLY old ticket
This commit was SVN r19294.
The following Trac tickets were found above:
Ticket 656 --> https://svn.open-mpi.org/trac/ompi/ticket/656
2008-08-14 18:59:01 +00:00
Jeff Squyres
bb585922fd
This is fixed a different way now; no need to be different than stock
...
PLPA.
This commit was SVN r19293.
2008-08-14 18:54:34 +00:00
Jeff Squyres
a6e0589f01
Update to PLPA v1.2b3. Sorry again for the mid-day configure change...
...
This commit was SVN r19292.
2008-08-14 14:26:26 +00:00
Jeff Squyres
5946d84023
Add some "canary" code to the debugger DLL so that we'll hopefully get
...
a compiler error if OMPI data structs that are used in the DLL are
changed in the main code base.
This commit was SVN r19289.
2008-08-14 12:57:44 +00:00
Matthias Jurenz
a62f421d2b
Bugfix (Ticket #1447 ): Removed included system headers inside 'extern "C" {}'
...
This commit was SVN r19287.
2008-08-14 12:17:24 +00:00
Brian Barrett
4a2cf9b9b9
OS X 10.5 provides a libutil in /usr/lib that is not the normal libutil.
...
Don't include it in LIBS if it doesn't actually contain the symboles we're
looking for. Darwin's won't, LInux's will, so things will work out right.
This commit was SVN r19283.
2008-08-13 20:56:06 +00:00
Jeff Squyres
a19cf02c2b
Refs trac:1435
...
Bring in a new version of PLPA (v1.2b2) with some new capabilities for
offline processors and mapping of the Nth processor/socket/core to its
corresponding Linux processor/socket/core ID.
(Sorry for the configure change in the middle of the day, folks -- I
need it to be able to continue to integrate paffinity changes for
#1435...)
This commit was SVN r19282.
The following Trac tickets were found above:
Ticket 1435 --> https://svn.open-mpi.org/trac/ompi/ticket/1435
2008-08-13 20:18:37 +00:00
Ralph Castain
dd16e4e4a6
Update process component of odls.
...
This commit was SVN r19281.
2008-08-13 20:07:59 +00:00