1
1
Граф коммитов

20504 Коммитов

Автор SHA1 Сообщение Дата
Joshua Ladd
801e2cb544 Fix error and warning messages after reverting
the mca_base_env_list to being semicolon delimited.

This commit was SVN r32179.
2014-07-09 14:46:19 +00:00
Nathan Hjelm
56ad231b7c coll/ml: temporarily disable binding check
This commit was SVN r32178.
2014-07-09 14:39:49 +00:00
Alex Mikheev
0dfd321b59 OSHMEM: fixes error handling in memheap
Memory registration is aborted on first failure.
Already registered memory is freed and
correct error code is returned.

Memory deregistration always suceeeds 

reviewed by miked
cmr=v1.8.2:reviewer=ompi-rm1.8

This commit was SVN r32175.
2014-07-09 09:26:25 +00:00
Alex Mikheev
c3e017c190 OSHMEM: refactoring of fix wrong btl/sm processing
Use exising fields of mkey struct to identify 'shared memory'
segments.

mkey.u.key is now always initialized to MAP_SEGMENT_SHM_INVALID instead
of 0

reviewed by Mike and Igor
cmr=v1.8.2:reviewer=ompi-rm1.8

This commit was SVN r32174.
2014-07-09 08:57:27 +00:00
Gilles Gouaillardet
3743c27c7a Handle error case in mca_spml_yoda_register
this commit fixes error propagation in :
 - mca_memheap_base_reg
 - mca_memheap_base_dereg

cmr=v1.8.2:reviewer=amikheev:ticket=4747

This commit was SVN r32173.

The following Trac tickets were found above:
  Ticket 4747 --> https://svn.open-mpi.org/trac/ompi/ticket/4747
2014-07-09 07:19:25 +00:00
Mike Dubman
32aeba4bdf opal: revert env_list separator to ";" from "+"
This commit was SVN r32172.
2014-07-09 05:38:51 +00:00
Joshua Ladd
057370364d Opal: Add a new MCA variable type "version_string". Also add a
new flag to ompi_info that allows a user to print all MCA variables of a specific type.  

 --type version_string

This command will print all MCA variables of type version_string.

This feature was developed by Elena Shipunova and was reviewed by Josh Ladd.

This commit was SVN r32166.
2014-07-09 01:37:23 +00:00
Jeff Squyres
cde2b67284 VERSION: remove libmpi_usempi_ignore_tkr_so_version; it isn't used anywhere
This commit was SVN r32164.
2014-07-09 01:15:25 +00:00
Joshua Ladd
30da6d3a17 Opal: add a new MCA parameter that allows the user to specify a list of environment variables. This parameter will become the standard mechanism by which environment variables are set for OMPI applications replacing the -x option.
mpirun ... -x env_foo1=val1 -x env_foo2 -x env_foo3=val3  should now be expressed as

mpirun ... -mca mca_base_env_list env_foo1=val1+env_foo2+env_foo3=val3. 

The motivation for doing this is so that a list of environment variables may be set via standard MCA mechanisms such as mca parameter files, amca lists, etc. 

This feature was developed by Elena Shipunova and was reviewed by Josh Ladd.

This commit was SVN r32163.
2014-07-09 00:38:25 +00:00
Jeff Squyres
5081f958a6 fortran: fix MPI_Win_allocate_shared and MPI_Win_shared_query
Several problems with MPI_Win_allocate_shared and MPI_Win_shared_query
were discovered in a code review.  This commit fixes them:

* Add _cptr versions of both subroutines in mpif-h, use-mpi-tkr, and
  use-mpi-ignore-tkr directories
* Fix case of PMPI weak symbols for both C implementations
* Add MPI and PMPI f08 implementations of both subroutines (there is
  no _cptr version in the mpi_f08 module)
* Fixed _f08 suffix on the f08 module of both subroutines

cmr=v1.8.2:ticket=trac:4736

This commit was SVN r32162.

The following Trac tickets were found above:
  Ticket 4736 --> https://svn.open-mpi.org/trac/ompi/ticket/4736
2014-07-09 00:10:04 +00:00
Nathan Hjelm
1eb6ac5e80 mpit: update the return code check for mca_base_var_get
mca_base_var_get now can return OPAL_ERR_NOT_FOUND if a variable no
longer exists. This commit updates the return code check to ensure
the correct MPI_T error code is returned to the user.

cmr=v1.8.2:reviewer=jsquyres

This commit was SVN r32161.
2014-07-08 21:17:47 +00:00
Nathan Hjelm
b6abe68972 osc/rdma: check for more types of window access violations
This commit adds a check to see if the target is in an access epoch. If
not we return OMPI_ERR_RMA_SYNC. This fixes test_start3 in the onesided
test suite. The cost of this extra check is 1 byte/peer for the boolean
flag indicating that the peer is in an access epoch.

I also fixed a problem where mupliple unexpected post messages are not
correctly handled.

cmr=v1.8.2:reviewer=jsquyres

This commit was SVN r32160.
2014-07-08 21:11:12 +00:00
Jeff Squyres
d63cf04d2e btl_usnic_map.c: Arrgh! Forgot to svn add this file.
cmr=v1.8.2:ticket=trac:4773

This commit was SVN r32159.

The following Trac tickets were found above:
  Ticket 4773 --> https://svn.open-mpi.org/trac/ompi/ticket/4773
2014-07-08 20:09:31 +00:00
Jeff Squyres
86f747c627 mca_base_var: use ERR_NOT_FOUND when var is inactive
After discussion with Nathan, change the ERR_VALUE_OUT_OF_BOUNDS to be
ERR_NOT_FOUND, for two reasons:

1. It's consistent with other uses of ERR_NOT_FOUND in the code.
1. In this case, we could have just looked up a variable that is
   basically a "hole" -- e.g., var indexes 0, 1, 2 are valid, and 4,
   5, and 5 are valid, but 3 is invalid (e.g., 3 was de-registered --
   remember that MPI_T explicitly does not allow re-using indexes).
   So returning ERR_OUT_OF_BOUNDS seems weird -- returning
   ERR_NOT_FOUND seems a bit more natural.

cmr=v1.8.2:ticket=trac:4587

This commit was SVN r32158.

The following Trac tickets were found above:
  Ticket 4587 --> https://svn.open-mpi.org/trac/ompi/ticket/4587
2014-07-08 20:00:18 +00:00
Jeff Squyres
1e17ab461b usnic: add btl_usnic_connectivity_map MCA param to output link information
If the btl_usnic_connectivity_map MCA param is set to a non-NULL
value, then each MPI process will output a file named
<prefix>-<hostname>.pid<pid>.job<jobid>.mcwrank<MCW rank>.txt.  Its
contents will detail which usNIC device(s) (and therefore which
link(s)) are being used to communicate with each peer MPI process.

Here is a sample output file (named
mpi005.pid26071.job1640759297.mcwrank0.txt):

{{{
device=usnic_0,interface=eth4,ip=10.10.0.5/16,mac=24:57:20:05:20:00,mtu=9000
device=usnic_1,interface=eth5,ip=10.2.0.5/16,mac=24:57:20:05:21:00,mtu=9000
device=usnic_2,interface=eth6,ip=10.3.0.5/16,mac=24:57:20:05:50:00,mtu=9000
peer=1,hostname=mpi006,device=usnic_0@peer_ip=10.10.0.6/16@peer_mac=24:57:20:06:20:00,device=usnic_1@peer_ip=10.2.0.6/16@peer_mac=24:57:20:06:21:00,device=usnic_2@peer_ip=10.3.0.6/16@peer_mac=24:57:20:06:50:00
peer=2,hostname=mpi007,device=usnic_0@peer_ip=10.10.0.7/16@peer_mac=24:57:20:07:20:00,device=usnic_1@peer_ip=10.2.0.7/16@peer_mac=24:57:20:07:21:00,device=usnic_2@peer_ip=10.3.0.7/16@peer_mac=24:57:20:07:50:00
peer=3,hostname=mpi008,device=usnic_0@peer_ip=10.10.0.8/16@peer_mac=24:57:20:08:20:00,device=usnic_1@peer_ip=10.2.0.8/16@peer_mac=24:57:20:08:21:00,device=usnic_2@peer_ip=10.3.0.8/16@peer_mac=24:57:20:08:50:00
}}}

Reviewed by Reese Faucette

cmr=v1.8.2

This commit was SVN r32156.
2014-07-08 19:14:46 +00:00
Jeff Squyres
df82810d03 opal_path_nfs.c test: skip fuse filesystems
Linux statfs(2) lies about the type of fuse filesystems (it reports
fuse.encfs as an NFS filesystem).  So just skip fuse filesystems in
this test until/if we ever care to add some kind of workaround.

Refs trac:4767

cmr=v1.8.2:reviewer=rhc

This commit was SVN r32152.

The following Trac tickets were found above:
  Ticket 4767 --> https://svn.open-mpi.org/trac/ompi/ticket/4767
2014-07-08 13:30:49 +00:00
Nathan Hjelm
309a6cf951 coll/ml: set n_resources to 0 when destructing an lmngr
Also keep track of the allocation base so we free the correct pointer
when cleaning up.

cmr=v1.8.2:reviewer=manjugv

This commit was SVN r32151.
2014-07-07 15:11:26 +00:00
Ralph Castain
1d5f8297c8 In case someone wants to use the pstat framework, we need to have the usual open/close functions that were lost in the conversion to the new framework system
This commit was SVN r32150.
2014-07-07 13:53:29 +00:00
Ralph Castain
b85471ac13 Add support for "double" to the DSS
This commit was SVN r32149.
2014-07-07 13:51:58 +00:00
Jeff Squyres
e498e20d46 openmpi.spec: several minor fixes
Thanks to Oliver Lahaye for supplying the patch.

This commit was SVN r32147.
2014-07-07 12:06:55 +00:00
Ralph Castain
5bb5b22573 When a user asks for cpus/rank > 1 and only has one slot, we need to ensure we always map at least one process when they don't tell us -np
cmr=v1.8.2:reviewer=rhc:subject=correct num_procs in corner case

This commit was SVN r32142.
2014-07-04 17:00:35 +00:00
Ralph Castain
832fa4a028 Ensure that the progress thread tracker properly cleans up the blocking event, if set. Also, use the blocking event to help wake up the progress thread for quick shutdown as some threads can be blocked in a long-running call to select.
This commit was SVN r32141.
2014-07-04 14:55:51 +00:00
Gilles Gouaillardet
bd72628a9d Cleanup : fix the cornercase with MPI_PROC_NULL persistent requests.
This commit was SVN r32140.
2014-07-04 07:20:44 +00:00
Gilles Gouaillardet
8d3bea2771 Fix the cornercase with MPI_PROC_NULL persistent requests.
This corner case is now handled in the pml so the same code
is invoked for both MPI_Start and MPI_Startall.
This also correctly report an error if MPI_Startall is invoked twice
on a MPI_PROC_NULL persistent request.

This commit was SVN r32139.
2014-07-04 04:58:52 +00:00
Edgar Gabriel
a16e4c5bf9 As discussed during the Open MPI meeting, make ompio the default parallel I/O
library on the trunk in order to expose it to more testing.

This commit was SVN r32138.
2014-07-03 20:04:58 +00:00
Ralph Castain
f6d4b4c11b As discussed at the OMPI developer's meeting, add functions to start, stop, and restart libevent-driven progress threads. Critical NOTE: if you don't have a file descriptor event defined for your progress thread, it will spin hard! Accordingly, the "start progress thread" function has a boolean parameter you can use to request that the function automatically create one for you.
This commit was SVN r32137.
2014-07-03 18:56:46 +00:00
Ralph Castain
9f97c74ba3 Silence warning
This commit was SVN r32136.
2014-07-03 17:29:04 +00:00
Jeff Squyres
e022dd30bc usnic: EHOSTUNREACH means there is no route
ibv_create_ah() can also return EHOSTUNREACH, which means that there
is no route to the peer.  Treat that as a non-fatal warning.

Reviewed by Reese Faucette.

cmr=v1.8.2:reviewer=ompi-rm1.8

This commit was SVN r32135.
2014-07-03 17:19:30 +00:00
Jeff Squyres
81edddff61 usnic: make this show_help message like the others
There's no need for the port number (since usNIC has no port numbers),
and make the wording the same as other help messages.

Reviewed by Reese Faucette.

cmr=v1.8.2:reviewer=ompi-rm1.8

This commit was SVN r32134.
2014-07-03 17:17:34 +00:00
Ralph Castain
356e7ea904 Move all collective id's into the attributes and let the job pack/unpack take care of them instead of singling them out. Add the envars just prior to forking the children instead of into the launch message itself. Remove a few #if CR as the attributes functionality can handle this condition now.
This commit was SVN r32133.
2014-07-03 15:58:13 +00:00
Ralph Castain
0a4639308e Remove a potential race condition - we'll cleanup the local children when we are all done
This commit was SVN r32132.
2014-07-03 14:13:43 +00:00
Jeff Squyres
852af8b834 ompi_mpi_abort: fix corner cases, simplify logic
I recently found a case where ompi_mpi_abort() segv's:

{{{
$ mpirun --mca btl non_existent_btl_name ...
}}}

In this case, the BML init fails because we have no paths to any
peers.  It calls ompi_mpi_abort(), but this is before ompi_comm_self
has been setup.  ompi_mpi_abort() assumes that if the comm parameter
is != NULL, it can be used.  But since we aborted so early in
MPI_INIT, that's a false assumption.

(note that this isn't happening on v1.8 because the check for
INIT/FINALIZE in ompi_mpi_abort() is a little different.  Hence: this
is a trunk issue -- at least for now)

When fixing this problem, I noticed a few other problems in ompi_mpi_abort():

* the group access was incorrect (it didn't use accessor functions)
* it wasn't clear that ORTE's ompi_rte_abort_peers() returns
  NOT_IMPLEMENTED and falls through down to ompi_rte_abort()
* the check for my proc in the communicator was a little more
  complicated than necessary
* the logic for checking for aborts early in MPI_INIT wasn't right
* some comments were stale
* the hostname output in error messages would be NULL if MPI_FINALIZE
  had been invoked
* it was possible to abort, but still exit with a 0 status

This commit fixes all of the above problems, and makes the logic a
little more straightforward.  Thanks to Ralph Castain and George
Bosilca for the assists with this patch.

This commit was SVN r32125.
2014-07-03 02:38:27 +00:00
George Bosilca
843ef1fcb0 ompi_mpi_abort had one extra argument that was never used. Clean it up.
This commit was SVN r32124.
2014-07-03 00:34:44 +00:00
George Bosilca
2883adcdf3 Remove useless variables.
This commit was SVN r32123.
2014-07-03 00:30:54 +00:00
Ralph Castain
149810f02c Per request from Jeff, slightly modify the show_help message as the precise name of the NUMA-containing packages differs based on OS and distro
cmr=v1.8.2:reviewer=jsquyres:subject=modify show_help message

This commit was SVN r32122.
2014-07-02 14:46:00 +00:00
Gilles Gouaillardet
8a2a0293fd fix sort_devs_by_distance in btl/openib
no need to #include <math.h> ...

cmr=v1.8.2:reviewer=miked:ticket=4759

This commit was SVN r32121.

The following Trac tickets were found above:
  Ticket 4759 --> https://svn.open-mpi.org/trac/ompi/ticket/4759
2014-07-02 08:08:10 +00:00
Gilles Gouaillardet
134eee1c4f fix sort_devs_by_distance in btl/openib
The distances as returned by hwloc_get_whole_distance_matrix_by_type are typ float.
This patch handle all distances as float.

cmr=v1.8.2:reviewer=miked

This commit was SVN r32120.
2014-07-02 07:56:40 +00:00
Ryan Grant
a1d312343b This commit fixes trac:4681 - ibm c_fence_lock hangs
cmr=v1.8.2:reviewer=tkordenbrock:subject=Portals4/MTL hanging fix

This commit was SVN r32113.

The following Trac tickets were found above:
  Ticket 4681 --> https://svn.open-mpi.org/trac/ompi/ticket/4681
2014-07-01 17:03:03 +00:00
Ryan Grant
5cb8cc856c Refs trac:4682 - This commit fixes c_flush test failure in the ibm test suite for Portals 4 OSC
cmr=v1.8.2:reviewer=tkordenbrock:subject=Move r32112 to v1.8.2 branch

This commit was SVN r32112.

The following SVN revisions from the original message are invalid or
inconsistent and therefore were not cross-referenced:
  r32112

The following Trac tickets were found above:
  Ticket 4682 --> https://svn.open-mpi.org/trac/ompi/ticket/4682
2014-07-01 16:26:16 +00:00
Ralph Castain
e9d69ca370 Remove stale test
This commit was SVN r32104.
2014-06-29 16:37:19 +00:00
Mike Dubman
503db51715 OSHMEM: properly handle situation when verb is unavailable
fixed by Alex, reviewed by Miked
cmr=v1.8.2:reviewer=ompi-rm1.8

This commit was SVN r32103.
2014-06-28 19:02:24 +00:00
Mike Dubman
142f7290bc BUILD: update platform file with debug caps
cmr=v1.8.2:reviewer=ompi-rm1.8

This commit was SVN r32102.
2014-06-28 18:55:31 +00:00
Mike Dubman
ce6d5b8cd7 HCOLL: make it OFF by default
fixed by miked, reviewed by Alex

cmr=v1.8.2:reviewer=ompi-rm1.8

This commit was SVN r32101.
2014-06-28 18:45:03 +00:00
Mike Dubman
247da2819f OSHMEM: fix wrong btl/sm processing and typo
fixed by Igor reviewed by Alex,Mike,Yossi

cmr=v1.8.2:reviewer=ompi-rm1.8

This commit was SVN r32100.
2014-06-28 18:40:28 +00:00
Mike Dubman
5a06f5dff5 OSHMEM: fix bss check
fixed by AlexM reviewed by Miked

cmr=v1.8.2:reviewer=ompi-rm1.8

This commit was SVN r32099.
2014-06-28 18:37:45 +00:00
Dave Goodell
c104604387 common/verbs: update usnic transport probe
RHEL 7 has shipped with kernel support for the RDMA_TRANSPORT_USNIC
enum, but ''not'' the RDMA_TRANSPORT_USNIC_UDP enum.  This means that
when you install usNIC drivers from cisco.com, the kernel will report
IBV_TRANSPORT_USNIC, even though the transport is actually using UDP.

Therefore, we have to modify the logic in common/verbs to do the
additional magic probe if the device reports either an
IBV_TRANSPORT_IWARP or IBV_TRANSPORT_USNIC (because both of those might
be lies -- do the probe to figure out the real transport).

The code changed by this patch is fairly trivial; it simply moves the
logic of the magic probe to its own short function, and then calls that
short function in both the IBV_TRANSPORT_(IWARP|USNIC) cases.  It looks
longer because several lengthy comments were also updated.

Authored-by: Jeff Squyres <jsquyres@cisco.com>
Reviewed-by: Dave Goodell <dgoodell@cisco.com>

cmr=v1.8.2:reviewer=ompi-rm1.8

This commit was SVN r32098.
2014-06-27 18:43:32 +00:00
Devendar Bureddy
228772ae81 hcoll gatherv support
cmr=v1.8.2:reviewer=jladd

This commit was SVN r32097.
2014-06-26 18:14:41 +00:00
George Bosilca
99561c5cc1 If the enable fails don't give up, but instead keep going with
the other collective modules. If we endup without some of the
collective the code will raise an error anyway.

cmr=v1.8.2:reviewer=hjelmn

This commit was SVN r32096.
2014-06-26 15:52:45 +00:00
Jeff Squyres
8e52ba423f finalize/disconnect: add explicit comment about why we use an RTE barrier
Based on extensive discussions before/at the June 2014 developer's
meeting, put a lengthy comment explaining a second reason why we
''must'' use an RTE barrier during MPI_FINALIZE and
MPI_COMM_DISCONNECT (i.e., unreliable transports).  Slightly explain
more the original reason why we do this, too (BTLs can lie/buffer a
message without actually injecting it on the network). 

This commit was SVN r32095.
2014-06-26 14:31:40 +00:00
Adrian Reber
47b118c0ae fix FT compilation
This commit was SVN r32094.
2014-06-26 03:40:07 +00:00