1
1
Граф коммитов

7194 Коммитов

Автор SHA1 Сообщение Дата
Nathan Hjelm
a9fb4976d5 coll/ml: more fixes
There were a couple of issues with the memory leak fixes and several more verbose
issues. This fixes those issues.

cmr=v1.8.1:ticket=trac:4473

This commit was SVN r31273.

The following Trac tickets were found above:
  Ticket 4473 --> https://svn.open-mpi.org/trac/ompi/ticket/4473
2014-03-28 18:31:28 +00:00
Nathan Hjelm
efa37c17c8 osc/base: fix one more case in ompi_osc_base_sndrcv_op
This fixes more issues identified by armci. More issues still remain and fixes are
coming for those as well.

cmr=v1.8:reviewer=jsquyres

This commit was SVN r31272.
2014-03-28 18:31:10 +00:00
Jeff Squyres
173c046617 build: add Automake-like silent/verbose macros for "ln -s ..." operations
Also, since I put some of the macros for these silent/verbose rules up
in the top-level Makefile.man-page-rules file, I renamed it to
Makefile.ompi-rules.

I've had this sitting around for a while; now seems like as good a
time as any to commit it.

This commit was SVN r31271.
2014-03-28 18:24:32 +00:00
Nathan Hjelm
ecce211403 btl/vader: create the shared memory backing file in the proc's session
directory not the job's

This bug didn't affect the correctness of the vader results just the
cleanup. This commit removes an error message about removing a non-existent
file.

cmr=v1.8:reviewer=jsquyres

This commit was SVN r31265.
2014-03-28 00:38:19 +00:00
Nathan Hjelm
bd3b550c6d coll/ml: fix leaks
Thanks to ggouaillardet for finding and fixing these issues.

Closes trac:4460

cmr=v1.8.1:reviewer=manjugv

This commit was SVN r31264.

The following Trac tickets were found above:
  Ticket 4460 --> https://svn.open-mpi.org/trac/ompi/ticket/4460
2014-03-27 23:25:31 +00:00
Nathan Hjelm
595a6e94e6 Fix typos in r31260
Also added some missing values and sentinels.

cmr=v1.8:ticket=trac:4470

This commit was SVN r31263.

The following SVN revision numbers were found above:
  r31260 --> open-mpi/ompi@69036437b7

The following Trac tickets were found above:
  Ticket 4470 --> https://svn.open-mpi.org/trac/ompi/ticket/4470
2014-03-27 22:34:28 +00:00
Jeff Squyres
24f7bd327e MPI-3: Add missing MPI_Comm_get|set_info functions
Thanks to Lisandro Dalcin for pointing out the issue.

cmr=v1.8:reviewer=hjelmn

This commit was SVN r31262.
2014-03-27 21:41:59 +00:00
Nathan Hjelm
93238b2c58 Fix typo in r31260
cmr=v1.8:ticket=trac:4470

This commit was SVN r31261.

The following SVN revision numbers were found above:
  r31260 --> open-mpi/ompi@69036437b7

The following Trac tickets were found above:
  Ticket 4470 --> https://svn.open-mpi.org/trac/ompi/ticket/4470
2014-03-27 21:04:56 +00:00
Nathan Hjelm
69036437b7 Add missing MPI_WEIGHTS_EMPTY constant
cmr=v1.8:reviewer=jsquyres

This commit was SVN r31260.
2014-03-27 20:59:52 +00:00
Nathan Hjelm
545d5daced osc: add missing MPI_ERR_RMA_SHARED error code and internal equivalent
cmr=v1.8:reviewer=jsquyres

This commit was SVN r31259.
2014-03-27 20:06:43 +00:00
Jeff Squyres
cdb396697c usnic: do not disqualify if a peer does not put usnic modex info
If ompi_modex_recv() fails with OPAL_ERR_DATA_VALUE_NOT_FOUND, it
simply means that the peer process did not put any usnic BTL modex
info -- it is not an error.  So have the usnic BTL simply ignore that
peer (vs. disqualifying itself / treating this like a real error).

Refs trac:4442.

This commit was SVN r31258.

The following Trac tickets were found above:
  Ticket 4442 --> https://svn.open-mpi.org/trac/ompi/ticket/4442
2014-03-27 19:37:07 +00:00
Nathan Hjelm
b3bb90cf2d Do not include inttypes.h directly in Open MPI. Use opal_stdint.h instead.
This commit should finish the work started for #869. Closing that ticket
with this commit.

Closes trac:869

cmr=v1.8.1:reviewer=jsquyres

This commit was SVN r31257.

The following Trac tickets were found above:
  Ticket 869 --> https://svn.open-mpi.org/trac/ompi/ticket/869
2014-03-27 17:56:00 +00:00
Vasily Filipov
8ef2e746e6 BTL/OPENIB: fix for rdma cm AF_IB case - user private data pointer points to a lib RDMA CM header and not to a "Consumer Private Data".
This commit was SVN r31247.
2014-03-27 14:04:02 +00:00
Jeff Squyres
224842e4c9 ompi_info.1: Include much more info about the --level CLI option
Add a lot more information about the --level CLI option, and the nine
levels.

Also remove some now-erroneous examples regarding --version.

cmr=v1.8:reviewer=rhc

This commit was SVN r31246.
2014-03-27 12:23:21 +00:00
Alina Sklarevich
5cbf085dc2 mtl mxm: silent a warning.
in ompi_mtl_mxm_add_procs, define the ep_index variable only
for an older version of mxm.

submitted by Alina, reviewed by Mike.
cmr=v1.8:reviewer=ompi-rm1.8

This commit was SVN r31245.
2014-03-27 08:39:51 +00:00
Nathan Hjelm
0cccb2fb59 coll/ml: reduce noise from coll/ml error messages
The error doesn't prevent the user from running so there is no reason
to display it unless the user requested it (through coll_ml_verbose).

cmr=v1.8:reviewer=jsquyres

This commit was SVN r31242.
2014-03-26 22:50:06 +00:00
Nathan Hjelm
b9da3ef462 btl/vader: actually set the correct send size in all cases
Fix a one line bug when dealing with non-contiguous sends in prepare_src. Bug was
identified by the intel test suite.

cmr=v1.8:reviewer=jsquyres

This commit was SVN r31232.
2014-03-26 21:50:07 +00:00
Nathan Hjelm
fc941edaf8 osc/base: adjust the logic in ompi_osc_base_sndrcv_op to adjust for
the case fix in ompi_osc_base_process_op in r31204.

There are two cases that needed to be handled:

 - The target is a simple datatype (contiguous block of a primitive
   type) but the origin is not. In this case we still need to pack
   the origin data but we can not rely on the convertor to do the
   unpack (see r31204).

 - Both the origin and target datatypes are simple datatypes. In this
   case we can use ompi_op_reduce to do the accumulation without having
   to pack the origin data.

cmr=v1.8:ticket=trac:4449

This commit was SVN r31231.

The following SVN revision numbers were found above:
  r31204 --> open-mpi/ompi@949abe45cd

The following Trac tickets were found above:
  Ticket 4449 --> https://svn.open-mpi.org/trac/ompi/ticket/4449
2014-03-26 17:07:29 +00:00
Nathan Hjelm
5400e21688 btl/vader: unlink the shared memory segment when finished
cmr=v1.8:reviewer=jsquyres

This commit was SVN r31230.
2014-03-26 16:25:02 +00:00
Nathan Hjelm
925af4706c osc/sm: fix bugs in window initialization and finalization
Fixed two bugs:

 - Use module->comm NOT comm to get the CID for the shared memory backing
   file. This fixes the case where there are multiple shared memory windows
   at the same time.

 - Remember to unlink the shared memory backing file.

Refs trac:4438

cmr=v1.8:reviewer=jsquyres

This commit was SVN r31227.

The following Trac tickets were found above:
  Ticket 4438 --> https://svn.open-mpi.org/trac/ompi/ticket/4438
2014-03-26 15:52:51 +00:00
Nathan Hjelm
020f011552 osc/rdma: fix bugs in lock_all and flush_all
This commit fixes two bugs:

 - We were not correctly setting the lock type in the outstanding lock
   for lock_all. This caused undefined behavior.

 - flush_all was incorrectly checking for comm size - 1 lock acks but
   comm size flush acks. This is the reverse of what was intended.

cmr=v1.8:reviewer=jsquyres

This commit was SVN r31226.
2014-03-25 23:39:43 +00:00
Jeff Squyres
5a09ee5d8c usnic: drop unknown connection checker packets without erroring out
In most cases, bad messages received by the connectivty checker are
just dropped.  However, in one specific code path, a bad packet caused
an abort.  Doh!

This commit does two things:

1. Improve verbose messages for all these cases
1. Simply drop incoming messages that cannot be identified as ACKs or PINGs

Submitted by Jeff Squyres, reviewed by Dave Goodell.

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

This commit was SVN r31225.
2014-03-25 21:05:20 +00:00
Nathan Hjelm
0d703759f6 osc/rdma: fix possible error when encountering accumulate lock contention
It is possible to get into a situation where a small accumulate operation
can not be completed because a large accumulate operation holds the lock.
In this case we may return from wait/flush/etc before the operation is
complete. To handle this case increment the expected incoming fragment
count when queuing an accumulate operation and increment the incoming
fragment count after processing the accumulate operation.

cmr=v1.8:reviewer=jsquyres

This commit was SVN r31224.
2014-03-25 21:00:43 +00:00
Nathan Hjelm
3df85b47e9 osc/rdma: quiet warning in r31197
cmr=v1.8:ticket=trac:4441

This commit was SVN r31223.

The following SVN revision numbers were found above:
  r31197 --> open-mpi/ompi@0ed44f2fdb

The following Trac tickets were found above:
  Ticket 4441 --> https://svn.open-mpi.org/trac/ompi/ticket/4441
2014-03-25 21:00:36 +00:00
Nathan Hjelm
20af8339e6 osc/base: add support for datatypes that are a contiguous combination
of the primitive datatype

In this case we can not use the convertor to run the accumulate operation
since the datatype is a more or less a primitive type.

cmr=v1.8:ticket=trac:4449

This commit was SVN r31222.

The following Trac tickets were found above:
  Ticket 4449 --> https://svn.open-mpi.org/trac/ompi/ticket/4449
2014-03-25 21:00:26 +00:00
Nathan Hjelm
d681eb4655 osc/rdma: fix warnings introduced by r31204
cmr=v1.8:ticket=trac:4449

This commit was SVN r31221.

The following SVN revision numbers were found above:
  r31204 --> open-mpi/ompi@949abe45cd

The following Trac tickets were found above:
  Ticket 4449 --> https://svn.open-mpi.org/trac/ompi/ticket/4449
2014-03-25 21:00:19 +00:00
Nathan Hjelm
949abe45cd osc: fix datatype related issues in the one-sided code
This commit fixes two issues:

 - osc/rdma: The target side of an accumulate was using the target datatype
   in the receive to the packed buffer. This was conflicting with the way
   the reduction is done into the target buffer. Changed the receive to use
   the primitive datatype.

 - osc/base: The copy table was completely wrong. Fixed the table to match
   the underlying datatypes (which are opal not ompi datatypes).

 - osc/base: There is a problem using the optimized description. Fall back
   on using the non-optimized description until we can understand what is
   going wrong.

cmr=v1.8:reviewer=jsquyres

This commit was SVN r31204.
2014-03-25 15:28:48 +00:00
Nathan Hjelm
bc55276844 osc/rdma: fix bug in the active message code that could cause erroneous
results

The code to handle completion messages did not correctly increment the
number of expected messages. This could cause wait to return before all
incoming messages are complete.

I also added a check to ensure that start returns an error if we are in
a passive access epoch.

cmr=v1.8:reviewer=jsquyres

This commit was SVN r31203.
2014-03-25 15:28:36 +00:00
Jeff Squyres
8c2b9658ce Commit upstream ROMIO fix: dbad7873926a75adbff0fd0140ae321412f70d66
ROMIO code assumes all processes will use the same ROMIO driver.  we
were not reaching the "find a common file system" logic when NFS was
enabled, everyone stat-ed the file system without errors, but some
processees found a different file system (like if some processes are
writing to NFS and others to UFS)

See discussion beginning here:
http://lists.mpich.org/pipermail/discuss/2014-March/002403.html

Tested-by: Jeff Squyres <jsquyres@cisco.com>

Submitted by Rob Lathan, reviewed by Jeff Squyres

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

This commit was SVN r31201.
2014-03-25 14:50:07 +00:00
Alina Sklarevich
947233f539 common/verbs: added a call to ompi_ibv_free_device_list.
the ompi_common_verbs_find_ports function had a call to
ompi_ibv_get_device_list, but not to ompi_ibv_free_device_list.

fixed by Alina, reviewed by Vasily/Mike.
cmr=v1.8:reviewer=ompi-rm1.8 

This commit was SVN r31200.
2014-03-25 14:41:09 +00:00
Mike Dubman
b8dddabcfb add config section for upcoming ConnectiX4 card
cmr=v1.8:reviewer=ompi-rm1.8

This commit was SVN r31199.
2014-03-25 14:27:09 +00:00
Oscar Vega-Gisbert
cc511d0efc Avoid use Status member in Comm, Message and File.
This commit was SVN r31198.
2014-03-24 22:28:30 +00:00
Nathan Hjelm
0ed44f2fdb osc/rdma: add support for datatypes with large descriptions
This commit adds large datatype description support to the osc/rdma
component. Support is provided by an additional send/recv of the datatype
description if the description does not fit in an eager buffer. The
code is designed to require minimal new code and not for speed. We
consider this code path to be a slow path.

Refs trac:1905

cmr=v1.8:reviewer=jsquyres

This commit was SVN r31197.

The following Trac tickets were found above:
  Ticket 1905 --> https://svn.open-mpi.org/trac/ompi/ticket/1905
2014-03-24 18:57:29 +00:00
Vasily Filipov
c424ad94f3 BTL/OPENIB: remove AC_RUN_IFELSE from configure and check AF_IB support by lib rdmacm during component_init.
This commit was SVN r31194.
2014-03-24 13:36:04 +00:00
Nathan Hjelm
15a8c9d7b8 coll/ml: addendum to r31189. increment the bcol_index
cmr=v1.8:ticket=trac:4436

This commit was SVN r31193.

The following SVN revision numbers were found above:
  r31189 --> open-mpi/ompi@c7d830f4b9

The following Trac tickets were found above:
  Ticket 4436 --> https://svn.open-mpi.org/trac/ompi/ticket/4436
2014-03-21 22:03:56 +00:00
Nathan Hjelm
128cfe0a39 coll/ml: cleanup tabs, indentation, and trailing whitespace in
bcol_basesmuma_bcast.c

This commit was SVN r31192.
2014-03-21 21:54:48 +00:00
Nathan Hjelm
d241f95af1 squash into previous. fix coll ml bcast
This commit was SVN r31191.
2014-03-21 21:54:41 +00:00
Nathan Hjelm
6740813c27 bcol/basesmuma: fix selection of coll/ml when only using local procs
When we are only using local ranks basesmuma needs to provide an allreduce
function for both large and small message or else the coll/ml selection
logic will fail. In the future this logic should probably be updated to
just disable allreduce in coll/ml instead of disabling coll/ml. For now
it should be correct to say the basesmuma allgather works for larger
messages.

cmr=v1.8:reviewer=manjugv

This commit was SVN r31190.
2014-03-21 21:54:35 +00:00
Nathan Hjelm
c7d830f4b9 coll/ml: improve the buffer size calculation and ensure the bcol_index in
a hierarchy actually matches a bcol that is in use.

There was a bug in one of the paths to calculate the ml buffer size. I fixed
the bug and squashed all the paths together to avoid further issues (the
result was correct in another path that calculated the same value).

Additionally, the i_hier was being used as the bcol_index. This is not
correct in a couple of cases so I added a variable to keep track of the
real bcol_index.

cmr=v1.8:reviewer=pasha

This commit was SVN r31189.
2014-03-21 21:54:28 +00:00
Nathan Hjelm
f1dd589092 coll/ml: there is no reason not to enable coll/ml when a process in not
bound.

This case is correctly handled by coll/ml so remove the check that diables
coll/ml in the not bound case.

cmr=v1.8:reviewer=manjugv

This commit was SVN r31188.
2014-03-21 21:54:21 +00:00
Nathan Hjelm
08bbdcbf61 coll/ml: fix leaks in coll/ml resources
This patch fixes two leaks:

 - Fix typo in fallback collective code that caused coll/ml to retain
   the ibcast module twice but only release it once. One of those ibcast
   saves was supposed to be bcast.

 - Do not check for module initialization in the module destructor. It
   is possible to destruct a module that is partially setup.

cmr=v1.8:reviewer=manjugv

This commit was SVN r31187.
2014-03-21 21:54:14 +00:00
Matthias Jurenz
c49a5d1e12 Changes to VT:
Disabled support for CUPTI API version > 4 (CUDA 6) due to API mismatch

This commit was SVN r31186.
2014-03-21 09:16:46 +00:00
Nathan Hjelm
20fe3804b0 Fix comment in r31146
cmr=v1.7.5:ticket=trac:4425

This commit was SVN r31148.

The following SVN revision numbers were found above:
  r31146 --> open-mpi/ompi@dca2f0027e

The following Trac tickets were found above:
  Ticket 4425 --> https://svn.open-mpi.org/trac/ompi/ticket/4425
2014-03-19 16:09:20 +00:00
Jeff Squyres
22e6417d9e Return non-SUCCESS error codes from attribute copy functions.
Without this, an attribute copy function could return non-success, but
it would not be propagated upwards.  This caused the intel
MPI_Keyval3_* tests to fail.

cmr=v1.8:reviewer=hjelmn

This commit was SVN r31147.
2014-03-19 15:45:38 +00:00
Nathan Hjelm
dca2f0027e Protect against 0-byte allocations in carte_create and cart_sub.
cmr=v1.7.5:reviewer=jsquyres

This commit was SVN r31146.
2014-03-19 15:38:12 +00:00
Jeff Squyres
7adb137409 Fix segv in MPI_Graph_create_undef_c Intel test.
When you call MPI_Graph_create with a old_comm of size N, and pass
nnodes=(N=1), then the Nth proc is supposed to get MPI_COMM_NULL out.
The code in this base function didn't properly handle the proc(s) that
are supposed to get MPI_COMM_NULL out.

cmr=v1.7.5:reviewer=hjelmn

This commit was SVN r31145.
2014-03-19 15:16:28 +00:00
Jeff Squyres
c6994adf66 Add missing show_help message.
Found via Cisco MTT (i.e., it complained of not being able to find
this show_help message).

cmr=v1.8:reviewer=dgoodell

This commit was SVN r31144.
2014-03-19 14:09:19 +00:00
Matthias Jurenz
cc3dd86121 Changes to VT:
Fixed compiler warning with the Clang compiler (no previous prototype for function '__fprintf_chk')

This commit was SVN r31143.
2014-03-19 13:39:26 +00:00
Nathan Hjelm
e764d3bebc coll/ml: really remove the asserts in the barrier setup
cmr=v1.7.5:reviewer=ompi-rm1.7

This commit was SVN r31136.
2014-03-18 22:04:50 +00:00
Nathan Hjelm
e030443d45 coll/ml: further improve the hierarchy discovery to handle the case where a
sbgp module fails to group any processes on any nodes.

cmr=v1.7.5:reviewer=manjugv

This commit was SVN r31131.
2014-03-18 21:26:24 +00:00