1
1

24 Коммитов

Автор SHA1 Сообщение Дата
Ralph Castain
894acb0aa8 configury: new OPAL_SET_MCA_PREFIX/ORTE_SET_MCA_CMD_LINE_ID macros
These two macros set the MCA prefix and MCA cmd line id,
   respectively.  Specifically, MCA parameters will be named
   PREFIX<foo> in the environment, and the cmd line will use
   -ID foo bar.

   These macros must be called during configure.ac and a value
   supplied. In the case of Open MPI, the values given are
   PREFIX=OMPI_MCA_ and ID=mca.

   Other projects (such as ORCM) will call these macros with
   their own unique values.  For example, ORCM uses PREFIX=ORCM_MCA_
   and ID=omca

   This scheme is necessary to allow running Open MPI applications under
   systems that use their own versions of ORTE and OPAL.  For example,
   when running OMPI applications under ORCM, we need the MCA params passed
   to the ORCM daemons to be separated from those recognized by the OMPI application.
2014-10-22 18:57:40 -07:00
Ralph Castain
5059077510 Sigh - revert changes to file that shouldn't have been included in the prior commit 2014-10-22 14:06:14 -07:00
Ralph Castain
2ec59acac4 Silence a slew of warnings when --enable-memchecker is given. Reviewed by Jeff 2014-10-22 13:59:08 -07:00
Ralph Castain
552c9ca5a0 George did the work and deserves all the credit for it. Ralph did the merge, and deserves whatever blame results from errors in it :-)
WHAT:    Open our low-level communication infrastructure by moving all necessary components (btl/rcache/allocator/mpool) down in OPAL

All the components required for inter-process communications are currently deeply integrated in the OMPI layer. Several groups/institutions have express interest in having a more generic communication infrastructure, without all the OMPI layer dependencies.  This communication layer should be made available at a different software level, available to all layers in the Open MPI software stack. As an example, our ORTE layer could replace the current OOB and instead use the BTL directly, gaining access to more reactive network interfaces than TCP.  Similarly, external software libraries could take advantage of our highly optimized AM (active message) communication layer for their own purpose.  UTK with support from Sandia, developped a version of Open MPI where the entire communication infrastucture has been moved down to OPAL (btl/rcache/allocator/mpool). Most of the moved components have been updated to match the new schema, with few exceptions (mainly BTLs where I have no way of compiling/testing them). Thus, the completion of this RFC is tied to being able to completing this move for all BTLs. For this we need help from the rest of the Open MPI community, especially those supporting some of the BTLs.  A non-exhaustive list of BTLs that qualify here is: mx, portals4, scif, udapl, ugni, usnic.

This commit was SVN r32317.
2014-07-26 00:47:28 +00:00
Jeff Squyres
94a5ae16b2 memory linux: show_help.h is not needed in this file
This commit was SVN r31316.
2014-04-07 15:37:16 +00:00
Jeff Squyres
d8c0c919e1 Clarify the comment: if ummunotify is present *and* if we were
compiled with ummunotify support (which is the check that r29720 just
recently added).

This commit was SVN r29961.

The following SVN revision numbers were found above:
  r29720 --> open-mpi/ompi@ae8c826527
2013-12-18 23:39:22 +00:00
Vasily Filipov
ae8c826527 "If" statement wrapping with #if MEMORY_LINUX_UMMUNOTIFY in order to prevent ptmalloc2 hooks disabling in case if OMPI was not configured with ummunotify support.
This commit was SVN r29720.
2013-11-19 07:00:21 +00:00
Nathan Hjelm
3744c5e0be Also check for /dev/mic/scif when deciding whether to enable the Linux
memory hooks.

The MIC has a /dev/scif device and the host has /dev/mic/scif. I do not
know if this device exists when no MIC is connected.

cmr=v1.7.4:ticket=trac:3733:reviewer=jsquyres

This commit was SVN r29071.

The following Trac tickets were found above:
  Ticket 3733 --> https://svn.open-mpi.org/trac/ompi/ticket/3733
2013-08-27 19:40:02 +00:00
Nathan Hjelm
6e1656279e Enable the use of the Linux memory hooks on Intel MIC.
cmr=v1.7.3:reviewer=jsquyres

This commit was SVN r29069.
2013-08-27 18:25:18 +00:00
Jeff Squyres
ad16bcd6d1 Followup from Justin Bronder: Looks like I spoke too soon. The
sandbox team has informed me that they are getting rid of SANDBOX_PID
in the future and that using SANDBOX_ON would be preferred.

This commit was SVN r28708.
2013-07-03 01:38:26 +00:00
Jeff Squyres
fea15ec34e Add memory hooks override for Gentoo sandbox v2.5, too. Thanks to
Justin Bronder for the patch.

This commit was SVN r28702.
2013-07-02 12:34:51 +00:00
Nathan Hjelm
cf377db823 MCA/base: Add new MCA variable system
Features:
 - Support for an override parameter file (openmpi-mca-param-override.conf).
   Variable values in this file can not be overridden by any file or environment
   value.
 - Support for boolean, unsigned, and unsigned long long variables.
 - Support for true/false values.
 - Support for enumerations on integer variables.
 - Support for MPIT scope, verbosity, and binding.
 - Support for command line source.
 - Support for setting variable source via the environment using
   OMPI_MCA_SOURCE_<var name>=source (either command or file:filename)
 - Cleaner API.
 - Support for variable groups (equivalent to MPIT categories).

Notes:
 - Variables must be created with a backing store (char **, int *, or bool *)
   that must live at least as long as the variable.
 - Creating a variable with the MCA_BASE_VAR_FLAG_SETTABLE enables the use of
   mca_base_var_set_value() to change the value.
 - String values are duplicated when the variable is registered. It is up to
   the caller to free the original value if necessary. The new value will be
   freed by the mca_base_var system and must not be freed by the user.
 - Variables with constant scope may not be settable.
 - Variable groups (and all associated variables) are deregistered when the
   component is closed or the component repository item is freed. This
   prevents a segmentation fault from accessing a variable after its component
   is unloaded.
 - After some discussion we decided we should remove the automatic registration
   of component priority variables. Few component actually made use of this
   feature.
 - The enumerator interface was updated to be general enough to handle
   future uses of the interface.
 - The code to generate ompi_info output has been moved into the MCA variable
   system. See mca_base_var_dump().

opal: update core and components to mca_base_var system
orte: update core and components to mca_base_var system
ompi: update core and components to mca_base_var system

This commit also modifies the rmaps framework. The following variables were
moved from ppr and lama: rmaps_base_pernode, rmaps_base_n_pernode,
rmaps_base_n_persocket. Both lama and ppr create synonyms for these variables.

This commit was SVN r28236.
2013-03-27 21:09:41 +00:00
Brian Barrett
6c3f986d79 * Fix issue with duplicate symbol for the initialize hook due to it existing in both libmpi and libopen-pal by removing the one for libopen-pal. This won't work if we eventually need registration caching in opal/orte, but I'm hoping that by that point, OFED will have gotten off its butt and properly integrated ummunotify into the verbs layer so that this code can go away.
At the same time, fix a minor issue where the init hook was being called twice, once by the libc malloc and once by our malloc by removing the call from our malloc.

This commit was SVN r28202.
2013-03-21 23:05:54 +00:00
Brian Barrett
fc2b3b8d46 Ugh. Work around an issue with memory hooks and the change from one big
library to multiple libraries that are implicitly sucked into the executable
as a dependency of libmpi.  The initialize hook isn't visible to libc on some
linux distributions when it's in libopal and libopal isn't explicity linked
into the executable.  The fix is to have a duplicate initialize hook in
libmpi as well as libopal.  *sigh*.

This commit was SVN r28164.
2013-03-11 19:22:24 +00:00
Jeff Squyres
e9ae2567f0 Based on a bug report and suggested fix from Darshan maintainer Phil
Carns, change to use access(.., F_OK) instead of stat() to check for
the presence of files.

Also remove redundant check for FAKEROOTKEY, and update all comments
to match.

This commit was SVN r27785.
2013-01-10 14:43:07 +00:00
Mike Dubman
ff1c84c53f revert previous commit
This commit was SVN r26206.
2012-03-29 14:07:13 +00:00
Mike Dubman
43a5775e8a performance fix: set alignment for openib internal buffers
This commit was SVN r26205.
2012-03-29 14:00:08 +00:00
Jeff Squyres
028f471a20 Using the right env variable name helps!
This commit was SVN r26204.
2012-03-28 17:59:21 +00:00
Jeff Squyres
8a2df3311d Fixes trac:2812: check for env. markers indicating that we're in a
fakeroot.  If so, exit out of the pre-main hook immediately (without
calling functions such as stat, which will be replaced by fakeroot to
things that are not safe to call in a pre-main environment).

This commit was SVN r26203.

The following Trac tickets were found above:
  Ticket 2812 --> https://svn.open-mpi.org/trac/ompi/ticket/2812
2012-03-28 16:41:29 +00:00
Nathan Hjelm
239e9c8740 clean up tabs
This commit was SVN r25622.
2011-12-12 20:54:14 +00:00
Nathan Hjelm
885d5cbcf8 enable ptmalloc with using uGNI
This commit was SVN r25621.
2011-12-12 20:52:51 +00:00
Sylvain Jeaugey
5fb2a2f2c9 Add a check for the ummunotify device before setting up ptmalloc2 hooks.
This commit was SVN r23882.
2010-10-11 15:05:57 +00:00
Christopher Yeoh
8a3d5d4e1c Adds missing sys/stat.h include needed for more recent versions of glibc
This commit was SVN r23440.
2010-07-20 06:31:16 +00:00
Jeff Squyres
c7c3de87f5 Add ummunotify support to Open MPI. See
http://marc.info/?l=linux-mm-commits&m=127352503417787&w=2 for more
details.

 * Remove the ptmalloc memory component; replace it with a new "linux"
   memory component.
 * The linux memory component will conditionally compile in support
   for ummunotify.  At run-time, if it has ummunotify support and
   finds run-time support for ummunotify (i.e., /dev/ummunotify), it
   uses it.  If not, it tries to use ptmalloc via the glibc memory
   hooks. 
 * Add some more API functions to the memory framework to accomodate
   the ummunotify model (i.e., poll to see if memory has "changed").
 * Add appropriate calls in the rcache to the new memory APIs to see
   if memory has changed, and to react accordingly.
 * Add a few comments in the openib BTL to indicate why we don't need
   to notify the OPAL memory framework about specific instances of
   registered memory.
 * Add dummy API calls in the solaris malloc component (since it
   doesn't have polling/"did memory change" support).

This commit was SVN r23113.
2010-05-11 21:43:19 +00:00