Multiple conduits can exist at the same time, and can even point to the same base transport. Each conduit can have its own characteristics (e.g., flow control) based on the info keys provided to the "open_conduit" call. For ease during the transition period, the "legacy" RML interfaces remain as wrappers over the new conduit-based APIs using a default conduit opened during orte_init - this default conduit is tied to the OOB framework so that current behaviors are preserved. Once the transition has been completed, a one-time cleanup will be done to update all RML calls to the new APIs and the "legacy" interfaces will be deleted.
While we are at it: Remove oob/usock component to eliminate the TMPDIR length problem - get all working, including oob_stress
* In open-mpi/ompi@f6f24a4f67 I missed
updating the library references for the wrapper compilers.
* Fixes the CXX wrapper compiler and CXX library is renamed as needed.
* Fixes the Java wrapper compiler and the Java library is renamed as needed.
Update the script to auto-generate the entire AUTHORS file from two
sources:
1. The existing AUTHORS file
2. The output from "git log --format=tformat:=tformat:'%aN <%aE>'"
Merge these two together (which will preserve organization
affiliations) and warn in two cases:
1. If a person has no organization affiliation
1. If the same email address appears for more than one person
Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
The Open MPI configure script has long-since only paid attention to
FCFLAGS. Indeed, it will warn if you set FFLAGS or F77FLAGS. So
remove them from the spec file.
Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
Add the following to zsh shell completion:
* --get-stack-traces
* --report-state-upon-timeout
* --timeout
Signed-off-by: Jeff Squyres <jsquyres@cisco.com>
This commit adds a framework to abstract runtime code patching.
Components in the new framework can provide functions for either
patching a named function or a function pointer. The later
functionality is not being used but may provide a way to allow memory
hooks when dlopen functionality is disabled.
This commit adds two different flavors of code patching. The first is
provided by the overwrite component. This component overwrites the
first several instructions of the target function with code to jump to
the provided hook function. The hook is expected to provide the full
functionality of the hooked function.
The linux patcher component is based on the memory hooks in ucx. It
only works on linux and operates by overwriting function pointers in
the symbol table. In this case the hook is free to call the original
function using the function pointer returned by dlsym.
Both components restore the original functions when the patcher
framework closes.
Changes had to be made to support Power/PowerPC with the Linux
dynamic loader patcher. Some of the changes:
- Move code necessary for powerpc/power support to the patcher
base. The code is needed by both the overwrite and linux
components.
- Move patch structure down to base and move the patch list to
mca_patcher_base_module_t. The structure has been modified to
include a function pointer to the function that will unapply the
patch. This allows the mixing of multiple different types of
patches in the patch_list.
- Update linux patching code to keep track of the matching between
got entry and original (unpatched) address. This allows us to
completely clean up the patch on finalize.
All patchers keep track of the changes they made so that they can be
reversed when the patcher framework is closed.
At this time there are bugs in the Linux dynamic loader patcher so
its priority is lower than the overwrite patcher.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
All BTL-only operations (basically all data movements
with the exception of the matching operation) can now
be handled for the TCP BTL by a progress thread.
This script is useful to measure times from launching ompi
application to different internal points. A user can easy add
it`s test basing on existing tests.
See readme information inside the script.
Fixes to lanl platform files to pick up lustre header
files, etc. for romio and ompi i/o.
Fixes#1033
Thanks to Jerome Vienne for spotting this.
Signed-off-by: Howard Pritchard <howardp@lanl.gov>
Do not need to test with -f. If directories ever show up in git
ls-files (unlikely) their mime type is application/x-directory which
will fail the test ${file::4} == text check.
Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov>
Simple perl script for processing owner files into markdown
tables for the open mpi wiki. Get fancy with later versions.
Signed-off-by: Howard Pritchard <howardp@lanl.gov>
The previous safe_system() is quite thorough, but much more than we
really need in this script. Use a far simpler version that is
significantly easier to maintain.
Also log some of the critical steps that a human can examine the
output upon a failure (e.g., when the failure happens when launched
via cron).
Finally, set the version number to not include "openmpi-", because
Coverity has a limited-width display of the version number.
Move the openmpi-nightly-coverity.pl script into the directory where
all the other build server scripts live.
Leave the coverity-model.c file in the coverity dir, because it's
specific to coverity. Other items can be added into the
coverity-model.c, if helpful (and then we can re-submit that model
file).
Ensure to build support for:
* usnic
* PSM
* MXM
* OSHMEM
* Fortran (MPI and OSHMEM)
* Java (MPI and OSHMEM)
So that the OMPI code for all of these networks can be analyzed by
Coverity.
build moar stuff -- squashme
This is a first cut at scripts to run the Coverity Scan tool and
upload the results (Coverity used to do this for us automatically; now
we need to do it ourselves).
We recognize that this means other users of OPAL will need to "wrap" the opal_process_name_t if they desire to abstract it in some fashion. This is regrettable, and we are looking at possible alternatives that might mitigate that requirement. Meantime, however, we have to put the needs of the OMPI community first, and are taking this step to restore hetero and SPARC support.
Several updates, including:
* Remove -single dash options
* Don't chmod the whole tree; just chmod the files we're trying to remove
* No more support for SVN or HG; 100% git
* Strengthen the dirty repo checks
* Use git describe for the repo version
* Set tarball_version to "" (i.e., empty) in VERSION
Removed a redundant copy of the scripts running on the build server
and moved the remaining copy out to a top-level directory in contrib
(i.e., contrib/build-server vs. contrib/dist/build-server, where I
never could remember where to find them).
This is a first cut at updating various infrastructure for git. There
will definitely be more commits; some of the scripts require
committed/pushed code (e.g., the various make-tarball scripts). So
it's not possible to know if we got it right without committing/pushing.
We don't use this script any more (we use gitdub now), but it took a
long time to figure this out. So I'm putting this script in git just
so that it's in history if we ever need it again.
Description:
setting mpi_abort_print_stack in mca params file now makes openmpi
unhappy. Comment these out in all the LANL platform files.
Requested by TOSS OpenMPI support person.
cmr=v1.8.3
This commit was SVN r32782.
Have the make_dist_tarball script check to ensure that the source tree
is clean before continuing. This ensures that we don't accidentally
build a distribution tarball with something that is not committed in
the repo.
There is a --dirtyok option to override this check, and if you access
this script via the "make_tarball" link, --dirtyok is added to the
default set of options.
cmr=v1.8.3:reviewer=rhc
This commit was SVN r32623.
The script used to get confused if you ran it in a subdir of the OMPI
tree (e.g., it would report help files not found if source code
referred to a help file that was not under the subdir in which it was
run).
Now the script searches the whole tree for help files, but only
analyzes the source from the subdir in which it was started. Meaning:
it should always find all help files, and won't get confused like it
did before.
This commit was SVN r32548.
Don't use "ompi" names with top-level constructs, because the OMPI
project may not be built. Instead, just use "opal" names -- they'll
always be there.
This commit was SVN r32446.
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.
new automake requires subdirs-object directive, to resolve this:
09:43:37 automake: warning: possible forward-incompatibility.
09:43:37 automake: At least a source file is in a subdirectory, but the 'subdir-objects'
09:43:37 automake: automake option hasn't been enabled. For now, the corresponding output
09:43:37 automake: object file(s) will be placed in the top-level directory. However,
09:43:37 automake: this behaviour will change in future Automake versions: they will
09:43:37 automake: unconditionally cause object files to be placed in the same subdirectory
09:43:37 automake: of the corresponding sources.
09:43:37 automake: You are advised to start using 'subdir-objects' option throughout your
09:43:37 automake: project, to avoid future incompatibilities.
09:43:37 tools/otfmerge/Makefile.common:13: warning: source file '$(OTFMERGESRCDIR)/otfmerge.c' is in a subdirectory,
09:43:37 tools/otfmerge/Makefile.common:13: but option 'subdir-objects' is disabled
cmr=v1.8.2:reviewer=ompi-rm1.8
This commit was SVN r32225.
