KNC is effectively dead. Remove corresponding SCIF
support in Open MPI.
cherry pick of PR #5737
+
news update
Signed-off-by: Howard Pritchard <howardp@lanl.gov>
(cherry picked from commit b9ac3d8931)
Forgot as part of #3970 to disable use of XRC
recv bufs by default in LANL platform config
file.
related to #4300
Signed-off-by: Howard Pritchard <howardp@lanl.gov>
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>
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>
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.
To support the new mpool two changes were made to the mpool infrastructure:
1) Added an mpool flag to indicate that an mpool does not need the memory
hooks to use the leave pinned protocols. This flag is checked in the
mpool lookup.
2) Add a mpool context to the base registration. This new member is used
by the udreg mpool to store the udreg context associated with the
particular registration. The new member will not break the ABI
compatibility as the new member is only currently used by the udreg
mpool.
Dynamics support for Cray systems makes use of the global rank provided by
orte to give the ugni library a unique rank for each process. Dynamics
support is not available under direct-launch (srun.)
cmr=v1.7.4
This commit was SVN r29719.
Simplify the whole stripping of prefix method by consolidating it into a single MCA param. Allow for multiple prefixes to be stripped, each separated in the param by a comma. If no prefix is given, or the specified prefix isn't in the nodename, then just use the hostname itself.
This commit was SVN r28974.
The following Trac tickets were found above:
Ticket 3710 --> https://svn.open-mpi.org/trac/ompi/ticket/3710
on.
This corrects a problem with Cray systems where the login node's hostname
was being stripped causing the login node to be used as a compute node by
mpirun.
cmr=v1.7.3:reviewer=rhc
This commit was SVN r28970.
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.
So provide a new parameter (can't have too many!) that handles this situation by stripping the prefix from the returned node name. Also do a little cleanup to ensure we cleanly exit from errors, without generating too many annoying messages.
This commit was SVN r25562.
