2007-03-16 23:11:45 +00:00
|
|
|
# -*- shell-script -*-
|
|
|
|
#
|
2010-03-12 23:57:50 +00:00
|
|
|
# Copyright (c) 2004-2010 The Trustees of Indiana University.
|
2007-03-16 23:11:45 +00:00
|
|
|
# All rights reserved.
|
|
|
|
# Copyright (c) 2004-2005 The Trustees of the University of Tennessee.
|
|
|
|
# All rights reserved.
|
|
|
|
# Copyright (c) 2004-2005 High Performance Computing Center Stuttgart,
|
|
|
|
# University of Stuttgart. All rights reserved.
|
|
|
|
# Copyright (c) 2004-2006 The Regents of the University of California.
|
|
|
|
# All rights reserved.
|
2010-09-17 23:04:06 +00:00
|
|
|
# Copyright (c) 2009-2010 Cisco Systems, Inc. All rights reserved.
|
2011-12-07 21:36:03 +00:00
|
|
|
# Copyright (c) 2011 Oak Ridge National Labs. All rights reserved.
|
2007-03-16 23:11:45 +00:00
|
|
|
# $COPYRIGHT$
|
|
|
|
#
|
|
|
|
# Additional copyrights may follow
|
|
|
|
#
|
|
|
|
# $HEADER$
|
|
|
|
#
|
|
|
|
|
|
|
|
# MCA_crs_blcr_CONFIG([action-if-found], [action-if-not-found])
|
|
|
|
# -----------------------------------------------------------
|
2010-09-17 23:04:06 +00:00
|
|
|
AC_DEFUN([MCA_opal_crs_blcr_CONFIG],[
|
|
|
|
AC_CONFIG_FILES([opal/mca/crs/blcr/Makefile])
|
|
|
|
|
2007-03-16 23:11:45 +00:00
|
|
|
AC_ARG_WITH([blcr],
|
2008-09-22 19:48:47 +00:00
|
|
|
[AC_HELP_STRING([--with-blcr(=DIR)],
|
2007-03-16 23:11:45 +00:00
|
|
|
[Path to BLCR Installation])])
|
2009-01-29 17:59:04 +00:00
|
|
|
OMPI_CHECK_WITHDIR([blcr], [$with_blcr], [include/libcr.h])
|
2008-09-22 19:48:47 +00:00
|
|
|
AC_ARG_WITH([blcr-libdir],
|
|
|
|
[AC_HELP_STRING([--with-blcr-libdir=DIR],
|
|
|
|
[Search for BLCR libraries in DIR])])
|
2009-01-29 17:59:04 +00:00
|
|
|
OMPI_CHECK_WITHDIR([blcr-libdir], [$with_blcr_libdir], [libcr.*])
|
2008-07-08 02:48:20 +00:00
|
|
|
|
|
|
|
check_crs_blcr_good="no"
|
2009-01-19 20:21:58 +00:00
|
|
|
|
|
|
|
# If we do not want FT, don't compile this component
|
2011-12-07 21:36:03 +00:00
|
|
|
#
|
|
|
|
# If we wanted BLCR, but did not specify the FT option,
|
|
|
|
# error out with a warning for the user
|
2010-03-30 16:47:39 +00:00
|
|
|
AS_IF([test "$opal_want_ft_cr" = "0"],
|
2008-09-03 20:10:29 +00:00
|
|
|
[$2
|
2011-12-07 21:36:03 +00:00
|
|
|
check_crs_blcr_good="no"
|
|
|
|
AS_IF([test ! -z "$with_blcr" -a "$with_blcr" != "no"],
|
|
|
|
[AC_MSG_WARN([BLCR support requested, but FT support not requested. You need to specify the --with-ft=cr configure option.])
|
|
|
|
AC_MSG_ERROR([Aborting.])])
|
|
|
|
],
|
2008-09-03 20:10:29 +00:00
|
|
|
[check_crs_blcr_good="yes"])
|
2008-09-02 20:15:57 +00:00
|
|
|
|
2009-01-19 20:21:58 +00:00
|
|
|
# If we do not want BLCR, then do not compile it
|
|
|
|
AS_IF([test "$with_blcr" = "no" -o "$check_crs_blcr_good" = "no"],
|
2008-09-03 20:10:29 +00:00
|
|
|
[$2
|
|
|
|
check_crs_blcr_good="no"],
|
|
|
|
[check_crs_blcr_good="yes"])
|
2008-07-08 02:48:20 +00:00
|
|
|
|
2008-09-22 19:48:47 +00:00
|
|
|
# Defaults
|
|
|
|
check_crs_blcr_dir_msg="compiler default"
|
|
|
|
check_crs_blcr_libdir_msg="linker default"
|
|
|
|
check_crs_blcr_dir=""
|
|
|
|
check_crs_blcr_libdir=""
|
|
|
|
|
2008-09-03 20:10:29 +00:00
|
|
|
# Determine the search paths for the headers and libraries
|
2008-09-02 20:15:57 +00:00
|
|
|
AS_IF([test "$check_crs_blcr_good" != "yes"], [$2],
|
|
|
|
[AS_IF([test ! -z "$with_blcr" -a "$with_blcr" != "yes"],
|
2008-09-03 20:10:29 +00:00
|
|
|
[check_crs_blcr_dir="$with_blcr"
|
2008-09-22 19:48:47 +00:00
|
|
|
check_crs_blcr_dir_msg="$with_blcr (from --with-blcr)"])
|
|
|
|
AS_IF([test ! -z "$with_blcr_libdir" -a "$with_blcr_libdir" != "yes"],
|
|
|
|
[check_crs_blcr_libdir="$with_blcr_libdir"
|
|
|
|
check_crs_blcr_libdir_msg="$with_blcr_libdir (from --with-blcr-libdir)"])
|
|
|
|
])
|
|
|
|
|
2008-07-08 02:48:20 +00:00
|
|
|
AS_IF([test "$check_crs_blcr_good" != "yes"], [$2],
|
2008-09-22 19:48:47 +00:00
|
|
|
[AC_MSG_CHECKING([for BLCR dir])
|
|
|
|
AC_MSG_RESULT([$check_crs_blcr_dir_msg])
|
|
|
|
AC_MSG_CHECKING([for BLCR library dir])
|
|
|
|
AC_MSG_RESULT([$check_crs_blcr_libdir_msg])
|
|
|
|
OMPI_CHECK_PACKAGE([crs_blcr_check],
|
|
|
|
[libcr.h],
|
|
|
|
[cr],
|
|
|
|
[cr_init],
|
|
|
|
[],
|
|
|
|
[$check_crs_blcr_dir],
|
|
|
|
[$check_crs_blcr_libdir],
|
|
|
|
[check_crs_blcr_good="yes"],
|
|
|
|
[check_crs_blcr_good="no"])
|
|
|
|
])
|
|
|
|
|
2009-08-21 20:07:18 +00:00
|
|
|
crs_blcr_save_CFLAGS="$CFLAGS"
|
|
|
|
crs_blcr_save_CPPFLAGS="$CPPFLAGS"
|
|
|
|
crs_blcr_save_LDFLAGS="$LDFLAGS"
|
|
|
|
crs_blcr_save_LIBS="$LIBS"
|
|
|
|
|
|
|
|
crs_blcr_CFLAGS="$CFLAGS $crs_blcr_check_CFLAGS"
|
|
|
|
crs_blcr_CPPFLAGS="$CPPFLAGS $crs_blcr_check_CPPFLAGS"
|
|
|
|
crs_blcr_LDFLAGS="$LDFLAGS $crs_blcr_check_LDFLAGS"
|
|
|
|
crs_blcr_LIBS="$LIBS $crs_blcr_check_LIBS"
|
|
|
|
|
2008-09-22 19:48:47 +00:00
|
|
|
# Check to see if we found the BLCR libcr.h library
|
|
|
|
# If we did then add the arguments to the wrapper compiler
|
|
|
|
AS_IF([test "$check_crs_blcr_good" != "yes"], [$2],
|
|
|
|
[
|
|
|
|
#
|
|
|
|
# Since BLCR libraries are not fully ISO99 C compliant
|
|
|
|
# -pedantic and -Wundef raise a bunch of warnings, so
|
|
|
|
# we just strip them off for this component
|
|
|
|
AC_MSG_WARN([Removed -pedantic and -Wundef from CFLAGS for blcr component because libcr.h is not really ANSI C])
|
|
|
|
# Strip off problematic arguments
|
2009-08-21 20:07:18 +00:00
|
|
|
crs_blcr_CFLAGS="`echo $crs_blcr_CFLAGS | sed 's/-pedantic//g'`"
|
2008-09-22 19:48:47 +00:00
|
|
|
crs_blcr_CFLAGS="`echo $crs_blcr_CFLAGS | sed 's/-Wundef//g'`"
|
2009-08-21 20:07:18 +00:00
|
|
|
crs_blcr_CPPFLAGS="`echo $crs_blcr_CPPFLAGS | sed 's/-pedantic//g'`"
|
2008-09-22 19:48:47 +00:00
|
|
|
crs_blcr_CPPFLAGS="`echo $crs_blcr_CPPFLAGS | sed 's/-Wundef//g'`"
|
2009-08-21 20:07:18 +00:00
|
|
|
crs_blcr_LDFLAGS="$crs_blcr_LDFLAGS"
|
|
|
|
crs_blcr_LIBS="$crs_blcr_LIBS"
|
|
|
|
#
|
|
|
|
# Setup wrapper options for static builds
|
2008-09-22 19:48:47 +00:00
|
|
|
#
|
2007-03-16 23:11:45 +00:00
|
|
|
crs_blcr_WRAPPER_EXTRA_CPPFLAGS="$crs_blcr_CPPFLAGS"
|
2008-09-22 19:48:47 +00:00
|
|
|
crs_blcr_WRAPPER_EXTRA_LDFLAGS="$crs_blcr_LDFLAGS"
|
|
|
|
crs_blcr_WRAPPER_EXTRA_LIBS="$crs_blcr_LIBS"
|
2008-07-08 02:48:20 +00:00
|
|
|
$1])
|
2007-11-09 06:13:40 +00:00
|
|
|
|
|
|
|
#
|
2008-12-11 00:08:34 +00:00
|
|
|
# Check for version difference which may have:
|
2007-11-09 06:13:40 +00:00
|
|
|
# - working cr_request_file
|
2008-12-11 00:08:34 +00:00
|
|
|
# - working cr_request_checkpoint (which should be used instead of cr_request_file)
|
2007-11-09 06:13:40 +00:00
|
|
|
# - 'requester' parameter to checkpoint_info
|
|
|
|
#
|
2008-07-08 02:48:20 +00:00
|
|
|
AS_IF([test "$check_crs_blcr_good" != "yes"], [$2], [
|
2009-08-21 20:07:18 +00:00
|
|
|
CFLAGS="$crs_blcr_CFLAGS"
|
|
|
|
CPPFLAGS="$crs_blcr_CPPFLAGS"
|
|
|
|
LDFLAGS="$crs_blcr_LDFLAGS"
|
|
|
|
LIBS="$crs_blcr_LIBS"
|
2008-12-11 00:08:34 +00:00
|
|
|
#
|
|
|
|
# First look for the cr_request_file function
|
|
|
|
#
|
2008-07-08 02:48:20 +00:00
|
|
|
crs_blcr_have_working_cr_request=0
|
|
|
|
AC_MSG_CHECKING(for BLCR working cr_request)
|
2008-12-11 00:08:34 +00:00
|
|
|
OMPI_CHECK_FUNC_LIB([cr_request_file],[cr],
|
|
|
|
[AC_TRY_COMPILE([#include <libcr.h>],
|
|
|
|
[#if CR_RELEASE_MAJOR <= 0 && CR_RELEASE_MINOR < 6
|
|
|
|
#error Version earlier than 0.6.0
|
|
|
|
#endif
|
|
|
|
],
|
|
|
|
[crs_blcr_have_working_cr_request=1
|
|
|
|
],
|
|
|
|
[crs_blcr_have_working_cr_request=0
|
|
|
|
AC_MSG_WARN([This BLCR version does not contain a known working version of cr_request_file])
|
|
|
|
])],
|
2008-07-08 02:48:20 +00:00
|
|
|
[crs_blcr_have_working_cr_request=0
|
2008-12-11 00:08:34 +00:00
|
|
|
AC_MSG_WARN([This BLCR version does not contain the cr_request_file function])
|
|
|
|
])
|
2008-07-08 02:48:20 +00:00
|
|
|
AC_DEFINE_UNQUOTED([CRS_BLCR_HAVE_CR_REQUEST], [$crs_blcr_have_working_cr_request],
|
2008-12-11 00:08:34 +00:00
|
|
|
[BLCR cr_request_file check])
|
2007-11-09 06:13:40 +00:00
|
|
|
|
2008-12-11 00:08:34 +00:00
|
|
|
#
|
|
|
|
# Look for the cr_request_checkpoint function
|
|
|
|
#
|
|
|
|
crs_blcr_have_cr_request_checkpoint=0
|
|
|
|
AC_MSG_CHECKING(for BLCR cr_request_checkpoint)
|
|
|
|
OMPI_CHECK_FUNC_LIB([cr_request_checkpoint],[cr],
|
|
|
|
[crs_blcr_have_cr_request_checkpoint=1
|
|
|
|
],
|
|
|
|
[crs_blcr_have_cr_request_checkpoint=0
|
|
|
|
AC_MSG_WARN([This BLCR version does not contain the cr_request_checkpoint function])
|
|
|
|
])
|
|
|
|
AC_DEFINE_UNQUOTED([CRS_BLCR_HAVE_CR_REQUEST_CHECKPOINT], [$crs_blcr_have_cr_request_checkpoint],
|
|
|
|
[BLCR cr_request_checkpoint check])
|
2007-11-09 06:13:40 +00:00
|
|
|
|
2008-12-11 00:08:34 +00:00
|
|
|
#
|
|
|
|
# Look for the cr_checkpoint_info.requester member
|
|
|
|
#
|
2008-07-08 02:48:20 +00:00
|
|
|
crs_blcr_have_info_requester=0
|
|
|
|
AC_CHECK_MEMBER([struct cr_checkpoint_info.requester],
|
|
|
|
[crs_blcr_have_info_requester=1],
|
|
|
|
[AC_MSG_WARN([This BLCR version does not contain a 'requester' member of the 'cr_checkpoint_info' struct])],
|
|
|
|
[#include <libcr.h>])
|
|
|
|
AC_DEFINE_UNQUOTED([CRS_BLCR_HAVE_INFO_REQUESTER], [$crs_blcr_have_info_requester],
|
|
|
|
[BLCRs cr_checkpoint_info.requester member availability])
|
|
|
|
$1])
|
2007-03-16 23:11:45 +00:00
|
|
|
|
A number of C/R enhancements per RFC below:
http://www.open-mpi.org/community/lists/devel/2010/07/8240.php
Documentation:
http://osl.iu.edu/research/ft/
Major Changes:
--------------
* Added C/R-enabled Debugging support.
Enabled with the --enable-crdebug flag. See the following website for more information:
http://osl.iu.edu/research/ft/crdebug/
* Added Stable Storage (SStore) framework for checkpoint storage
* 'central' component does a direct to central storage save
* 'stage' component stages checkpoints to central storage while the application continues execution.
* 'stage' supports offline compression of checkpoints before moving (sstore_stage_compress)
* 'stage' supports local caching of checkpoints to improve automatic recovery (sstore_stage_caching)
* Added Compression (compress) framework to support
* Add two new ErrMgr recovery policies
* {{{crmig}}} C/R Process Migration
* {{{autor}}} C/R Automatic Recovery
* Added the {{{ompi-migrate}}} command line tool to support the {{{crmig}}} ErrMgr component
* Added CR MPI Ext functions (enable them with {{{--enable-mpi-ext=cr}}} configure option)
* {{{OMPI_CR_Checkpoint}}} (Fixes trac:2342)
* {{{OMPI_CR_Restart}}}
* {{{OMPI_CR_Migrate}}} (may need some more work for mapping rules)
* {{{OMPI_CR_INC_register_callback}}} (Fixes trac:2192)
* {{{OMPI_CR_Quiesce_start}}}
* {{{OMPI_CR_Quiesce_checkpoint}}}
* {{{OMPI_CR_Quiesce_end}}}
* {{{OMPI_CR_self_register_checkpoint_callback}}}
* {{{OMPI_CR_self_register_restart_callback}}}
* {{{OMPI_CR_self_register_continue_callback}}}
* The ErrMgr predicted_fault() interface has been changed to take an opal_list_t of ErrMgr defined types. This will allow us to better support a wider range of fault prediction services in the future.
* Add a progress meter to:
* FileM rsh (filem_rsh_process_meter)
* SnapC full (snapc_full_progress_meter)
* SStore stage (sstore_stage_progress_meter)
* Added 2 new command line options to ompi-restart
* --showme : Display the full command line that would have been exec'ed.
* --mpirun_opts : Command line options to pass directly to mpirun. (Fixes trac:2413)
* Deprecated some MCA params:
* crs_base_snapshot_dir deprecated, use sstore_stage_local_snapshot_dir
* snapc_base_global_snapshot_dir deprecated, use sstore_base_global_snapshot_dir
* snapc_base_global_shared deprecated, use sstore_stage_global_is_shared
* snapc_base_store_in_place deprecated, replaced with different components of SStore
* snapc_base_global_snapshot_ref deprecated, use sstore_base_global_snapshot_ref
* snapc_base_establish_global_snapshot_dir deprecated, never well supported
* snapc_full_skip_filem deprecated, use sstore_stage_skip_filem
Minor Changes:
--------------
* Fixes trac:1924 : {{{ompi-restart}}} now recognizes path prefixed checkpoint handles and does the right thing.
* Fixes trac:2097 : {{{ompi-info}}} should now report all available CRS components
* Fixes trac:2161 : Manual checkpoint movement. A user can 'mv' a checkpoint directory from the original location to another and still restart from it.
* Fixes trac:2208 : Honor various TMPDIR varaibles instead of forcing {{{/tmp}}}
* Move {{{ompi_cr_continue_like_restart}}} to {{{orte_cr_continue_like_restart}}} to be more flexible in where this should be set.
* opal_crs_base_metadata_write* functions have been moved to SStore to support a wider range of metadata handling functionality.
* Cleanup the CRS framework and components to work with the SStore framework.
* Cleanup the SnapC framework and components to work with the SStore framework (cleans up these code paths considerably).
* Add 'quiesce' hook to CRCP for a future enhancement.
* We now require a BLCR version that supports {{{cr_request_file()}}} or {{{cr_request_checkpoint()}}} in order to make the code more maintainable. Note that {{{cr_request_file}}} has been deprecated since 0.7.0, so we prefer to use {{{cr_request_checkpoint()}}}.
* Add optional application level INC callbacks (registered through the CR MPI Ext interface).
* Increase the {{{opal_cr_thread_sleep_wait}}} parameter to 1000 microseconds to make the C/R thread less aggressive.
* {{{opal-restart}}} now looks for cache directories before falling back on stable storage when asked.
* {{{opal-restart}}} also support local decompression before restarting
* {{{orte-checkpoint}}} now uses the SStore framework to work with the metadata
* {{{orte-restart}}} now uses the SStore framework to work with the metadata
* Remove the {{{orte-restart}}} preload option. This was removed since the user only needs to select the 'stage' component in order to support this functionality.
* Since the '-am' parameter is saved in the metadata, {{{ompi-restart}}} no longer hard codes {{{-am ft-enable-cr}}}.
* Fix {{{hnp}}} ErrMgr so that if a previous component in the stack has 'fixed' the problem, then it should be skipped.
* Make sure to decrement the number of 'num_local_procs' in the orted when one goes away.
* odls now checks the SStore framework to see if it needs to load any checkpoint files before launching (to support 'stage'). This separates the SStore logic from the --preload-[binary|files] options.
* Add unique IDs to the named pipes established between the orted and the app in SnapC. This is to better support migration and automatic recovery activities.
* Improve the checks for 'already checkpointing' error path.
* A a recovery output timer, to show how long it takes to restart a job
* Do a better job of cleaning up the old session directory on restart.
* Add a local module to the autor and crmig ErrMgr components. These small modules prevent the 'orted' component from attempting a local recovery (Which does not work for MPI apps at the moment)
* Add a fix for bounding the checkpointable region between MPI_Init and MPI_Finalize.
This commit was SVN r23587.
The following Trac tickets were found above:
Ticket 1924 --> https://svn.open-mpi.org/trac/ompi/ticket/1924
Ticket 2097 --> https://svn.open-mpi.org/trac/ompi/ticket/2097
Ticket 2161 --> https://svn.open-mpi.org/trac/ompi/ticket/2161
Ticket 2192 --> https://svn.open-mpi.org/trac/ompi/ticket/2192
Ticket 2208 --> https://svn.open-mpi.org/trac/ompi/ticket/2208
Ticket 2342 --> https://svn.open-mpi.org/trac/ompi/ticket/2342
Ticket 2413 --> https://svn.open-mpi.org/trac/ompi/ticket/2413
2010-08-10 20:51:11 +00:00
|
|
|
#
|
|
|
|
# Require either a working cr_request_file() or cr_request_checkpoint() function
|
|
|
|
#
|
|
|
|
AS_IF([test "$crs_blcr_have_working_cr_request" = "0" -a "$crs_blcr_have_cr_request_checkpoint" = "0"],
|
|
|
|
[$2
|
|
|
|
check_crs_blcr_good="no"
|
|
|
|
AC_MSG_WARN([The BLCR CRS component requires either the cr_request_checkpoint() or cr_request_file() functions])])
|
|
|
|
|
2009-08-21 20:07:18 +00:00
|
|
|
#
|
|
|
|
# Reset the flags
|
|
|
|
#
|
2008-09-22 19:48:47 +00:00
|
|
|
CFLAGS="$crs_blcr_save_CFLAGS"
|
|
|
|
CPPFLAGS="$crs_blcr_save_CPPFLAGS"
|
|
|
|
LDFLAGS="$crs_blcr_save_LDFLAGS"
|
|
|
|
LIBS="$crs_blcr_save_LIBS"
|
|
|
|
|
2008-07-08 02:48:20 +00:00
|
|
|
#
|
2008-09-22 19:48:47 +00:00
|
|
|
AS_IF([test "$check_crs_blcr_good" = "yes"],
|
2009-08-21 20:07:18 +00:00
|
|
|
[ AC_SUBST([crs_blcr_WRAPPER_EXTRA_LDFLAGS])
|
|
|
|
AC_SUBST([crs_blcr_WRAPPER_EXTRA_LIBS])
|
|
|
|
AC_SUBST([crs_blcr_WRAPPER_EXTRA_CPPFLAGS])
|
2008-07-08 02:48:20 +00:00
|
|
|
AC_SUBST([crs_blcr_CFLAGS])
|
|
|
|
AC_SUBST([crs_blcr_CPPFLAGS])
|
|
|
|
AC_SUBST([crs_blcr_LDFLAGS])
|
|
|
|
AC_SUBST([crs_blcr_LIBS])
|
2008-09-22 19:48:47 +00:00
|
|
|
$1],
|
|
|
|
[AS_IF([test ! -z "$with_blcr" -a "$with_blcr" != "no"],
|
|
|
|
[AC_MSG_WARN([BLCR support requested but not found. Perhaps you need to specify the location of the BLCR libraries.])
|
|
|
|
AC_MSG_ERROR([Aborting.])])
|
|
|
|
$3])
|
|
|
|
|
2007-03-16 23:11:45 +00:00
|
|
|
])dnl
|