1
1
openmpi/orte/mca/ess/env/ess_env_module.c
Josh Hursey e12ca48cd9 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

661 строка
19 KiB
C

/*
* Copyright (c) 2004-2010 The Trustees of Indiana University and Indiana
* University Research and Technology
* Corporation. All rights reserved.
* Copyright (c) 2004-2009 The University of Tennessee and The University
* of Tennessee Research Foundation. All rights
* reserved.
* Copyright (c) 2004-2005 High Performance Computing Center Stuttgart,
* University of Stuttgart. All rights reserved.
* Copyright (c) 2004-2005 The Regents of the University of California.
* All rights reserved.
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*
*/
#include "orte_config.h"
#include "orte/constants.h"
#include <sys/types.h>
#include <stdio.h>
#ifdef HAVE_FCNTL_H
#include <fcntl.h>
#endif
#ifdef HAVE_UNISTD_H
#include <unistd.h>
#endif
#include <stdlib.h>
#include "opal/event/event.h"
#include "opal/runtime/opal.h"
#include "opal/mca/paffinity/paffinity.h"
#include "orte/util/show_help.h"
#include "opal/mca/mca.h"
#include "opal/mca/base/base.h"
#include "opal/mca/base/mca_base_param.h"
#include "opal/util/output.h"
#include "opal/util/opal_sos.h"
#include "opal/util/malloc.h"
#include "opal/util/argv.h"
#include "orte/mca/rml/base/base.h"
#include "orte/mca/rml/rml_types.h"
#include "orte/mca/routed/base/base.h"
#include "orte/mca/routed/routed.h"
#include "orte/mca/errmgr/base/base.h"
#include "orte/mca/grpcomm/base/base.h"
#include "orte/mca/iof/base/base.h"
#include "orte/mca/ess/base/base.h"
#include "orte/mca/ess/ess.h"
#include "orte/mca/ras/base/base.h"
#include "orte/mca/plm/base/base.h"
#include "orte/mca/rmaps/base/base.h"
#if OPAL_ENABLE_FT_CR == 1
#include "orte/mca/snapc/base/base.h"
#endif
#include "orte/mca/filem/base/base.h"
#include "orte/util/proc_info.h"
#include "orte/util/session_dir.h"
#include "orte/util/name_fns.h"
#include "orte/util/nidmap.h"
#include "orte/runtime/runtime.h"
#include "orte/runtime/orte_wait.h"
#include "orte/runtime/orte_globals.h"
#include "orte/runtime/orte_cr.h"
#include "orte/mca/ess/ess.h"
#include "orte/mca/ess/base/base.h"
#include "orte/mca/ess/env/ess_env.h"
static int env_set_name(void);
static int rte_init(void);
static int rte_finalize(void);
static uint8_t proc_get_locality(orte_process_name_t *proc);
static orte_vpid_t proc_get_daemon(orte_process_name_t *proc);
static char* proc_get_hostname(orte_process_name_t *proc);
static orte_local_rank_t proc_get_local_rank(orte_process_name_t *proc);
static orte_node_rank_t proc_get_node_rank(orte_process_name_t *proc);
static int update_pidmap(opal_byte_object_t *bo);
static int update_nidmap(opal_byte_object_t *bo);
#if OPAL_ENABLE_FT_CR == 1
static int rte_ft_event(int state);
#endif
orte_ess_base_module_t orte_ess_env_module = {
rte_init,
rte_finalize,
orte_ess_base_app_abort,
proc_get_locality,
proc_get_daemon,
proc_get_hostname,
proc_get_local_rank,
proc_get_node_rank,
update_pidmap,
update_nidmap,
orte_ess_base_query_sys_info,
#if OPAL_ENABLE_FT_CR == 1
rte_ft_event
#else
NULL
#endif
};
/*
* Local variables
*/
static orte_node_rank_t my_node_rank=ORTE_NODE_RANK_INVALID;
static int rte_init(void)
{
int ret;
char *error = NULL;
char **hosts = NULL;
char *nodelist;
/* run the prolog */
if (ORTE_SUCCESS != (ret = orte_ess_base_std_prolog())) {
error = "orte_ess_base_std_prolog";
goto error;
}
/* Start by getting a unique name from the enviro */
env_set_name();
/* if I am a daemon, complete my setup using the
* default procedure
*/
if (ORTE_PROC_IS_DAEMON) {
/* get the list of nodes used for this job */
nodelist = getenv("OMPI_MCA_orte_nodelist");
if (NULL != nodelist) {
/* split the node list into an argv array */
hosts = opal_argv_split(nodelist, ',');
}
if (ORTE_SUCCESS != (ret = orte_ess_base_orted_setup(hosts))) {
ORTE_ERROR_LOG(ret);
error = "orte_ess_base_orted_setup";
goto error;
}
opal_argv_free(hosts);
return ORTE_SUCCESS;
}
if (ORTE_PROC_IS_TOOL) {
/* otherwise, if I am a tool proc, use that procedure */
if (ORTE_SUCCESS != (ret = orte_ess_base_tool_setup())) {
ORTE_ERROR_LOG(ret);
error = "orte_ess_base_tool_setup";
goto error;
}
/* as a tool, I don't need a nidmap - so just return now */
return ORTE_SUCCESS;
}
/* otherwise, I must be an application process - use
* the default procedure to finish my setup
*/
if (ORTE_SUCCESS != (ret = orte_ess_base_app_setup())) {
ORTE_ERROR_LOG(ret);
error = "orte_ess_base_app_setup";
goto error;
}
/* if one was provided, build my nidmap */
if (ORTE_SUCCESS != (ret = orte_util_nidmap_init(orte_process_info.sync_buf))) {
ORTE_ERROR_LOG(ret);
error = "orte_util_nidmap_init";
goto error;
}
return ORTE_SUCCESS;
error:
orte_show_help("help-orte-runtime.txt",
"orte_init:startup:internal-failure",
true, error, ORTE_ERROR_NAME(ret), ret);
return ret;
}
static int rte_finalize(void)
{
int ret;
/* if I am a daemon, finalize using the default procedure */
if (ORTE_PROC_IS_DAEMON) {
if (ORTE_SUCCESS != (ret = orte_ess_base_orted_finalize())) {
ORTE_ERROR_LOG(ret);
}
} else if (ORTE_PROC_IS_TOOL) {
/* otherwise, if I am a tool proc, use that procedure */
if (ORTE_SUCCESS != (ret = orte_ess_base_tool_finalize())) {
ORTE_ERROR_LOG(ret);
}
/* as a tool, I didn't create a nidmap - so just return now */
return ret;
} else {
/* otherwise, I must be an application process
* use the default procedure to finish
*/
if (ORTE_SUCCESS != (ret = orte_ess_base_app_finalize())) {
ORTE_ERROR_LOG(ret);
}
}
/* deconstruct the nidmap and jobmap arrays */
orte_util_nidmap_finalize();
return ret;
}
static uint8_t proc_get_locality(orte_process_name_t *proc)
{
orte_nid_t *nid;
if (NULL == (nid = orte_util_lookup_nid(proc))) {
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
return OPAL_PROC_NON_LOCAL;
}
if (nid->daemon == ORTE_PROC_MY_DAEMON->vpid) {
OPAL_OUTPUT_VERBOSE((2, orte_ess_base_output,
"%s ess:env: proc %s on LOCAL NODE",
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
ORTE_NAME_PRINT(proc)));
return (OPAL_PROC_ON_NODE | OPAL_PROC_ON_CU | OPAL_PROC_ON_CLUSTER);
}
OPAL_OUTPUT_VERBOSE((2, orte_ess_base_output,
"%s ess:env: proc %s is REMOTE",
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
ORTE_NAME_PRINT(proc)));
return OPAL_PROC_NON_LOCAL;
}
static orte_vpid_t proc_get_daemon(orte_process_name_t *proc)
{
orte_nid_t *nid;
if( ORTE_JOBID_IS_DAEMON(proc->jobid) ) {
return proc->vpid;
}
if (NULL == (nid = orte_util_lookup_nid(proc))) {
return ORTE_VPID_INVALID;
}
OPAL_OUTPUT_VERBOSE((2, orte_ess_base_output,
"%s ess:env: proc %s is hosted by daemon %s",
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
ORTE_NAME_PRINT(proc),
ORTE_VPID_PRINT(nid->daemon)));
return nid->daemon;
}
static char* proc_get_hostname(orte_process_name_t *proc)
{
orte_nid_t *nid;
if (NULL == (nid = orte_util_lookup_nid(proc))) {
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
return NULL;
}
OPAL_OUTPUT_VERBOSE((2, orte_ess_base_output,
"%s ess:env: proc %s is on host %s",
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
ORTE_NAME_PRINT(proc),
nid->name));
return nid->name;
}
static orte_local_rank_t proc_get_local_rank(orte_process_name_t *proc)
{
orte_pmap_t *pmap;
if (NULL == (pmap = orte_util_lookup_pmap(proc))) {
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
return ORTE_LOCAL_RANK_INVALID;
}
OPAL_OUTPUT_VERBOSE((2, orte_ess_base_output,
"%s ess:env: proc %s has local rank %d",
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
ORTE_NAME_PRINT(proc),
(int)pmap->local_rank));
return pmap->local_rank;
}
static orte_node_rank_t proc_get_node_rank(orte_process_name_t *proc)
{
orte_pmap_t *pmap;
/* is this me? */
if (proc->jobid == ORTE_PROC_MY_NAME->jobid &&
proc->vpid == ORTE_PROC_MY_NAME->vpid) {
/* yes it is - reply with my rank. This is necessary
* because the pidmap will not have arrived when I
* am starting up, and if we use static ports, then
* I need to know my node rank during init
*/
return my_node_rank;
}
if (NULL == (pmap = orte_util_lookup_pmap(proc))) {
return ORTE_NODE_RANK_INVALID;
}
OPAL_OUTPUT_VERBOSE((2, orte_ess_base_output,
"%s ess:env: proc %s has node rank %d",
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
ORTE_NAME_PRINT(proc),
(int)pmap->node_rank));
return pmap->node_rank;
}
static int update_pidmap(opal_byte_object_t *bo)
{
int ret;
OPAL_OUTPUT_VERBOSE((2, orte_ess_base_output,
"%s ess:env: updating pidmap",
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME)));
/* build the pmap */
if (ORTE_SUCCESS != (ret = orte_util_decode_pidmap(bo))) {
ORTE_ERROR_LOG(ret);
}
return ret;
}
static int update_nidmap(opal_byte_object_t *bo)
{
int rc;
/* decode the nidmap - the util will know what to do */
if (ORTE_SUCCESS != (rc = orte_util_decode_nodemap(bo))) {
ORTE_ERROR_LOG(rc);
}
return rc;
}
static int env_set_name(void)
{
char *tmp;
int rc;
orte_jobid_t jobid;
orte_vpid_t vpid;
mca_base_param_reg_string_name("orte", "ess_jobid", "Process jobid",
true, false, NULL, &tmp);
if (NULL == tmp) {
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
return ORTE_ERR_NOT_FOUND;
}
if (ORTE_SUCCESS != (rc = orte_util_convert_string_to_jobid(&jobid, tmp))) {
ORTE_ERROR_LOG(rc);
return(rc);
}
free(tmp);
mca_base_param_reg_string_name("orte", "ess_vpid", "Process vpid",
true, false, NULL, &tmp);
if (NULL == tmp) {
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
return ORTE_ERR_NOT_FOUND;
}
if (ORTE_SUCCESS != (rc = orte_util_convert_string_to_vpid(&vpid, tmp))) {
ORTE_ERROR_LOG(rc);
return(rc);
}
free(tmp);
ORTE_PROC_MY_NAME->jobid = jobid;
ORTE_PROC_MY_NAME->vpid = vpid;
OPAL_OUTPUT_VERBOSE((1, orte_ess_base_output,
"ess:env set name to %s", ORTE_NAME_PRINT(ORTE_PROC_MY_NAME)));
/* get my node rank in case we are using static ports - this won't
* be present for daemons, so don't error out if we don't have it
*/
mca_base_param_reg_string_name("orte", "ess_node_rank", "Process node rank",
true, false, NULL, &tmp);
if (NULL != tmp) {
my_node_rank = strtol(tmp, NULL, 10);
}
/* get the non-name common environmental variables */
if (ORTE_SUCCESS != (rc = orte_ess_env_get())) {
ORTE_ERROR_LOG(rc);
return rc;
}
return ORTE_SUCCESS;
}
#if OPAL_ENABLE_FT_CR == 1
static int rte_ft_event(int state)
{
int ret, exit_status = ORTE_SUCCESS;
orte_proc_type_t svtype;
/******** Checkpoint Prep ********/
if(OPAL_CRS_CHECKPOINT == state) {
/*
* Notify SnapC
*/
if( ORTE_SUCCESS != (ret = orte_snapc.ft_event(OPAL_CRS_CHECKPOINT))) {
ORTE_ERROR_LOG(ret);
exit_status = ret;
goto cleanup;
}
/*
* Notify Routed
*/
if( ORTE_SUCCESS != (ret = orte_routed.ft_event(OPAL_CRS_CHECKPOINT))) {
ORTE_ERROR_LOG(ret);
exit_status = ret;
goto cleanup;
}
/*
* Notify RML -> OOB
*/
if( ORTE_SUCCESS != (ret = orte_rml.ft_event(OPAL_CRS_CHECKPOINT))) {
ORTE_ERROR_LOG(ret);
exit_status = ret;
goto cleanup;
}
}
/******** Continue Recovery ********/
else if (OPAL_CRS_CONTINUE == state ) {
OPAL_OUTPUT_VERBOSE((1, orte_ess_base_output,
"ess:env ft_event(%2d) - %s is Continuing",
state, ORTE_NAME_PRINT(ORTE_PROC_MY_NAME)));
/*
* Notify RML -> OOB
*/
if( ORTE_SUCCESS != (ret = orte_rml.ft_event(OPAL_CRS_CONTINUE))) {
ORTE_ERROR_LOG(ret);
exit_status = ret;
goto cleanup;
}
/*
* Notify Routed
*/
if( ORTE_SUCCESS != (ret = orte_routed.ft_event(OPAL_CRS_CONTINUE))) {
ORTE_ERROR_LOG(ret);
exit_status = ret;
goto cleanup;
}
/*
* Notify SnapC
*/
if( ORTE_SUCCESS != (ret = orte_snapc.ft_event(OPAL_CRS_CONTINUE))) {
ORTE_ERROR_LOG(ret);
exit_status = ret;
goto cleanup;
}
if( orte_cr_continue_like_restart ) {
/*
* Barrier to make all processes have been successfully restarted before
* we try to remove some restart only files.
*/
if (ORTE_SUCCESS != (ret = orte_grpcomm.barrier())) {
opal_output(0, "ess:env: ft_event(%2d): Failed in orte_grpcomm.barrier (%d)",
state, ret);
return ret;
}
if( orte_cr_flush_restart_files ) {
OPAL_OUTPUT_VERBOSE((1, orte_ess_base_output,
"ess:env ft_event(%2d): %s "
"Cleanup restart files...",
state, ORTE_NAME_PRINT(ORTE_PROC_MY_NAME)));
opal_crs_base_cleanup_flush();
}
}
}
/******** Restart Recovery ********/
else if (OPAL_CRS_RESTART == state ) {
OPAL_OUTPUT_VERBOSE((1, orte_ess_base_output,
"ess:env ft_event(%2d) - %s is Restarting",
state, ORTE_NAME_PRINT(ORTE_PROC_MY_NAME)));
/*
* This should follow the ess init() function
*/
/*
* Clear nidmap and jmap
*/
orte_util_nidmap_finalize();
/*
* - Reset Contact information
*/
if( ORTE_SUCCESS != (ret = env_set_name() ) ) {
exit_status = ret;
}
/*
* Notify RML -> OOB
*/
if( ORTE_SUCCESS != (ret = orte_rml.ft_event(OPAL_CRS_RESTART))) {
ORTE_ERROR_LOG(ret);
exit_status = ret;
goto cleanup;
}
/*
* Restart the routed framework
* JJH: Lie to the finalize function so it does not try to contact the daemon.
*/
svtype = orte_process_info.proc_type;
orte_process_info.proc_type = ORTE_PROC_TOOL;
if (ORTE_SUCCESS != (ret = orte_routed.finalize()) ) {
ORTE_ERROR_LOG(ret);
exit_status = ret;
goto cleanup;
}
orte_process_info.proc_type = svtype;
if (ORTE_SUCCESS != (ret = orte_routed.initialize()) ) {
ORTE_ERROR_LOG(ret);
exit_status = ret;
goto cleanup;
}
/*
* Group Comm - Clean out stale data
*/
orte_grpcomm.finalize();
if (ORTE_SUCCESS != (ret = orte_grpcomm.init())) {
ORTE_ERROR_LOG(ret);
exit_status = ret;
goto cleanup;
}
if (ORTE_SUCCESS != (ret = orte_grpcomm.purge_proc_attrs())) {
ORTE_ERROR_LOG(ret);
exit_status = ret;
goto cleanup;
}
/*
* Restart the PLM - Does nothing at the moment, but included for completeness
*/
if (ORTE_SUCCESS != (ret = orte_plm.finalize())) {
ORTE_ERROR_LOG(ret);
exit_status = ret;
goto cleanup;
}
if (ORTE_SUCCESS != (ret = orte_plm.init())) {
ORTE_ERROR_LOG(ret);
exit_status = ret;
goto cleanup;
}
/*
* RML - Enable communications
*/
if (ORTE_SUCCESS != (ret = orte_rml.enable_comm())) {
ORTE_ERROR_LOG(ret);
exit_status = ret;
goto cleanup;
}
/*
* Notify Routed
*/
if( ORTE_SUCCESS != (ret = orte_routed.ft_event(OPAL_CRS_RESTART))) {
ORTE_ERROR_LOG(ret);
exit_status = ret;
goto cleanup;
}
/* if one was provided, build my nidmap */
if (ORTE_SUCCESS != (ret = orte_util_nidmap_init(orte_process_info.sync_buf))) {
ORTE_ERROR_LOG(ret);
exit_status = ret;
goto cleanup;
}
/*
* Barrier to make all processes have been successfully restarted before
* we try to remove some restart only files.
*/
if (ORTE_SUCCESS != (ret = orte_grpcomm.barrier())) {
opal_output(0, "ess:env ft_event(%2d): Failed in orte_grpcomm.barrier (%d)",
state, ret);
return ret;
}
if( orte_cr_flush_restart_files ) {
OPAL_OUTPUT_VERBOSE((1, orte_ess_base_output,
"ess:env ft_event(%2d): %s "
"Cleanup restart files...",
state, ORTE_NAME_PRINT(ORTE_PROC_MY_NAME)));
opal_crs_base_cleanup_flush();
}
/*
* Session directory re-init
*/
if (orte_create_session_dirs) {
if (ORTE_SUCCESS != (ret = orte_session_dir(true,
orte_process_info.tmpdir_base,
orte_process_info.nodename,
NULL, /* Batch ID -- Not used */
ORTE_PROC_MY_NAME))) {
exit_status = ret;
}
opal_output_set_output_file_info(orte_process_info.proc_session_dir,
"output-", NULL, NULL);
}
/*
* Notify SnapC
*/
if( ORTE_SUCCESS != (ret = orte_snapc.ft_event(OPAL_CRS_RESTART))) {
ORTE_ERROR_LOG(ret);
exit_status = ret;
goto cleanup;
}
}
else if (OPAL_CRS_TERM == state ) {
/* Nothing */
}
else {
/* Error state = Nothing */
}
cleanup:
return exit_status;
}
#endif