2008-02-28 04:57:57 +03:00
|
|
|
/*
|
|
|
|
* Copyright (c) 2004-2005 The Trustees of Indiana University and Indiana
|
|
|
|
* University Research and Technology
|
|
|
|
* Corporation. All rights reserved.
|
2008-02-28 08:32:23 +03:00
|
|
|
* Copyright (c) 2004-2008 The University of Tennessee and The University
|
2008-02-28 04:57:57 +03:00
|
|
|
* 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 (c) 2007 Cisco, Inc. All rights reserved.
|
|
|
|
* $COPYRIGHT$
|
|
|
|
*
|
|
|
|
* Additional copyrights may follow
|
|
|
|
*
|
|
|
|
* $HEADER$
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include "orte_config.h"
|
|
|
|
#include "orte/constants.h"
|
|
|
|
#include "orte/types.h"
|
|
|
|
|
|
|
|
#ifdef HAVE_SYS_TIME_H
|
|
|
|
#include <sys/time.h>
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#include "opal/mca/base/mca_base_param.h"
|
|
|
|
#include "opal/threads/mutex.h"
|
|
|
|
#include "opal/threads/condition.h"
|
2008-09-01 21:49:31 +04:00
|
|
|
#include "opal/util/argv.h"
|
2008-02-28 08:32:23 +03:00
|
|
|
#include "opal/class/opal_pointer_array.h"
|
2008-02-28 04:57:57 +03:00
|
|
|
#include "opal/dss/dss.h"
|
This commit represents a bunch of work on a Mercurial side branch. As
such, the commit message back to the master SVN repository is fairly
long.
= ORTE Job-Level Output Messages =
Add two new interfaces that should be used for all new code throughout
the ORTE and OMPI layers (we already make the search-and-replace on
the existing ORTE / OMPI layers):
* orte_output(): (and corresponding friends ORTE_OUTPUT,
orte_output_verbose, etc.) This function sends the output directly
to the HNP for processing as part of a job-specific output
channel. It supports all the same outputs as opal_output()
(syslog, file, stdout, stderr), but for stdout/stderr, the output
is sent to the HNP for processing and output. More on this below.
* orte_show_help(): This function is a drop-in-replacement for
opal_show_help(), with two differences in functionality:
1. the rendered text help message output is sent to the HNP for
display (rather than outputting directly into the process' stderr
stream)
1. the HNP detects duplicate help messages and does not display them
(so that you don't see the same error message N times, once from
each of your N MPI processes); instead, it counts "new" instances
of the help message and displays a message every ~5 seconds when
there are new ones ("I got X new copies of the help message...")
opal_show_help and opal_output still exist, but they only output in
the current process. The intent for the new orte_* functions is that
they can apply job-level intelligence to the output. As such, we
recommend that all new ORTE and OMPI code use the new orte_*
functions, not thei opal_* functions.
=== New code ===
For ORTE and OMPI programmers, here's what you need to do differently
in new code:
* Do not include opal/util/show_help.h or opal/util/output.h.
Instead, include orte/util/output.h (this one header file has
declarations for both the orte_output() series of functions and
orte_show_help()).
* Effectively s/opal_output/orte_output/gi throughout your code.
Note that orte_output_open() takes a slightly different argument
list (as a way to pass data to the filtering stream -- see below),
so you if explicitly call opal_output_open(), you'll need to
slightly adapt to the new signature of orte_output_open().
* Literally s/opal_show_help/orte_show_help/. The function signature
is identical.
=== Notes ===
* orte_output'ing to stream 0 will do similar to what
opal_output'ing did, so leaving a hard-coded "0" as the first
argument is safe.
* For systems that do not use ORTE's RML or the HNP, the effect of
orte_output_* and orte_show_help will be identical to their opal
counterparts (the additional information passed to
orte_output_open() will be lost!). Indeed, the orte_* functions
simply become trivial wrappers to their opal_* counterparts. Note
that we have not tested this; the code is simple but it is quite
possible that we mucked something up.
= Filter Framework =
Messages sent view the new orte_* functions described above and
messages output via the IOF on the HNP will now optionally be passed
through a new "filter" framework before being output to
stdout/stderr. The "filter" OPAL MCA framework is intended to allow
preprocessing to messages before they are sent to their final
destinations. The first component that was written in the filter
framework was to create an XML stream, segregating all the messages
into different XML tags, etc. This will allow 3rd party tools to read
the stdout/stderr from the HNP and be able to know exactly what each
text message is (e.g., a help message, another OMPI infrastructure
message, stdout from the user process, stderr from the user process,
etc.).
Filtering is not active by default. Filter components must be
specifically requested, such as:
{{{
$ mpirun --mca filter xml ...
}}}
There can only be one filter component active.
= New MCA Parameters =
The new functionality described above introduces two new MCA
parameters:
* '''orte_base_help_aggregate''': Defaults to 1 (true), meaning that
help messages will be aggregated, as described above. If set to 0,
all help messages will be displayed, even if they are duplicates
(i.e., the original behavior).
* '''orte_base_show_output_recursions''': An MCA parameter to help
debug one of the known issues, described below. It is likely that
this MCA parameter will disappear before v1.3 final.
= Known Issues =
* The XML filter component is not complete. The current output from
this component is preliminary and not real XML. A bit more work
needs to be done to configure.m4 search for an appropriate XML
library/link it in/use it at run time.
* There are possible recursion loops in the orte_output() and
orte_show_help() functions -- e.g., if RML send calls orte_output()
or orte_show_help(). We have some ideas how to fix these, but
figured that it was ok to commit before feature freeze with known
issues. The code currently contains sub-optimal workarounds so
that this will not be a problem, but it would be good to actually
solve the problem rather than have hackish workarounds before v1.3 final.
This commit was SVN r18434.
2008-05-14 00:00:55 +04:00
|
|
|
|
2008-02-28 04:57:57 +03:00
|
|
|
#include "orte/mca/errmgr/errmgr.h"
|
2008-06-09 18:53:58 +04:00
|
|
|
#include "orte/util/show_help.h"
|
2008-02-28 04:57:57 +03:00
|
|
|
|
|
|
|
#include "orte/runtime/runtime.h"
|
2008-06-18 07:15:56 +04:00
|
|
|
#include "orte/runtime/runtime_internals.h"
|
2008-02-28 04:57:57 +03:00
|
|
|
#include "orte/runtime/orte_globals.h"
|
|
|
|
|
|
|
|
/* need the data type support functions here */
|
|
|
|
#include "orte/runtime/data_type_support/orte_dt_support.h"
|
|
|
|
|
2008-09-01 21:15:01 +04:00
|
|
|
#if !ORTE_DISABLE_FULL_SUPPORT
|
2008-02-28 04:57:57 +03:00
|
|
|
|
|
|
|
/* globals used by RTE */
|
|
|
|
bool orte_timing;
|
2008-03-28 05:20:37 +03:00
|
|
|
bool orte_debug_daemons_file_flag = false;
|
2008-08-14 22:59:01 +04:00
|
|
|
bool orte_leave_session_attached;
|
2008-04-17 17:50:59 +04:00
|
|
|
bool orte_do_not_launch = false;
|
2008-03-28 05:20:37 +03:00
|
|
|
bool orted_spin_flag = false;
|
|
|
|
bool orte_static_ports = false;
|
2008-04-02 00:32:17 +04:00
|
|
|
bool orte_keep_fqdn_hostnames = false;
|
2008-06-03 01:46:34 +04:00
|
|
|
int orted_debug_failure;
|
|
|
|
int orted_debug_failure_delay;
|
2008-06-24 21:50:56 +04:00
|
|
|
bool orte_homogeneous_nodes = false;
|
|
|
|
bool orte_hetero_apps = false;
|
2008-08-19 19:19:30 +04:00
|
|
|
bool orte_never_launched = false;
|
2008-09-23 19:46:34 +04:00
|
|
|
bool orte_devel_level_output = false;
|
2008-04-10 02:10:53 +04:00
|
|
|
|
2008-04-30 23:49:53 +04:00
|
|
|
int32_t orte_contiguous_nodes;
|
2008-02-28 04:57:57 +03:00
|
|
|
char **orte_launch_environ;
|
2008-04-14 22:26:08 +04:00
|
|
|
opal_pointer_array_t orte_daemonmap;
|
2008-07-25 21:13:22 +04:00
|
|
|
|
|
|
|
bool orte_hnp_is_allocated = false;
|
2008-08-04 18:25:19 +04:00
|
|
|
bool orte_allocation_required;
|
2008-07-25 21:13:22 +04:00
|
|
|
|
Per the July technical meeting:
Standardize the handling of the orte launch agent option across PLMs. This has been a consistent complaint I have received - each PLM would register its own MCA param to get input on the launch agent for remote nodes (in fact, one or two didn't, but most did). This would then get handled in various and contradictory ways.
Some PLMs would accept only a one-word input. Others accepted multi-word args such as "valgrind orted", but then some would error by putting any prefix specified on the cmd line in front of the incorrect argument.
For example, while using the rsh launcher, if you specified "valgrind orted" as your launch agent and had "--prefix foo" on you cmd line, you would attempt to execute "ssh foo/valgrind orted" - which obviously wouldn't work.
This was all -very- confusing to users, who had to know which PLM was being used so they could even set the right mca param in the first place! And since we don't warn about non-recognized or non-used mca params, half of the time they would wind up not doing what they thought they were telling us to do.
To solve this problem, we did the following:
1. removed all mca params from the individual plms for the launch agent
2. added a new mca param "orte_launch_agent" for this purpose. To further simplify for users, this comes with a new cmd line option "--launch-agent" that can take a multi-word string argument. The value of the param defaults to "orted".
3. added a PLM base function that processes the orte_launch_agent value and adds the contents to a provided argv array. This can subsequently be harvested at-will to handle multi-word values
4. modified the PLMs to use this new function. All the PLMs except for the rsh PLM required very minor change - just called the function and moved on. The rsh PLM required much larger changes as - because of the rsh/ssh cmd line limitations - we had to correctly prepend any provided prefix to the correct argv entry.
5. added a new opal_argv_join_range function that allows the caller to "join" argv entries between two specified indices
Please let me know of any problems. I tried to make this as clean as possible, but cannot compile all PLMs to ensure all is correct.
This commit was SVN r19097.
2008-07-30 22:26:24 +04:00
|
|
|
char *orte_launch_agent;
|
2008-02-28 04:57:57 +03:00
|
|
|
char **orted_cmd_line=NULL;
|
2008-08-05 19:09:29 +04:00
|
|
|
|
2008-08-13 21:47:24 +04:00
|
|
|
orte_job_t *orte_debugger_daemon=NULL;
|
|
|
|
bool orte_enable_debug_cospawn_while_running;
|
|
|
|
int orte_debugger_check_rate;
|
|
|
|
|
2008-08-05 19:09:29 +04:00
|
|
|
orte_trigger_event_t orte_exit, orteds_exit;
|
2008-02-28 04:57:57 +03:00
|
|
|
int orte_exit_status = 0;
|
|
|
|
bool orte_abnormal_term_ordered = false;
|
2008-06-03 01:46:34 +04:00
|
|
|
bool orte_shutdown_in_progress = false;
|
|
|
|
|
|
|
|
int orte_heartbeat_rate;
|
|
|
|
int orte_startup_timeout;
|
2008-04-10 02:10:53 +04:00
|
|
|
|
2008-02-28 04:57:57 +03:00
|
|
|
int orte_timeout_usec_per_proc;
|
|
|
|
float orte_max_timeout;
|
2008-03-05 07:54:57 +03:00
|
|
|
char *orte_default_hostfile;
|
2008-02-28 04:57:57 +03:00
|
|
|
|
2008-05-01 23:19:34 +04:00
|
|
|
opal_buffer_t *orte_tree_launch_cmd = NULL;
|
|
|
|
|
2008-02-28 04:57:57 +03:00
|
|
|
/* global arrays for data storage */
|
2008-02-28 08:32:23 +03:00
|
|
|
opal_pointer_array_t *orte_job_data;
|
|
|
|
opal_pointer_array_t *orte_node_pool;
|
2008-02-28 04:57:57 +03:00
|
|
|
|
2008-09-01 21:15:01 +04:00
|
|
|
#endif /* !ORTE_DISABLE_FULL_RTE */
|
|
|
|
|
2008-09-02 19:07:48 +04:00
|
|
|
int orte_debug_output = -1;
|
2008-09-01 21:15:01 +04:00
|
|
|
bool orte_debug_daemons_flag = false;
|
|
|
|
bool orte_xml_output = false;
|
|
|
|
|
2008-08-01 02:11:46 +04:00
|
|
|
/* See comment in orte/tools/orterun/debuggers.c about this MCA
|
|
|
|
param */
|
|
|
|
bool orte_in_parallel_debugger = false;
|
|
|
|
|
2008-09-01 21:15:01 +04:00
|
|
|
|
2008-05-28 17:29:58 +04:00
|
|
|
int orte_dt_init(void)
|
2008-02-28 04:57:57 +03:00
|
|
|
{
|
2008-05-28 17:29:58 +04:00
|
|
|
int rc;
|
|
|
|
opal_data_type_t tmp;
|
|
|
|
|
2008-02-28 04:57:57 +03:00
|
|
|
/* set default output */
|
2008-06-09 18:53:58 +04:00
|
|
|
orte_debug_output = opal_output_open(NULL);
|
2008-02-28 04:57:57 +03:00
|
|
|
/* open up the verbose output for ORTE debugging */
|
|
|
|
if (orte_debug_flag || 0 < orte_debug_verbosity ||
|
|
|
|
(orte_debug_daemons_flag && (orte_process_info.daemon || orte_process_info.hnp))) {
|
|
|
|
if (0 < orte_debug_verbosity) {
|
2008-06-09 18:53:58 +04:00
|
|
|
opal_output_set_verbosity(orte_debug_output, orte_debug_verbosity);
|
2008-02-28 04:57:57 +03:00
|
|
|
} else {
|
2008-06-09 18:53:58 +04:00
|
|
|
opal_output_set_verbosity(orte_debug_output, 1);
|
2008-02-28 04:57:57 +03:00
|
|
|
}
|
|
|
|
}
|
2008-05-28 17:29:58 +04:00
|
|
|
|
2008-02-28 04:57:57 +03:00
|
|
|
/** register the base system types with the DSS */
|
|
|
|
tmp = ORTE_STD_CNTR;
|
|
|
|
if (ORTE_SUCCESS != (rc = opal_dss.register_type(orte_dt_pack_std_cntr,
|
|
|
|
orte_dt_unpack_std_cntr,
|
|
|
|
(opal_dss_copy_fn_t)orte_dt_copy_std_cntr,
|
|
|
|
(opal_dss_compare_fn_t)orte_dt_compare_std_cntr,
|
|
|
|
(opal_dss_size_fn_t)orte_dt_std_size,
|
|
|
|
(opal_dss_print_fn_t)orte_dt_std_print,
|
|
|
|
(opal_dss_release_fn_t)orte_dt_std_release,
|
|
|
|
OPAL_DSS_UNSTRUCTURED,
|
|
|
|
"ORTE_STD_CNTR", &tmp))) {
|
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
tmp = ORTE_NAME;
|
|
|
|
if (ORTE_SUCCESS != (rc = opal_dss.register_type(orte_dt_pack_name,
|
|
|
|
orte_dt_unpack_name,
|
|
|
|
(opal_dss_copy_fn_t)orte_dt_copy_name,
|
|
|
|
(opal_dss_compare_fn_t)orte_dt_compare_name,
|
|
|
|
(opal_dss_size_fn_t)orte_dt_std_size,
|
|
|
|
(opal_dss_print_fn_t)orte_dt_print_name,
|
|
|
|
(opal_dss_release_fn_t)orte_dt_std_release,
|
|
|
|
OPAL_DSS_UNSTRUCTURED,
|
|
|
|
"ORTE_NAME", &tmp))) {
|
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
|
|
|
tmp = ORTE_VPID;
|
|
|
|
if (ORTE_SUCCESS != (rc = opal_dss.register_type(orte_dt_pack_vpid,
|
|
|
|
orte_dt_unpack_vpid,
|
|
|
|
(opal_dss_copy_fn_t)orte_dt_copy_vpid,
|
|
|
|
(opal_dss_compare_fn_t)orte_dt_compare_vpid,
|
|
|
|
(opal_dss_size_fn_t)orte_dt_std_size,
|
|
|
|
(opal_dss_print_fn_t)orte_dt_std_print,
|
|
|
|
(opal_dss_release_fn_t)orte_dt_std_release,
|
|
|
|
OPAL_DSS_UNSTRUCTURED,
|
|
|
|
"ORTE_VPID", &tmp))) {
|
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
|
|
|
tmp = ORTE_JOBID;
|
|
|
|
if (ORTE_SUCCESS != (rc = opal_dss.register_type(orte_dt_pack_jobid,
|
|
|
|
orte_dt_unpack_jobid,
|
|
|
|
(opal_dss_copy_fn_t)orte_dt_copy_jobid,
|
|
|
|
(opal_dss_compare_fn_t)orte_dt_compare_jobid,
|
|
|
|
(opal_dss_size_fn_t)orte_dt_std_size,
|
|
|
|
(opal_dss_print_fn_t)orte_dt_std_print,
|
|
|
|
(opal_dss_release_fn_t)orte_dt_std_release,
|
|
|
|
OPAL_DSS_UNSTRUCTURED,
|
|
|
|
"ORTE_JOBID", &tmp))) {
|
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
return rc;
|
|
|
|
}
|
2008-09-01 21:15:01 +04:00
|
|
|
|
|
|
|
#if !ORTE_DISABLE_FULL_SUPPORT
|
2008-02-28 04:57:57 +03:00
|
|
|
tmp = ORTE_JOB;
|
|
|
|
if (ORTE_SUCCESS != (rc = opal_dss.register_type(orte_dt_pack_job,
|
|
|
|
orte_dt_unpack_job,
|
|
|
|
(opal_dss_copy_fn_t)orte_dt_copy_job,
|
|
|
|
(opal_dss_compare_fn_t)orte_dt_compare_job,
|
|
|
|
(opal_dss_size_fn_t)orte_dt_size_job,
|
|
|
|
(opal_dss_print_fn_t)orte_dt_print_job,
|
|
|
|
(opal_dss_release_fn_t)orte_dt_std_obj_release,
|
|
|
|
OPAL_DSS_STRUCTURED,
|
|
|
|
"ORTE_JOB", &tmp))) {
|
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
|
|
|
tmp = ORTE_NODE;
|
|
|
|
if (ORTE_SUCCESS != (rc = opal_dss.register_type(orte_dt_pack_node,
|
|
|
|
orte_dt_unpack_node,
|
|
|
|
(opal_dss_copy_fn_t)orte_dt_copy_node,
|
|
|
|
(opal_dss_compare_fn_t)orte_dt_compare_node,
|
|
|
|
(opal_dss_size_fn_t)orte_dt_size_node,
|
|
|
|
(opal_dss_print_fn_t)orte_dt_print_node,
|
|
|
|
(opal_dss_release_fn_t)orte_dt_std_obj_release,
|
|
|
|
OPAL_DSS_STRUCTURED,
|
|
|
|
"ORTE_NODE", &tmp))) {
|
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
|
|
|
tmp = ORTE_PROC;
|
|
|
|
if (ORTE_SUCCESS != (rc = opal_dss.register_type(orte_dt_pack_proc,
|
|
|
|
orte_dt_unpack_proc,
|
|
|
|
(opal_dss_copy_fn_t)orte_dt_copy_proc,
|
|
|
|
(opal_dss_compare_fn_t)orte_dt_compare_proc,
|
|
|
|
(opal_dss_size_fn_t)orte_dt_size_proc,
|
|
|
|
(opal_dss_print_fn_t)orte_dt_print_proc,
|
|
|
|
(opal_dss_release_fn_t)orte_dt_std_obj_release,
|
|
|
|
OPAL_DSS_STRUCTURED,
|
|
|
|
"ORTE_PROC", &tmp))) {
|
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
|
|
|
tmp = ORTE_APP_CONTEXT;
|
|
|
|
if (ORTE_SUCCESS != (rc = opal_dss.register_type(orte_dt_pack_app_context,
|
|
|
|
orte_dt_unpack_app_context,
|
|
|
|
(opal_dss_copy_fn_t)orte_dt_copy_app_context,
|
|
|
|
(opal_dss_compare_fn_t)orte_dt_compare_app_context,
|
|
|
|
(opal_dss_size_fn_t)orte_dt_size_app_context,
|
|
|
|
(opal_dss_print_fn_t)orte_dt_print_app_context,
|
|
|
|
(opal_dss_release_fn_t)orte_dt_std_obj_release,
|
|
|
|
OPAL_DSS_STRUCTURED,
|
|
|
|
"ORTE_APP_CONTEXT", &tmp))) {
|
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
|
|
|
tmp = ORTE_NODE_STATE;
|
|
|
|
if (ORTE_SUCCESS != (rc = opal_dss.register_type(orte_dt_pack_node_state,
|
|
|
|
orte_dt_unpack_node_state,
|
|
|
|
(opal_dss_copy_fn_t)orte_dt_copy_node_state,
|
|
|
|
(opal_dss_compare_fn_t)orte_dt_compare_node_state,
|
|
|
|
(opal_dss_size_fn_t)orte_dt_std_size,
|
|
|
|
(opal_dss_print_fn_t)orte_dt_std_print,
|
|
|
|
(opal_dss_release_fn_t)orte_dt_std_release,
|
|
|
|
OPAL_DSS_UNSTRUCTURED,
|
|
|
|
"ORTE_NODE_STATE", &tmp))) {
|
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
|
|
|
tmp = ORTE_PROC_STATE;
|
|
|
|
if (ORTE_SUCCESS != (rc = opal_dss.register_type(orte_dt_pack_proc_state,
|
|
|
|
orte_dt_unpack_proc_state,
|
|
|
|
(opal_dss_copy_fn_t)orte_dt_copy_proc_state,
|
|
|
|
(opal_dss_compare_fn_t)orte_dt_compare_proc_state,
|
|
|
|
(opal_dss_size_fn_t)orte_dt_std_size,
|
|
|
|
(opal_dss_print_fn_t)orte_dt_std_print,
|
|
|
|
(opal_dss_release_fn_t)orte_dt_std_release,
|
|
|
|
OPAL_DSS_UNSTRUCTURED,
|
|
|
|
"ORTE_PROC_STATE", &tmp))) {
|
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
|
|
|
tmp = ORTE_JOB_STATE;
|
|
|
|
if (ORTE_SUCCESS != (rc = opal_dss.register_type(orte_dt_pack_job_state,
|
|
|
|
orte_dt_unpack_job_state,
|
|
|
|
(opal_dss_copy_fn_t)orte_dt_copy_job_state,
|
|
|
|
(opal_dss_compare_fn_t)orte_dt_compare_job_state,
|
|
|
|
(opal_dss_size_fn_t)orte_dt_std_size,
|
|
|
|
(opal_dss_print_fn_t)orte_dt_std_print,
|
|
|
|
(opal_dss_release_fn_t)orte_dt_std_release,
|
|
|
|
OPAL_DSS_UNSTRUCTURED,
|
|
|
|
"ORTE_JOB_STATE", &tmp))) {
|
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
|
|
|
tmp = ORTE_EXIT_CODE;
|
|
|
|
if (ORTE_SUCCESS != (rc = opal_dss.register_type(orte_dt_pack_exit_code,
|
|
|
|
orte_dt_unpack_exit_code,
|
|
|
|
(opal_dss_copy_fn_t)orte_dt_copy_exit_code,
|
|
|
|
(opal_dss_compare_fn_t)orte_dt_compare_exit_code,
|
|
|
|
(opal_dss_size_fn_t)orte_dt_std_size,
|
|
|
|
(opal_dss_print_fn_t)orte_dt_std_print,
|
|
|
|
(opal_dss_release_fn_t)orte_dt_std_release,
|
|
|
|
OPAL_DSS_UNSTRUCTURED,
|
|
|
|
"ORTE_EXIT_CODE", &tmp))) {
|
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
|
|
|
tmp = ORTE_JOB_MAP;
|
|
|
|
if (ORTE_SUCCESS != (rc = opal_dss.register_type(orte_dt_pack_map,
|
|
|
|
orte_dt_unpack_map,
|
|
|
|
(opal_dss_copy_fn_t)orte_dt_copy_map,
|
|
|
|
(opal_dss_compare_fn_t)orte_dt_compare_map,
|
|
|
|
(opal_dss_size_fn_t)orte_dt_size_map,
|
|
|
|
(opal_dss_print_fn_t)orte_dt_print_map,
|
|
|
|
(opal_dss_release_fn_t)orte_dt_std_obj_release,
|
|
|
|
OPAL_DSS_STRUCTURED,
|
|
|
|
"ORTE_JOB_MAP", &tmp))) {
|
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
|
|
|
tmp = ORTE_RML_TAG;
|
|
|
|
if (ORTE_SUCCESS != (rc = opal_dss.register_type(orte_dt_pack_tag,
|
|
|
|
orte_dt_unpack_tag,
|
|
|
|
(opal_dss_copy_fn_t)orte_dt_copy_tag,
|
|
|
|
(opal_dss_compare_fn_t)orte_dt_compare_tags,
|
|
|
|
(opal_dss_size_fn_t)orte_dt_std_size,
|
|
|
|
(opal_dss_print_fn_t)orte_dt_std_print,
|
|
|
|
(opal_dss_release_fn_t)orte_dt_std_release,
|
|
|
|
OPAL_DSS_UNSTRUCTURED,
|
|
|
|
"ORTE_RML_TAG", &tmp))) {
|
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
|
|
|
tmp = ORTE_DAEMON_CMD;
|
|
|
|
if (ORTE_SUCCESS != (rc = opal_dss.register_type(orte_dt_pack_daemon_cmd,
|
|
|
|
orte_dt_unpack_daemon_cmd,
|
|
|
|
(opal_dss_copy_fn_t)orte_dt_copy_daemon_cmd,
|
|
|
|
(opal_dss_compare_fn_t)orte_dt_compare_daemon_cmd,
|
|
|
|
(opal_dss_size_fn_t)orte_dt_std_size,
|
|
|
|
(opal_dss_print_fn_t)orte_dt_std_print,
|
|
|
|
(opal_dss_release_fn_t)orte_dt_std_release,
|
|
|
|
OPAL_DSS_UNSTRUCTURED,
|
|
|
|
"ORTE_DAEMON_CMD", &tmp))) {
|
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
|
|
|
tmp = ORTE_GRPCOMM_MODE;
|
|
|
|
if (ORTE_SUCCESS != (rc = opal_dss.register_type(orte_dt_pack_grpcomm_mode,
|
|
|
|
orte_dt_unpack_grpcomm_mode,
|
|
|
|
(opal_dss_copy_fn_t)orte_dt_copy_grpcomm_mode,
|
|
|
|
(opal_dss_compare_fn_t)orte_dt_compare_grpcomm_mode,
|
|
|
|
(opal_dss_size_fn_t)orte_dt_std_size,
|
|
|
|
(opal_dss_print_fn_t)orte_dt_std_print,
|
|
|
|
(opal_dss_release_fn_t)orte_dt_std_release,
|
|
|
|
OPAL_DSS_UNSTRUCTURED,
|
|
|
|
"ORTE_GRPCOMM_MODE", &tmp))) {
|
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
return rc;
|
|
|
|
}
|
2008-09-01 21:15:01 +04:00
|
|
|
|
|
|
|
#endif /* !ORTE_DISABLE_FULL_SUPPORT */
|
2008-02-28 04:57:57 +03:00
|
|
|
|
|
|
|
return ORTE_SUCCESS;
|
|
|
|
}
|
|
|
|
|
2008-08-31 22:06:55 +04:00
|
|
|
#if !ORTE_DISABLE_FULL_SUPPORT
|
2008-02-28 04:57:57 +03:00
|
|
|
int orte_hnp_globals_init(void)
|
|
|
|
{
|
|
|
|
int rc;
|
|
|
|
|
2008-02-28 08:32:23 +03:00
|
|
|
orte_job_data = OBJ_NEW(opal_pointer_array_t);
|
|
|
|
if (ORTE_SUCCESS != (rc = opal_pointer_array_init(orte_job_data,
|
2008-02-28 04:57:57 +03:00
|
|
|
1,
|
|
|
|
ORTE_GLOBAL_ARRAY_MAX_SIZE,
|
|
|
|
1))) {
|
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
2008-02-28 08:32:23 +03:00
|
|
|
orte_node_pool = OBJ_NEW(opal_pointer_array_t);
|
|
|
|
if (ORTE_SUCCESS != (rc = opal_pointer_array_init(orte_node_pool,
|
2008-02-28 04:57:57 +03:00
|
|
|
ORTE_GLOBAL_ARRAY_BLOCK_SIZE,
|
|
|
|
ORTE_GLOBAL_ARRAY_MAX_SIZE,
|
|
|
|
ORTE_GLOBAL_ARRAY_BLOCK_SIZE))) {
|
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
|
|
|
return ORTE_SUCCESS;
|
|
|
|
}
|
2008-09-01 21:15:01 +04:00
|
|
|
|
2008-02-28 04:57:57 +03:00
|
|
|
|
|
|
|
orte_job_t* orte_get_job_data_object(orte_jobid_t job)
|
|
|
|
{
|
|
|
|
orte_job_t **jptr;
|
|
|
|
orte_std_cntr_t i;
|
|
|
|
|
|
|
|
/* if I am not an HNP, I cannot provide this object */
|
|
|
|
if (!orte_process_info.hnp) {
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
jptr = (orte_job_t**)orte_job_data->addr;
|
|
|
|
for (i=0; i < orte_job_data->size; i++) {
|
|
|
|
if (NULL != jptr[i] && job == jptr[i]->jobid) {
|
|
|
|
return jptr[i];
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
|
|
|
|
return NULL;
|
|
|
|
}
|
2008-09-01 21:15:01 +04:00
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* CONSTRUCTORS, DESTRUCTORS, AND CLASS INSTANTIATIONS
|
|
|
|
* FOR ORTE CLASSES
|
|
|
|
*/
|
|
|
|
|
|
|
|
static void orte_app_context_construct(orte_app_context_t* app_context)
|
|
|
|
{
|
|
|
|
app_context->idx=0;
|
|
|
|
app_context->app=NULL;
|
|
|
|
app_context->num_procs=0;
|
|
|
|
app_context->argv=NULL;
|
|
|
|
app_context->env=NULL;
|
|
|
|
app_context->cwd=NULL;
|
|
|
|
app_context->user_specified_cwd=false;
|
|
|
|
app_context->hostfile=NULL;
|
|
|
|
app_context->add_hostfile=NULL;
|
|
|
|
app_context->dash_host = NULL;
|
|
|
|
app_context->prefix_dir = NULL;
|
|
|
|
app_context->preload_binary = false;
|
|
|
|
app_context->preload_files = NULL;
|
|
|
|
app_context->preload_files_dest_dir = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void orte_app_context_destructor(orte_app_context_t* app_context)
|
|
|
|
{
|
|
|
|
if (NULL != app_context->app) {
|
|
|
|
free (app_context->app);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* argv and env lists created by util/argv copy functions */
|
|
|
|
if (NULL != app_context->argv) {
|
|
|
|
opal_argv_free(app_context->argv);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (NULL != app_context->env) {
|
|
|
|
opal_argv_free(app_context->env);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (NULL != app_context->cwd) {
|
|
|
|
free (app_context->cwd);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (NULL != app_context->hostfile) {
|
|
|
|
free(app_context->hostfile);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (NULL != app_context->add_hostfile) {
|
|
|
|
free(app_context->add_hostfile);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (NULL != app_context->dash_host) {
|
|
|
|
opal_argv_free(app_context->dash_host);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (NULL != app_context->prefix_dir) {
|
|
|
|
free(app_context->prefix_dir);
|
|
|
|
}
|
|
|
|
|
|
|
|
app_context->preload_binary = false;
|
|
|
|
|
|
|
|
if(NULL != app_context->preload_files) {
|
|
|
|
free(app_context->preload_files);
|
|
|
|
}
|
|
|
|
|
|
|
|
if(NULL != app_context->preload_files_dest_dir) {
|
|
|
|
free(app_context->preload_files_dest_dir);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
OBJ_CLASS_INSTANCE(orte_app_context_t,
|
|
|
|
opal_object_t,
|
|
|
|
orte_app_context_construct,
|
|
|
|
orte_app_context_destructor);
|
|
|
|
|
|
|
|
static void orte_job_construct(orte_job_t* job)
|
|
|
|
{
|
|
|
|
job->jobid = ORTE_JOBID_INVALID;
|
|
|
|
job->apps = OBJ_NEW(opal_pointer_array_t);
|
|
|
|
opal_pointer_array_init(job->apps,
|
|
|
|
1,
|
|
|
|
ORTE_GLOBAL_ARRAY_MAX_SIZE,
|
|
|
|
2);
|
|
|
|
job->num_apps = 0;
|
|
|
|
job->controls = 0;
|
|
|
|
job->total_slots_alloc = 0;
|
|
|
|
job->num_procs = 0;
|
|
|
|
job->procs = OBJ_NEW(opal_pointer_array_t);
|
|
|
|
opal_pointer_array_init(job->procs,
|
|
|
|
ORTE_GLOBAL_ARRAY_BLOCK_SIZE,
|
|
|
|
ORTE_GLOBAL_ARRAY_MAX_SIZE,
|
|
|
|
ORTE_GLOBAL_ARRAY_BLOCK_SIZE);
|
|
|
|
|
|
|
|
job->map = NULL;
|
|
|
|
job->bookmark = NULL;
|
|
|
|
job->oversubscribe_override = false;
|
|
|
|
job->state = ORTE_JOB_STATE_UNDEF;
|
|
|
|
|
|
|
|
job->num_launched = 0;
|
|
|
|
job->num_reported = 0;
|
|
|
|
job->num_terminated = 0;
|
|
|
|
job->abort = false;
|
|
|
|
job->aborted_proc = NULL;
|
|
|
|
|
|
|
|
#if OPAL_ENABLE_FT == 1
|
|
|
|
job->ckpt_state = 0;
|
|
|
|
job->ckpt_snapshot_ref = NULL;
|
|
|
|
job->ckpt_snapshot_loc = NULL;
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
|
|
|
static void orte_job_destruct(orte_job_t* job)
|
|
|
|
{
|
|
|
|
orte_std_cntr_t i;
|
|
|
|
orte_vpid_t j;
|
|
|
|
|
|
|
|
for (i=0; i < job->num_apps; i++) {
|
|
|
|
if (NULL != job->apps->addr[i]) OBJ_RELEASE(job->apps->addr[i]);
|
|
|
|
}
|
|
|
|
OBJ_RELEASE(job->apps);
|
|
|
|
|
|
|
|
for (j=0; j < job->num_procs; j++) {
|
|
|
|
if (NULL != job->procs->addr[j]) OBJ_RELEASE(job->procs->addr[j]);
|
|
|
|
}
|
|
|
|
OBJ_RELEASE(job->procs);
|
|
|
|
|
|
|
|
if (NULL != job->map) OBJ_RELEASE(job->map);
|
|
|
|
|
|
|
|
#if OPAL_ENABLE_FT == 1
|
|
|
|
if (NULL != job->ckpt_snapshot_ref) {
|
|
|
|
free(job->ckpt_snapshot_ref);
|
|
|
|
}
|
|
|
|
if (NULL != job->ckpt_snapshot_loc) {
|
|
|
|
free(job->ckpt_snapshot_loc);
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
|
|
|
OBJ_CLASS_INSTANCE(orte_job_t,
|
|
|
|
opal_list_item_t,
|
|
|
|
orte_job_construct,
|
|
|
|
orte_job_destruct);
|
|
|
|
|
|
|
|
|
|
|
|
static void orte_node_construct(orte_node_t* node)
|
|
|
|
{
|
|
|
|
node->name = NULL;
|
|
|
|
node->index = -1;
|
|
|
|
node->daemon = NULL;
|
|
|
|
node->daemon_launched = false;
|
|
|
|
node->launch_id = -1;
|
|
|
|
|
|
|
|
node->num_procs = 0;
|
|
|
|
node->procs = OBJ_NEW(opal_pointer_array_t);
|
|
|
|
opal_pointer_array_init(node->procs,
|
|
|
|
ORTE_GLOBAL_ARRAY_BLOCK_SIZE,
|
|
|
|
ORTE_GLOBAL_ARRAY_MAX_SIZE,
|
|
|
|
ORTE_GLOBAL_ARRAY_BLOCK_SIZE);
|
|
|
|
node->next_node_rank = 0;
|
|
|
|
|
|
|
|
node->oversubscribed = false;
|
|
|
|
node->arch = 0;
|
|
|
|
node->state = ORTE_NODE_STATE_UNKNOWN;
|
|
|
|
node->slots = 0;
|
|
|
|
node->slots_inuse = 0;
|
|
|
|
node->slots_alloc = 0;
|
|
|
|
node->slots_max = 0;
|
|
|
|
node->username = NULL;
|
|
|
|
node->slot_list = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void orte_node_destruct(orte_node_t* node)
|
|
|
|
{
|
|
|
|
orte_vpid_t i;
|
|
|
|
|
|
|
|
if (NULL != node->name) {
|
|
|
|
free(node->name);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (NULL != node->daemon) OBJ_RELEASE(node->daemon);
|
|
|
|
|
|
|
|
for (i=0; i < node->num_procs; i++) {
|
|
|
|
if (NULL != node->procs->addr[i]) OBJ_RELEASE(node->procs->addr[i]);
|
|
|
|
}
|
|
|
|
OBJ_RELEASE(node->procs);
|
|
|
|
|
|
|
|
if (NULL != node->username) {
|
|
|
|
free(node->username);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
OBJ_CLASS_INSTANCE(orte_node_t,
|
|
|
|
opal_list_item_t,
|
|
|
|
orte_node_construct,
|
|
|
|
orte_node_destruct);
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
static void orte_proc_construct(orte_proc_t* proc)
|
|
|
|
{
|
|
|
|
proc->name = *ORTE_NAME_INVALID;
|
|
|
|
proc->pid = 0;
|
|
|
|
proc->local_rank = UINT8_MAX;
|
|
|
|
proc->node_rank = UINT8_MAX;
|
|
|
|
proc->state = ORTE_PROC_STATE_UNDEF;
|
|
|
|
proc->app_idx = -1;
|
|
|
|
proc->slot_list = NULL;
|
|
|
|
proc->node = NULL;
|
|
|
|
proc->nodename = NULL;
|
|
|
|
proc->rml_uri = NULL;
|
|
|
|
proc->beat = 0;
|
|
|
|
#if OPAL_ENABLE_FT == 1
|
|
|
|
proc->ckpt_state = 0;
|
|
|
|
proc->ckpt_snapshot_ref = NULL;
|
|
|
|
proc->ckpt_snapshot_loc = NULL;
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
|
|
|
static void orte_proc_destruct(orte_proc_t* proc)
|
|
|
|
{
|
|
|
|
/* do NOT free the nodename field as this is
|
|
|
|
* simply a pointer to a field in the
|
|
|
|
* associated node object - the node object
|
|
|
|
* will free it
|
|
|
|
*/
|
|
|
|
|
|
|
|
if (NULL != proc->slot_list) {
|
|
|
|
free(proc->slot_list);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (NULL != proc->node) OBJ_RELEASE(proc->node);
|
|
|
|
|
|
|
|
if (NULL != proc->rml_uri) free(proc->rml_uri);
|
|
|
|
|
|
|
|
#if OPAL_ENABLE_FT == 1
|
|
|
|
if (NULL != proc->ckpt_snapshot_ref) {
|
|
|
|
free(proc->ckpt_snapshot_ref);
|
|
|
|
}
|
|
|
|
if (NULL != proc->ckpt_snapshot_loc) {
|
|
|
|
free(proc->ckpt_snapshot_loc);
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
|
|
|
OBJ_CLASS_INSTANCE(orte_proc_t,
|
|
|
|
opal_list_item_t,
|
|
|
|
orte_proc_construct,
|
|
|
|
orte_proc_destruct);
|
|
|
|
|
|
|
|
static void orte_nid_construct(orte_nid_t *ptr)
|
|
|
|
{
|
|
|
|
ptr->name = NULL;
|
|
|
|
ptr->daemon = ORTE_VPID_INVALID;
|
|
|
|
ptr->arch = orte_process_info.arch;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void orte_nid_destruct(orte_nid_t *ptr)
|
|
|
|
{
|
|
|
|
if (NULL != ptr->name) {
|
|
|
|
free(ptr->name);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
OBJ_CLASS_INSTANCE(orte_nid_t,
|
|
|
|
opal_object_t,
|
|
|
|
orte_nid_construct,
|
|
|
|
orte_nid_destruct);
|
|
|
|
|
|
|
|
static void orte_pmap_construct(orte_pmap_t *ptr)
|
|
|
|
{
|
|
|
|
ptr->node = -1;
|
|
|
|
ptr->local_rank = 0;
|
|
|
|
ptr->node_rank = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
OBJ_CLASS_INSTANCE(orte_pmap_t,
|
|
|
|
opal_object_t,
|
|
|
|
orte_pmap_construct,
|
|
|
|
NULL);
|
|
|
|
|
|
|
|
|
|
|
|
static void orte_jmap_construct(orte_jmap_t *ptr)
|
|
|
|
{
|
|
|
|
ptr->job = ORTE_JOBID_INVALID;
|
|
|
|
OBJ_CONSTRUCT(&ptr->pmap, opal_value_array_t);
|
|
|
|
opal_value_array_init(&ptr->pmap, sizeof(orte_pmap_t));
|
|
|
|
}
|
|
|
|
|
|
|
|
static void orte_jmap_destruct(orte_jmap_t *ptr)
|
|
|
|
{
|
|
|
|
OBJ_DESTRUCT(&ptr->pmap);
|
|
|
|
}
|
|
|
|
|
|
|
|
OBJ_CLASS_INSTANCE(orte_jmap_t,
|
|
|
|
opal_object_t,
|
|
|
|
orte_jmap_construct,
|
|
|
|
orte_jmap_destruct);
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
static void orte_job_map_construct(orte_job_map_t* map)
|
|
|
|
{
|
|
|
|
map->policy = ORTE_RMAPS_BYSLOT; /* default to byslot mapping as per orterun options */
|
|
|
|
map->pernode = false;
|
|
|
|
map->npernode = 0;
|
|
|
|
map->oversubscribe = true; /* default to allowing oversubscribe */
|
|
|
|
map->display_map = false;
|
|
|
|
map->cpu_lists = false;
|
|
|
|
map->num_new_daemons = 0;
|
|
|
|
map->daemon_vpid_start = ORTE_VPID_INVALID;
|
|
|
|
map->num_nodes = 0;
|
|
|
|
map->nodes = OBJ_NEW(opal_pointer_array_t);
|
|
|
|
opal_pointer_array_init(map->nodes,
|
|
|
|
ORTE_GLOBAL_ARRAY_BLOCK_SIZE,
|
|
|
|
ORTE_GLOBAL_ARRAY_MAX_SIZE,
|
|
|
|
ORTE_GLOBAL_ARRAY_BLOCK_SIZE);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void orte_job_map_destruct(orte_job_map_t* map)
|
|
|
|
{
|
|
|
|
orte_std_cntr_t i;
|
|
|
|
|
|
|
|
for (i=0; i < map->nodes->size; i++) {
|
|
|
|
if (NULL != map->nodes->addr[i]) {
|
|
|
|
OBJ_RELEASE(map->nodes->addr[i]);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
OBJ_RELEASE(map->nodes);
|
|
|
|
}
|
|
|
|
|
|
|
|
OBJ_CLASS_INSTANCE(orte_job_map_t,
|
|
|
|
opal_object_t,
|
|
|
|
orte_job_map_construct,
|
|
|
|
orte_job_map_destruct);
|
|
|
|
#endif
|