Source

mpi3-fortran / orte / orted / orted_main.c

Full commit
  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
/*
 * Copyright (c) 2004-2010 The Trustees of Indiana University and Indiana
 *                         University Research and Technology
 *                         Corporation.  All rights reserved.
 * Copyright (c) 2004-2011 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 (c) 2007-2011 Cisco Systems, Inc.  All rights reserved.
 * Copyright (c) 2007-2012 Los Alamos National Security, LLC.  All rights
 *                         reserved. 
 * Copyright (c) 2009      Institut National de Recherche en Informatique
 *                         et Automatique. All rights reserved.
 * Copyright (c) 2010      Oracle and/or its affiliates.  All rights reserved. 
 * $COPYRIGHT$
 *
 * Additional copyrights may follow
 *
 * $HEADER$
 */

#include "orte_config.h"
#include "orte/constants.h"

#ifdef HAVE_STRING_H
#include <string.h>
#endif

#include <stdio.h>
#include <ctype.h>
#ifdef HAVE_UNISTD_H
#include <unistd.h>
#endif
#ifdef HAVE_NETDB_H
#include <netdb.h>
#endif
#ifdef HAVE_SYS_PARAM_H
#include <sys/param.h>
#endif
#include <fcntl.h>
#include <errno.h>
#include <signal.h>
#ifdef HAVE_SYS_TIME_H
#include <sys/time.h>
#endif  /* HAVE_SYS_TIME_H */


#include "opal/mca/event/event.h"
#include "opal/mca/base/base.h"
#include "opal/util/output.h"
#include "opal/util/cmd_line.h"
#include "opal/util/opal_environ.h"
#include "opal/util/os_path.h"
#include "opal/util/printf.h"
#include "opal/util/argv.h"
#include "opal/runtime/opal.h"
#include "opal/mca/base/mca_base_param.h"
#include "opal/util/daemon_init.h"
#include "opal/dss/dss.h"
#include "opal/mca/hwloc/hwloc.h"

#include "orte/util/show_help.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/mca/rml/base/rml_contact.h"

#include "orte/mca/errmgr/errmgr.h"
#include "orte/mca/ess/ess.h"
#include "orte/mca/grpcomm/grpcomm.h"
#include "orte/mca/grpcomm/base/base.h"
#include "orte/mca/rml/rml.h"
#include "orte/mca/rml/rml_types.h"
#include "orte/mca/odls/odls.h"
#include "orte/mca/odls/base/odls_private.h"
#include "orte/mca/plm/plm.h"
#include "orte/mca/ras/ras.h"
#include "orte/mca/routed/routed.h"
#include "orte/mca/rmaps/rmaps_types.h"
#include "orte/mca/state/state.h"

/* need access to the create_jobid fn used by plm components
* so we can set singleton name, if necessary
*/
#include "orte/mca/plm/base/plm_private.h"

#include "orte/runtime/runtime.h"
#include "orte/runtime/orte_globals.h"
#include "orte/runtime/orte_locks.h"
#include "orte/runtime/orte_quit.h"

#include "orte/orted/orted.h"

/*
 * Globals
 */
static opal_event_t *pipe_handler;
static void shutdown_callback(int fd, short flags, void *arg);
static void pipe_closed(int fd, short flags, void *arg);

static struct {
    bool debug;
    bool help;
    bool set_sid;
    bool hnp;
    bool daemonize;
    char* name;
    char* vpid_start;
    char* num_procs;
    int uri_pipe;
    int singleton_died_pipe;
    int fail;
    int fail_delay;
    bool abort;
    bool mapreduce;
    bool tree_spawn;
} orted_globals;

/*
 * define the orted context table for obtaining parameters
 */
opal_cmd_line_init_t orte_cmd_line_opts[] = {
    /* Various "obvious" options */
    { NULL, 'h', NULL, "help", 0,
      &orted_globals.help, OPAL_CMD_LINE_TYPE_BOOL,
      "This help message" },

    { "orte_daemon_spin", 's', NULL, "spin", 0,
      &orted_spin_flag, OPAL_CMD_LINE_TYPE_BOOL,
      "Have the orted spin until we can connect a debugger to it" },

    { NULL, '\0', NULL, "debug-failure", 1,
      &orted_globals.fail, OPAL_CMD_LINE_TYPE_INT,
      "Have the specified orted fail after init for debugging purposes" },
    
    { NULL, '\0', NULL, "debug-failure-delay", 1,
      &orted_globals.fail_delay, OPAL_CMD_LINE_TYPE_INT,
      "Have the orted specified for failure delay for the provided number of seconds before failing" },
    
    { "orte_debug", 'd', NULL, "debug", 0,
      NULL, OPAL_CMD_LINE_TYPE_BOOL,
      "Debug the OpenRTE" },
        
    { "orte_daemonize", '\0', NULL, "daemonize", 0,
      &orted_globals.daemonize, OPAL_CMD_LINE_TYPE_BOOL,
      "Daemonize the orted into the background" },

    { "orte_debug_daemons", '\0', NULL, "debug-daemons", 0,
      &orted_globals.debug, OPAL_CMD_LINE_TYPE_BOOL,
      "Enable debugging of OpenRTE daemons" },

    { "orte_debug_daemons_file", '\0', NULL, "debug-daemons-file", 0,
      NULL, OPAL_CMD_LINE_TYPE_BOOL,
      "Enable debugging of OpenRTE daemons, storing output in files" },

    { NULL, '\0', NULL, "hnp", 0,
      &orted_globals.hnp, OPAL_CMD_LINE_TYPE_BOOL,
      "Direct the orted to act as the HNP"},

    { "orte_hnp_uri", '\0', NULL, "hnp-uri", 1,
      NULL, OPAL_CMD_LINE_TYPE_STRING,
      "URI for the HNP"},
    
    { "orte_parent_uri", '\0', NULL, "parent-uri", 1,
      NULL, OPAL_CMD_LINE_TYPE_STRING,
      "URI for the parent if tree launch is enabled."},
    
    { "orte_use_common_port", '\0', NULL, "use-common-port", 0,
      NULL, OPAL_CMD_LINE_TYPE_BOOL,
      "Use the same port as the HNP."},
    
    { NULL, '\0', NULL, "tree-spawn", 0,
      &orted_globals.tree_spawn, OPAL_CMD_LINE_TYPE_BOOL,
      "Tree spawn is underway"},
    
    { NULL, '\0', NULL, "set-sid", 0,
      &orted_globals.set_sid, OPAL_CMD_LINE_TYPE_BOOL,
      "Direct the orted to separate from the current session"},
    
    { "tmpdir_base", '\0', NULL, "tmpdir", 1,
      NULL, OPAL_CMD_LINE_TYPE_STRING,
      "Set the root for the session directory tree" },

    { NULL, '\0', NULL, "report-uri", 1,
      &orted_globals.uri_pipe, OPAL_CMD_LINE_TYPE_INT,
      "Report this process' uri on indicated pipe"},

    { NULL, '\0', NULL, "singleton-died-pipe", 1,
      &orted_globals.singleton_died_pipe, OPAL_CMD_LINE_TYPE_INT,
      "Watch on indicated pipe for singleton termination"},
    
    { "orte_output_filename", '\0', "output-filename", "output-filename", 1,
      NULL, OPAL_CMD_LINE_TYPE_STRING,
      "Redirect output from application processes into filename.rank" },
    
    { "orte_xterm", '\0', "xterm", "xterm", 1,
      NULL, OPAL_CMD_LINE_TYPE_STRING,
      "Create a new xterm window and display output from the specified ranks there" },

    { "orte_report_bindings", '\0', "report-bindings", "report-bindings", 0,
      NULL, OPAL_CMD_LINE_TYPE_BOOL,
      "Whether to report process bindings to stderr" },

    { "orte_node_regex", '\0', "nodes", "nodes", 1,
      NULL, OPAL_CMD_LINE_TYPE_STRING,
      "Regular expression defining nodes in system" },

#if OPAL_HAVE_HWLOC
    { "orte_hetero_nodes", '\0', NULL, "hetero-nodes", 0,
      NULL, OPAL_CMD_LINE_TYPE_BOOL,
      "Nodes in cluster may differ in topology, so send the topology back from each node [Default = false]" },
#endif

    { NULL, '\0', "mapreduce", "mapreduce", 0,
      &orted_globals.mapreduce, OPAL_CMD_LINE_TYPE_BOOL,
      "Whether to report process bindings to stderr" },

    /* End of list */
    { NULL, '\0', NULL, NULL, 0,
      NULL, OPAL_CMD_LINE_TYPE_NULL, NULL }
};

static void rml_cbfunc(int status,
                       struct orte_process_name_t* peer,
                       struct opal_buffer_t* buffer,
                       orte_rml_tag_t tag,
                       void* cbdata)
{
    OBJ_RELEASE(buffer);
}

int orte_daemon(int argc, char *argv[])
{
    int ret = 0;
    opal_cmd_line_t *cmd_line = NULL;
    char *rml_uri;
    int i;
    opal_buffer_t *buffer;
    char hostname[100];
    char *tmp_env_var = NULL;
    
    /* initialize the globals */
    memset(&orted_globals, 0, sizeof(orted_globals));
    /* initialize the singleton died pipe to an illegal value so we can detect it was set */
    orted_globals.singleton_died_pipe = -1;
    /* init the failure orted vpid to an invalid value */
    orted_globals.fail = ORTE_VPID_INVALID;
    
    /* setup to check common command line options that just report and die */
    cmd_line = OBJ_NEW(opal_cmd_line_t);
    if (OPAL_SUCCESS != opal_cmd_line_create(cmd_line, orte_cmd_line_opts)) {
        OBJ_RELEASE(cmd_line);
        exit(1);
    }
    mca_base_cmd_line_setup(cmd_line);
    if (ORTE_SUCCESS != (ret = opal_cmd_line_parse(cmd_line, false,
                                                   argc, argv))) {
        char *args = NULL;
        args = opal_cmd_line_get_usage_msg(cmd_line);
        fprintf(stderr, "Usage: %s [OPTION]...\n%s\n", argv[0], args);
        free(args);
        OBJ_RELEASE(cmd_line);
        return ret;
    }
    
    /*
     * Since this process can now handle MCA/GMCA parameters, make sure to
     * process them.
     */
    mca_base_cmd_line_process_args(cmd_line, &environ, &environ);
    
    /* Ensure that enough of OPAL is setup for us to be able to run */
    /*
     * NOTE: (JJH)
     *  We need to allow 'mca_base_cmd_line_process_args()' to process command
     *  line arguments *before* calling opal_init_util() since the command
     *  line could contain MCA parameters that affect the way opal_init_util()
     *  functions. AMCA parameters are one such option normally received on the
     *  command line that affect the way opal_init_util() behaves.
     *  It is "safe" to call mca_base_cmd_line_process_args() before 
     *  opal_init_util() since mca_base_cmd_line_process_args() does *not*
     *  depend upon opal_init_util() functionality.
     */
    if (OPAL_SUCCESS != opal_init_util(&argc, &argv)) {
        fprintf(stderr, "OPAL failed to initialize -- orted aborting\n");
        exit(1);
    }

    /* save the environment for launch purposes. This MUST be
     * done so that we can pass it to any local procs we
     * spawn - otherwise, those local procs won't see any
     * non-MCA envars that were set in the enviro when the
     * orted was executed - e.g., by .csh
     */
    orte_launch_environ = opal_argv_copy(environ);
    
    /* purge any ess flag set in the environ when we were launched */
    opal_unsetenv("OMPI_MCA_ess", &orte_launch_environ);
    
    /* if orte_daemon_debug is set, let someone know we are alive right
     * away just in case we have a problem along the way
     */
    if (orted_globals.debug) {
        gethostname(hostname, 100);
        fprintf(stderr, "Daemon was launched on %s - beginning to initialize\n", hostname);
    }
    
    /* check for help request */
    if (orted_globals.help) {
        char *args = NULL;
        args = opal_cmd_line_get_usage_msg(cmd_line);
        orte_show_help("help-orted.txt", "orted:usage", false,
                       argv[0], args);
        free(args);
        return 1;
    }
#if defined(HAVE_SETSID) && !defined(__WINDOWS__)
    /* see if we were directed to separate from current session */
    if (orted_globals.set_sid) {
        setsid();
    }
#endif  /* !defined(__WINDOWS__) */
    /* see if they want us to spin until they can connect a debugger to us */
    i=0;
    while (orted_spin_flag) {
        i++;
        if (1000 < i) i=0;        
    }

#if OPAL_ENABLE_FT_CR == 1
    /* Mark as a tool program */
    tmp_env_var = mca_base_param_env_var("opal_cr_is_tool");
    opal_setenv(tmp_env_var,
                "1",
                true, &environ);
    free(tmp_env_var);
#endif
    tmp_env_var = NULL; /* Silence compiler warning */

    /* if mapreduce set, flag it */
    if (orted_globals.mapreduce) {
        orte_map_reduce = true;
    }

    /* Set the flag telling OpenRTE that I am NOT a
     * singleton, but am "infrastructure" - prevents setting
     * up incorrect infrastructure that only a singleton would
     * require.
     */
    if (orted_globals.hnp) {
        if (ORTE_SUCCESS != (ret = orte_init(&argc, &argv, ORTE_PROC_HNP))) {
            ORTE_ERROR_LOG(ret);
            return ret;
        }
    } else {
        if (ORTE_SUCCESS != (ret = orte_init(&argc, &argv, ORTE_PROC_DAEMON))) {
            ORTE_ERROR_LOG(ret);
            return ret;
        }
    }
    /* finalize the OPAL utils. As they are opened again from orte_init->opal_init
     * we continue to have a reference count on them. So we have to finalize them twice...
     */
    opal_finalize_util();

    if ((int)ORTE_VPID_INVALID != orted_globals.fail) {
        orted_globals.abort=false;
        /* some vpid was ordered to fail. The value can be positive
         * or negative, depending upon the desired method for failure,
         * so need to check both here
         */
        if (0 > orted_globals.fail) {
            orted_globals.fail = -1*orted_globals.fail;
            orted_globals.abort = true;
        }
        /* are we the specified vpid? */
        if ((int)ORTE_PROC_MY_NAME->vpid == orted_globals.fail) {
            /* if the user specified we delay, then setup a timer
             * and have it kill us
             */
            if (0 < orted_globals.fail_delay) {
                ORTE_TIMER_EVENT(orted_globals.fail_delay, 0, shutdown_callback, ORTE_SYS_PRI);
                
            } else {
                opal_output(0, "%s is executing clean %s", ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
                            orted_globals.abort ? "abort" : "abnormal termination");

                /* do -not- call finalize as this will send a message to the HNP
                 * indicating clean termination! Instead, just forcibly cleanup
                 * the local session_dir tree and exit
                 */
                orte_session_dir_cleanup(ORTE_JOBID_WILDCARD);
                
                /* if we were ordered to abort, do so */
                if (orted_globals.abort) {
                    abort();
                }
                
                /* otherwise, return with non-zero status */
                ret = ORTE_ERROR_DEFAULT_EXIT_CODE;
                goto DONE;
            }
        }
    }

    /* detach from controlling terminal
     * otherwise, remain attached so output can get to us
     */
    if(!orte_debug_flag &&
       !orte_debug_daemons_flag &&
       orted_globals.daemonize) {
        opal_daemon_init(NULL);
    }
    
    /* insert our contact info into our process_info struct so we
     * have it for later use and set the local daemon field to our name
     */
    orte_process_info.my_daemon_uri = orte_rml.get_contact_info();
    ORTE_PROC_MY_DAEMON->jobid = ORTE_PROC_MY_NAME->jobid;
    ORTE_PROC_MY_DAEMON->vpid = ORTE_PROC_MY_NAME->vpid;
    
    /* if I am also the hnp, then update that contact info field too */
    if (ORTE_PROC_IS_HNP) {
        orte_process_info.my_hnp_uri = orte_rml.get_contact_info();
        ORTE_PROC_MY_HNP->jobid = ORTE_PROC_MY_NAME->jobid;
        ORTE_PROC_MY_HNP->vpid = ORTE_PROC_MY_NAME->vpid;
    }
    
    /* setup the primary daemon command receive function */
    ret = orte_rml.recv_buffer_nb(ORTE_NAME_WILDCARD, ORTE_RML_TAG_DAEMON,
                                  ORTE_RML_PERSISTENT, orte_daemon_recv, NULL);
    if (ret != ORTE_SUCCESS && ret != ORTE_ERR_NOT_IMPLEMENTED) {
        ORTE_ERROR_LOG(ret);
        goto DONE;
    }
    
    /* output a message indicating we are alive, our name, and our pid
     * for debugging purposes
     */
    if (orte_debug_daemons_flag) {
        fprintf(stderr, "Daemon %s checking in as pid %ld on host %s\n",
                ORTE_NAME_PRINT(ORTE_PROC_MY_NAME), (long)orte_process_info.pid,
                orte_process_info.nodename);
    }

    /* We actually do *not* want the orted to voluntarily yield() the
       processor more than necessary.  The orted already blocks when
       it is doing nothing, so it doesn't use any more CPU cycles than
       it should; but when it *is* doing something, we do not want it
       to be unnecessarily delayed because it voluntarily yielded the
       processor in the middle of its work.

       For example: when a message arrives at the orted, we want the
       OS to wake up the orted in a timely fashion (which most OS's
       seem good about doing) and then we want the orted to process
       the message as fast as possible.  If the orted yields and lets
       aggressive MPI applications get the processor back, it may be a
       long time before the OS schedules the orted to run again
       (particularly if there is no IO event to wake it up).  Hence,
       routed OOB messages (for example) may be significantly delayed
       before being delivered to MPI processes, which can be
       problematic in some scenarios (e.g., COMM_SPAWN, BTL's that
       require OOB messages for wireup, etc.). */
    opal_progress_set_yield_when_idle(false);

    /* Change the default behavior of libevent such that we want to
       continually block rather than blocking for the default timeout
       and then looping around the progress engine again.  There
       should be nothing in the orted that cannot block in libevent
       until "something" happens (i.e., there's no need to keep
       cycling through progress because the only things that should
       happen will happen in libevent).  This is a minor optimization,
       but what the heck... :-) */
    opal_progress_set_event_flag(OPAL_EVLOOP_ONCE);

    /* if requested, obtain and report a new process name and my uri to the indicated pipe */
    if (orted_globals.uri_pipe > 0) {
        orte_job_t *jdata;
        orte_proc_t *proc;
        orte_node_t *node;
        orte_app_context_t *app;
        char *tmp, *nptr, *sysinfo;
        int32_t ljob;
        orte_grpcomm_collective_t *coll;
        orte_namelist_t *nm;

        /* setup the singleton's job */
        jdata = OBJ_NEW(orte_job_t);
        orte_plm_base_create_jobid(jdata);
        ljob = ORTE_LOCAL_JOBID(jdata->jobid);
        opal_pointer_array_set_item(orte_job_data, ljob, jdata);

        /* must create a map for it (even though it has no
         * info in it) so that the job info will be picked
         * up in subsequent pidmaps or other daemons won't
         * know how to route
         */
        jdata->map = OBJ_NEW(orte_job_map_t);

        /* setup an app_context for the singleton */
        app = OBJ_NEW(orte_app_context_t);
        app->app = strdup("singleton");
        app->num_procs = 1;
        opal_pointer_array_add(jdata->apps, app);
        
        /* setup a proc object for the singleton - since we
         * -must- be the HNP, and therefore we stored our
         * node on the global node pool, and since the singleton
         * -must- be on the same node as us, indicate that
         */
        proc = OBJ_NEW(orte_proc_t);
        proc->name.jobid = jdata->jobid;
        proc->name.vpid = 0;
        proc->alive = true;
        proc->state = ORTE_PROC_STATE_RUNNING;
        proc->app_idx = 0;
        /* obviously, it is on my node */
        node = (orte_node_t*)opal_pointer_array_get_item(orte_node_pool, 0);
        proc->node = node;
        OBJ_RETAIN(node);  /* keep accounting straight */
        opal_pointer_array_add(jdata->procs, proc);
        jdata->num_procs = 1;
        /* and it obviously is on the node */
        OBJ_RETAIN(proc);
        opal_pointer_array_add(node->procs, proc);
        node->num_procs++;
        /* and obviously it is one of my local procs */
        OBJ_RETAIN(proc);
        opal_pointer_array_add(orte_local_children, proc);
        jdata->num_local_procs = 1;
        /* set the trivial */
        proc->local_rank = 0;
        proc->node_rank = 0;
        proc->app_rank = 0;
        proc->state = ORTE_PROC_STATE_RUNNING;
        proc->alive = true;
        proc->app_idx = 0;
        proc->local_proc = true;
#if OPAL_HAVE_HWLOC
        proc->bind_idx = 0;
#endif

        /* create the collectives for its modex/barriers */
        jdata->peer_modex = orte_grpcomm_base_get_coll_id();
        coll = orte_grpcomm_base_setup_collective(jdata->peer_modex);
        nm = OBJ_NEW(orte_namelist_t);
        nm->name.jobid = jdata->jobid;
        nm->name.vpid = ORTE_VPID_WILDCARD;
        opal_list_append(&coll->participants, &nm->super);

        jdata->peer_init_barrier = orte_grpcomm_base_get_coll_id();
        coll = orte_grpcomm_base_setup_collective(jdata->peer_init_barrier);
        nm = OBJ_NEW(orte_namelist_t);
        nm->name.jobid = jdata->jobid;
        nm->name.vpid = ORTE_VPID_WILDCARD;
        opal_list_append(&coll->participants, &nm->super);

        jdata->peer_fini_barrier = orte_grpcomm_base_get_coll_id();
        coll = orte_grpcomm_base_setup_collective(jdata->peer_fini_barrier);
        nm = OBJ_NEW(orte_namelist_t);
        nm->name.jobid = jdata->jobid;
        nm->name.vpid = ORTE_VPID_WILDCARD;
        opal_list_append(&coll->participants, &nm->super);

        /* need to setup a pidmap for it */
        if (ORTE_SUCCESS != (ret = orte_util_encode_pidmap(&orte_pidmap, false))) {
            ORTE_ERROR_LOG(ret);
            goto DONE;
        }
    
        /* if we don't yet have a daemon map, then we have to generate one
         * to pass back to it
         */
        if (NULL != orte_nidmap.bytes) {
            free(orte_nidmap.bytes);
        }
        if (ORTE_SUCCESS != (ret = orte_util_encode_nodemap(&orte_nidmap, false))) {
            ORTE_ERROR_LOG(ret);
            goto DONE;
        }

        /* create a string that contains our uri + the singleton's name + sysinfo */
        orte_util_convert_process_name_to_string(&nptr, &proc->name);
        orte_util_convert_sysinfo_to_string(&sysinfo, orte_local_cpu_type, orte_local_cpu_model);
        asprintf(&tmp, "%s[%s][%s]", orte_process_info.my_daemon_uri, nptr, sysinfo);
        free(nptr);
	free(sysinfo);

        /* pass that info to the singleton */
#ifndef __WINDOWS__
        write(orted_globals.uri_pipe, tmp, strlen(tmp)+1); /* need to add 1 to get the NULL */
#else
        send(orted_globals.uri_pipe, tmp, strlen(tmp)+1, 0); /* need to add 1 to get the NULL */
#endif

        /* cleanup */
        free(tmp);

        /* since a singleton spawned us, we need to harvest
         * any MCA params from the local environment so
         * we can pass them along to any subsequent daemons
         * we may start as the result of a comm_spawn
         */
        for (i=0; NULL != environ[i]; i++) {
            if (0 == strncmp(environ[i], "OMPI_MCA", 8)) {
                /* make a copy to manipulate */
                tmp = strdup(environ[i]);
                /* find the equal sign */
                nptr = strchr(tmp, '=');
                *nptr = '\0';
                nptr++;
                /* add the mca param to the orted cmd line */
                opal_argv_append_nosize(&orted_cmd_line, "-mca");
                opal_argv_append_nosize(&orted_cmd_line, &tmp[9]);
                opal_argv_append_nosize(&orted_cmd_line, nptr);
                free(tmp);
            }
        }
    }

    /* if we were given a pipe to monitor for singleton termination, set that up */
    if (orted_globals.singleton_died_pipe > 0) {
        /* register shutdown handler */
        pipe_handler = (opal_event_t*)malloc(sizeof(opal_event_t));
        opal_event_set(orte_event_base, pipe_handler,
                       orted_globals.singleton_died_pipe,
                       OPAL_EV_READ,
                       pipe_closed,
                       pipe_handler);
        opal_event_add(pipe_handler, NULL);
    }

    /* If I have a parent, then save his contact info so
     * any messages we send can flow thru him.
     */
    mca_base_param_reg_string_name("orte", "parent_uri",
                                   "URI for the parent if tree launch is enabled.",
                                   true, false, NULL,  &rml_uri);
    if (NULL != rml_uri) {
        orte_process_name_t parent;

        /* set the contact info into the hash table */
        if (ORTE_SUCCESS != (ret = orte_rml.set_contact_info(rml_uri))) {
            ORTE_ERROR_LOG(ret);
            free(rml_uri);
            goto DONE;
        }
        ret = orte_rml_base_parse_uris(rml_uri, &parent, NULL );
        if( ORTE_SUCCESS != ret ) {
            ORTE_ERROR_LOG(ret);
            free(rml_uri);
            goto DONE;
        }
        free(rml_uri);
        /* tell the routed module that we have a path
         * back to the HNP
         */
        if (ORTE_SUCCESS != (ret = orte_routed.update_route(ORTE_PROC_MY_HNP, &parent))) {
            ORTE_ERROR_LOG(ret);
            goto DONE;
        }
        /* set the lifeline to point to our parent so that we
         * can handle the situation if that lifeline goes away
         */
        if (ORTE_SUCCESS != (ret = orte_routed.set_lifeline(&parent))) {
            ORTE_ERROR_LOG(ret);
            goto DONE;
        }
    }

    /* if we are not the HNP...the only time we will be an HNP
     * is if we are launched by a singleton to provide support
     * for it
     */
    if (!ORTE_PROC_IS_HNP) {
        /* send the information to the orted report-back point - this function
         * will process the data, but also counts the number of
         * orteds that reported back so the launch procedure can continue.
         * We need to do this at the last possible second as the HNP
         * can turn right around and begin issuing orders to us
         */

        buffer = OBJ_NEW(opal_buffer_t);
        /* insert our name for rollup purposes */
        if (ORTE_SUCCESS != (ret = opal_dss.pack(buffer, ORTE_PROC_MY_NAME, 1, ORTE_NAME))) {
            ORTE_ERROR_LOG(ret);
            OBJ_RELEASE(buffer);
            goto DONE;
        }
        /* for now, always include our contact info, even if we are using
         * static ports. Eventually, this will be removed
         */
        rml_uri = orte_rml.get_contact_info();
        if (ORTE_SUCCESS != (ret = opal_dss.pack(buffer, &rml_uri, 1, OPAL_STRING))) {
            ORTE_ERROR_LOG(ret);
            OBJ_RELEASE(buffer);
            goto DONE;
        }

        /* include our node name */
        opal_dss.pack(buffer, &orte_process_info.nodename, 1, OPAL_STRING);
        
#if OPAL_HAVE_HWLOC
        /* add the local topology */
        if (NULL != opal_hwloc_topology &&
            (1 == ORTE_PROC_MY_NAME->vpid || orte_hetero_nodes)) {
            if (ORTE_SUCCESS != (ret = opal_dss.pack(buffer, &opal_hwloc_topology, 1, OPAL_HWLOC_TOPO))) {
                ORTE_ERROR_LOG(ret);
            }
        }
#endif

        if ((orte_static_ports || orte_use_common_port) && !orted_globals.tree_spawn) {
            /* use the rollup collective to send our data to the HNP
             * so we minimize the HNP bottleneck
             */
            orte_grpcomm_collective_t *coll;
            coll = OBJ_NEW(orte_grpcomm_collective_t);
            /* get the list of contributors we need from the routed module */
            orte_routed.get_routing_list(ORTE_GRPCOMM_COLL_PEERS, coll);
            /* add the collective to our list */
            opal_list_append(&orte_grpcomm_base.active_colls, &coll->super);
            /* send the buffer to ourselves to start the collective */
            if (0 > (ret = orte_rml.send_buffer_nb(ORTE_PROC_MY_NAME, buffer,
                                                   ORTE_RML_TAG_ROLLUP, 0,
                                                   rml_cbfunc, NULL))) {
                ORTE_ERROR_LOG(ret);
                OBJ_RELEASE(buffer);
                goto DONE;
            }
        } else {
            /* send directly to the HNP's callback */
            if (0 > (ret = orte_rml.send_buffer_nb(ORTE_PROC_MY_HNP, buffer,
                                                   ORTE_RML_TAG_ORTED_CALLBACK, 0,
                                                   rml_cbfunc, NULL))) {
                ORTE_ERROR_LOG(ret);
                OBJ_RELEASE(buffer);
                goto DONE;
            }
        }
    }

    /* if we are tree-spawning, then we need to capture the MCA params
     * from our cmd line so we can pass them along to the daemons we spawn -
     * otherwise, only the first layer of daemons will ever see them
     */
    if (orted_globals.tree_spawn) {
        int j, k;
        bool ignore;
        char *no_keep[] = {
            "orte_hnp_uri",
            "orte_ess_jobid",
            "orte_ess_vpid",
            "orte_ess_num_procs",
            "orte_parent_uri",
            NULL
        };
        for (i=0; i < argc; i++) {
            if (0 == strcmp("-mca",  argv[i]) ||
                0 == strcmp("--mca", argv[i]) ) {
                ignore = false;
                /* see if this is something we cannot pass along */
                for (k=0; NULL != no_keep[k]; k++) {
                    if (0 == strcmp(no_keep[k], argv[i+1])) {
                        ignore = true;
                        break;
                    }
                }
                if (!ignore) {
                    /* see if this is already present so we at least can
                     * avoid growing the cmd line with duplicates
                     */
                    if (NULL != orted_cmd_line) {
                        for (j=0; NULL != orted_cmd_line[j]; j++) {
                            if (0 == strcmp(argv[i+1], orted_cmd_line[j])) {
                                /* already here - ignore it */
                                ignore = true;
                                break;
                            }
                        }
                    }
                    if (!ignore) {
                        opal_argv_append_nosize(&orted_cmd_line, argv[i]);
                        opal_argv_append_nosize(&orted_cmd_line, argv[i+1]);
                        opal_argv_append_nosize(&orted_cmd_line, argv[i+2]);
                    }
                }
                i += 2;
            }
        }
    }
            
    if (orte_debug_daemons_flag) {
        opal_output(0, "%s orted: up and running - waiting for commands!", ORTE_NAME_PRINT(ORTE_PROC_MY_NAME));
    }

    /* loop the event lib until an exit event is detected */
    while (orte_event_base_active) {
        opal_event_loop(orte_event_base, OPAL_EVLOOP_ONCE);
    }

    /* ensure all local procs are dead */
    orte_odls.kill_local_procs(NULL);

 DONE:
    /* update the exit status, in case it wasn't done */
    ORTE_UPDATE_EXIT_STATUS(orte_exit_status);

    /* cleanup and leave */
    orte_finalize();

    if (orte_debug_flag) {
        fprintf(stderr, "exiting with status %d\n", orte_exit_status);
    }
    exit(orte_exit_status);
}

static void pipe_closed(int fd, short flags, void *arg)
{
    opal_event_t *ev = (opal_event_t*)arg;

    /* no error here - we just want to terminate */
    opal_event_free(ev);
    ORTE_ACTIVATE_JOB_STATE(NULL, ORTE_JOB_STATE_DAEMONS_TERMINATED);
}

static void shutdown_callback(int fd, short flags, void *arg)
{
    orte_timer_t *tm = (orte_timer_t*)arg;

    if (NULL != tm) {
        /* release the timer */
        OBJ_RELEASE(tm);
    }
    
    /* if we were ordered to abort, do so */
    if (orted_globals.abort) {
        opal_output(0, "%s is executing clean abort", ORTE_NAME_PRINT(ORTE_PROC_MY_NAME));
        /* do -not- call finalize as this will send a message to the HNP
         * indicating clean termination! Instead, just kill our
         * local procs, forcibly cleanup the local session_dir tree, and abort
         */
        orte_odls.kill_local_procs(NULL);
        orte_session_dir_cleanup(ORTE_JOBID_WILDCARD);
        abort();
    }
    opal_output(0, "%s is executing clean abnormal termination", ORTE_NAME_PRINT(ORTE_PROC_MY_NAME));
    /* do -not- call finalize as this will send a message to the HNP
     * indicating clean termination! Instead, just forcibly cleanup
     * the local session_dir tree and exit
     */
    orte_odls.kill_local_procs(NULL);
    orte_session_dir_cleanup(ORTE_JOBID_WILDCARD);
    exit(ORTE_ERROR_DEFAULT_EXIT_CODE);
}