1
1
openmpi/orte/test/system/orte_exit.c
Ralph Castain f56f37d364 Shifting to an event-driven RTE raises some interesting issues during shutdown. We want the last messages to get thru, but also need to correctly shutdown the virtual machine. This requires a delicate balancing act across event priorities, and the need to check for termination conditions in places where related events get processed.
Change the priority of comm_failure and job_termination events to ensure we process final messages prior to terminating. Check for termination conditions when processing proc termination events as we may order proc termination when the daemon gets an exit command, but we can't see the proc actually terminate until we get out of that message event.

Jeff: probably easiest to review this by testing. I tested it under both Slurm and rsh on v1.7.5 as well as trunk

cmr=v1.7.5:reviewer=jsquyres:subject=resolve event priorities during VM shutdown

This commit was SVN r31042.
2014-03-12 16:49:58 +00:00

52 строки
1.1 KiB
C

/* -*- C -*-
*
* $HEADER$
*
* A program that just spins, with vpid 3 aborting - provides mechanism for testing
* abnormal program termination
*/
#include <stdio.h>
#include <unistd.h>
#include "orte/runtime/runtime.h"
#include "orte/util/proc_info.h"
#include "orte/util/name_fns.h"
#include "orte/runtime/orte_globals.h"
#include "orte/mca/errmgr/errmgr.h"
int main(int argc, char* argv[])
{
int i, rc;
double pi;
pid_t pid;
char hostname[500];
if (0 > (rc = orte_init(&argc, &argv, ORTE_PROC_NON_MPI))) {
fprintf(stderr, "orte_abort: couldn't init orte - error code %d\n", rc);
return rc;
}
pid = getpid();
gethostname(hostname, 500);
printf("orte_abort: Name %s Host: %s Pid %ld\n", ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
hostname, (long)pid);
i = 0;
while (1) {
i++;
pi = i / 3.14159256;
if (i == 9995) {
if (ORTE_PROC_MY_NAME->vpid == 1) {
orte_finalize();
exit(77);
} else {
i=0;
}
}
}
return 0;
}