int orte_show_help(const char *filename, const char *topic,
bool want_error_header, ...)
{
int rc = ORTE_SUCCESS;
va_list arglist;
char *output;
if (orte_execute_quiet) {
return ORTE_SUCCESS;
}
va_start(arglist, want_error_header);
output = opal_show_help_vstring(filename, topic, want_error_header,
arglist);
va_end(arglist);
/* If nothing came back, there's nothing to do */
if (NULL == output) {
return ORTE_SUCCESS;
}
rc = orte_show_help_norender(filename, topic, want_error_header, output);
free(output);
return rc;
}
static int do_parent(orte_app_context_t* context,
orte_proc_t *child,
char **environ_copy,
orte_job_t *jobdat, int read_fd,
orte_iof_base_io_conf_t opts)
{
int rc;
orte_odls_pipe_err_msg_t msg;
char file[ORTE_ODLS_MAX_FILE_LEN + 1], topic[ORTE_ODLS_MAX_TOPIC_LEN + 1], *str = NULL;
if (NULL != child && ORTE_FLAG_TEST(jobdat, ORTE_JOB_FLAG_FORWARD_OUTPUT)) {
/* connect endpoints IOF */
rc = orte_iof_base_setup_parent(&child->name, &opts);
if (ORTE_SUCCESS != rc) {
ORTE_ERROR_LOG(rc);
close(read_fd);
if (NULL != child) {
child->state = ORTE_PROC_STATE_UNDEF;
}
return rc;
}
}
/* Block reading a message from the pipe */
while (1) {
rc = opal_fd_read(read_fd, sizeof(msg), &msg);
/* If the pipe closed, then the child successfully launched */
if (OPAL_ERR_TIMEOUT == rc) {
break;
}
/* If Something Bad happened in the read, error out */
if (OPAL_SUCCESS != rc) {
ORTE_ERROR_LOG(rc);
close(read_fd);
if (NULL != child) {
child->state = ORTE_PROC_STATE_UNDEF;
}
return rc;
}
/* Otherwise, we got a warning or error message from the child */
if (NULL != child) {
if (msg.fatal) {
ORTE_FLAG_UNSET(child, ORTE_PROC_FLAG_ALIVE);
} else {
ORTE_FLAG_SET(child, ORTE_PROC_FLAG_ALIVE);
}
}
/* Read in the strings; ensure to terminate them with \0 */
if (msg.file_str_len > 0) {
rc = opal_fd_read(read_fd, msg.file_str_len, file);
if (OPAL_SUCCESS != rc) {
orte_show_help("help-orte-odls-default.txt", "syscall fail",
true,
orte_process_info.nodename, context->app,
"opal_fd_read", __FILE__, __LINE__);
if (NULL != child) {
child->state = ORTE_PROC_STATE_UNDEF;
}
return rc;
}
file[msg.file_str_len] = '\0';
}
if (msg.topic_str_len > 0) {
rc = opal_fd_read(read_fd, msg.topic_str_len, topic);
if (OPAL_SUCCESS != rc) {
orte_show_help("help-orte-odls-default.txt", "syscall fail",
true,
orte_process_info.nodename, context->app,
"opal_fd_read", __FILE__, __LINE__);
if (NULL != child) {
child->state = ORTE_PROC_STATE_UNDEF;
}
return rc;
}
topic[msg.topic_str_len] = '\0';
}
if (msg.msg_str_len > 0) {
str = calloc(1, msg.msg_str_len + 1);
if (NULL == str) {
orte_show_help("help-orte-odls-default.txt", "syscall fail",
true,
orte_process_info.nodename, context->app,
"opal_fd_read", __FILE__, __LINE__);
if (NULL != child) {
child->state = ORTE_PROC_STATE_UNDEF;
}
return rc;
}
rc = opal_fd_read(read_fd, msg.msg_str_len, str);
}
/* Print out what we got. We already have a rendered string,
so use orte_show_help_norender(). */
if (msg.msg_str_len > 0) {
orte_show_help_norender(file, topic, false, str);
free(str);
str = NULL;
}
/* If msg.fatal is true, then the child exited with an error.
Otherwise, whatever we just printed was a warning, so loop
around and see what else is on the pipe (or if the pipe
closed, indicating that the child launched
successfully). */
if (msg.fatal) {
if (NULL != child) {
child->state = ORTE_PROC_STATE_FAILED_TO_START;
ORTE_FLAG_UNSET(child, ORTE_PROC_FLAG_ALIVE);
}
close(read_fd);
return ORTE_ERR_FAILED_TO_START;
}
}
/* If we got here, it means that the pipe closed without
indication of a fatal error, meaning that the child process
launched successfully. */
if (NULL != child) {
child->state = ORTE_PROC_STATE_RUNNING;
ORTE_FLAG_SET(child, ORTE_PROC_FLAG_ALIVE);
}
close(read_fd);
return ORTE_SUCCESS;
}
static int do_parent(orte_odls_spawn_caddy_t *cd, int read_fd)
{
int rc;
orte_odls_pipe_err_msg_t msg;
char file[ORTE_ODLS_MAX_FILE_LEN + 1], topic[ORTE_ODLS_MAX_TOPIC_LEN + 1], *str = NULL;
if (cd->opts.connect_stdin) {
close(cd->opts.p_stdin[0]);
}
close(cd->opts.p_stdout[1]);
if( !orte_iof_base.redirect_app_stderr_to_stdout ) {
close(cd->opts.p_stderr[1]);
}
#if OPAL_PMIX_V1
close(cd->opts.p_internal[1]);
#endif
/* Block reading a message from the pipe */
while (1) {
rc = opal_fd_read(read_fd, sizeof(msg), &msg);
/* If the pipe closed, then the child successfully launched */
if (OPAL_ERR_TIMEOUT == rc) {
break;
}
/* If Something Bad happened in the read, error out */
if (OPAL_SUCCESS != rc) {
ORTE_ERROR_LOG(rc);
close(read_fd);
if (NULL != cd->child) {
cd->child->state = ORTE_PROC_STATE_UNDEF;
}
return rc;
}
/* Otherwise, we got a warning or error message from the child */
if (NULL != cd->child) {
if (msg.fatal) {
ORTE_FLAG_UNSET(cd->child, ORTE_PROC_FLAG_ALIVE);
} else {
ORTE_FLAG_SET(cd->child, ORTE_PROC_FLAG_ALIVE);
}
}
/* Read in the strings; ensure to terminate them with \0 */
if (msg.file_str_len > 0) {
rc = opal_fd_read(read_fd, msg.file_str_len, file);
if (OPAL_SUCCESS != rc) {
orte_show_help("help-orte-odls-alps.txt", "syscall fail",
true,
orte_process_info.nodename, cd->app,
"opal_fd_read", __FILE__, __LINE__);
if (NULL != cd->child) {
cd->child->state = ORTE_PROC_STATE_UNDEF;
}
return rc;
}
file[msg.file_str_len] = '\0';
}
if (msg.topic_str_len > 0) {
rc = opal_fd_read(read_fd, msg.topic_str_len, topic);
if (OPAL_SUCCESS != rc) {
orte_show_help("help-orte-odls-alps.txt", "syscall fail",
true,
orte_process_info.nodename, cd->app,
"opal_fd_read", __FILE__, __LINE__);
if (NULL != cd->child) {
cd->child->state = ORTE_PROC_STATE_UNDEF;
}
return rc;
}
topic[msg.topic_str_len] = '\0';
}
if (msg.msg_str_len > 0) {
str = calloc(1, msg.msg_str_len + 1);
if (NULL == str) {
orte_show_help("help-orte-odls-alps.txt", "syscall fail",
true,
orte_process_info.nodename, cd->app,
"opal_fd_read", __FILE__, __LINE__);
if (NULL != cd->child) {
cd->child->state = ORTE_PROC_STATE_UNDEF;
}
return rc;
}
rc = opal_fd_read(read_fd, msg.msg_str_len, str);
}
/* Print out what we got. We already have a rendered string,
so use orte_show_help_norender(). */
if (msg.msg_str_len > 0) {
orte_show_help_norender(file, topic, false, str);
free(str);
str = NULL;
}
/* If msg.fatal is true, then the child exited with an error.
Otherwise, whatever we just printed was a warning, so loop
around and see what else is on the pipe (or if the pipe
closed, indicating that the child launched
successfully). */
if (msg.fatal) {
if (NULL != cd->child) {
cd->child->state = ORTE_PROC_STATE_FAILED_TO_START;
ORTE_FLAG_UNSET(cd->child, ORTE_PROC_FLAG_ALIVE);
}
close(read_fd);
return ORTE_ERR_FAILED_TO_START;
}
}
/* If we got here, it means that the pipe closed without
indication of a fatal error, meaning that the child process
launched successfully. */
if (NULL != cd->child) {
cd->child->state = ORTE_PROC_STATE_RUNNING;
ORTE_FLAG_SET(cd->child, ORTE_PROC_FLAG_ALIVE);
}
close(read_fd);
return ORTE_SUCCESS;
}
