6e5d844c36
1. completely and cleanly separates responsibilities between the HNP, orted, and tool components. 2. removes all wireup messaging during launch and shutdown. 3. maintains flow control for stdin to avoid large-scale consumption of memory by orteds when large input files are forwarded. This is done using an xon/xoff protocol. 4. enables specification of stdin recipients on the mpirun cmd line. Allowed options include rank, "all", or "none". Default is rank 0. 5. creates a new MPI_Info key "ompi_stdin_target" that supports the above options for child jobs. Default is "none". 6. adds a new tool "orte-iof" that can connect to a running mpirun and display the output. Cmd line options allow selection of any combination of stdout, stderr, and stddiag. Default is stdout. 7. adds a new mpirun and orte-iof cmd line option "tag-output" that will tag each line of output with process name and stream ident. For example, "[1,0]<stdout>this is output" This is not intended for the 1.3 release as it is a major change requiring considerable soak time. This commit was SVN r19767.
92 строки
3.3 KiB
C
92 строки
3.3 KiB
C
/*
|
|
* Copyright (c) 2004-2007 The Trustees of Indiana University and Indiana
|
|
* University Research and Technology
|
|
* Corporation. All rights reserved.
|
|
* Copyright (c) 2004-2005 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 <stdio.h>
|
|
|
|
#include "opal/event/event.h"
|
|
#include "opal/mca/mca.h"
|
|
#include "opal/mca/base/base.h"
|
|
|
|
#include "orte/util/proc_info.h"
|
|
|
|
#include "orte/mca/iof/iof.h"
|
|
#include "orte/mca/iof/base/base.h"
|
|
|
|
|
|
int orte_iof_base_close(void)
|
|
{
|
|
bool dump;
|
|
opal_list_item_t *item;
|
|
orte_iof_write_output_t *output;
|
|
int num_written;
|
|
|
|
/* shutdown any remaining opened components */
|
|
if (0 != opal_list_get_size(&orte_iof_base.iof_components_opened)) {
|
|
mca_base_components_close(orte_iof_base.iof_output,
|
|
&orte_iof_base.iof_components_opened, NULL);
|
|
}
|
|
OBJ_DESTRUCT(&orte_iof_base.iof_components_opened);
|
|
|
|
OPAL_THREAD_LOCK(&orte_iof_base.iof_write_output_lock);
|
|
if (!orte_process_info.daemon) {
|
|
/* check if anything is still trying to be written out */
|
|
if (!opal_list_is_empty(&orte_iof_base.iof_write_stdout.outputs)) {
|
|
dump = false;
|
|
/* make one last attempt to write this out */
|
|
while (NULL != (item = opal_list_remove_first(&orte_iof_base.iof_write_stdout.outputs))) {
|
|
output = (orte_iof_write_output_t*)item;
|
|
if (!dump) {
|
|
num_written = write(orte_iof_base.iof_write_stdout.fd, output->data, output->numbytes);
|
|
if (num_written < output->numbytes) {
|
|
/* don't retry - just cleanout the list and dump it */
|
|
dump = true;
|
|
}
|
|
}
|
|
OBJ_RELEASE(output);
|
|
}
|
|
}
|
|
OBJ_DESTRUCT(&orte_iof_base.iof_write_stdout);
|
|
if (!opal_list_is_empty(&orte_iof_base.iof_write_stderr.outputs)) {
|
|
dump = false;
|
|
/* make one last attempt to write this out */
|
|
while (NULL != (item = opal_list_remove_first(&orte_iof_base.iof_write_stderr.outputs))) {
|
|
output = (orte_iof_write_output_t*)item;
|
|
if (!dump) {
|
|
num_written = write(orte_iof_base.iof_write_stderr.fd, output->data, output->numbytes);
|
|
if (num_written < output->numbytes) {
|
|
/* don't retry - just cleanout the list and dump it */
|
|
dump = true;
|
|
}
|
|
}
|
|
OBJ_RELEASE(output);
|
|
}
|
|
}
|
|
OBJ_DESTRUCT(&orte_iof_base.iof_write_stderr);
|
|
}
|
|
OPAL_THREAD_UNLOCK(&orte_iof_base.iof_write_output_lock);
|
|
|
|
OBJ_DESTRUCT(&orte_iof_base.iof_write_output_lock);
|
|
|
|
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|