ee5a626d25
1. Changed the RMGR and PLS APIs to add "signal_job" and "signal_proc" entry points. Only the "signal_job" entries are implemented - none of the components have implementations for "signal_proc" at this time. Thus, you can signal all of the procs in a job, but cannot currently signal only one specific proc. 2. Implemented those new API functions in all components except xgrid (Brian will do so very soon). Only the rsh/ssh and fork modules have been tested, however, and only under OS-X. 3. Added signal traps and callback functions for SIGUSR1/2 to orterun/mpirun that catch those signals and call the appropriate commands to propagate them out to all processes in the job. 4. Added a new test directory under the orte branch to (eventually) hold unit and system level tests for just the run-time. Since our test branch of the repository is under restricted access, people working on the RTE were continually developing their own system-level tests - thus making it hard to help diagnose problems. I have moved the more commonly-used functions here, and added one specifically for testing the SIGUSR1/2 functionality. I will be contacting people directly to seek help with testing the changes on more environments. Other than compile issues, you should see absolutely no change in behavior on any of your systems - this additional functionality is transparent to anyone who does not issue a SIGUSR1/2 to mpirun. Ralph This commit was SVN r10258.
219 строки
4.5 KiB
C
219 строки
4.5 KiB
C
/*
|
|
* Copyright (c) 2004-2005 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.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
#include "orte_config.h"
|
|
#include <errno.h>
|
|
#ifdef HAVE_UNISTD_H
|
|
#include <unistd.h>
|
|
#endif
|
|
#include <string.h>
|
|
|
|
#include "opal/util/trace.h"
|
|
|
|
#include "orte/orte_constants.h"
|
|
#include "orte/dss/dss.h"
|
|
#include "orte/mca/rmgr/base/base.h"
|
|
#include "orte/mca/errmgr/errmgr.h"
|
|
|
|
|
|
/*
|
|
*
|
|
*/
|
|
|
|
int orte_rmgr_base_pack_cmd(orte_buffer_t* buffer, orte_rmgr_cmd_t cmd, orte_jobid_t jobid)
|
|
{
|
|
int rc;
|
|
|
|
OPAL_TRACE(4);
|
|
|
|
rc = orte_dss.pack(buffer, &cmd, 1, ORTE_RMGR_CMD);
|
|
if(ORTE_SUCCESS != rc) {
|
|
ORTE_ERROR_LOG(rc);
|
|
return rc;
|
|
}
|
|
|
|
rc = orte_dss.pack(buffer, &jobid, 1, ORTE_JOBID);
|
|
if(ORTE_SUCCESS != rc) {
|
|
ORTE_ERROR_LOG(rc);
|
|
return rc;
|
|
}
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
/*
|
|
*
|
|
*/
|
|
|
|
int orte_rmgr_base_pack_create_cmd(
|
|
orte_buffer_t* buffer,
|
|
orte_app_context_t** context,
|
|
size_t num_context)
|
|
{
|
|
int rc;
|
|
|
|
orte_rmgr_cmd_t cmd = ORTE_RMGR_CMD_CREATE;
|
|
|
|
OPAL_TRACE(4);
|
|
|
|
rc = orte_dss.pack(buffer, &cmd, 1, ORTE_RMGR_CMD);
|
|
if(ORTE_SUCCESS != rc) {
|
|
ORTE_ERROR_LOG(rc);
|
|
return rc;
|
|
}
|
|
|
|
rc = orte_dss.pack(buffer, &num_context, 1, ORTE_SIZE);
|
|
if(ORTE_SUCCESS != rc) {
|
|
ORTE_ERROR_LOG(rc);
|
|
return rc;
|
|
}
|
|
rc = orte_dss.pack(buffer, context, num_context, ORTE_APP_CONTEXT);
|
|
if(ORTE_SUCCESS != rc) {
|
|
ORTE_ERROR_LOG(rc);
|
|
return rc;
|
|
}
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
|
|
int orte_rmgr_base_pack_terminate_proc_cmd(
|
|
orte_buffer_t* buffer,
|
|
const orte_process_name_t* name)
|
|
{
|
|
int rc;
|
|
|
|
orte_rmgr_cmd_t cmd = ORTE_RMGR_CMD_TERM_PROC;
|
|
|
|
OPAL_TRACE(4);
|
|
|
|
rc = orte_dss.pack(buffer, &cmd, 1, ORTE_RMGR_CMD);
|
|
if(ORTE_SUCCESS != rc) {
|
|
ORTE_ERROR_LOG(rc);
|
|
return rc;
|
|
}
|
|
|
|
rc = orte_dss.pack(buffer, (void*)name, 1, ORTE_NAME);
|
|
if(ORTE_SUCCESS != rc) {
|
|
ORTE_ERROR_LOG(rc);
|
|
return rc;
|
|
}
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
|
|
int orte_rmgr_base_pack_signal_job_cmd(
|
|
orte_buffer_t* buffer,
|
|
orte_jobid_t job,
|
|
int32_t signal)
|
|
{
|
|
int rc;
|
|
|
|
orte_rmgr_cmd_t cmd = ORTE_RMGR_CMD_SIGNAL_JOB;
|
|
|
|
OPAL_TRACE(4);
|
|
|
|
rc = orte_dss.pack(buffer, &cmd, 1, ORTE_RMGR_CMD);
|
|
if(ORTE_SUCCESS != rc) {
|
|
ORTE_ERROR_LOG(rc);
|
|
return rc;
|
|
}
|
|
|
|
rc = orte_dss.pack(buffer, &job, 1, ORTE_JOBID);
|
|
if(ORTE_SUCCESS != rc) {
|
|
ORTE_ERROR_LOG(rc);
|
|
return rc;
|
|
}
|
|
|
|
rc = orte_dss.pack(buffer, (void*)&signal, 1, ORTE_INT32);
|
|
if(ORTE_SUCCESS != rc) {
|
|
ORTE_ERROR_LOG(rc);
|
|
return rc;
|
|
}
|
|
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
|
|
int orte_rmgr_base_pack_signal_proc_cmd(
|
|
orte_buffer_t* buffer,
|
|
const orte_process_name_t* name,
|
|
int32_t signal)
|
|
{
|
|
int rc;
|
|
|
|
orte_rmgr_cmd_t cmd = ORTE_RMGR_CMD_SIGNAL_PROC;
|
|
|
|
OPAL_TRACE(4);
|
|
|
|
rc = orte_dss.pack(buffer, &cmd, 1, ORTE_RMGR_CMD);
|
|
if(ORTE_SUCCESS != rc) {
|
|
ORTE_ERROR_LOG(rc);
|
|
return rc;
|
|
}
|
|
|
|
rc = orte_dss.pack(buffer, (void*)name, 1, ORTE_NAME);
|
|
if(ORTE_SUCCESS != rc) {
|
|
ORTE_ERROR_LOG(rc);
|
|
return rc;
|
|
}
|
|
|
|
rc = orte_dss.pack(buffer, (void*)&signal, 1, ORTE_INT32);
|
|
if(ORTE_SUCCESS != rc) {
|
|
ORTE_ERROR_LOG(rc);
|
|
return rc;
|
|
}
|
|
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
|
|
int orte_rmgr_base_unpack_rsp(
|
|
orte_buffer_t* buffer)
|
|
{
|
|
int32_t rc;
|
|
size_t cnt = 1;
|
|
|
|
OPAL_TRACE(4);
|
|
|
|
if(ORTE_SUCCESS != (rc = orte_dss.unpack(buffer,&rc,&cnt,ORTE_INT32))) {
|
|
ORTE_ERROR_LOG(rc);
|
|
return rc;
|
|
}
|
|
return rc;
|
|
}
|
|
|
|
int orte_rmgr_base_unpack_create_rsp(
|
|
orte_buffer_t* buffer,
|
|
orte_jobid_t* jobid)
|
|
{
|
|
int32_t rc;
|
|
size_t cnt;
|
|
|
|
OPAL_TRACE(4);
|
|
|
|
cnt = 1;
|
|
if(ORTE_SUCCESS != (rc = orte_dss.unpack(buffer,jobid,&cnt,ORTE_JOBID))) {
|
|
ORTE_ERROR_LOG(rc);
|
|
return rc;
|
|
}
|
|
cnt = 1;
|
|
if(ORTE_SUCCESS != (rc = orte_dss.unpack(buffer,&rc,&cnt,ORTE_INT32))) {
|
|
ORTE_ERROR_LOG(rc);
|
|
return rc;
|
|
}
|
|
return rc;
|
|
}
|
|
|
|
|