2006-02-07 06:32:36 +03:00
|
|
|
/*
|
|
|
|
* 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 (c) 2004-2005 The Regents of the University of California.
|
|
|
|
* All rights reserved.
|
2010-04-23 08:44:41 +04:00
|
|
|
* Copyright (c) 2010 Cisco Systems, Inc. All rights reserved.
|
2006-02-07 06:32:36 +03:00
|
|
|
* $COPYRIGHT$
|
|
|
|
*
|
|
|
|
* Additional copyrights may follow
|
|
|
|
*
|
|
|
|
* $HEADER$
|
|
|
|
*/
|
|
|
|
|
|
|
|
/** @file **/
|
|
|
|
|
|
|
|
#include "orte_config.h"
|
2008-02-28 04:57:57 +03:00
|
|
|
#include "orte/constants.h"
|
2006-02-07 06:32:36 +03:00
|
|
|
|
2006-02-07 08:41:31 +03:00
|
|
|
#include <stdio.h>
|
2006-02-07 06:32:36 +03:00
|
|
|
|
2010-04-23 08:44:41 +04:00
|
|
|
#include "orte/util/error_strings.h"
|
|
|
|
|
|
|
|
const char *orte_err2str(int errnum)
|
2006-02-07 06:32:36 +03:00
|
|
|
{
|
|
|
|
const char *retval;
|
|
|
|
switch (errnum) {
|
|
|
|
case ORTE_ERR_RECV_LESS_THAN_POSTED:
|
|
|
|
retval = "Receive was less than posted size";
|
|
|
|
break;
|
|
|
|
case ORTE_ERR_RECV_MORE_THAN_POSTED:
|
|
|
|
retval = "Receive was greater than posted size";
|
|
|
|
break;
|
|
|
|
case ORTE_ERR_NO_MATCH_YET:
|
|
|
|
retval = "No match for receive posted";
|
|
|
|
break;
|
|
|
|
case ORTE_ERR_REQUEST:
|
|
|
|
retval = "Request error";
|
|
|
|
break;
|
|
|
|
case ORTE_ERR_NO_CONNECTION_ALLOWED:
|
|
|
|
retval = "No connection allowed";
|
|
|
|
break;
|
|
|
|
case ORTE_ERR_CONNECTION_REFUSED:
|
|
|
|
retval = "Connection refused";
|
|
|
|
break;
|
|
|
|
case ORTE_ERR_CONNECTION_FAILED:
|
|
|
|
retval = "Connection failed";
|
|
|
|
break;
|
|
|
|
case ORTE_ERR_COMM_FAILURE:
|
|
|
|
retval = "Communication failure";
|
|
|
|
break;
|
|
|
|
case ORTE_ERR_TYPE_MISMATCH:
|
|
|
|
retval = "Type mismatch";
|
|
|
|
break;
|
|
|
|
case ORTE_ERR_COMPARE_FAILURE:
|
|
|
|
retval = "Data comparison failure";
|
|
|
|
break;
|
|
|
|
case ORTE_ERR_COPY_FAILURE:
|
|
|
|
retval = "Data copy failure";
|
|
|
|
break;
|
2006-03-23 18:31:43 +03:00
|
|
|
case ORTE_ERR_PROC_STATE_MISSING:
|
|
|
|
retval = "The process state information is missing on the registry";
|
|
|
|
break;
|
|
|
|
case ORTE_ERR_PROC_EXIT_STATUS_MISSING:
|
|
|
|
retval = "The process exit status is missing on the registry";
|
|
|
|
break;
|
|
|
|
case ORTE_ERR_INDETERMINATE_STATE_INFO:
|
|
|
|
retval = "Request for state returned multiple responses";
|
|
|
|
break;
|
2006-07-10 18:10:21 +04:00
|
|
|
case ORTE_ERR_NODE_FULLY_USED:
|
|
|
|
retval = "All the slots on a given node have been used";
|
|
|
|
break;
|
2006-07-11 01:25:33 +04:00
|
|
|
case ORTE_ERR_INVALID_NUM_PROCS:
|
|
|
|
retval = "Multiple applications were specified, but at least one failed to specify the number of processes to run";
|
|
|
|
break;
|
2006-12-11 21:07:07 +03:00
|
|
|
case ORTE_ERR_SILENT:
|
|
|
|
retval = NULL;
|
|
|
|
break;
|
2007-04-23 22:25:03 +04:00
|
|
|
case ORTE_ERR_ADDRESSEE_UNKNOWN:
|
|
|
|
retval = "A message is attempting to be sent to a process whose contact information is unknown";
|
|
|
|
break;
|
|
|
|
case ORTE_ERR_SYS_LIMITS_PIPES:
|
|
|
|
retval = "The system limit on number of pipes a process can open was reached";
|
|
|
|
break;
|
|
|
|
case ORTE_ERR_PIPE_SETUP_FAILURE:
|
|
|
|
retval = "A pipe could not be setup between a daemon and one of its local processes";
|
|
|
|
break;
|
|
|
|
case ORTE_ERR_SYS_LIMITS_CHILDREN:
|
|
|
|
retval = "The system limit on number of children a process can have was reached";
|
|
|
|
break;
|
|
|
|
case ORTE_ERR_FAILED_GET_TERM_ATTRS:
|
|
|
|
retval = "The I/O forwarding system was unable to get the attributes of your terminal";
|
|
|
|
break;
|
|
|
|
case ORTE_ERR_WDIR_NOT_FOUND:
|
|
|
|
retval = "The specified working directory could not be found";
|
|
|
|
break;
|
|
|
|
case ORTE_ERR_EXE_NOT_FOUND:
|
|
|
|
retval = "The specified executable could not be found";
|
|
|
|
break;
|
|
|
|
case ORTE_ERR_PIPE_READ_FAILURE:
|
|
|
|
retval = "A pipe could not be read";
|
|
|
|
break;
|
|
|
|
case ORTE_ERR_EXE_NOT_ACCESSIBLE:
|
|
|
|
retval = "The specified executable could not be executed";
|
|
|
|
break;
|
2007-05-18 17:29:11 +04:00
|
|
|
case ORTE_ERR_FAILED_TO_START:
|
|
|
|
retval = "The specified application failed to start";
|
|
|
|
break;
|
2007-07-12 23:53:18 +04:00
|
|
|
case ORTE_ERR_FILE_NOT_EXECUTABLE:
|
|
|
|
retval = "A system-required executable either could not be found or was not executable by this user";
|
|
|
|
break;
|
|
|
|
case ORTE_ERR_HNP_COULD_NOT_START:
|
|
|
|
retval = "Unable to start a daemon on the local node";
|
|
|
|
break;
|
2009-05-27 00:03:21 +04:00
|
|
|
case ORTE_ERR_SYS_LIMITS_SOCKETS:
|
|
|
|
retval = "The system limit on number of network connections a process can open was reached";
|
|
|
|
break;
|
2009-08-22 06:58:20 +04:00
|
|
|
case ORTE_ERR_SOCKET_NOT_AVAILABLE:
|
|
|
|
retval = "Unable to open a TCP socket for out-of-band communications";
|
|
|
|
break;
|
2009-10-01 03:30:24 +04:00
|
|
|
case ORTE_ERR_SYSTEM_WILL_BOOTSTRAP:
|
|
|
|
retval = "System will determine resources during bootstrap of daemons";
|
|
|
|
break;
|
2010-05-04 17:44:33 +04:00
|
|
|
case ORTE_ERR_RELOCATE_LIMIT_EXCEEDED:
|
|
|
|
retval = "Limit on number of process relocations was exceeded";
|
|
|
|
break;
|
2010-05-11 04:34:12 +04:00
|
|
|
case ORTE_ERR_UNRECOVERABLE:
|
|
|
|
retval = "Unrecoverable error";
|
|
|
|
break;
|
|
|
|
|
2010-05-04 17:44:33 +04:00
|
|
|
|
2006-02-07 06:32:36 +03:00
|
|
|
default:
|
|
|
|
retval = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
return retval;
|
|
|
|
}
|
2010-04-23 08:44:41 +04:00
|
|
|
|
|
|
|
const char *orte_job_state_to_str(orte_job_state_t state)
|
|
|
|
{
|
|
|
|
switch(state) {
|
|
|
|
case ORTE_JOB_STATE_UNDEF:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "UNDEFINED";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_JOB_STATE_INIT:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "INITIALIZED";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_JOB_STATE_RESTART:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "RESTARTING";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_JOB_STATE_LAUNCHED:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "LAUNCHED";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_JOB_STATE_RUNNING:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "RUNNING";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_JOB_STATE_SUSPENDED:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "SUSPENDED";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_JOB_STATE_REGISTERED:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "SYNC REGISTERED";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_JOB_STATE_UNTERMINATED:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "UNTERMINATED";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_JOB_STATE_TERMINATED:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "NORMALLY TERMINATED";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_JOB_STATE_ABORTED:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "ABORTED";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_JOB_STATE_FAILED_TO_START:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "FAILED TO START";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_JOB_STATE_ABORTED_BY_SIG:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "ABORTED BY SIGNAL";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_JOB_STATE_ABORTED_WO_SYNC:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "TERMINATED WITHOUT SYNC";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_JOB_STATE_KILLED_BY_CMD:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "KILLED BY INTERNAL COMMAND";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_JOB_STATE_COMM_FAILED:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "COMMUNICATION FAILURE";
|
2010-04-26 16:36:40 +04:00
|
|
|
case ORTE_JOB_STATE_SENSOR_BOUND_EXCEEDED:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "SENSOR BOUND EXCEEDED";
|
2010-04-26 16:36:40 +04:00
|
|
|
break;
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_JOB_STATE_NEVER_LAUNCHED:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "NEVER LAUNCHED";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_JOB_STATE_ABORT_ORDERED:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "ABORT IN PROGRESS";
|
2010-05-05 04:48:43 +04:00
|
|
|
case ORTE_JOB_STATE_HEARTBEAT_FAILED:
|
|
|
|
return "HEARTBEAT FAILED";
|
2010-04-23 08:44:41 +04:00
|
|
|
default:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "UNKNOWN STATE!";
|
2010-04-23 08:44:41 +04:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
const char *orte_proc_state_to_str(orte_proc_state_t state)
|
|
|
|
{
|
|
|
|
switch(state) {
|
|
|
|
case ORTE_PROC_STATE_UNDEF:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "UNDEFINED";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_PROC_STATE_INIT:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "INITIALIZED";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_PROC_STATE_RESTART:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "RESTARTING";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_PROC_STATE_LAUNCHED:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "LAUNCHED";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_PROC_STATE_RUNNING:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "RUNNING";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_PROC_STATE_REGISTERED:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "SYNC REGISTERED";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_PROC_STATE_UNTERMINATED:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "UNTERMINATED";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_PROC_STATE_TERMINATED:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "NORMALLY TERMINATED";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_PROC_STATE_ABORTED:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "ABORTED";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_PROC_STATE_FAILED_TO_START:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "FAILED TO START";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_PROC_STATE_ABORTED_BY_SIG:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "ABORTED BY SIGNAL";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_PROC_STATE_TERM_WO_SYNC:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "TERMINATED WITHOUT SYNC";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_PROC_STATE_KILLED_BY_CMD:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "KILLED BY INTERNAL COMMAND";
|
2010-04-23 08:44:41 +04:00
|
|
|
case ORTE_PROC_STATE_COMM_FAILED:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "COMMUNICATION FAILURE";
|
2010-04-26 16:36:40 +04:00
|
|
|
case ORTE_PROC_STATE_SENSOR_BOUND_EXCEEDED:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "SENSOR BOUND EXCEEDED";
|
2010-04-26 16:36:40 +04:00
|
|
|
break;
|
2010-05-05 04:48:43 +04:00
|
|
|
case ORTE_PROC_STATE_HEARTBEAT_FAILED:
|
|
|
|
return "HEARTBEAT FAILED";
|
|
|
|
break;
|
2010-04-23 08:44:41 +04:00
|
|
|
default:
|
2010-04-27 02:15:57 +04:00
|
|
|
return "UNKNOWN STATE!";
|
2010-04-23 08:44:41 +04:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|