e4e678e234
George and I were talking about ORTE's error handling the other day in regards to the right way to deal with errors in the updated OOB. Specifically, it seemed a bad idea for a library such as ORTE to be aborting the job on its own prerogative. If we lose a connection or cannot send a message, then we really should just report it upwards and let the application and/or upper layers decide what to do about it. The current code base only allows a single error callback to exist, which seemed unduly limiting. So, based on the conversation, I've modified the errmgr interface to provide a mechanism for registering any number of error handlers (this replaces the current "set_fault_callback" API). When an error occurs, these handlers will be called in order until one responds that the error has been "resolved" - i.e., no further action is required - by returning OMPI_SUCCESS. The default MPI layer error handler is specified to go "last" and calls mpi_abort, so the current "abort" behavior is preserved unless other error handlers are registered. In the register_callback function, I provide an "order" param so you can specify "this callback must come first" or "this callback must come last". Seemed to me that we will probably have different code areas registering callbacks, and one might require it go first (the default "abort" will always require it go last). So you can append and prepend, or go first. Note that only one registration can declare itself "first" or "last", and since the default "abort" callback automatically takes "last", that one isn't available. :-) The errhandler callback function passes an opal_pointer_array of structs, each of which contains the name of the proc involved (which can be yourself for internal errors) and the error code. This is a change from the current fault callback which returned an opal_pointer_array of just process names. Rationale is that you might need to see the cause of the error to decide what action to take. I realize that isn't a requirement for remote procs, but remember that we will use the SAME interface to report RTE errors internal to the proc itself. In those cases, you really do need to see the error code. It is legal to pass a NULL for the pointer array (e.g., when reporting an internal failure without error code), so handlers must be prepared for that possibility. If people find that too burdensome, we can remove it. Should we ever decide to create a separate callback path for internal errors vs remote process failures, or if we decide to do something different based on experience, then we can adjust this API. This commit was SVN r28852.
99 строки
3.4 KiB
C
99 строки
3.4 KiB
C
/*
|
|
* Copyright (c) 2004-2010 The Trustees of Indiana University and Indiana
|
|
* University Research and Technology
|
|
* Corporation. All rights reserved.
|
|
* Copyright (c) 2004-2011 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 (c) 2012-2013 Los Alamos National Security, Inc. All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
/** @file:
|
|
*/
|
|
|
|
#ifndef ORTE_MCA_ERRMGR_BASE_H
|
|
#define ORTE_MCA_ERRMGR_BASE_H
|
|
|
|
/*
|
|
* includes
|
|
*/
|
|
#include "orte_config.h"
|
|
#include "orte/constants.h"
|
|
|
|
#include "opal/class/opal_list.h"
|
|
|
|
#include "opal/mca/mca.h"
|
|
#include "orte/mca/snapc/base/base.h"
|
|
#include "orte/mca/errmgr/errmgr.h"
|
|
|
|
|
|
BEGIN_C_DECLS
|
|
|
|
/*
|
|
* MCA Framework
|
|
*/
|
|
ORTE_DECLSPEC extern mca_base_framework_t orte_errmgr_base_framework;
|
|
/* select a component */
|
|
ORTE_DECLSPEC int orte_errmgr_base_select(void);
|
|
|
|
/**
|
|
* Interfaces for orte-migrate tool
|
|
*/
|
|
#if OPAL_ENABLE_FT_CR
|
|
/**
|
|
* Migrating States
|
|
*/
|
|
#define ORTE_ERRMGR_MIGRATE_STATE_ERROR (ORTE_SNAPC_CKPT_MAX + 1)
|
|
#define ORTE_ERRMGR_MIGRATE_STATE_ERR_INPROGRESS (ORTE_SNAPC_CKPT_MAX + 2)
|
|
#define ORTE_ERRMGR_MIGRATE_STATE_NONE (ORTE_SNAPC_CKPT_MAX + 3)
|
|
#define ORTE_ERRMGR_MIGRATE_STATE_REQUEST (ORTE_SNAPC_CKPT_MAX + 4)
|
|
#define ORTE_ERRMGR_MIGRATE_STATE_RUNNING (ORTE_SNAPC_CKPT_MAX + 5)
|
|
#define ORTE_ERRMGR_MIGRATE_STATE_RUN_CKPT (ORTE_SNAPC_CKPT_MAX + 6)
|
|
#define ORTE_ERRMGR_MIGRATE_STATE_STARTUP (ORTE_SNAPC_CKPT_MAX + 7)
|
|
#define ORTE_ERRMGR_MIGRATE_STATE_FINISH (ORTE_SNAPC_CKPT_MAX + 8)
|
|
#define ORTE_ERRMGR_MIGRATE_MAX (ORTE_SNAPC_CKPT_MAX + 9)
|
|
|
|
/*
|
|
* Commands for command line tool and ErrMgr interaction
|
|
*/
|
|
typedef uint8_t orte_errmgr_tool_cmd_flag_t;
|
|
#define ORTE_ERRMGR_MIGRATE_TOOL_CMD OPAL_UINT8
|
|
#define ORTE_ERRMGR_MIGRATE_TOOL_INIT_CMD 1
|
|
#define ORTE_ERRMGR_MIGRATE_TOOL_UPDATE_CMD 2
|
|
|
|
/* Initialize/Finalize the orte-migrate communication functionality */
|
|
ORTE_DECLSPEC int orte_errmgr_base_tool_init(void);
|
|
ORTE_DECLSPEC int orte_errmgr_base_tool_finalize(void);
|
|
|
|
ORTE_DECLSPEC void orte_errmgr_base_migrate_state_notify(int state);
|
|
ORTE_DECLSPEC int orte_errmgr_base_migrate_state_str(char ** state_str, int state);
|
|
|
|
ORTE_DECLSPEC int orte_errmgr_base_migrate_update(int status);
|
|
|
|
/*
|
|
* Interfaces for C/R related recovery
|
|
*/
|
|
ORTE_DECLSPEC int orte_errmgr_base_update_app_context_for_cr_recovery(orte_job_t *jobdata,
|
|
orte_proc_t *proc,
|
|
opal_list_t *local_snapshots);
|
|
|
|
ORTE_DECLSPEC int orte_errmgr_base_restart_job(orte_jobid_t jobid, char * global_handle, int seq_num);
|
|
ORTE_DECLSPEC int orte_errmgr_base_migrate_job(orte_jobid_t jobid, orte_snapc_base_request_op_t *datum);
|
|
|
|
/* Interface to report process state to the notifier */
|
|
ORTE_DECLSPEC int orte_errmgr_base_proc_state_notify(orte_proc_state_t state, orte_process_name_t *proc);
|
|
|
|
#endif /* OPAL_ENABLE_FT_CR */
|
|
|
|
END_C_DECLS
|
|
|
|
#endif
|