1
1
openmpi/orte/mca/rml/base/base.h

89 строки
3.2 KiB
C
Исходник Обычный вид История

/*
* 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
*
* $HEADER$
*/
#ifndef MCA_RML_BASE_H
#define MCA_RML_BASE_H
#include "orte_config.h"
#include "opal/mca/mca.h"
#include "orte/mca/rml/rml.h"
#include "orte/dss/dss_types.h"
BEGIN_C_DECLS
/*
* Global functions for the RML
*/
ORTE_DECLSPEC int orte_rml_base_open(void);
ORTE_DECLSPEC int orte_rml_base_select(void);
ORTE_DECLSPEC int orte_rml_base_close(void);
Commit the orted-failed-to-start code. This correctly causes the system to detect the failure of an orted to start and allows the system to terminate all procs/orteds that *did* start. The primary change that underlies all this is in the OOB. Specifically, the problem in the code until now has been that the OOB attempts to resolve an address when we call the "send" to an unknown recipient. The OOB would then wait forever if that recipient never actually started (and hence, never reported back its OOB contact info). In the case of an orted that failed to start, we would correctly detect that the orted hadn't started, but then we would attempt to order all orteds (including the one that failed to start) to die. This would cause the OOB to "hang" the system. Unfortunately, revising how the OOB resolves addresses introduced a number of additional problems. Specifically, and most troublesome, was the fact that comm_spawn involved the immediate transmission of the rendezvous point from parent-to-child after the child was spawned. The current code used the OOB address resolution as a "barrier" - basically, the parent would attempt to send the info to the child, and then "hold" there until the child's contact info had arrived (meaning the child had started) and the send could be completed. Note that this also caused comm_spawn to "hang" the entire system if the child never started... The app-failed-to-start helped improve that behavior - this code provides additional relief. With this change, the OOB will return an ADDRESSEE_UNKNOWN error if you attempt to send to a recipient whose contact info isn't already in the OOB's hash tables. To resolve comm_spawn issues, we also now force the cross-sharing of connection info between parent and child jobs during spawn. Finally, to aid in setting triggers to the right values, we introduce the "arith" API for the GPR. This function allows you to atomically change the value in a registry location (either divide, multiply, add, or subtract) by the provided operand. It is equivalent to first fetching the value using a "get", then modifying it, and then putting the result back into the registry via a "put". This commit was SVN r14711.
2007-05-21 22:31:28 +04:00
/*
* Data type support
*/
ORTE_DECLSPEC int orte_rml_base_compare_tags(orte_rml_tag_t *value1,
orte_rml_tag_t *value2,
orte_data_type_t type);
ORTE_DECLSPEC int orte_rml_base_copy_tag(orte_rml_tag_t **dest,
orte_rml_tag_t *src,
orte_data_type_t type);
ORTE_DECLSPEC int orte_rml_base_pack_tag(orte_buffer_t *buffer,
const void *src,
orte_std_cntr_t num_vals,
orte_data_type_t type);
ORTE_DECLSPEC int orte_rml_base_print_tag(char **output,
char *prefix,
orte_rml_tag_t *src,
orte_data_type_t type);
Commit the orted-failed-to-start code. This correctly causes the system to detect the failure of an orted to start and allows the system to terminate all procs/orteds that *did* start. The primary change that underlies all this is in the OOB. Specifically, the problem in the code until now has been that the OOB attempts to resolve an address when we call the "send" to an unknown recipient. The OOB would then wait forever if that recipient never actually started (and hence, never reported back its OOB contact info). In the case of an orted that failed to start, we would correctly detect that the orted hadn't started, but then we would attempt to order all orteds (including the one that failed to start) to die. This would cause the OOB to "hang" the system. Unfortunately, revising how the OOB resolves addresses introduced a number of additional problems. Specifically, and most troublesome, was the fact that comm_spawn involved the immediate transmission of the rendezvous point from parent-to-child after the child was spawned. The current code used the OOB address resolution as a "barrier" - basically, the parent would attempt to send the info to the child, and then "hold" there until the child's contact info had arrived (meaning the child had started) and the send could be completed. Note that this also caused comm_spawn to "hang" the entire system if the child never started... The app-failed-to-start helped improve that behavior - this code provides additional relief. With this change, the OOB will return an ADDRESSEE_UNKNOWN error if you attempt to send to a recipient whose contact info isn't already in the OOB's hash tables. To resolve comm_spawn issues, we also now force the cross-sharing of connection info between parent and child jobs during spawn. Finally, to aid in setting triggers to the right values, we introduce the "arith" API for the GPR. This function allows you to atomically change the value in a registry location (either divide, multiply, add, or subtract) by the provided operand. It is equivalent to first fetching the value using a "get", then modifying it, and then putting the result back into the registry via a "put". This commit was SVN r14711.
2007-05-21 22:31:28 +04:00
ORTE_DECLSPEC void orte_rml_base_std_obj_release(orte_data_value_t *value);
ORTE_DECLSPEC int orte_rml_base_size_tag(size_t *size,
orte_rml_tag_t *src,
orte_data_type_t type);
ORTE_DECLSPEC int orte_rml_base_unpack_tag(orte_buffer_t *buffer,
void *dest,
orte_std_cntr_t *num_vals,
orte_data_type_t type);
Commit the orted-failed-to-start code. This correctly causes the system to detect the failure of an orted to start and allows the system to terminate all procs/orteds that *did* start. The primary change that underlies all this is in the OOB. Specifically, the problem in the code until now has been that the OOB attempts to resolve an address when we call the "send" to an unknown recipient. The OOB would then wait forever if that recipient never actually started (and hence, never reported back its OOB contact info). In the case of an orted that failed to start, we would correctly detect that the orted hadn't started, but then we would attempt to order all orteds (including the one that failed to start) to die. This would cause the OOB to "hang" the system. Unfortunately, revising how the OOB resolves addresses introduced a number of additional problems. Specifically, and most troublesome, was the fact that comm_spawn involved the immediate transmission of the rendezvous point from parent-to-child after the child was spawned. The current code used the OOB address resolution as a "barrier" - basically, the parent would attempt to send the info to the child, and then "hold" there until the child's contact info had arrived (meaning the child had started) and the send could be completed. Note that this also caused comm_spawn to "hang" the entire system if the child never started... The app-failed-to-start helped improve that behavior - this code provides additional relief. With this change, the OOB will return an ADDRESSEE_UNKNOWN error if you attempt to send to a recipient whose contact info isn't already in the OOB's hash tables. To resolve comm_spawn issues, we also now force the cross-sharing of connection info between parent and child jobs during spawn. Finally, to aid in setting triggers to the right values, we introduce the "arith" API for the GPR. This function allows you to atomically change the value in a registry location (either divide, multiply, add, or subtract) by the provided operand. It is equivalent to first fetching the value using a "get", then modifying it, and then putting the result back into the registry via a "put". This commit was SVN r14711.
2007-05-21 22:31:28 +04:00
/*
* Internal functions
*/
int orte_rml_base_comm_start(void);
int orte_rml_base_comm_stop(void);
void orte_rml_base_recv(int status, orte_process_name_t* sender,
orte_buffer_t* buffer, orte_rml_tag_t tag,
void* cbdata);
ORTE_DECLSPEC extern int orte_rml_base_output;
ORTE_DECLSPEC extern opal_list_t orte_rml_base_components;
/* For FT only, please don't use */
ORTE_DECLSPEC extern orte_rml_component_t *orte_rml_component;
/*
* This is the base priority for a RML wrapper component
* If there exists more than one wrapper, then the one with
* the lowest priority wins.
*/
#define RML_SELECT_WRAPPER_PRIORITY -128
END_C_DECLS
#endif /* MCA_RML_BASE_H */