0995a6f3b9
* automatically retrieve the hostname (and all RTE info) for all procs during MPI_Init if nprocs < cutoff * if nprocs > cutoff, retrieve the hostname (and all RTE info) for a proc upon the first call to modex_recv for that proc. This would provide the hostname for debugging purposes as we only report errors on messages, and so we must have called modex_recv to get the endpoint info * BTLs are not to call modex_recv until they need the endpoint info for first message - i.e., not during add_procs so we don't call it for every process in the job, but only those with whom we communicate My understanding is that only some BTLs have been modified to meet that third requirement, but those include the Cray ones where jobs are big enough that launch times were becoming an issue. Other BTLs would hopefully be modified as time went on and interest in using them at scale arose. Meantime, those BTLs would call modex_recv on every proc, and we would therefore be no worse than the prior behavior. This commit revises the MPI-RTE interface to pass the ompi_proc_t instead of the ompi_process_name_t for the proc so that the hostname can be easily inserted. I have advised the ORNL folks of the change. cmr=v1.7.4:reviewer=jsquyres:subject=Fix thread deadlock This commit was SVN r29931. The following SVN revision numbers were found above: r29917 --> open-mpi/ompi@1a972e2c9d
128 строки
5.0 KiB
C
128 строки
5.0 KiB
C
/*
|
|
* Copyright (c) 2012-2013 Los Alamos National Security, LLC.
|
|
* All rights reserved.
|
|
* Copyright (c) 2013 Intel, Inc. All rights reserved
|
|
*
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*
|
|
* When this component is used, this file is included in the rest of
|
|
* the OPAL/ORTE/OMPI code base via ompi/mca/rte/rte.h. As such,
|
|
* this header represents the public interface to this static component.
|
|
*/
|
|
|
|
#ifndef MCA_OMPI_RTE_ORTE_H
|
|
#define MCA_OMPI_RTE_ORTE_H
|
|
|
|
#include "ompi_config.h"
|
|
#include "ompi/constants.h"
|
|
|
|
#include "ompi/info/info.h"
|
|
struct ompi_proc_t;
|
|
|
|
#include "orte/types.h"
|
|
#include "orte/mca/errmgr/errmgr.h"
|
|
#include "orte/mca/grpcomm/grpcomm.h"
|
|
#include "orte/mca/rml/base/rml_contact.h"
|
|
#include "orte/mca/rml/rml.h"
|
|
#include "orte/mca/routed/routed.h"
|
|
#include "orte/runtime/orte_data_server.h"
|
|
#include "orte/runtime/runtime.h"
|
|
#include "orte/util/name_fns.h"
|
|
#include "orte/util/proc_info.h"
|
|
|
|
BEGIN_C_DECLS
|
|
|
|
/* Process name objects and operations */
|
|
typedef orte_process_name_t ompi_process_name_t;
|
|
typedef orte_jobid_t ompi_jobid_t;
|
|
typedef orte_vpid_t ompi_vpid_t;
|
|
typedef orte_ns_cmp_bitmask_t ompi_rte_cmp_bitmask_t;
|
|
#define OMPI_PROC_MY_NAME ORTE_PROC_MY_NAME
|
|
#define OMPI_NAME_PRINT(a) ORTE_NAME_PRINT(a)
|
|
#define ompi_rte_compare_name_fields(a, b, c) orte_util_compare_name_fields(a, b, c)
|
|
#define OMPI_NAME_WILDCARD ORTE_NAME_WILDCARD
|
|
#define OMPI_NODE_RANK_INVALID ORTE_NODE_RANK_INVALID
|
|
#define OMPI_LOCAL_RANK_INVALID ORTE_LOCAL_RANK_INVALID
|
|
#define OMPI_RTE_CMP_JOBID ORTE_NS_CMP_JOBID
|
|
#define OMPI_RTE_CMP_VPID ORTE_NS_CMP_VPID
|
|
#define OMPI_RTE_CMP_ALL ORTE_NS_CMP_ALL
|
|
#define ompi_rte_hash_name(a) orte_util_hash_name(a)
|
|
/* This is the DSS tag to serialize a proc name */
|
|
#define OMPI_NAME ORTE_NAME
|
|
#define OMPI_PROCESS_NAME_HTON ORTE_PROCESS_NAME_HTON
|
|
#define OMPI_PROCESS_NAME_NTOH ORTE_PROCESS_NAME_NTOH
|
|
#define OMPI_RTE_NODE_ID ORTE_DB_DAEMON_VPID
|
|
#define OMPI_RTE_MY_NODEID ORTE_PROC_MY_DAEMON->vpid
|
|
#define OMPI_RTE_HOST_ID ORTE_DB_HOSTID
|
|
|
|
/* Collective objects and operations */
|
|
#define ompi_rte_collective_t orte_grpcomm_collective_t
|
|
typedef orte_grpcomm_coll_id_t ompi_rte_collective_id_t;
|
|
#define ompi_rte_modex(a) orte_grpcomm.modex(a)
|
|
#define ompi_rte_barrier(a) orte_grpcomm.barrier(a)
|
|
|
|
/* Process info struct and values */
|
|
typedef orte_node_rank_t ompi_node_rank_t;
|
|
typedef orte_local_rank_t ompi_local_rank_t;
|
|
#define ompi_process_info orte_process_info
|
|
#define ompi_rte_proc_is_bound orte_proc_is_bound
|
|
|
|
/* Error handling objects and operations */
|
|
OMPI_DECLSPEC void ompi_rte_abort(int error_code, char *fmt, ...);
|
|
#define ompi_rte_abort_peers(a, b, c) orte_errmgr.abort_peers(a, b, c)
|
|
#define OMPI_RTE_ERRHANDLER_FIRST ORTE_ERRMGR_CALLBACK_FIRST
|
|
#define OMPI_RTE_ERRHANDLER_LAST ORTE_ERRMGR_CALLBACK_LAST
|
|
#define OMPI_RTE_ERRHANDLER_PREPEND ORTE_ERRMGR_CALLBACK_PREPEND
|
|
#define OMPI_RTE_ERRHANDLER_APPEND ORTE_ERRMGR_CALLBACK_APPEND
|
|
typedef orte_error_t ompi_rte_error_report_t;
|
|
#define ompi_rte_register_errhandler(a, b) orte_errmgr.register_error_callback(a, b)
|
|
#define OMPI_ERROR_LOG ORTE_ERROR_LOG
|
|
|
|
/* Init and finalize objects and operations */
|
|
#define ompi_rte_init(a, b) orte_init(a, b, ORTE_PROC_MPI)
|
|
#define ompi_rte_finalize() orte_finalize()
|
|
OMPI_DECLSPEC void ompi_rte_wait_for_debugger(void);
|
|
|
|
/* Database operations */
|
|
OMPI_DECLSPEC int ompi_rte_db_store(const ompi_process_name_t *nm, const char* key,
|
|
const void *data, opal_data_type_t type);
|
|
OMPI_DECLSPEC int ompi_rte_db_fetch(const struct ompi_proc_t *proc,
|
|
const char *key,
|
|
void **data, opal_data_type_t type);
|
|
OMPI_DECLSPEC int ompi_rte_db_fetch_pointer(const struct ompi_proc_t *proc,
|
|
const char *key,
|
|
void **data, opal_data_type_t type);
|
|
OMPI_DECLSPEC int ompi_rte_db_fetch_multiple(const struct ompi_proc_t *proc,
|
|
const char *key,
|
|
opal_list_t *kvs);
|
|
OMPI_DECLSPEC int ompi_rte_db_remove(const ompi_process_name_t *nm,
|
|
const char *key);
|
|
#define OMPI_DB_HOSTNAME ORTE_DB_HOSTNAME
|
|
#define OMPI_DB_LOCALITY ORTE_DB_LOCALITY
|
|
#define OMPI_DB_GLOBAL_RANK ORTE_DB_GLOBAL_RANK
|
|
|
|
/* Communications */
|
|
typedef orte_rml_tag_t ompi_rml_tag_t;
|
|
#define ompi_rte_send_buffer_nb(a, b, c, d, e) orte_rml.send_buffer_nb(a, b, c, d, e)
|
|
#define ompi_rte_recv_buffer_nb(a, b, c, d, e) orte_rml.recv_buffer_nb(a, b, c, d, e)
|
|
#define ompi_rte_recv_cancel(a, b) orte_rml.recv_cancel(a, b)
|
|
#define ompi_rte_parse_uris(a, b, c) orte_rml_base_parse_uris(a, b, c)
|
|
#define ompi_rte_send_cbfunc orte_rml_send_callback
|
|
|
|
/* Communication tags */
|
|
/* carry over the INVALID def */
|
|
#define OMPI_RML_TAG_INVALID ORTE_RML_TAG_INVALID
|
|
/* define a starting point to avoid conflicts */
|
|
#define OMPI_RML_TAG_BASE ORTE_RML_TAG_MAX
|
|
|
|
#define OMPI_RML_PERSISTENT ORTE_RML_PERSISTENT
|
|
#define OMPI_RML_NON_PERSISTENT ORTE_RML_NON_PERSISTENT
|
|
|
|
END_C_DECLS
|
|
|
|
#endif /* MCA_OMPI_RTE_ORTE_H */
|