a200e4f865
*** THIS RFC INCLUDES A MINOR CHANGE TO THE MPI-RTE INTERFACE *** Note: during the course of this work, it was necessary to completely separate the MPI and RTE progress engines. There were multiple places in the MPI layer where ORTE_WAIT_FOR_COMPLETION was being used. A new OMPI_WAIT_FOR_COMPLETION macro was created (defined in ompi/mca/rte/rte.h) that simply cycles across opal_progress until the provided flag becomes false. Places where the MPI layer blocked waiting for RTE to complete an event have been modified to use this macro. *************************************************************************************** I am reissuing this RFC because of the time that has passed since its original release. Since its initial release and review, I have debugged it further to ensure it fully supports tests like loop_spawn. It therefore seems ready for merge back to the trunk. Given its prior review, I have set the timeout for one week. The code is in https://bitbucket.org/rhc/ompi-oob2 WHAT: Rewrite of ORTE OOB WHY: Support asynchronous progress and a host of other features WHEN: Wed, August 21 SYNOPSIS: The current OOB has served us well, but a number of limitations have been identified over the years. Specifically: * it is only progressed when called via opal_progress, which can lead to hangs or recursive calls into libevent (which is not supported by that code) * we've had issues when multiple NICs are available as the code doesn't "shift" messages between transports - thus, all nodes had to be available via the same TCP interface. * the OOB "unloads" incoming opal_buffer_t objects during the transmission, thus preventing use of OBJ_RETAIN in the code when repeatedly sending the same message to multiple recipients * there is no failover mechanism across NICs - if the selected NIC (or its attached switch) fails, we are forced to abort * only one transport (i.e., component) can be "active" The revised OOB resolves these problems: * async progress is used for all application processes, with the progress thread blocking in the event library * each available TCP NIC is supported by its own TCP module. The ability to asynchronously progress each module independently is provided, but not enabled by default (a runtime MCA parameter turns it "on") * multi-address TCP NICs (e.g., a NIC with both an IPv4 and IPv6 address, or with virtual interfaces) are supported - reachability is determined by comparing the contact info for a peer against all addresses within the range covered by the address/mask pairs for the NIC. * a message that arrives on one TCP NIC is automatically shifted to whatever NIC that is connected to the next "hop" if that peer cannot be reached by the incoming NIC. If no TCP module will reach the peer, then the OOB attempts to send the message via all other available components - if none can reach the peer, then an "error" is reported back to the RML, which then calls the errmgr for instructions. * opal_buffer_t now conforms to standard object rules re OBJ_RETAIN as we no longer "unload" the incoming object * NIC failure is reported to the TCP component, which then tries to resend the message across any other available TCP NIC. If that doesn't work, then the message is given back to the OOB base to try using other components. If all that fails, then the error is reported to the RML, which reports to the errmgr for instructions * obviously from the above, multiple OOB components (e.g., TCP and UD) can be active in parallel * the matching code has been moved to the RML (and out of the OOB/TCP component) so it is independent of transport * routing is done by the individual OOB modules (as opposed to the RML). Thus, both routed and non-routed transports can simultaneously be active * all blocking send/recv APIs have been removed. Everything operates asynchronously. KNOWN LIMITATIONS: * although provision is made for component failover as described above, the code for doing so has not been fully implemented yet. At the moment, if all connections for a given peer fail, the errmgr is notified of a "lost connection", which by default results in termination of the job if it was a lifeline * the IPv6 code is present and compiles, but is not complete. Since the current IPv6 support in the OOB doesn't work anyway, I don't consider this a blocker * routing is performed at the individual module level, yet the active routed component is selected on a global basis. We probably should update that to reflect that different transports may need/choose to route in different ways * obviously, not every error path has been tested nor necessarily covered * determining abnormal termination is more challenging than in the old code as we now potentially have multiple ways of connecting to a process. Ideally, we would declare "connection failed" when *all* transports can no longer reach the process, but that requires some additional (possibly complex) code. For now, the code replicates the old behavior only somewhat modified - i.e., if a module sees its connection fail, it checks to see if it is a lifeline. If so, it notifies the errmgr that the lifeline is lost - otherwise, it notifies the errmgr that a non-lifeline connection was lost. * reachability is determined solely on the basis of a shared subnet address/mask - more sophisticated algorithms (e.g., the one used in the tcp btl) are required to handle routing via gateways * the RML needs to assign sequence numbers to each message on a per-peer basis. The receiving RML will then deliver messages in order, thus preventing out-of-order messaging in the case where messages travel across different transports or a message needs to be redirected/resent due to failure of a NIC This commit was SVN r29058.
123 строки
4.8 KiB
C
123 строки
4.8 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"
|
|
|
|
#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
|
|
|
|
/* 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) orte_errmgr.abort_peers(a, b)
|
|
#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 ompi_process_name_t *nm,
|
|
const char *key,
|
|
void **data, opal_data_type_t type);
|
|
OMPI_DECLSPEC int ompi_rte_db_fetch_pointer(const ompi_process_name_t *nm,
|
|
const char *key,
|
|
void **data, opal_data_type_t type);
|
|
OMPI_DECLSPEC int ompi_rte_db_fetch_multiple(const ompi_process_name_t *nm,
|
|
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
|
|
|
|
/* 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 */
|