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.
107 строки
4.7 KiB
C
107 строки
4.7 KiB
C
/*
|
|
* Copyright (c) 2004-2007 The Trustees of Indiana University and Indiana
|
|
* University Research and Technology
|
|
* Corporation. All rights reserved.
|
|
* Copyright (c) 2004-2006 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) 2006-2013 Los Alamos National Security, LLC.
|
|
* All rights reserved.
|
|
* Copyright (c) 2010-2011 Cisco Systems, Inc. All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
|
|
#ifndef _MCA_OOB_TCP_COMPONENT_H_
|
|
#define _MCA_OOB_TCP_COMPONENT_H_
|
|
|
|
#include "orte_config.h"
|
|
|
|
#ifdef HAVE_SYS_TIME_H
|
|
#include <sys/time.h>
|
|
#endif
|
|
|
|
#include "opal/class/opal_bitmap.h"
|
|
#include "opal/class/opal_list.h"
|
|
#include "opal/class/opal_pointer_array.h"
|
|
|
|
#include "orte/mca/oob/oob.h"
|
|
#include "oob_tcp.h"
|
|
|
|
/**
|
|
* OOB TCP Component
|
|
*/
|
|
typedef struct {
|
|
mca_oob_base_component_t super; /**< base OOB component */
|
|
uint32_t addr_count; /**< total number of addresses */
|
|
int num_links; /**< number of logical links per physical device */
|
|
opal_pointer_array_t modules; /**< array of available modules */
|
|
int num_modules;
|
|
int max_retries; /**< max number of retries before declaring peer gone */
|
|
opal_list_t events; /**< events for monitoring connections */
|
|
int peer_limit; /**< max size of tcp peer cache */
|
|
|
|
/* Port specifications */
|
|
char* if_include; /**< list of ip interfaces to include */
|
|
char* if_exclude; /**< list of ip interfaces to exclude */
|
|
int tcp_sndbuf; /**< socket send buffer size */
|
|
int tcp_rcvbuf; /**< socket recv buffer size */
|
|
|
|
/* IPv4 support */
|
|
bool disable_ipv4_family; /**< disable this AF */
|
|
char** tcp_static_ports; /**< Static ports - IPV4 */
|
|
char** tcp_dyn_ports; /**< Dynamic ports - IPV4 */
|
|
char** ipv4conns;
|
|
char** ipv4ports;
|
|
|
|
#if OPAL_ENABLE_IPV6
|
|
/* IPv6 support */
|
|
bool disable_ipv6_family; /**< disable this AF */
|
|
char** tcp6_static_ports; /**< Static ports - IPV6 */
|
|
char** tcp6_dyn_ports; /**< Dynamic ports - IPV6 */
|
|
char** ipv6conns;
|
|
char** ipv6ports;
|
|
#endif
|
|
|
|
/* connection support */
|
|
char* my_uri; /**< uri for connecting to the TCP modules */
|
|
int num_hnp_ports; /**< number of ports the HNP should listen on */
|
|
opal_list_t listeners; /**< List of sockets being monitored by event or thread */
|
|
opal_thread_t listen_thread; /**< handle to the listening thread */
|
|
bool listen_thread_active;
|
|
struct timeval listen_thread_tv; /**< Timeout when using listen thread */
|
|
|
|
/* peers available via this transport - the index is the process name,
|
|
* and the pointer returned is the pointer to the last module that
|
|
* said it could reach that peer. When a module loses its connection
|
|
* to the peer, this pointer either gets set to NULL (if nobody can
|
|
* reach the peer) or to the next module that can. Must be accessed
|
|
* only from the framework-level event base
|
|
*/
|
|
opal_hash_table_t peers;
|
|
} mca_oob_tcp_component_t;
|
|
|
|
ORTE_MODULE_DECLSPEC extern mca_oob_tcp_component_t mca_oob_tcp_component;
|
|
|
|
typedef struct {
|
|
opal_object_t super;
|
|
mca_oob_tcp_module_t *mod; // current module handling this peer
|
|
opal_bitmap_t reachable; // marks the modules that can reach at least one of the peer's addresses
|
|
} mca_oob_tcp_component_peer_t;
|
|
OBJ_CLASS_DECLARATION(mca_oob_tcp_component_peer_t);
|
|
|
|
ORTE_MODULE_DECLSPEC void mca_oob_tcp_component_set_module(int fd, short args, void *cbdata);
|
|
ORTE_MODULE_DECLSPEC void mca_oob_tcp_component_lost_connection(int fd, short args, void *cbdata);
|
|
ORTE_MODULE_DECLSPEC void mca_oob_tcp_component_failed_to_connect(int fd, short args, void *cbdata);
|
|
ORTE_MODULE_DECLSPEC void mca_oob_tcp_component_no_route(int fd, short args, void *cbdata);
|
|
ORTE_MODULE_DECLSPEC void mca_oob_tcp_component_hop_unknown(int fd, short args, void *cbdata);
|
|
|
|
#endif /* _MCA_OOB_TCP_COMPONENT_H_ */
|