1
1
openmpi/orte/runtime/orte_wait.h

201 строка
8.4 KiB
C
Исходник Обычный вид История

/*
* Copyright (c) 2004-2005 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.
2015-06-24 06:59:57 +03:00
* 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) 2008 Institut National de Recherche en Informatique
* et Automatique. All rights reserved.
* Copyright (c) 2011 Los Alamos National Security, LLC.
* All rights reserved.
* Copyright (c) 2014-2017 Intel, Inc. All rights reserved.
* $COPYRIGHT$
2015-06-24 06:59:57 +03:00
*
* Additional copyrights may follow
2015-06-24 06:59:57 +03:00
*
* $HEADER$
*/
/**
* @file
*
* Interface for waitpid / async notification of child death with the
* libevent runtime system.
*/
#ifndef ORTE_WAIT_H
#define ORTE_WAIT_H
#include "orte_config.h"
#ifdef HAVE_SYS_TYPES_H
#include <sys/types.h>
#endif
#include <time.h>
#if HAVE_SYS_TIME_H
#include <sys/time.h>
#endif
#include "opal/dss/dss.h"
#include "opal/util/output.h"
#include "opal/sys/atomic.h"
Update libevent to the 2.0 series, currently at 2.0.7rc. We will update to their final release when it becomes available. Currently known errors exist in unused portions of the libevent code. This revision passes the IBM test suite on a Linux machine and on a standalone Mac. This is a fairly intrusive change, but outside of the moving of opal/event to opal/mca/event, the only changes involved (a) changing all calls to opal_event functions to reflect the new framework instead, and (b) ensuring that all opal_event_t objects are properly constructed since they are now true opal_objects. Note: Shiqing has just returned from vacation and has not yet had a chance to complete the Windows integration. Thus, this commit almost certainly breaks Windows support on the trunk. However, I want this to have a chance to soak for as long as possible before I become less available a week from today (going to be at a class for 5 days, and thus will only be sparingly available) so we can find and fix any problems. Biggest change is moving the libevent code from opal/event to a new opal/mca/event framework. This was done to make it much easier to update libevent in the future. New versions can be inserted as a new component and tested in parallel with the current version until validated, then we can remove the earlier version if we so choose. This is a statically built framework ala installdirs, so only one component will build at a time. There is no selection logic - the sole compiled component simply loads its function pointers into the opal_event struct. I have gone thru the code base and converted all the libevent calls I could find. However, I cannot compile nor test every environment. It is therefore quite likely that errors remain in the system. Please keep an eye open for two things: 1. compile-time errors: these will be obvious as calls to the old functions (e.g., opal_evtimer_new) must be replaced by the new framework APIs (e.g., opal_event.evtimer_new) 2. run-time errors: these will likely show up as segfaults due to missing constructors on opal_event_t objects. It appears that it became a typical practice for people to "init" an opal_event_t by simply using memset to zero it out. This will no longer work - you must either OBJ_NEW or OBJ_CONSTRUCT an opal_event_t. I tried to catch these cases, but may have missed some. Believe me, you'll know when you hit it. There is also the issue of the new libevent "no recursion" behavior. As I described on a recent email, we will have to discuss this and figure out what, if anything, we need to do. This commit was SVN r23925.
2010-10-24 22:35:54 +04:00
#include "opal/mca/event/event.h"
#include "orte/types.h"
#include "orte/mca/rml/rml_types.h"
#include "orte/runtime/orte_globals.h"
#include "orte/util/threads.h"
BEGIN_C_DECLS
/** typedef for callback function used in \c orte_wait_cb */
typedef void (*orte_wait_cbfunc_t)(int fd, short args, void* cb);
/* define a tracker */
typedef struct {
opal_list_item_t super;
opal_event_t ev;
opal_event_base_t *evb;
orte_proc_t *child;
orte_wait_cbfunc_t cbfunc;
void *cbdata;
} orte_wait_tracker_t;
OBJ_CLASS_DECLARATION(orte_wait_tracker_t);
/**
* Disable / re-Enable SIGCHLD handler
*
* These functions have to be used after orte_wait_init was called.
*/
ORTE_DECLSPEC void orte_wait_enable(void);
ORTE_DECLSPEC void orte_wait_disable(void);
/**
* Register a callback for process termination
*
* Register a callback for notification when this process causes a SIGCHLD.
* \c waitpid() will have already been called on the process at this
2015-06-24 06:59:57 +03:00
* time.
*/
ORTE_DECLSPEC void orte_wait_cb(orte_proc_t *proc, orte_wait_cbfunc_t callback,
opal_event_base_t *evb, void *data);
ORTE_DECLSPEC void orte_wait_cb_cancel(orte_proc_t *proc);
/* In a few places, we need to barrier until something happens
* that changes a flag to indicate we can release - e.g., waiting
* for a specific message to arrive. If no progress thread is running,
* we cycle across opal_progress - however, if a progress thread
* is active, then we need to just nanosleep to avoid cross-thread
* confusion
*/
#define ORTE_WAIT_FOR_COMPLETION(flg) \
do { \
opal_output_verbose(1, orte_progress_thread_debug, \
"%s waiting on progress thread at %s:%d", \
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME), \
__FILE__, __LINE__); \
while ((flg)) { \
As per the RFC, bring in the ORTE async progress code and the rewrite of OOB: *** 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.
2013-08-22 20:37:40 +04:00
/* provide a short quiet period so we \
* don't hammer the cpu while waiting \
*/ \
As per the RFC, bring in the ORTE async progress code and the rewrite of OOB: *** 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.
2013-08-22 20:37:40 +04:00
struct timespec tp = {0, 100000}; \
nanosleep(&tp, NULL); \
} \
ORTE_ACQUIRE_OBJECT(flg); \
}while(0);
/**
* In a number of places within the code, we want to setup a timer
* to detect when some procedure failed to complete. For example,
* when we launch the daemons, we frequently have no way to directly
* detect that a daemon failed to launch. Setting a timer allows us
* to automatically fail out of the launch if we don't hear from a
* daemon in some specified time window.
*
* Computing the amount of time to wait takes a few lines of code, but
* this macro encapsulates those lines along with the timer event
* definition just as a convenience. It also centralizes the
* necessary checks to ensure that the microsecond field is always
* less than 1M since some systems care about that, and to ensure
* that the computed wait time doesn't exceed the desired max
* wait
*
* NOTE: the callback function is responsible for releasing the timer
* event back to the event pool!
*/
#define ORTE_DETECT_TIMEOUT(n, deltat, maxwait, cbfunc, cbd) \
do { \
orte_timer_t *tmp; \
int timeout; \
tmp = OBJ_NEW(orte_timer_t); \
tmp->payload = (cbd); \
opal_event_evtimer_set(orte_event_base, \
tmp->ev, (cbfunc), tmp); \
opal_event_set_priority(tmp->ev, ORTE_ERROR_PRI); \
timeout = (deltat) * (n); \
if ((maxwait) > 0 && timeout > (maxwait)) { \
timeout = (maxwait); \
} \
tmp->tv.tv_sec = timeout/1000000; \
tmp->tv.tv_usec = timeout%1000000; \
OPAL_OUTPUT_VERBOSE((1, orte_debug_output, \
"defining timeout: %ld sec %ld usec at %s:%d", \
(long)tmp->tv.tv_sec, (long)tmp->tv.tv_usec, \
__FILE__, __LINE__)); \
ORTE_POST_OBJECT(tmp); \
opal_event_evtimer_add(tmp->ev, &tmp->tv); \
}while(0); \
/**
* There are places in the code where we just want to periodically
* wakeup to do something, and then go back to sleep again. Setting
* a timer allows us to do this
*
* NOTE: the callback function is responsible for releasing the timer
* event back to the event pool when done! Otherwise, the finalize
* function will take care of it.
*/
#define ORTE_TIMER_EVENT(sec, usec, cbfunc, pri) \
do { \
orte_timer_t *tm; \
tm = OBJ_NEW(orte_timer_t); \
opal_event_evtimer_set(orte_event_base, \
tm->ev, (cbfunc), tm); \
opal_event_set_priority(tm->ev, (pri)); \
tm->tv.tv_sec = (sec) + (usec)/1000000; \
tm->tv.tv_usec = (usec) % 1000000; \
OPAL_OUTPUT_VERBOSE((1, orte_debug_output, \
"defining timer event: %ld sec %ld usec at %s:%d", \
(long)tm->tv.tv_sec, (long)tm->tv.tv_usec, \
__FILE__, __LINE__)); \
ORTE_POST_OBJECT(tm); \
opal_event_evtimer_add(tm->ev, &tm->tv); \
}while(0); \
/**
* \internal
*
* Initialize the wait system (allocate mutexes, etc.)
*/
ORTE_DECLSPEC int orte_wait_init(void);
/**
* \internal
*
* Finalize the wait system (deallocate mutexes, etc.)
*/
ORTE_DECLSPEC int orte_wait_finalize(void);
END_C_DECLS
#endif /* #ifndef ORTE_WAIT_H */