1
1
openmpi/orte/tools/orte-server/orte-server.c

307 строки
10 KiB
C
Исходник Обычный вид История

/* -*- Mode: C; c-basic-offset:4 ; indent-tabs-mode:nil -*- */
/*
* Copyright (c) 2004-2010 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) 2007-2013 Cisco Systems, Inc. All rights reserved.
* Copyright (c) 2007-2016 Los Alamos National Security, LLC. All rights
* reserved.
* Copyright (c) 2015-2017 Intel, Inc. All rights reserved.
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*/
#include "orte_config.h"
#include "orte/constants.h"
#include <string.h>
#include <stdio.h>
#include <ctype.h>
#ifdef HAVE_UNISTD_H
#include <unistd.h>
#endif
#ifdef HAVE_NETDB_H
#include <netdb.h>
#endif
#ifdef HAVE_SYS_PARAM_H
#include <sys/param.h>
#endif
#include <fcntl.h>
#include <errno.h>
#include <signal.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 "opal/mca/base/base.h"
#include "opal/util/cmd_line.h"
#include "opal/util/output.h"
#include "opal/util/show_help.h"
#include "opal/util/daemon_init.h"
#include "opal/runtime/opal.h"
#include "opal/runtime/opal_cr.h"
#include "orte/util/name_fns.h"
#include "orte/util/proc_info.h"
#include "orte/util/threads.h"
#include "orte/mca/errmgr/errmgr.h"
#include "orte/mca/oob/base/base.h"
#include "orte/mca/rml/rml.h"
#include "orte/orted/orted.h"
#include "orte/runtime/runtime.h"
#include "orte/runtime/orte_globals.h"
#include "orte/runtime/orte_data_server.h"
/*
* Globals
*/
static opal_event_t term_handler;
static opal_event_t int_handler;
static void shutdown_callback(int fd, short flags, void *arg);
static bool help=false;
static bool debug=false;
static bool no_daemonize=false;
static char *report_uri=NULL;
/*
* define the context table for obtaining parameters
*/
opal_cmd_line_init_t orte_server_cmd_line_opts[] = {
/* Various "obvious" options */
{ NULL, 'h', NULL, "help", 0,
&help, OPAL_CMD_LINE_TYPE_BOOL,
"This help message" },
{ NULL, 'd', NULL, "debug", 0,
&debug, OPAL_CMD_LINE_TYPE_BOOL,
"Debug the Open MPI server" },
2015-06-24 06:59:57 +03:00
{ "orte_no_daemonize", '\0', NULL, "no-daemonize", 0,
&no_daemonize, OPAL_CMD_LINE_TYPE_BOOL,
"Don't daemonize into the background" },
2015-06-24 06:59:57 +03:00
{ NULL, 'r', NULL, "report-uri", 1,
&report_uri, OPAL_CMD_LINE_TYPE_STRING,
"Report the server's uri on stdout [-], stderr [+], or a file [anything else]"},
/* End of list */
{ NULL, '\0', NULL, NULL, 0,
NULL, OPAL_CMD_LINE_TYPE_NULL, NULL }
};
int main(int argc, char *argv[])
{
int ret = 0;
opal_cmd_line_t *cmd_line = NULL;
char *rml_uri;
#if OPAL_ENABLE_FT_CR == 1
char * tmp_env_var = NULL;
#endif
/* init enough of opal to process cmd lines */
if (OPAL_SUCCESS != opal_init_util(&argc, &argv)) {
fprintf(stderr, "OPAL failed to initialize -- orted aborting\n");
exit(1);
}
2015-06-24 06:59:57 +03:00
/* setup to check common command line options that just report and die */
cmd_line = OBJ_NEW(opal_cmd_line_t);
opal_cmd_line_create(cmd_line, orte_server_cmd_line_opts);
mca_base_cmd_line_setup(cmd_line);
if (OPAL_SUCCESS != (ret = opal_cmd_line_parse(cmd_line, false, false,
argc, argv))) {
if (OPAL_ERR_SILENT != ret) {
fprintf(stderr, "%s: command line error (%s)\n", argv[0],
opal_strerror(ret));
}
return 1;
}
2015-06-24 06:59:57 +03:00
/* check for help request */
if (help) {
char *str, *args = NULL;
args = opal_cmd_line_get_usage_msg(cmd_line);
2015-06-24 06:59:57 +03:00
str = opal_show_help_string("help-orte-server.txt",
"orteserver:usage", false,
argv[0], args);
if (NULL != str) {
printf("%s", str);
free(str);
}
free(args);
/* If we show the help message, that should be all we do */
return 0;
}
/*
* Since this process can now handle MCA/GMCA parameters, make sure to
* process them.
*/
mca_base_cmd_line_process_args(cmd_line, &environ, &environ);
2015-06-24 06:59:57 +03:00
/* if debug is set, then set orte_debug_flag so that the data server
* code will output
*/
if (debug) {
putenv(OPAL_MCA_PREFIX"orte_debug=1");
}
2015-06-24 06:59:57 +03:00
/* detach from controlling terminal
* otherwise, remain attached so output can get to us
*/
if(debug == false &&
no_daemonize == false) {
opal_daemon_init(NULL);
}
#if OPAL_ENABLE_FT_CR == 1
/* Disable the checkpoint notification routine for this
* tool. As we will never need to checkpoint this tool.
* Note: This must happen before opal_init().
*/
opal_cr_set_enabled(false);
2015-06-24 06:59:57 +03:00
/* Select the none component, since we don't actually use a checkpointer */
MCA/base: Add new MCA variable system Features: - Support for an override parameter file (openmpi-mca-param-override.conf). Variable values in this file can not be overridden by any file or environment value. - Support for boolean, unsigned, and unsigned long long variables. - Support for true/false values. - Support for enumerations on integer variables. - Support for MPIT scope, verbosity, and binding. - Support for command line source. - Support for setting variable source via the environment using OMPI_MCA_SOURCE_<var name>=source (either command or file:filename) - Cleaner API. - Support for variable groups (equivalent to MPIT categories). Notes: - Variables must be created with a backing store (char **, int *, or bool *) that must live at least as long as the variable. - Creating a variable with the MCA_BASE_VAR_FLAG_SETTABLE enables the use of mca_base_var_set_value() to change the value. - String values are duplicated when the variable is registered. It is up to the caller to free the original value if necessary. The new value will be freed by the mca_base_var system and must not be freed by the user. - Variables with constant scope may not be settable. - Variable groups (and all associated variables) are deregistered when the component is closed or the component repository item is freed. This prevents a segmentation fault from accessing a variable after its component is unloaded. - After some discussion we decided we should remove the automatic registration of component priority variables. Few component actually made use of this feature. - The enumerator interface was updated to be general enough to handle future uses of the interface. - The code to generate ompi_info output has been moved into the MCA variable system. See mca_base_var_dump(). opal: update core and components to mca_base_var system orte: update core and components to mca_base_var system ompi: update core and components to mca_base_var system This commit also modifies the rmaps framework. The following variables were moved from ppr and lama: rmaps_base_pernode, rmaps_base_n_pernode, rmaps_base_n_persocket. Both lama and ppr create synonyms for these variables. This commit was SVN r28236.
2013-03-28 01:09:41 +04:00
(void) mca_base_var_env_name("crs", &tmp_env_var);
opal_setenv(tmp_env_var,
"none",
true, &environ);
free(tmp_env_var);
tmp_env_var = NULL;
/* Mark as a tool program */
MCA/base: Add new MCA variable system Features: - Support for an override parameter file (openmpi-mca-param-override.conf). Variable values in this file can not be overridden by any file or environment value. - Support for boolean, unsigned, and unsigned long long variables. - Support for true/false values. - Support for enumerations on integer variables. - Support for MPIT scope, verbosity, and binding. - Support for command line source. - Support for setting variable source via the environment using OMPI_MCA_SOURCE_<var name>=source (either command or file:filename) - Cleaner API. - Support for variable groups (equivalent to MPIT categories). Notes: - Variables must be created with a backing store (char **, int *, or bool *) that must live at least as long as the variable. - Creating a variable with the MCA_BASE_VAR_FLAG_SETTABLE enables the use of mca_base_var_set_value() to change the value. - String values are duplicated when the variable is registered. It is up to the caller to free the original value if necessary. The new value will be freed by the mca_base_var system and must not be freed by the user. - Variables with constant scope may not be settable. - Variable groups (and all associated variables) are deregistered when the component is closed or the component repository item is freed. This prevents a segmentation fault from accessing a variable after its component is unloaded. - After some discussion we decided we should remove the automatic registration of component priority variables. Few component actually made use of this feature. - The enumerator interface was updated to be general enough to handle future uses of the interface. - The code to generate ompi_info output has been moved into the MCA variable system. See mca_base_var_dump(). opal: update core and components to mca_base_var system orte: update core and components to mca_base_var system ompi: update core and components to mca_base_var system This commit also modifies the rmaps framework. The following variables were moved from ppr and lama: rmaps_base_pernode, rmaps_base_n_pernode, rmaps_base_n_persocket. Both lama and ppr create synonyms for these variables. This commit was SVN r28236.
2013-03-28 01:09:41 +04:00
(void) mca_base_var_env_name("opal_cr_is_tool", &tmp_env_var);
opal_setenv(tmp_env_var,
"1",
true, &environ);
free(tmp_env_var);
#endif
/* don't want session directories */
orte_create_session_dirs = false;
/* Perform the standard init, but flag that we are an HNP */
if (ORTE_SUCCESS != (ret = orte_init(&argc, &argv, ORTE_PROC_HNP))) {
fprintf(stderr, "orte-server: failed to initialize -- aborting\n");
exit(1);
}
2015-06-24 06:59:57 +03:00
/* report out our URI, if we were requested to do so, using syntax
* proposed in an email thread by Jeff Squyres
*/
if (NULL != report_uri) {
orte_oob_base_get_addr(&rml_uri);
if (0 == strcmp(report_uri, "-")) {
/* if '-', then output to stdout */
printf("%s\n", rml_uri);
} else if (0 == strcmp(report_uri, "+")) {
/* if '+', output to stderr */
fprintf(stderr, "%s\n", rml_uri);
} else {
/* treat it as a filename and output into it */
FILE *fp;
fp = fopen(report_uri, "w");
if (NULL == fp) {
fprintf(stderr, "orte-server: failed to open designated file %s -- aborting\n", report_uri);
orte_finalize();
exit(1);
}
fprintf(fp, "%s\n", rml_uri);
fclose(fp);
}
free(rml_uri);
}
2015-06-24 06:59:57 +03:00
/* setup the data server to listen for commands */
if (ORTE_SUCCESS != (ret = orte_data_server_init())) {
fprintf(stderr, "orte-server: failed to start data server -- aborting\n");
orte_finalize();
exit(1);
}
2015-06-24 06:59:57 +03:00
/* setup to listen for commands sent specifically to me */
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
orte_rml.recv_buffer_nb(ORTE_NAME_WILDCARD, ORTE_RML_TAG_DAEMON,
ORTE_RML_NON_PERSISTENT, orte_daemon_recv, NULL);
/* Set signal handlers to catch kill signals so we can properly clean up
2015-06-24 06:59:57 +03:00
* after ourselves.
*/
opal_event_set(orte_event_base, &term_handler, SIGTERM, OPAL_EV_SIGNAL,
shutdown_callback, NULL);
opal_event_add(&term_handler, NULL);
opal_event_set(orte_event_base, &int_handler, SIGINT, OPAL_EV_SIGNAL,
shutdown_callback, NULL);
opal_event_add(&int_handler, NULL);
/* We actually do *not* want the server to voluntarily yield() the
processor more than necessary. The server already blocks when
it is doing nothing, so it doesn't use any more CPU cycles than
it should; but when it *is* doing something, we do not want it
to be unnecessarily delayed because it voluntarily yielded the
processor in the middle of its work.
For example: when a message arrives at the server, we want the
OS to wake up the server in a timely fashion (which most OS's
seem good about doing) and then we want the server to process
the message as fast as possible. If the server yields and lets
aggressive MPI applications get the processor back, it may be a
long time before the OS schedules the server to run again
(particularly if there is no IO event to wake it up). Hence,
publish and lookup (for example) may be significantly delayed
before being delivered to MPI processes, which can be
problematic in some scenarios (e.g., COMM_SPAWN). */
opal_progress_set_yield_when_idle(false);
/* Change the default behavior of libevent such that we want to
continually block rather than blocking for the default timeout
and then looping around the progress engine again. There
should be nothing in the server that cannot block in libevent
until "something" happens (i.e., there's no need to keep
cycling through progress because the only things that should
happen will happen in libevent). This is a minor optimization,
but what the heck... :-) */
opal_progress_set_event_flag(OPAL_EVLOOP_ONCE);
if (debug) {
opal_output(0, "%s orte-server: up and running!", ORTE_NAME_PRINT(ORTE_PROC_MY_NAME));
}
/* wait to hear we are done */
while (orte_event_base_active) {
opal_event_loop(orte_event_base, OPAL_EVLOOP_ONCE);
}
ORTE_ACQUIRE_OBJECT(orte_event_base_active);
/* should never get here, but if we do... */
2015-06-24 06:59:57 +03:00
/* Finalize and clean up ourselves */
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
orte_finalize();
return orte_exit_status;
}
static void shutdown_callback(int fd, short flags, void *arg)
{
if (debug) {
opal_output(0, "%s orte-server: finalizing", ORTE_NAME_PRINT(ORTE_PROC_MY_NAME));
}
2015-06-24 06:59:57 +03:00
/* Finalize and clean up ourselves */
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
orte_finalize();
exit(orte_exit_status);
}