ea35e47228
Changing the client to leave its socket as blocking during the connect doesn't solve the problem by itself - you also have to introduce a sleep delay once the backlog is hit to avoid simply machine-gunning your way thru retries. This gets somewhat difficult to adjust as you don't want to unnecessarily prolong startup time. We've solved this before by adding a listening thread that simply reaps accepts and shoves them into the event library for subsequent processing. This would resolve the problem, but meant yet another daemon-level thread. So I centralized the listening thread support and let multiple elements register listeners on it. Thus, each daemon now has a single listening thread that reaps accepts from multiple sources - for now, the orte/pmix server and the oob/usock support are using it. I'll add in the oob/tcp component later. This still didn't fully resolve the SMP problem, especially on coprocessor cards (e.g., KNC). Removing the shared memory dstore support helped further improve the behavior - it looks like there is some kind of memory paging issue there that needs further understanding. Given that the shared memory support was about to be lost when I bring over the PMIx integration (until it is restored in that library), it seemed like a reasonable thing to just remove it at this point.
90 строки
2.6 KiB
C
90 строки
2.6 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) 2009 Cisco Systems, Inc. All rights reserved.
|
|
* Copyright (c) 2011-2013 Los Alamos National Security, LLC.
|
|
* All rights reserved.
|
|
* Copyright (c) 2014-2015 Intel, Inc. All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
|
|
/** @file **/
|
|
|
|
#include "orte_config.h"
|
|
#include "orte/constants.h"
|
|
|
|
#include "opal/runtime/opal.h"
|
|
#include "opal/util/output.h"
|
|
|
|
#include "orte/mca/ess/ess.h"
|
|
#include "orte/mca/ess/base/base.h"
|
|
#include "orte/runtime/orte_globals.h"
|
|
#include "orte/runtime/runtime.h"
|
|
#include "orte/runtime/orte_locks.h"
|
|
#include "orte/util/listener.h"
|
|
#include "orte/util/name_fns.h"
|
|
#include "orte/util/show_help.h"
|
|
|
|
int orte_finalize(void)
|
|
{
|
|
int rc;
|
|
|
|
--orte_initialized;
|
|
if (0 != orte_initialized) {
|
|
/* check for mismatched calls */
|
|
if (0 > orte_initialized) {
|
|
opal_output(0, "%s MISMATCHED CALLS TO ORTE FINALIZE",
|
|
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME));
|
|
}
|
|
return ORTE_ERROR;
|
|
}
|
|
|
|
/* protect against multiple calls */
|
|
if (opal_atomic_trylock(&orte_finalize_lock)) {
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
/* flag that we are finalizing */
|
|
orte_finalizing = true;
|
|
|
|
if (ORTE_PROC_IS_HNP || ORTE_PROC_IS_DAEMON) {
|
|
/* stop listening for connections - will
|
|
* be ignored if no listeners were registered */
|
|
orte_stop_listening();
|
|
}
|
|
|
|
/* flush the show_help system */
|
|
orte_show_help_finalize();
|
|
|
|
/* call the finalize function for this environment */
|
|
if (ORTE_SUCCESS != (rc = orte_ess.finalize())) {
|
|
return rc;
|
|
}
|
|
|
|
/* close the ess itself */
|
|
(void) mca_base_framework_close(&orte_ess_base_framework);
|
|
|
|
/* cleanup the process info */
|
|
orte_proc_info_finalize();
|
|
|
|
/* Close the general debug stream */
|
|
opal_output_close(orte_debug_output);
|
|
|
|
/* finalize the opal utilities */
|
|
rc = opal_finalize();
|
|
|
|
return rc;
|
|
}
|