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.
84 строки
2.7 KiB
Makefile
84 строки
2.7 KiB
Makefile
#
|
|
# Copyright (c) 2004-2005 The Trustees of Indiana University and Indiana
|
|
# University Research and Technology
|
|
# Corporation. All rights reserved.
|
|
# Copyright (c) 2004-2005 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) 2008 Sun Microsystems, Inc. All rights reserved.
|
|
# Copyright (c) 2014 Cisco Systems, Inc. All rights reserved.
|
|
# Copyright (c) 2014-2015 Intel, Inc. All rights reserved.
|
|
# $COPYRIGHT$
|
|
#
|
|
# Additional copyrights may follow
|
|
#
|
|
# $HEADER$
|
|
#
|
|
|
|
# This makefile.am does not stand on its own - it is included from orte/Makefile.am
|
|
|
|
include $(top_srcdir)/Makefile.ompi-rules
|
|
|
|
dist_ortedata_DATA += util/hostfile/help-hostfile.txt \
|
|
util/dash_host/help-dash-host.txt \
|
|
util/help-regex.txt
|
|
|
|
nodist_man_MANS = util/hostfile/orte_hosts.7
|
|
|
|
# We are using $(am_dirstamp) instead of creating our own dirstamp since there
|
|
# is src code in util/hostfile directory is created. The automake process
|
|
# creates the $(am_dirstamp), we found the use of this in the generated Makefile
|
|
# in the util/Makefile
|
|
$(nodist_man_MANS): util/hostfile/$(am__dirstamp) $(top_builddir)/opal/include/opal_config.h
|
|
|
|
EXTRA_DIST += $(nodist_man_MANS:.7=.7in)
|
|
|
|
AM_LFLAGS = -Porte_util_hostfile_
|
|
LEX_OUTPUT_ROOT = lex.orte_util_hostfile_
|
|
|
|
headers += \
|
|
util/name_fns.h \
|
|
util/proc_info.h \
|
|
util/session_dir.h \
|
|
util/show_help.h \
|
|
util/error_strings.h \
|
|
util/context_fns.h \
|
|
util/parse_options.h \
|
|
util/pre_condition_transports.h \
|
|
util/hnp_contact.h \
|
|
util/hostfile/hostfile.h \
|
|
util/hostfile/hostfile_lex.h \
|
|
util/dash_host/dash_host.h \
|
|
util/comm/comm.h \
|
|
util/nidmap.h \
|
|
util/regex.h \
|
|
util/attr.h \
|
|
util/listener.h
|
|
|
|
lib@ORTE_LIB_PREFIX@open_rte_la_SOURCES += \
|
|
util/error_strings.c \
|
|
util/name_fns.c \
|
|
util/proc_info.c \
|
|
util/session_dir.c \
|
|
util/show_help.c \
|
|
util/context_fns.c \
|
|
util/parse_options.c \
|
|
util/pre_condition_transports.c \
|
|
util/hnp_contact.c \
|
|
util/hostfile/hostfile_lex.l \
|
|
util/hostfile/hostfile.c \
|
|
util/dash_host/dash_host.c \
|
|
util/comm/comm.c \
|
|
util/nidmap.c \
|
|
util/regex.c \
|
|
util/attr.c \
|
|
util/listener.c
|
|
|
|
# Remove the generated man pages
|
|
distclean-local:
|
|
rm -f $(nodist_man_MANS)
|