fceabb2498
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.
468 строки
14 KiB
C
468 строки
14 KiB
C
/*
|
|
* Copyright (c) 2004-2010 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) 2007-2010 Cisco Systems, Inc. All rights reserved.
|
|
* Copyright (c) 2007 Sun Microsystems, Inc. All rights reserved.
|
|
* Copyright (c) 2009 Oak Ridge National Labs. All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
|
|
/** @file **/
|
|
|
|
#include "opal_config.h"
|
|
|
|
#include "opal/util/malloc.h"
|
|
#include "opal/util/output.h"
|
|
#include "opal/util/trace.h"
|
|
#include "opal/util/show_help.h"
|
|
#include "opal/memoryhooks/memory.h"
|
|
#include "opal/mca/base/base.h"
|
|
#include "opal/runtime/opal.h"
|
|
#include "opal/util/net.h"
|
|
#include "opal/datatype/opal_datatype.h"
|
|
#include "opal/mca/installdirs/base/base.h"
|
|
#include "opal/mca/memory/base/base.h"
|
|
#include "opal/mca/memcpy/base/base.h"
|
|
#include "opal/mca/paffinity/base/base.h"
|
|
#include "opal/mca/timer/base/base.h"
|
|
#include "opal/mca/memchecker/base/base.h"
|
|
#include "opal/dss/dss.h"
|
|
#include "opal/mca/carto/base/base.h"
|
|
#if OPAL_ENABLE_FT_CR == 1
|
|
#include "opal/mca/compress/base/base.h"
|
|
#endif
|
|
|
|
#include "opal/runtime/opal_cr.h"
|
|
#include "opal/mca/crs/base/base.h"
|
|
|
|
#include "opal/runtime/opal_progress.h"
|
|
#include "opal/mca/event/base/base.h"
|
|
#include "opal/mca/backtrace/base/base.h"
|
|
|
|
#include "opal/constants.h"
|
|
#include "opal/util/error.h"
|
|
#include "opal/util/stacktrace.h"
|
|
#include "opal/util/keyval_parse.h"
|
|
#include "opal/util/sys_limits.h"
|
|
#include "opal/util/opal_sos.h"
|
|
|
|
#if OPAL_CC_USE_PRAGMA_IDENT
|
|
#pragma ident OPAL_IDENT_STRING
|
|
#elif OPAL_CC_USE_IDENT
|
|
#ident OPAL_IDENT_STRING
|
|
#endif
|
|
const char opal_version_string[] = OPAL_IDENT_STRING;
|
|
|
|
int opal_initialized = 0;
|
|
int opal_util_initialized = 0;
|
|
bool opal_profile = false;
|
|
char *opal_profile_file = NULL;
|
|
int opal_cache_line_size;
|
|
|
|
static const char *
|
|
opal_err2str(int errnum)
|
|
{
|
|
const char *retval;
|
|
|
|
switch (OPAL_SOS_GET_ERROR_CODE(errnum)) {
|
|
case OPAL_SUCCESS:
|
|
retval = "Success";
|
|
break;
|
|
case OPAL_ERROR:
|
|
retval = "Error";
|
|
break;
|
|
case OPAL_ERR_OUT_OF_RESOURCE:
|
|
retval = "Out of resource";
|
|
break;
|
|
case OPAL_ERR_TEMP_OUT_OF_RESOURCE:
|
|
retval = "Temporarily out of resource";
|
|
break;
|
|
case OPAL_ERR_RESOURCE_BUSY:
|
|
retval = "Resource busy";
|
|
break;
|
|
case OPAL_ERR_BAD_PARAM:
|
|
retval = "Bad parameter";
|
|
break;
|
|
case OPAL_ERR_FATAL:
|
|
retval = "Fatal";
|
|
break;
|
|
case OPAL_ERR_NOT_IMPLEMENTED:
|
|
retval = "Not implemented";
|
|
break;
|
|
case OPAL_ERR_NOT_SUPPORTED:
|
|
retval = "Not supported";
|
|
break;
|
|
case OPAL_ERR_INTERUPTED:
|
|
retval = "Interupted";
|
|
break;
|
|
case OPAL_ERR_WOULD_BLOCK:
|
|
retval = "Would block";
|
|
break;
|
|
case OPAL_ERR_IN_ERRNO:
|
|
retval = "In errno";
|
|
break;
|
|
case OPAL_ERR_UNREACH:
|
|
retval = "Unreachable";
|
|
break;
|
|
case OPAL_ERR_NOT_FOUND:
|
|
retval = "Not found";
|
|
break;
|
|
case OPAL_EXISTS:
|
|
retval = "Exists";
|
|
break;
|
|
case OPAL_ERR_TIMEOUT:
|
|
retval = "Timeout";
|
|
break;
|
|
case OPAL_ERR_NOT_AVAILABLE:
|
|
retval = "Not available";
|
|
break;
|
|
case OPAL_ERR_PERM:
|
|
retval = "No permission";
|
|
break;
|
|
case OPAL_ERR_VALUE_OUT_OF_BOUNDS:
|
|
retval = "Value out of bounds";
|
|
break;
|
|
case OPAL_ERR_FILE_READ_FAILURE:
|
|
retval = "File read failure";
|
|
break;
|
|
case OPAL_ERR_FILE_WRITE_FAILURE:
|
|
retval = "File write failure";
|
|
break;
|
|
case OPAL_ERR_FILE_OPEN_FAILURE:
|
|
retval = "File open failure";
|
|
break;
|
|
case OPAL_ERR_PACK_MISMATCH:
|
|
retval = "Pack data mismatch";
|
|
break;
|
|
case OPAL_ERR_PACK_FAILURE:
|
|
retval = "Data pack failed";
|
|
break;
|
|
case OPAL_ERR_UNPACK_FAILURE:
|
|
retval = "Data unpack failed";
|
|
break;
|
|
case OPAL_ERR_UNPACK_INADEQUATE_SPACE:
|
|
retval = "Data unpack had inadequate space";
|
|
break;
|
|
case OPAL_ERR_UNPACK_READ_PAST_END_OF_BUFFER:
|
|
retval = "Data unpack would read past end of buffer";
|
|
break;
|
|
case OPAL_ERR_OPERATION_UNSUPPORTED:
|
|
retval = "Requested operation is not supported on referenced data type";
|
|
break;
|
|
case OPAL_ERR_UNKNOWN_DATA_TYPE:
|
|
retval = "Unknown data type";
|
|
break;
|
|
case OPAL_ERR_BUFFER:
|
|
retval = "Buffer type (described vs non-described) mismatch - operation not allowed";
|
|
break;
|
|
case OPAL_ERR_DATA_TYPE_REDEF:
|
|
retval = "Attempt to redefine an existing data type";
|
|
break;
|
|
case OPAL_ERR_DATA_OVERWRITE_ATTEMPT:
|
|
retval = "Attempt to overwrite a data value";
|
|
break;
|
|
case OPAL_ERR_MODULE_NOT_FOUND:
|
|
retval = "Framework requires at least one active module, but none found";
|
|
break;
|
|
case OPAL_ERR_TOPO_SLOT_LIST_NOT_SUPPORTED:
|
|
retval = "OS topology does not support slot_list process affinity";
|
|
break;
|
|
case OPAL_ERR_TOPO_SOCKET_NOT_SUPPORTED:
|
|
retval = "Could not obtain socket topology information";
|
|
break;
|
|
case OPAL_ERR_TOPO_CORE_NOT_SUPPORTED:
|
|
retval = "Could not obtain core topology information";
|
|
break;
|
|
case OPAL_ERR_NOT_ENOUGH_SOCKETS:
|
|
retval = "Not enough sockets to meet request";
|
|
break;
|
|
case OPAL_ERR_NOT_ENOUGH_CORES:
|
|
retval = "Not enough cores to meet request";
|
|
break;
|
|
case OPAL_ERR_INVALID_PHYS_CPU:
|
|
retval = "Invalid physical cpu number returned";
|
|
break;
|
|
case OPAL_ERR_MULTIPLE_AFFINITIES:
|
|
retval = "Multiple methods for assigning process affinity were specified";
|
|
break;
|
|
case OPAL_ERR_SLOT_LIST_RANGE:
|
|
retval = "Provided slot_list range is invalid";
|
|
break;
|
|
|
|
default:
|
|
retval = NULL;
|
|
}
|
|
|
|
return retval;
|
|
}
|
|
|
|
|
|
int
|
|
opal_init_util(int* pargc, char*** pargv)
|
|
{
|
|
int ret;
|
|
char *error = NULL;
|
|
|
|
if( ++opal_util_initialized != 1 ) {
|
|
if( opal_util_initialized < 1 ) {
|
|
return OPAL_ERROR;
|
|
}
|
|
return OPAL_SUCCESS;
|
|
}
|
|
|
|
/* JMS See note in runtime/opal.h -- this is temporary; to be
|
|
replaced with real hwloc information soon (in trunk/v1.5 and
|
|
beyond, only). This *used* to be a #define, so it's important
|
|
to define it very early. */
|
|
opal_cache_line_size = 128;
|
|
|
|
/* initialize the memory allocator */
|
|
opal_malloc_init();
|
|
|
|
/* initialize the output system */
|
|
opal_output_init();
|
|
|
|
/* initialize install dirs code */
|
|
if (OPAL_SUCCESS != (ret = opal_installdirs_base_open())) {
|
|
fprintf(stderr, "opal_installdirs_base_open() failed -- process will likely abort (%s:%d, returned %d instead of OPAL_INIT)\n",
|
|
__FILE__, __LINE__, ret);
|
|
return ret;
|
|
}
|
|
|
|
/* initialize the help system */
|
|
opal_show_help_init();
|
|
|
|
/* initialize the OPAL SOS system */
|
|
opal_sos_init();
|
|
|
|
/* register handler for errnum -> string converstion */
|
|
if (OPAL_SUCCESS !=
|
|
(ret = opal_error_register("OPAL",
|
|
OPAL_ERR_BASE, OPAL_ERR_MAX, opal_err2str))) {
|
|
error = "opal_error_register";
|
|
goto return_error;
|
|
}
|
|
|
|
/* init the trace function */
|
|
opal_trace_init();
|
|
|
|
/* keyval lex-based parser */
|
|
if (OPAL_SUCCESS != (ret = opal_util_keyval_parse_init())) {
|
|
error = "opal_util_keyval_parse_init";
|
|
goto return_error;
|
|
}
|
|
|
|
if (OPAL_SUCCESS != (ret = opal_net_init())) {
|
|
error = "opal_net_init";
|
|
goto return_error;
|
|
}
|
|
|
|
/* Setup the parameter system */
|
|
if (OPAL_SUCCESS != (ret = mca_base_param_init())) {
|
|
error = "mca_base_param_init";
|
|
goto return_error;
|
|
}
|
|
|
|
/* register params for opal */
|
|
if (OPAL_SUCCESS != (ret = opal_register_params())) {
|
|
error = "opal_register_params";
|
|
goto return_error;
|
|
}
|
|
|
|
/* pretty-print stack handlers */
|
|
if (OPAL_SUCCESS != (ret = opal_util_register_stackhandlers())) {
|
|
error = "opal_util_register_stackhandlers";
|
|
goto return_error;
|
|
}
|
|
|
|
if (OPAL_SUCCESS != (ret = opal_util_init_sys_limits())) {
|
|
error = "opal_util_init_sys_limits";
|
|
goto return_error;
|
|
}
|
|
|
|
/* initialize the datatype engine */
|
|
if (OPAL_SUCCESS != (ret = opal_datatype_init ())) {
|
|
error = "opal_datatype_init";
|
|
goto return_error;
|
|
}
|
|
|
|
/* Initialize the data storage service. */
|
|
if (OPAL_SUCCESS != (ret = opal_dss_open())) {
|
|
error = "opal_dss_open";
|
|
goto return_error;
|
|
}
|
|
|
|
return OPAL_SUCCESS;
|
|
|
|
return_error:
|
|
opal_show_help( "help-opal-runtime.txt",
|
|
"opal_init:startup:internal-failure", true,
|
|
error, ret );
|
|
return ret;
|
|
}
|
|
|
|
|
|
int
|
|
opal_init(int* pargc, char*** pargv)
|
|
{
|
|
int ret;
|
|
char *error = NULL;
|
|
|
|
if( ++opal_initialized != 1 ) {
|
|
if( opal_initialized < 1 ) {
|
|
return OPAL_ERROR;
|
|
}
|
|
return OPAL_SUCCESS;
|
|
}
|
|
|
|
/* initialize util code */
|
|
if (OPAL_SUCCESS != (ret = opal_init_util(pargc, pargv))) {
|
|
return ret;
|
|
}
|
|
|
|
/* initialize the mca */
|
|
if (OPAL_SUCCESS != (ret = mca_base_open())) {
|
|
error = "mca_base_open";
|
|
goto return_error;
|
|
}
|
|
|
|
/* open the processor affinity base */
|
|
if (OPAL_SUCCESS != (ret = opal_paffinity_base_open())) {
|
|
error = "opal_paffinity_base_open";
|
|
goto return_error;
|
|
}
|
|
if (OPAL_SUCCESS != (ret = opal_paffinity_base_select())) {
|
|
error = "opal_paffinity_base_select";
|
|
goto return_error;
|
|
}
|
|
|
|
/* the memcpy component should be one of the first who get
|
|
* loaded in order to make sure we ddo have all the available
|
|
* versions of memcpy correctly configured.
|
|
*/
|
|
if( OPAL_SUCCESS != (ret = opal_memcpy_base_open()) ) {
|
|
error = "opal_memcpy_base_open";
|
|
goto return_error;
|
|
}
|
|
|
|
/* open the memory manager components. Memory hooks may be
|
|
triggered before this (any time after mem_free_init(),
|
|
actually). This is a hook available for memory manager hooks
|
|
without good initialization routine support */
|
|
if (OPAL_SUCCESS != (ret = opal_memory_base_open())) {
|
|
error = "opal_memory_base_open";
|
|
goto return_error;
|
|
}
|
|
|
|
/* initialize the memory manager / tracker */
|
|
if (OPAL_SUCCESS != (ret = opal_mem_hooks_init())) {
|
|
error = "opal_mem_hooks_init";
|
|
goto return_error;
|
|
}
|
|
|
|
/* initialize the memory checker, to allow early support for annotation */
|
|
if (OPAL_SUCCESS != (ret = opal_memchecker_base_open())) {
|
|
error = "opal_memchecker_base_open";
|
|
goto return_error;
|
|
}
|
|
|
|
/* select the memory checker */
|
|
if (OPAL_SUCCESS != (ret = opal_memchecker_base_select())) {
|
|
error = "opal_memchecker_base_select";
|
|
goto return_error;
|
|
}
|
|
|
|
if (OPAL_SUCCESS != (ret = opal_backtrace_base_open())) {
|
|
error = "opal_backtrace_base_open";
|
|
goto return_error;
|
|
}
|
|
|
|
if (OPAL_SUCCESS != (ret = opal_timer_base_open())) {
|
|
error = "opal_timer_base_open";
|
|
goto return_error;
|
|
}
|
|
|
|
/* setup the carto framework */
|
|
if (OPAL_SUCCESS != (ret = opal_carto_base_open())) {
|
|
error = "opal_carto_base_open";
|
|
goto return_error;
|
|
}
|
|
|
|
if (OPAL_SUCCESS != (ret = opal_carto_base_select())) {
|
|
error = "opal_carto_base_select";
|
|
goto return_error;
|
|
}
|
|
|
|
/*
|
|
* Need to start the event and progress engines if noone else is.
|
|
* opal_cr_init uses the progress engine, so it is lumped together
|
|
* into this set as well.
|
|
*/
|
|
/*
|
|
* Initialize the event library
|
|
*/
|
|
if (OPAL_SUCCESS != (ret = opal_event_base_open())) {
|
|
error = "opal_event_base_open";
|
|
goto return_error;
|
|
}
|
|
|
|
/*
|
|
* Initialize the general progress engine
|
|
*/
|
|
if (OPAL_SUCCESS != (ret = opal_progress_init())) {
|
|
error = "opal_progress_init";
|
|
goto return_error;
|
|
}
|
|
/* we want to tick the event library whenever possible */
|
|
opal_progress_event_users_increment();
|
|
|
|
#if OPAL_ENABLE_FT_CR == 1
|
|
/*
|
|
* Initialize the compression framework
|
|
* Note: Currently only used in C/R so it has been marked to only
|
|
* initialize when C/R is enabled. If other places in the code
|
|
* wish to use this framework, it is safe to remove the protection.
|
|
*/
|
|
if( OPAL_SUCCESS != (ret = opal_compress_base_open()) ) {
|
|
error = "opal_compress_base_open() failed";
|
|
goto return_error;
|
|
}
|
|
if( OPAL_SUCCESS != (ret = opal_compress_base_select()) ) {
|
|
error = "opal_compress_base_select() failed";
|
|
goto return_error;
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* Initalize the checkpoint/restart functionality
|
|
* Note: Always do this so we can detect if the user
|
|
* attempts to checkpoint a non checkpointable job,
|
|
* otherwise the tools may hang or not clean up properly.
|
|
*/
|
|
if (OPAL_SUCCESS != (ret = opal_cr_init() ) ) {
|
|
error = "opal_cr_init() failed";
|
|
goto return_error;
|
|
}
|
|
|
|
return OPAL_SUCCESS;
|
|
|
|
return_error:
|
|
opal_show_help( "help-opal-runtime.txt",
|
|
"opal_init:startup:internal-failure", true,
|
|
error, ret );
|
|
return ret;
|
|
}
|
|
|