1
1

This commit represents a bunch of work on a Mercurial side branch. As

such, the commit message back to the master SVN repository is fairly
long.

= ORTE Job-Level Output Messages =

Add two new interfaces that should be used for all new code throughout
the ORTE and OMPI layers (we already make the search-and-replace on
the existing ORTE / OMPI layers):

 * orte_output(): (and corresponding friends ORTE_OUTPUT,
   orte_output_verbose, etc.)  This function sends the output directly
   to the HNP for processing as part of a job-specific output
   channel.  It supports all the same outputs as opal_output()
   (syslog, file, stdout, stderr), but for stdout/stderr, the output
   is sent to the HNP for processing and output.  More on this below.
 * orte_show_help(): This function is a drop-in-replacement for
   opal_show_help(), with two differences in functionality:
   1. the rendered text help message output is sent to the HNP for
      display (rather than outputting directly into the process' stderr
      stream)
   1. the HNP detects duplicate help messages and does not display them
      (so that you don't see the same error message N times, once from
      each of your N MPI processes); instead, it counts "new" instances
      of the help message and displays a message every ~5 seconds when
      there are new ones ("I got X new copies of the help message...")

opal_show_help and opal_output still exist, but they only output in
the current process.  The intent for the new orte_* functions is that
they can apply job-level intelligence to the output.  As such, we
recommend that all new ORTE and OMPI code use the new orte_*
functions, not thei opal_* functions.

=== New code ===

For ORTE and OMPI programmers, here's what you need to do differently
in new code:

 * Do not include opal/util/show_help.h or opal/util/output.h.
   Instead, include orte/util/output.h (this one header file has
   declarations for both the orte_output() series of functions and
   orte_show_help()).
 * Effectively s/opal_output/orte_output/gi throughout your code.
   Note that orte_output_open() takes a slightly different argument
   list (as a way to pass data to the filtering stream -- see below),
   so you if explicitly call opal_output_open(), you'll need to
   slightly adapt to the new signature of orte_output_open().
 * Literally s/opal_show_help/orte_show_help/.  The function signature
   is identical.

=== Notes ===

 * orte_output'ing to stream 0 will do similar to what
   opal_output'ing did, so leaving a hard-coded "0" as the first
   argument is safe.
 * For systems that do not use ORTE's RML or the HNP, the effect of
   orte_output_* and orte_show_help will be identical to their opal
   counterparts (the additional information passed to
   orte_output_open() will be lost!).  Indeed, the orte_* functions
   simply become trivial wrappers to their opal_* counterparts.  Note
   that we have not tested this; the code is simple but it is quite
   possible that we mucked something up.

= Filter Framework =

Messages sent view the new orte_* functions described above and
messages output via the IOF on the HNP will now optionally be passed
through a new "filter" framework before being output to
stdout/stderr.  The "filter" OPAL MCA framework is intended to allow
preprocessing to messages before they are sent to their final
destinations.  The first component that was written in the filter
framework was to create an XML stream, segregating all the messages
into different XML tags, etc.  This will allow 3rd party tools to read
the stdout/stderr from the HNP and be able to know exactly what each
text message is (e.g., a help message, another OMPI infrastructure
message, stdout from the user process, stderr from the user process,
etc.).

Filtering is not active by default.  Filter components must be
specifically requested, such as:

{{{
$ mpirun --mca filter xml ...
}}}

There can only be one filter component active.

= New MCA Parameters =

The new functionality described above introduces two new MCA
parameters:

 * '''orte_base_help_aggregate''': Defaults to 1 (true), meaning that
   help messages will be aggregated, as described above.  If set to 0,
   all help messages will be displayed, even if they are duplicates
   (i.e., the original behavior).
 * '''orte_base_show_output_recursions''': An MCA parameter to help
   debug one of the known issues, described below.  It is likely that
   this MCA parameter will disappear before v1.3 final.

= Known Issues =

 * The XML filter component is not complete.  The current output from
   this component is preliminary and not real XML.  A bit more work
   needs to be done to configure.m4 search for an appropriate XML
   library/link it in/use it at run time.
 * There are possible recursion loops in the orte_output() and
   orte_show_help() functions -- e.g., if RML send calls orte_output()
   or orte_show_help().  We have some ideas how to fix these, but
   figured that it was ok to commit before feature freeze with known
   issues.  The code currently contains sub-optimal workarounds so
   that this will not be a problem, but it would be good to actually
   solve the problem rather than have hackish workarounds before v1.3 final.

This commit was SVN r18434.
This commit is contained in:
Jeff Squyres 2008-05-13 20:00:55 +00:00
parent 125eb5a2ed
commit e7ecd56bd2
454 changed files with 5859 additions and 3432 deletions

View File

@ -22,7 +22,7 @@
#include "ompi/class/ompi_free_list.h"
#include "opal/include/opal/align.h"
#include "opal/sys/cache.h"
#include "opal/util/output.h"
#include "orte/util/output.h"
#include "ompi/mca/mpool/mpool.h"
static void ompi_free_list_construct(ompi_free_list_t* fl);
@ -62,7 +62,7 @@ static void ompi_free_list_destruct(ompi_free_list_t* fl)
#if 0 && OMPI_ENABLE_DEBUG
if(opal_list_get_size(&fl->super) != fl->fl_num_allocated) {
opal_output(0, "ompi_free_list: %d allocated %d returned: %s:%d\n",
orte_output(0, "ompi_free_list: %d allocated %d returned: %s:%d\n",
fl->fl_num_allocated, opal_list_get_size(&fl->super),
fl->super.super.cls_init_file_name, fl->super.super.cls_init_lineno);
}

View File

@ -20,7 +20,7 @@
#include "ompi/class/ompi_seq_tracker.h"
#include "opal/sys/cache.h"
#include "opal/util/output.h"
#include "orte/util/output.h"

View File

@ -30,7 +30,7 @@
#include "ompi/proc/proc.h"
#include "opal/threads/mutex.h"
#include "opal/util/bit_ops.h"
#include "opal/util/output.h"
#include "orte/util/output.h"
#include "opal/util/convert.h"
#include "ompi/mca/topo/topo.h"
#include "ompi/mca/topo/base/base.h"
@ -1154,7 +1154,7 @@ ompi_proc_t **ompi_comm_get_rprocs ( ompi_communicator_t *local_comm,
/* rprocs isn't freed unless we have an error,
since it is used in the communicator */
if ( OMPI_SUCCESS !=rc ) {
opal_output(0, "%d: Error in ompi_get_rprocs\n", local_rank);
orte_output(0, "%d: Error in ompi_get_rprocs\n", local_rank);
if ( NULL != rprocs ) {
free ( rprocs );
rprocs=NULL;
@ -1269,25 +1269,25 @@ int ompi_comm_determine_first ( ompi_communicator_t *intercomm, int high )
/********************************************************************************/
int ompi_comm_dump ( ompi_communicator_t *comm )
{
opal_output(0, "Dumping information for comm_cid %d\n", comm->c_contextid);
opal_output(0," f2c index:%d cube_dim: %d\n", comm->c_f_to_c_index,
orte_output(0, "Dumping information for comm_cid %d\n", comm->c_contextid);
orte_output(0," f2c index:%d cube_dim: %d\n", comm->c_f_to_c_index,
comm->c_cube_dim);
opal_output(0," Local group: size = %d my_rank = %d\n",
orte_output(0," Local group: size = %d my_rank = %d\n",
comm->c_local_group->grp_proc_count,
comm->c_local_group->grp_my_rank );
opal_output(0," Communicator is:");
orte_output(0," Communicator is:");
/* Display flags */
if ( OMPI_COMM_IS_INTER(comm) )
opal_output(0," inter-comm,");
orte_output(0," inter-comm,");
if ( OMPI_COMM_IS_CART(comm))
opal_output(0," topo-cart,");
orte_output(0," topo-cart,");
if ( OMPI_COMM_IS_GRAPH(comm))
opal_output(0," topo-graph");
opal_output(0,"\n");
orte_output(0," topo-graph");
orte_output(0,"\n");
if (OMPI_COMM_IS_INTER(comm)) {
opal_output(0," Remote group size:%d\n", comm->c_remote_group->grp_proc_count);
orte_output(0," Remote group size:%d\n", comm->c_remote_group->grp_proc_count);
}
return OMPI_SUCCESS;
}

View File

@ -258,7 +258,7 @@ int ompi_comm_finalize(void)
if ( NULL != comm ) {
/* Still here ? */
if ( ompi_debug_show_handle_leaks && !(OMPI_COMM_IS_FREED(comm)) ){
opal_output(0,"WARNING: MPI_Comm still allocated in MPI_Finalize\n");
orte_output(0,"WARNING: MPI_Comm still allocated in MPI_Finalize\n");
ompi_comm_dump ( comm);
OBJ_RELEASE(comm);
}

View File

@ -238,7 +238,7 @@ struct ompi_communicator_t {
{
#if OMPI_ENABLE_DEBUG
if(peer_id >= comm->c_remote_group->grp_proc_count) {
opal_output(0, "ompi_comm_lookup_peer: invalid peer index (%d)", peer_id);
orte_output(0, "ompi_comm_lookup_peer: invalid peer index (%d)", peer_id);
return (struct ompi_proc_t *) NULL;
}
#endif

View File

@ -130,7 +130,7 @@ ompi_convertor_find_or_create_master( uint32_t remote_arch )
} else if( opal_arch_checkmask( &master->remote_arch, OPAL_ARCH_BOOLIS32 ) ) {
remote_sizes[DT_CXX_BOOL] = 4;
} else {
opal_output( 0, "Unknown sizeof(bool) for the remote architecture\n" );
orte_output( 0, "Unknown sizeof(bool) for the remote architecture\n" );
}
/* check the length of the long */
@ -151,7 +151,7 @@ ompi_convertor_find_or_create_master( uint32_t remote_arch )
} else if( opal_arch_checkmask( &master->remote_arch, OPAL_ARCH_LOGICALIS32 ) ) {
remote_sizes[DT_LOGIC] = 4;
} else {
opal_output( 0, "Unknown sizeof(fortran logical) for the remote architecture\n" );
orte_output( 0, "Unknown sizeof(fortran logical) for the remote architecture\n" );
}
/**
@ -637,17 +637,17 @@ void ompi_convertor_dump( ompi_convertor_t* convertor )
void ompi_ddt_dump_stack( const dt_stack_t* pStack, int stack_pos,
const union dt_elem_desc* pDesc, const char* name )
{
opal_output( 0, "\nStack %p stack_pos %d name %s\n", (void*)pStack, stack_pos, name );
orte_output( 0, "\nStack %p stack_pos %d name %s\n", (void*)pStack, stack_pos, name );
for( ; stack_pos >= 0; stack_pos-- ) {
opal_output( 0, "%d: pos %d count %d disp %ld ", stack_pos, pStack[stack_pos].index,
orte_output( 0, "%d: pos %d count %d disp %ld ", stack_pos, pStack[stack_pos].index,
(int)pStack[stack_pos].count, (long)pStack[stack_pos].disp );
if( pStack->index != -1 )
opal_output( 0, "\t[desc count %d disp %ld extent %ld]\n",
orte_output( 0, "\t[desc count %d disp %ld extent %ld]\n",
pDesc[pStack[stack_pos].index].elem.count,
(long)pDesc[pStack[stack_pos].index].elem.disp,
(long)pDesc[pStack[stack_pos].index].elem.extent );
else
opal_output( 0, "\n" );
orte_output( 0, "\n" );
}
opal_output( 0, "\n" );
orte_output( 0, "\n" );
}

View File

@ -12,7 +12,7 @@
#include "ompi_config.h"
#include "opal/util/output.h"
#include "orte/util/output.h"
#include "opal/util/arch.h"
#include "opal/types.h"

View File

@ -23,7 +23,7 @@
#ifdef HAVE_STRING_H
#include <string.h>
#endif /* HAVE_STRING_H */
#include "opal/util/output.h"
#include "orte/util/output.h"
extern int ompi_ddt_dfd;
@ -31,17 +31,17 @@ extern int ompi_ddt_dfd;
# define DDT_DUMP_STACK( PSTACK, STACK_POS, PDESC, NAME ) \
ompi_ddt_dump_stack( (PSTACK), (STACK_POS), (PDESC), (NAME) )
# if defined(ACCEPT_C99)
# define DUMP( ARGS... ) opal_output(ompi_ddt_dfd, __VA_ARGS__)
# define DUMP( ARGS... ) orte_output(ompi_ddt_dfd, __VA_ARGS__)
# else
# if defined(__GNUC__) && !defined(__STDC__)
# define DUMP(ARGS...) opal_output( ompi_ddt_dfd, ARGS)
# define DUMP(ARGS...) orte_output( ompi_ddt_dfd, ARGS)
# else
static inline void DUMP( char* fmt, ... )
{
va_list list;
va_start( list, fmt );
opal_output( ompi_ddt_dfd, fmt, list );
orte_output( ompi_ddt_dfd, fmt, list );
va_end( list );
}
# define DUMP printf
@ -265,7 +265,7 @@ OMPI_DECLSPEC int ompi_ddt_safeguard_pointer_debug_breakpoint( const void* actua
((PDATA)->ub - (PDATA)->lb) * ((COUNT) - 1); \
if( ((ACTPTR) < __lower_bound) || ((ACTPTR) >= __upper_bound) ) { \
ompi_ddt_safeguard_pointer_debug_breakpoint( (ACTPTR), (LENGTH), (INITPTR), (PDATA), (COUNT) ); \
opal_output( 0, "%s:%d\n\tPointer %p size %lu is outside [%p,%p] for\n\tbase ptr %p count %d and data \n", \
orte_output( 0, "%s:%d\n\tPointer %p size %lu is outside [%p,%p] for\n\tbase ptr %p count %d and data \n", \
__FILE__, __LINE__, (ACTPTR), (unsigned long)(LENGTH), __lower_bound, __upper_bound, \
(INITPTR), (COUNT) ); \
ompi_ddt_dump( (PDATA) ); \

View File

@ -257,7 +257,7 @@ ompi_generic_simple_pack_function( ompi_convertor_t* pConvertor,
size_t iov_len_local;
uint32_t iov_count;
DO_DEBUG( opal_output( 0, "ompi_convertor_generic_simple_pack( %p, {%p, %lu}, %d )\n", (void*)pConvertor,
DO_DEBUG( orte_output( 0, "ompi_convertor_generic_simple_pack( %p, {%p, %lu}, %d )\n", (void*)pConvertor,
iov[0].iov_base, (unsigned long)iov[0].iov_len, *out_size ); );
description = pConvertor->use_desc->desc;
@ -275,7 +275,7 @@ ompi_generic_simple_pack_function( ompi_convertor_t* pConvertor,
pElem = &(description[pos_desc]);
source_base += pStack->disp;
DO_DEBUG( opal_output( 0, "unpack start pos_desc %d count_desc %d disp %ld\n"
DO_DEBUG( orte_output( 0, "unpack start pos_desc %d count_desc %d disp %ld\n"
"stack_pos %d pos_desc %d count_desc %d disp %ld\n",
pos_desc, count_desc, (long)(source_base - pConvertor->pBaseBuf),
pConvertor->stack_pos, pStack->index, (int)pStack->count, (long)pStack->disp ); );
@ -297,7 +297,7 @@ ompi_generic_simple_pack_function( ompi_convertor_t* pConvertor,
goto complete_loop;
}
if( DT_END_LOOP == pElem->elem.common.type ) { /* end of the current loop */
DO_DEBUG( opal_output( 0, "pack end_loop count %d stack_pos %d pos_desc %d disp %ld space %lu\n",
DO_DEBUG( orte_output( 0, "pack end_loop count %d stack_pos %d pos_desc %d disp %ld space %lu\n",
(int)pStack->count, pConvertor->stack_pos, pos_desc, (long)pStack->disp, (unsigned long)iov_len_local ); );
if( --(pStack->count) == 0 ) { /* end of loop */
if( pConvertor->stack_pos == 0 ) {
@ -321,7 +321,7 @@ ompi_generic_simple_pack_function( ompi_convertor_t* pConvertor,
}
source_base = pConvertor->pBaseBuf + pStack->disp;
UPDATE_INTERNAL_COUNTERS( description, pos_desc, pElem, count_desc );
DO_DEBUG( opal_output( 0, "pack new_loop count %d stack_pos %d pos_desc %d disp %ld space %lu\n",
DO_DEBUG( orte_output( 0, "pack new_loop count %d stack_pos %d pos_desc %d disp %ld space %lu\n",
(int)pStack->count, pConvertor->stack_pos, pos_desc, (long)pStack->disp, (unsigned long)iov_len_local ); );
}
if( DT_LOOP == pElem->elem.common.type ) {
@ -361,7 +361,7 @@ ompi_generic_simple_pack_function( ompi_convertor_t* pConvertor,
/* I complete an element, next step I should go to the next one */
PUSH_STACK( pStack, pConvertor->stack_pos, pos_desc, DT_BYTE, count_desc,
source_base - pStack->disp - pConvertor->pBaseBuf );
DO_DEBUG( opal_output( 0, "pack save stack stack_pos %d pos_desc %d count_desc %d disp %ld\n",
DO_DEBUG( orte_output( 0, "pack save stack stack_pos %d pos_desc %d count_desc %d disp %ld\n",
pConvertor->stack_pos, pStack->index, (int)pStack->count, (long)pStack->disp ); );
return 0;
}

View File

@ -36,7 +36,7 @@ static inline void pack_predefined_data( ompi_convertor_t* CONVERTOR,
/* the extent and the size of the basic datatype are equals */
OMPI_DDT_SAFEGUARD_POINTER( _source, _copy_blength, (CONVERTOR)->pBaseBuf,
(CONVERTOR)->pDesc, (CONVERTOR)->count );
DO_DEBUG( opal_output( 0, "pack 1. memcpy( %p, %p, %lu ) => space %lu\n",
DO_DEBUG( orte_output( 0, "pack 1. memcpy( %p, %p, %lu ) => space %lu\n",
*(DESTINATION), _source, (unsigned long)_copy_blength, (unsigned long)(*(SPACE)) ); );
MEMCPY_CSUM( *(DESTINATION), _source, _copy_blength, (CONVERTOR) );
_source += _copy_blength;
@ -46,7 +46,7 @@ static inline void pack_predefined_data( ompi_convertor_t* CONVERTOR,
for( _i = 0; _i < _copy_count; _i++ ) {
OMPI_DDT_SAFEGUARD_POINTER( _source, _copy_blength, (CONVERTOR)->pBaseBuf,
(CONVERTOR)->pDesc, (CONVERTOR)->count );
DO_DEBUG( opal_output( 0, "pack 2. memcpy( %p, %p, %lu ) => space %lu\n",
DO_DEBUG( orte_output( 0, "pack 2. memcpy( %p, %p, %lu ) => space %lu\n",
*(DESTINATION), _source, (unsigned long)_copy_blength, (unsigned long)(*(SPACE) - (_i * _copy_blength)) ); );
MEMCPY_CSUM( *(DESTINATION), _source, _copy_blength, (CONVERTOR) );
*(DESTINATION) += _copy_blength;
@ -77,7 +77,7 @@ static inline void pack_contiguous_loop( ompi_convertor_t* CONVERTOR,
for( _i = 0; _i < _copy_loops; _i++ ) {
OMPI_DDT_SAFEGUARD_POINTER( _source, _end_loop->size, (CONVERTOR)->pBaseBuf,
(CONVERTOR)->pDesc, (CONVERTOR)->count );
DO_DEBUG( opal_output( 0, "pack 3. memcpy( %p, %p, %lu ) => space %lu\n",
DO_DEBUG( orte_output( 0, "pack 3. memcpy( %p, %p, %lu ) => space %lu\n",
*(DESTINATION), _source, (unsigned long)_end_loop->size, (unsigned long)(*(SPACE) - _i * _end_loop->size) ); );
MEMCPY_CSUM( *(DESTINATION), _source, _end_loop->size, (CONVERTOR) );
*(DESTINATION) += _end_loop->size;

View File

@ -198,7 +198,7 @@ ompi_unpack_homogeneous_contig_function( ompi_convertor_t* pConv,
ptrdiff_t extent = pData->ub - pData->lb;
ptrdiff_t initial_displ = pConv->use_desc->desc[pConv->use_desc->used].end_loop.first_elem_disp;
DO_DEBUG( opal_output( 0, "unpack_homogeneous_contig( pBaseBuf %p, iov_count %d )\n",
DO_DEBUG( orte_output( 0, "unpack_homogeneous_contig( pBaseBuf %p, iov_count %d )\n",
pConv->pBaseBuf, *out_size ); );
for( iov_count = 0; iov_count < (*out_size); iov_count++ ) {
packed_buffer = (unsigned char*)iov[iov_count].iov_base;
@ -210,19 +210,19 @@ ompi_unpack_homogeneous_contig_function( ompi_convertor_t* pConv,
if( (ptrdiff_t)pData->size == extent ) {
user_memory += pConv->bConverted;
DO_DEBUG( opal_output( 0, "unpack_homogeneous_contig( user_memory %p, packed_buffer %p length %lu\n",
DO_DEBUG( orte_output( 0, "unpack_homogeneous_contig( user_memory %p, packed_buffer %p length %lu\n",
user_memory, packed_buffer, (unsigned long)remaining ); );
/* contiguous data or basic datatype with count */
OMPI_DDT_SAFEGUARD_POINTER( user_memory, remaining,
pConv->pBaseBuf, pData, pConv->count );
DO_DEBUG( opal_output( 0, "1. unpack contig dest %p src %p length %lu\n",
DO_DEBUG( orte_output( 0, "1. unpack contig dest %p src %p length %lu\n",
user_memory, packed_buffer, (unsigned long)remaining ); );
MEMCPY_CSUM( user_memory, packed_buffer, remaining, pConv );
} else {
user_memory += stack[0].disp + stack[1].disp;
DO_DEBUG( opal_output( 0, "unpack_homogeneous_contig( user_memory %p, packed_buffer %p length %lu\n",
DO_DEBUG( orte_output( 0, "unpack_homogeneous_contig( user_memory %p, packed_buffer %p length %lu\n",
user_memory, packed_buffer, (unsigned long)remaining ); );
length = pConv->bConverted / pData->size; /* already done */
@ -234,7 +234,7 @@ ompi_unpack_homogeneous_contig_function( ompi_convertor_t* pConv,
if( length <= remaining ) {
OMPI_DDT_SAFEGUARD_POINTER( user_memory, length, pConv->pBaseBuf,
pData, pConv->count );
DO_DEBUG( opal_output( 0, "2. unpack dest %p src %p length %lu\n",
DO_DEBUG( orte_output( 0, "2. unpack dest %p src %p length %lu\n",
user_memory, packed_buffer, (unsigned long)length ); );
MEMCPY_CSUM( user_memory, packed_buffer, length, pConv );
packed_buffer += length;
@ -245,7 +245,7 @@ ompi_unpack_homogeneous_contig_function( ompi_convertor_t* pConv,
for( i = 0; pData->size <= remaining; i++ ) {
OMPI_DDT_SAFEGUARD_POINTER( user_memory, pData->size, pConv->pBaseBuf,
pData, pConv->count );
DO_DEBUG( opal_output( 0, "3. unpack dest %p src %p length %lu\n",
DO_DEBUG( orte_output( 0, "3. unpack dest %p src %p length %lu\n",
user_memory, packed_buffer, (unsigned long)pData->size ); );
MEMCPY_CSUM( user_memory, packed_buffer, pData->size, pConv );
packed_buffer += pData->size;
@ -258,7 +258,7 @@ ompi_unpack_homogeneous_contig_function( ompi_convertor_t* pConv,
if( remaining != 0 ) {
OMPI_DDT_SAFEGUARD_POINTER( user_memory, remaining, pConv->pBaseBuf,
pData, pConv->count );
DO_DEBUG( opal_output( 0, "4. unpack dest %p src %p length %lu\n",
DO_DEBUG( orte_output( 0, "4. unpack dest %p src %p length %lu\n",
user_memory, packed_buffer, (unsigned long)remaining ); );
MEMCPY_CSUM( user_memory, packed_buffer, remaining, pConv );
user_memory += remaining;
@ -299,7 +299,7 @@ ompi_unpack_partial_datatype( ompi_convertor_t* pConvertor, dt_elem_desc_t* pEle
uint32_t i, length, count_desc = 1;
size_t data_length = ompi_ddt_basicDatatypes[pElem->elem.common.type]->size;
DO_DEBUG( opal_output( 0, "unpack partial data start %lu end %lu data_length %lu user %p\n"
DO_DEBUG( orte_output( 0, "unpack partial data start %lu end %lu data_length %lu user %p\n"
"\tbConverted %lu total_length %lu count %d\n",
(unsigned long)start_position, (unsigned long)end_position, (unsigned long)data_length, *user_buffer,
(unsigned long)pConvertor->bConverted, (unsigned long)pConvertor->local_size, pConvertor->count ); );
@ -365,7 +365,7 @@ ompi_generic_simple_unpack_function( ompi_convertor_t* pConvertor,
size_t iov_len_local;
uint32_t iov_count;
DO_DEBUG( opal_output( 0, "ompi_convertor_generic_simple_unpack( %p, {%p, %lu}, %u )\n",
DO_DEBUG( orte_output( 0, "ompi_convertor_generic_simple_unpack( %p, {%p, %lu}, %u )\n",
(void*)pConvertor, iov[0].iov_base, (unsigned long)iov[0].iov_len, *out_size ); );
description = pConvertor->use_desc->desc;
@ -383,7 +383,7 @@ ompi_generic_simple_unpack_function( ompi_convertor_t* pConvertor,
pElem = &(description[pos_desc]);
user_memory_base += pStack->disp;
DO_DEBUG( opal_output( 0, "unpack start pos_desc %d count_desc %d disp %ld\n"
DO_DEBUG( orte_output( 0, "unpack start pos_desc %d count_desc %d disp %ld\n"
"stack_pos %d pos_desc %d count_desc %d disp %ld\n",
pos_desc, count_desc, (long)(user_memory_base - pConvertor->pBaseBuf),
pConvertor->stack_pos, pStack->index, (int)pStack->count, (long)(pStack->disp) ); );
@ -443,7 +443,7 @@ ompi_generic_simple_unpack_function( ompi_convertor_t* pConvertor,
goto complete_loop;
}
if( DT_END_LOOP == pElem->elem.common.type ) { /* end of the current loop */
DO_DEBUG( opal_output( 0, "unpack end_loop count %d stack_pos %d pos_desc %d disp %ld space %lu\n",
DO_DEBUG( orte_output( 0, "unpack end_loop count %d stack_pos %d pos_desc %d disp %ld space %lu\n",
(int)pStack->count, pConvertor->stack_pos, pos_desc,
(long)pStack->disp, (unsigned long)iov_len_local ); );
if( --(pStack->count) == 0 ) { /* end of loop */
@ -466,7 +466,7 @@ ompi_generic_simple_unpack_function( ompi_convertor_t* pConvertor,
}
user_memory_base = pConvertor->pBaseBuf + pStack->disp;
UPDATE_INTERNAL_COUNTERS( description, pos_desc, pElem, count_desc );
DO_DEBUG( opal_output( 0, "unpack new_loop count %d stack_pos %d pos_desc %d disp %ld space %lu\n",
DO_DEBUG( orte_output( 0, "unpack new_loop count %d stack_pos %d pos_desc %d disp %ld space %lu\n",
(int)pStack->count, pConvertor->stack_pos, pos_desc,
(long)pStack->disp, (unsigned long)iov_len_local ); );
}
@ -506,7 +506,7 @@ ompi_generic_simple_unpack_function( ompi_convertor_t* pConvertor,
/* I complete an element, next step I should go to the next one */
PUSH_STACK( pStack, pConvertor->stack_pos, pos_desc, DT_BYTE, count_desc,
user_memory_base - pStack->disp - pConvertor->pBaseBuf );
DO_DEBUG( opal_output( 0, "unpack save stack stack_pos %d pos_desc %d count_desc %d disp %ld\n",
DO_DEBUG( orte_output( 0, "unpack save stack stack_pos %d pos_desc %d count_desc %d disp %ld\n",
pConvertor->stack_pos, pStack->index, (int)pStack->count, (long)pStack->disp ); );
return 0;
}

View File

@ -36,7 +36,7 @@ static inline void unpack_predefined_data( ompi_convertor_t* CONVERTOR, /* the c
/* the extent and the size of the basic datatype are equals */
OMPI_DDT_SAFEGUARD_POINTER( _destination, _copy_blength, (CONVERTOR)->pBaseBuf,
(CONVERTOR)->pDesc, (CONVERTOR)->count );
DO_DEBUG( opal_output( 0, "unpack 1. memcpy( %p, %p, %lu ) => space %lu\n",
DO_DEBUG( orte_output( 0, "unpack 1. memcpy( %p, %p, %lu ) => space %lu\n",
_destination, *(SOURCE), (unsigned long)_copy_blength, (unsigned long)(*(SPACE)) ); );
MEMCPY_CSUM( _destination, *(SOURCE), _copy_blength, (CONVERTOR) );
*(SOURCE) += _copy_blength;
@ -46,7 +46,7 @@ static inline void unpack_predefined_data( ompi_convertor_t* CONVERTOR, /* the c
for( _i = 0; _i < _copy_count; _i++ ) {
OMPI_DDT_SAFEGUARD_POINTER( _destination, _copy_blength, (CONVERTOR)->pBaseBuf,
(CONVERTOR)->pDesc, (CONVERTOR)->count );
DO_DEBUG( opal_output( 0, "unpack 2. memcpy( %p, %p, %lu ) => space %lu\n",
DO_DEBUG( orte_output( 0, "unpack 2. memcpy( %p, %p, %lu ) => space %lu\n",
_destination, *(SOURCE), (unsigned long)_copy_blength, (unsigned long)(*(SPACE) - (_i * _copy_blength)) ); );
MEMCPY_CSUM( _destination, *(SOURCE), _copy_blength, (CONVERTOR) );
*(SOURCE) += _copy_blength;
@ -77,7 +77,7 @@ static inline void unpack_contiguous_loop( ompi_convertor_t* CONVERTOR,
for( _i = 0; _i < _copy_loops; _i++ ) {
OMPI_DDT_SAFEGUARD_POINTER( _destination, _end_loop->size, (CONVERTOR)->pBaseBuf,
(CONVERTOR)->pDesc, (CONVERTOR)->count );
DO_DEBUG( opal_output( 0, "unpack 3. memcpy( %p, %p, %lu ) => space %lu\n",
DO_DEBUG( orte_output( 0, "unpack 3. memcpy( %p, %p, %lu ) => space %lu\n",
_destination, *(SOURCE), (unsigned long)_end_loop->size, (unsigned long)(*(SPACE) - _i * _end_loop->size) ); );
MEMCPY_CSUM( _destination, *(SOURCE), _end_loop->size, (CONVERTOR) );
*(SOURCE) += _end_loop->size;

View File

@ -125,7 +125,7 @@ int32_t ompi_ddt_add( ompi_datatype_t* pdtBase, const ompi_datatype_t* pdtAdd,
/* The data-type contain too many elements. We will be unable
* to handle it, so let's just complain by now.
*/
opal_output( 0, "Too many elements in the datatype. The limit is %ud\n",
orte_output( 0, "Too many elements in the datatype. The limit is %ud\n",
MAX_DT_COMPONENT_COUNT );
return OMPI_ERROR;
}

View File

@ -60,7 +60,7 @@ static inline void copy_predefined_data( const dt_elem_desc_t* ELEM,
OMPI_DDT_SAFEGUARD_POINTER( _source, _copy_blength, (SOURCE_BASE),
(DATATYPE), (TOTAL_COUNT) );
/* the extent and the size of the basic datatype are equals */
DO_DEBUG( opal_output( 0, "copy 1. memcpy( %p, %p, %lu ) => space %lu\n",
DO_DEBUG( orte_output( 0, "copy 1. memcpy( %p, %p, %lu ) => space %lu\n",
_destination, _source, (unsigned long)_copy_blength, (unsigned long)(*(SPACE)) ); );
MEMCPY( _destination, _source, _copy_blength );
_source += _copy_blength;
@ -70,7 +70,7 @@ static inline void copy_predefined_data( const dt_elem_desc_t* ELEM,
for( _i = 0; _i < _copy_count; _i++ ) {
OMPI_DDT_SAFEGUARD_POINTER( _source, _copy_blength, (SOURCE_BASE),
(DATATYPE), (TOTAL_COUNT) );
DO_DEBUG( opal_output( 0, "copy 2. memcpy( %p, %p, %lu ) => space %lu\n",
DO_DEBUG( orte_output( 0, "copy 2. memcpy( %p, %p, %lu ) => space %lu\n",
_destination, _source, (unsigned long)_copy_blength, (unsigned long)(*(SPACE) - (_i * _copy_blength)) ); );
MEMCPY( _destination, _source, _copy_blength );
_source += _elem->extent;
@ -106,7 +106,7 @@ static inline void copy_contiguous_loop( const dt_elem_desc_t* ELEM,
for( _i = 0; _i < _copy_loops; _i++ ) {
OMPI_DDT_SAFEGUARD_POINTER( _source, _end_loop->size, (SOURCE_BASE),
(DATATYPE), (TOTAL_COUNT) );
DO_DEBUG( opal_output( 0, "copy 3. memcpy( %p, %p, %lu ) => space %lu\n",
DO_DEBUG( orte_output( 0, "copy 3. memcpy( %p, %p, %lu ) => space %lu\n",
_destination, _source, (unsigned long)_end_loop->size, (unsigned long)(*(SPACE) - _i * _end_loop->size) ); );
MEMCPY( _destination, _source, _end_loop->size );
_source += _loop->extent;
@ -138,7 +138,7 @@ int32_t ompi_ddt_copy_content_same_ddt( const ompi_datatype_t* datatype, int32_t
unsigned char *source = (unsigned char*)source_base,
*destination = (unsigned char*)destination_base;
DO_DEBUG( opal_output( 0, "ompi_ddt_copy_content_same_ddt( %p, %d, dst %p, src %p )\n",
DO_DEBUG( orte_output( 0, "ompi_ddt_copy_content_same_ddt( %p, %d, dst %p, src %p )\n",
(void*)datatype, count, destination_base, source_base ); );
/* empty data ? then do nothing. This should normally be trapped
* at a higher level.
@ -166,7 +166,7 @@ int32_t ompi_ddt_copy_content_same_ddt( const ompi_datatype_t* datatype, int32_t
(unsigned char*)destination_base, datatype, count );
OMPI_DDT_SAFEGUARD_POINTER( source, memcpy_chunk,
(unsigned char*)source_base, datatype, count );
DO_DEBUG( opal_output( 0, "copy c1. memcpy( %p, %p, %lu ) => space %lu\n",
DO_DEBUG( orte_output( 0, "copy c1. memcpy( %p, %p, %lu ) => space %lu\n",
destination, source, (unsigned long)memcpy_chunk, (unsigned long)total_length ); );
MEMCPY( destination, source, memcpy_chunk );
destination += memcpy_chunk;
@ -180,7 +180,7 @@ int32_t ompi_ddt_copy_content_same_ddt( const ompi_datatype_t* datatype, int32_t
(unsigned char*)destination_base, datatype, count );
OMPI_DDT_SAFEGUARD_POINTER( source, datatype->size,
(unsigned char*)source_base, datatype, count );
DO_DEBUG( opal_output( 0, "copy c2. memcpy( %p, %p, %lu ) => space %lu\n",
DO_DEBUG( orte_output( 0, "copy c2. memcpy( %p, %p, %lu ) => space %lu\n",
destination, source, (unsigned long)datatype->size,
(unsigned long)(iov_len_local - (pos_desc * datatype->size)) ); );
MEMCPY( destination, source, datatype->size );
@ -218,7 +218,7 @@ int32_t ompi_ddt_copy_content_same_ddt( const ompi_datatype_t* datatype, int32_t
UPDATE_INTERNAL_COUNTERS( description, pos_desc, pElem, count_desc );
}
if( DT_END_LOOP == pElem->elem.common.type ) { /* end of the current loop */
DO_DEBUG( opal_output( 0, "copy end_loop count %d stack_pos %d pos_desc %d disp %ld space %lu\n",
DO_DEBUG( orte_output( 0, "copy end_loop count %d stack_pos %d pos_desc %d disp %ld space %lu\n",
(int)pStack->count, stack_pos, pos_desc, (long)pStack->disp, (unsigned long)iov_len_local ); );
if( --(pStack->count) == 0 ) { /* end of loop */
if( stack_pos == 0 ) {
@ -240,7 +240,7 @@ int32_t ompi_ddt_copy_content_same_ddt( const ompi_datatype_t* datatype, int32_t
source = (unsigned char*)source_base + pStack->disp;
destination = (unsigned char*)destination_base + pStack->disp;
UPDATE_INTERNAL_COUNTERS( description, pos_desc, pElem, count_desc );
DO_DEBUG( opal_output( 0, "copy new_loop count %d stack_pos %d pos_desc %d disp %ld space %lu\n",
DO_DEBUG( orte_output( 0, "copy new_loop count %d stack_pos %d pos_desc %d disp %ld space %lu\n",
(int)pStack->count, stack_pos, pos_desc, (long)pStack->disp, (unsigned long)iov_len_local ); );
}
if( DT_LOOP == pElem->elem.common.type ) {

View File

@ -837,7 +837,7 @@ int32_t ompi_ddt_finalize( void )
#if defined(VERBOSE)
if( ompi_ddt_dfd != -1 )
opal_output_close( ompi_ddt_dfd );
orte_output_close( ompi_ddt_dfd );
ompi_ddt_dfd = -1;
#endif /* VERBOSE */
@ -999,7 +999,7 @@ void ompi_ddt_dump( const ompi_datatype_t* pData )
index += snprintf( buffer + index, length - index, "No optimized description\n" );
}
buffer[index] = '\0'; /* make sure we end the string with 0 */
opal_output( 0, "%s\n", buffer );
orte_output( 0, "%s\n", buffer );
ompi_ddt_print_args( pData );

View File

@ -60,7 +60,7 @@ int ompi_convertor_create_stack_with_pos_general( ompi_convertor_t* pConvertor,
assert( pConvertor->bConverted != starting_point );
assert( starting_point <=(pConvertor->count * pData->size) );
/*opal_output( 0, "Data extent %d size %d count %d total_size %d starting_point %d\n",
/*orte_output( 0, "Data extent %d size %d count %d total_size %d starting_point %d\n",
pData->ub - pData->lb, pData->size, pConvertor->count,
pConvertor->local_size, starting_point );*/
pConvertor->stack_pos = 0;

View File

@ -120,7 +120,7 @@ int ompi_convertor_generic_simple_position( ompi_convertor_t* pConvertor,
if( iov_len_local > pConvertor->pDesc->size ) {
pStack = pConvertor->pStack; /* we're working with the full stack */
count_desc = (uint32_t)(iov_len_local / pConvertor->pDesc->size);
DO_DEBUG( opal_output( 0, "position before %lu asked %lu data size %lu"
DO_DEBUG( orte_output( 0, "position before %lu asked %lu data size %lu"
" iov_len_local %lu count_desc %d\n",
(unsigned long)pConvertor->bConverted, (unsigned long)*position, (unsigned long)pConvertor->pDesc->size,
(unsigned long)iov_len_local, count_desc ); );
@ -133,7 +133,7 @@ int ompi_convertor_generic_simple_position( ompi_convertor_t* pConvertor,
pConvertor->bConverted += count_desc * pConvertor->pDesc->size;
iov_len_local = *position - pConvertor->bConverted;
pStack[0].count -= count_desc;
DO_DEBUG( opal_output( 0, "after bConverted %lu remaining count %lu iov_len_local %lu\n",
DO_DEBUG( orte_output( 0, "after bConverted %lu remaining count %lu iov_len_local %lu\n",
(unsigned long)pConvertor->bConverted, (unsigned long)pStack[0].count, (unsigned long)iov_len_local ); );
}
@ -146,14 +146,14 @@ int ompi_convertor_generic_simple_position( ompi_convertor_t* pConvertor,
pElem = &(description[pos_desc]);
base_pointer += pStack->disp;
DO_DEBUG( opal_output( 0, "position start pos_desc %d count_desc %d disp %llx\n"
DO_DEBUG( orte_output( 0, "position start pos_desc %d count_desc %d disp %llx\n"
"stack_pos %d pos_desc %d count_desc %d disp %llx\n",
pos_desc, count_desc, (unsigned long long)(base_pointer - pConvertor->pBaseBuf),
pConvertor->stack_pos, pStack->index, (int)pStack->count, (unsigned long long)pStack->disp ); );
while( 1 ) {
if( DT_END_LOOP == pElem->elem.common.type ) { /* end of the current loop */
DO_DEBUG( opal_output( 0, "position end_loop count %d stack_pos %d pos_desc %d disp %llx space %lu\n",
DO_DEBUG( orte_output( 0, "position end_loop count %d stack_pos %d pos_desc %d disp %llx space %lu\n",
(int)pStack->count, pConvertor->stack_pos, pos_desc,
(unsigned long long)pStack->disp, (unsigned long)iov_len_local ); );
if( --(pStack->count) == 0 ) { /* end of loop */
@ -176,7 +176,7 @@ int ompi_convertor_generic_simple_position( ompi_convertor_t* pConvertor,
}
base_pointer = pConvertor->pBaseBuf + pStack->disp;
UPDATE_INTERNAL_COUNTERS( description, pos_desc, pElem, count_desc );
DO_DEBUG( opal_output( 0, "position new_loop count %d stack_pos %d pos_desc %d disp %llx space %lu\n",
DO_DEBUG( orte_output( 0, "position new_loop count %d stack_pos %d pos_desc %d disp %llx space %lu\n",
(int)pStack->count, pConvertor->stack_pos, pos_desc,
(unsigned long long)pStack->disp, (unsigned long)iov_len_local ); );
}
@ -199,7 +199,7 @@ int ompi_convertor_generic_simple_position( ompi_convertor_t* pConvertor,
base_pointer = pConvertor->pBaseBuf + pStack->disp;
UPDATE_INTERNAL_COUNTERS( description, pos_desc, pElem, count_desc );
DDT_DUMP_STACK( pConvertor->pStack, pConvertor->stack_pos, pElem, "advance loop" );
DO_DEBUG( opal_output( 0, "position set loop count %d stack_pos %d pos_desc %d disp %llx space %lu\n",
DO_DEBUG( orte_output( 0, "position set loop count %d stack_pos %d pos_desc %d disp %llx space %lu\n",
(int)pStack->count, pConvertor->stack_pos, pos_desc,
(unsigned long long)pStack->disp, (unsigned long)iov_len_local ); );
continue;
@ -216,7 +216,7 @@ int ompi_convertor_generic_simple_position( ompi_convertor_t* pConvertor,
base_pointer = pConvertor->pBaseBuf + pStack->disp;
pos_desc++; /* advance to the next data */
UPDATE_INTERNAL_COUNTERS( description, pos_desc, pElem, count_desc );
DO_DEBUG( opal_output( 0, "position set loop count %d stack_pos %d pos_desc %d disp %llx space %lu\n",
DO_DEBUG( orte_output( 0, "position set loop count %d stack_pos %d pos_desc %d disp %llx space %lu\n",
(int)pStack->count, pConvertor->stack_pos, pos_desc,
(unsigned long long)pStack->disp, (unsigned long)iov_len_local ); );
}
@ -228,7 +228,7 @@ int ompi_convertor_generic_simple_position( ompi_convertor_t* pConvertor,
/* I complete an element, next step I should go to the next one */
PUSH_STACK( pStack, pConvertor->stack_pos, pos_desc, DT_BYTE, count_desc,
base_pointer - pStack->disp - pConvertor->pBaseBuf );
DO_DEBUG( opal_output( 0, "position save stack stack_pos %d pos_desc %d count_desc %d disp %llx\n",
DO_DEBUG( orte_output( 0, "position save stack stack_pos %d pos_desc %d count_desc %d disp %llx\n",
pConvertor->stack_pos, pStack->index, (int)pStack->count, (unsigned long long)pStack->disp ); );
return 0;
}

View File

@ -21,7 +21,7 @@
#include <stdlib.h>
#include <stdarg.h>
#include "opal/util/output.h"
#include "orte/util/output.h"
#include "ompi/errhandler/errhandler.h"
#include "ompi/errhandler/errhandler_predefined.h"
#include "ompi/errhandler/errcode.h"
@ -139,9 +139,9 @@ static void out(char *str, char *arg)
{
if (ompi_mpi_initialized && !ompi_mpi_finalized) {
if (NULL != arg) {
opal_output(0, str, arg);
orte_output(0, str, arg);
} else {
opal_output(0, str);
orte_output(0, str);
}
} else {
if (NULL != arg) {

View File

@ -24,7 +24,7 @@
#include "ompi/runtime/params.h"
#include "ompi/mca/io/base/base.h"
#include "ompi/info/info.h"
#include "opal/util/output.h"
#include "orte/util/output.h"
/*
* Table for Fortran <-> C file handle conversion
@ -200,7 +200,7 @@ int ompi_file_finalize(void)
we're destroying everything, it isn't worth it */
}
if (num_unnamed > 0) {
opal_output(0, "WARNING: %lu unnamed MPI_File handles still allocated at MPI_FINALIZE", (unsigned long)num_unnamed);
orte_output(0, "WARNING: %lu unnamed MPI_File handles still allocated at MPI_FINALIZE", (unsigned long)num_unnamed);
}
OBJ_DESTRUCT(&ompi_file_f_to_c_table);

View File

@ -28,7 +28,7 @@
#ifndef OMPI_GROUP_H
#define OMPI_GROUP_H
#include "opal/util/output.h"
#include "orte/util/output.h"
#include "mpi.h"
#include "opal/class/opal_pointer_array.h"
#if defined(c_plusplus) || defined(__cplusplus)
@ -310,7 +310,7 @@ static inline struct ompi_proc_t* ompi_group_peer_lookup(ompi_group_t *group, in
{
#if OMPI_ENABLE_DEBUG
if (peer_id >= group->grp_proc_count) {
opal_output(0, "ompi_group_lookup_peer: invalid peer index (%d)", peer_id);
orte_output(0, "ompi_group_lookup_peer: invalid peer index (%d)", peer_id);
return (struct ompi_proc_t *) NULL;
}
#endif

View File

@ -33,7 +33,7 @@
#include "ompi/constants.h"
#include "ompi/info/info.h"
#include "ompi/runtime/params.h"
#include "opal/util/output.h"
#include "orte/util/output.h"
/*
@ -378,12 +378,12 @@ int ompi_info_finalize(void)
if (!info->i_freed && ompi_debug_show_handle_leaks) {
if (ompi_debug_show_handle_leaks) {
opal_output(0, "WARNING: MPI_Info still allocated at MPI_FINALIZE");
orte_output(0, "WARNING: MPI_Info still allocated at MPI_FINALIZE");
for (item = opal_list_get_first(&(info->super));
opal_list_get_end(&(info->super)) != item;
item = opal_list_get_next(item)) {
entry = (ompi_info_entry_t *) item;
opal_output(0, "WARNING: key=\"%s\", value=\"%s\"",
orte_output(0, "WARNING: key=\"%s\", value=\"%s\"",
entry->ie_key,
NULL != entry->ie_value ? entry->ie_value : "(null)");
found = true;
@ -397,7 +397,7 @@ int ompi_info_finalize(void)
since we're destroying everything, it isn't worth it */
if (!found && ompi_debug_show_handle_leaks) {
opal_output(0, "WARNING: (no keys)");
orte_output(0, "WARNING: (no keys)");
}
}
}

View File

@ -18,7 +18,7 @@
*/
#include "ompi_config.h"
#include "opal/util/output.h"
#include "orte/util/output.h"
#include "allocator_basic.h"
#include "ompi/constants.h"

View File

@ -108,7 +108,7 @@ int mca_bml_base_send( mca_bml_base_btl_t* bml_btl,
}
if(mca_bml_base_error_count % 2) {
/* local completion - network "drops" packet */
opal_output(0, "%s:%d: dropping data, with local completion\n", __FILE__, __LINE__);
orte_output(0, "%s:%d: dropping data, with local completion\n", __FILE__, __LINE__);
des->des_cbfunc(bml_btl->btl, bml_btl->btl_endpoint, des, OMPI_SUCCESS);
return OMPI_SUCCESS;
} else {
@ -116,7 +116,7 @@ int mca_bml_base_send( mca_bml_base_btl_t* bml_btl,
mca_bml_base_context_t* ctx = (mca_bml_base_context_t*)
malloc(sizeof(mca_bml_base_context_t));
if(NULL != ctx) {
opal_output(0, "%s:%d: corrupting data\n", __FILE__, __LINE__);
orte_output(0, "%s:%d: corrupting data\n", __FILE__, __LINE__);
ctx->index = (size_t) ((des->des_src[0].seg_len * rand() * 1.0) / (RAND_MAX + 1.0));
ctx->cbfunc = des->des_cbfunc;
ctx->cbdata = des->des_cbdata;

View File

@ -24,7 +24,7 @@
#include "opal/mca/mca.h"
#include "ompi/mca/bml/bml.h"
#include "opal/util/output.h"
#include "orte/util/output.h"
/*
* Global functions for the BML

View File

@ -24,7 +24,7 @@
#include "opal/mca/mca.h"
#include "ompi/mca/bml/bml.h"
#include "opal/util/output.h"
#include "orte/util/output.h"
#include "opal/threads/mutex.h"
#include "bml_base_btl.h"

View File

@ -67,7 +67,7 @@ int mca_bml_base_init( bool enable_progress_threads,
cli = (mca_base_component_list_item_t*) item;
component = (mca_bml_base_component_t*) cli->cli_component;
if(NULL == component->bml_init) {
opal_output_verbose( 10, mca_bml_base_output,
orte_output_verbose( 10, mca_bml_base_output,
"select: no init function; ignoring component %s",
component->bml_version.mca_component_name );
continue;

View File

@ -133,7 +133,7 @@ static inline mca_bml_base_btl_t* mca_bml_base_btl_array_insert(mca_bml_base_btl
{
#if OMPI_ENABLE_DEBUG
if(array->arr_size >= array->arr_reserve) {
opal_output(0, "mca_bml_base_btl_array_insert: invalid array index %lu >= %lu",
orte_output(0, "mca_bml_base_btl_array_insert: invalid array index %lu >= %lu",
(unsigned long)array->arr_size, (unsigned long)array->arr_reserve);
return 0;
}
@ -179,7 +179,7 @@ static inline mca_bml_base_btl_t* mca_bml_base_btl_array_get_index(mca_bml_base_
{
#if OMPI_ENABLE_DEBUG
if(item_index >= array->arr_size) {
opal_output(0, "mca_bml_base_btl_array_get_index: invalid array index %lu >= %lu",
orte_output(0, "mca_bml_base_btl_array_get_index: invalid array index %lu >= %lu",
(unsigned long)item_index, (unsigned long)array->arr_size);
return 0;
}
@ -198,7 +198,7 @@ static inline mca_bml_base_btl_t* mca_bml_base_btl_array_get_next(mca_bml_base_b
{
#if OMPI_ENABLE_DEBUG
if(array->arr_size == 0) {
opal_output(0, "mca_bml_base_btl_array_get_next: invalid array size");
orte_output(0, "mca_bml_base_btl_array_get_next: invalid array size");
return 0;
}
#endif

View File

@ -23,7 +23,7 @@
#include <stdlib.h>
#include <string.h>
#include "opal/util/show_help.h"
#include "orte/util/output.h"
#include "ompi/class/ompi_bitmap.h"
#include "ompi/mca/bml/bml.h"
#include "ompi/mca/bml/base/base.h"
@ -244,7 +244,7 @@ int mca_bml_r2_add_procs(
/* allocate bml specific proc data */
bml_endpoint = OBJ_NEW(mca_bml_base_endpoint_t);
if (NULL == bml_endpoint) {
opal_output(0, "mca_bml_r2_add_procs: unable to allocate resources");
orte_output(0, "mca_bml_r2_add_procs: unable to allocate resources");
free(btl_endpoints);
return OMPI_ERR_OUT_OF_RESOURCE;
}
@ -299,14 +299,14 @@ int mca_bml_r2_add_procs(
bml_btl->btl_flags = btl->btl_flags;
bml_btl->btl_put = btl->btl_put;
if( (bml_btl->btl_flags & MCA_BTL_FLAGS_PUT) && (NULL == bml_btl->btl_put) ) {
opal_output(0, "mca_bml_r2_add_procs: The PUT flag is specified for"
orte_output(0, "mca_bml_r2_add_procs: The PUT flag is specified for"
" the %s BTL without any PUT function attached. Disard the flag !",
bml_btl->btl->btl_component->btl_version.mca_component_name);
bml_btl->btl_flags ^= MCA_BTL_FLAGS_PUT;
}
bml_btl->btl_get = btl->btl_get;
if( (bml_btl->btl_flags & MCA_BTL_FLAGS_GET) && (NULL == bml_btl->btl_get) ) {
opal_output(0, "mca_bml_r2_add_procs: The GET flag is specified for"
orte_output(0, "mca_bml_r2_add_procs: The GET flag is specified for"
" the %s BTL without any GET function attached. Disard the flag !",
bml_btl->btl->btl_component->btl_version.mca_component_name);
bml_btl->btl_flags ^= MCA_BTL_FLAGS_GET;
@ -460,7 +460,7 @@ int mca_bml_r2_add_procs(
remote = strdup("Unknown");
}
opal_show_help("help-mca-bml-r2",
orte_show_help("help-mca-bml-r2",
"unreachable proc",
true, local, remote, NULL);
@ -607,7 +607,7 @@ int mca_bml_r2_del_btl(mca_btl_base_module_t* btl)
return OMPI_SUCCESS;
if(opal_list_get_size(&mca_btl_base_modules_initialized) == 2){
opal_output(0, "only one BTL left, can't failover");
orte_output(0, "only one BTL left, can't failover");
goto CLEANUP;
}

View File

@ -23,7 +23,7 @@
#include <stdlib.h>
#include <string.h>
#include "opal/util/show_help.h"
#include "orte/util/output.h"
#include "ompi/runtime/ompi_cr.h"
#include "ompi/class/ompi_bitmap.h"
#include "ompi/mca/bml/bml.h"
@ -99,7 +99,7 @@ int mca_bml_r2_ft_event(int state)
*/
if( NULL != (mca_bml_r2.btl_modules[btl_idx])->btl_mpool &&
NULL != (mca_bml_r2.btl_modules[btl_idx])->btl_mpool->mpool_ft_event ) {
opal_output_verbose(10, ompi_cr_output,
orte_output_verbose(10, ompi_cr_output,
"bml:r2: ft_event: Notify the %s MPool.\n",
(mca_bml_r2.btl_modules[btl_idx])->btl_mpool->mpool_component->mpool_version.mca_component_name);
if(OMPI_SUCCESS != (ret = (mca_bml_r2.btl_modules[btl_idx])->btl_mpool->mpool_ft_event(loc_state) ) ) {
@ -111,7 +111,7 @@ int mca_bml_r2_ft_event(int state)
* Notify BTL
*/
if( NULL != (mca_bml_r2.btl_modules[btl_idx])->btl_ft_event) {
opal_output_verbose(10, ompi_cr_output,
orte_output_verbose(10, ompi_cr_output,
"bml:r2: ft_event: Notify the %s BTL.\n",
(mca_bml_r2.btl_modules[btl_idx])->btl_component->btl_version.mca_component_name);
if(OMPI_SUCCESS != (ret = (mca_bml_r2.btl_modules[btl_idx])->btl_ft_event(loc_state) ) ) {
@ -140,7 +140,7 @@ int mca_bml_r2_ft_event(int state)
mca_bml_r2.btl_progress = NULL;
}
opal_output_verbose(10, ompi_cr_output,
orte_output_verbose(10, ompi_cr_output,
"bml:r2: ft_event(Restart): Reselect BTLs\n");
/*
@ -152,7 +152,7 @@ int mca_bml_r2_ft_event(int state)
* are not available now.
*/
if( OMPI_SUCCESS != (ret = mca_btl_base_close())) {
opal_output(0, "bml:r2: ft_event(Restart): Failed to close BTL framework\n");
orte_output(0, "bml:r2: ft_event(Restart): Failed to close BTL framework\n");
return ret;
}
@ -164,11 +164,11 @@ int mca_bml_r2_ft_event(int state)
* we try to remove some restart only files.
*/
if (OMPI_SUCCESS != (ret = orte_grpcomm.barrier())) {
opal_output(0, "bml:r2: ft_event(Restart): Failed in orte_grpcomm.barrier (%d)", ret);
orte_output(0, "bml:r2: ft_event(Restart): Failed in orte_grpcomm.barrier (%d)", ret);
return ret;
}
opal_output_verbose(10, ompi_cr_output,
orte_output_verbose(10, ompi_cr_output,
"bml:r2: ft_event(Restart): Cleanup restart files\n");
opal_crs_base_cleanup_flush();
@ -176,7 +176,7 @@ int mca_bml_r2_ft_event(int state)
* Re-open the BTL framework to get the full list of components.
*/
if( OMPI_SUCCESS != (ret = mca_btl_base_open()) ) {
opal_output(0, "bml:r2: ft_event(Restart): Failed to open BTL framework\n");
orte_output(0, "bml:r2: ft_event(Restart): Failed to open BTL framework\n");
return ret;
}
@ -187,7 +187,7 @@ int mca_bml_r2_ft_event(int state)
*/
if( OMPI_SUCCESS != (ret = mca_btl_base_select(OMPI_ENABLE_PROGRESS_THREADS,
OMPI_ENABLE_MPI_THREADS) ) ) {
opal_output(0, "bml:r2: ft_event(Restart): Failed to select in BTL framework\n");
orte_output(0, "bml:r2: ft_event(Restart): Failed to select in BTL framework\n");
return ret;
}

View File

@ -21,7 +21,7 @@
#ifndef MCA_BML_R2_FT_H
#define MCA_BML_R2_FT_H
#include "opal/util/output.h"
#include "orte/util/output.h"
#include "ompi/mca/btl/btl.h"
#if defined(c_plusplus) || defined(__cplusplus)

View File

@ -24,8 +24,8 @@
#include "base.h"
#include "btl_base_error.h"
#include "opal/util/show_help.h"
#include "orte/util/output.h"
#include "orte/util/proc_info.h"
#include "orte/types.h"
#include "orte/util/name_fns.h"
@ -65,7 +65,7 @@ void mca_btl_base_error_no_nics(const char* transport,
/* print out no-nic warning if user told us to */
asprintf(&procid, "%s", ORTE_NAME_PRINT(ORTE_PROC_MY_NAME));
opal_show_help("help-mpi-btl-base.txt", "btl:no-nics",
orte_show_help("help-mpi-btl-base.txt", "btl:no-nics",
true, procid, transport, orte_process_info.nodename,
nic_name);
free(procid);

View File

@ -9,7 +9,7 @@
* University of Stuttgart. All rights reserved.
* Copyright (c) 2004-2005 The Regents of the University of California.
* All rights reserved.
* Copyright (c) 2007 Cisco Systems, Inc. All rights reserved.
* Copyright (c) 2007-2008 Cisco Systems, Inc. All rights reserved.
* Copyright (c) 2007 Sun Microsystems, Inc. All rights reserved.
* $COPYRIGHT$
*
@ -28,6 +28,7 @@
#include "orte/util/proc_info.h"
#include "orte/util/name_fns.h"
#include "orte/util/output.h"
#include "orte/runtime/orte_globals.h"
OMPI_DECLSPEC extern int mca_btl_base_verbose;

7