Author: jjhursey
Date: 2008-02-07 10:28:28 EST (Thu, 07 Feb 2008)
New Revision: 17398
URL: https://svn.open-mpi.org/trac/ompi/changeset/17398
Log:
A quick try at ticket refs #1207.
Here we are processing the BML structure attached to ompi_proc_t well after
add_procs has been called.
Currently only Rank 0 displays data, and makes no attempt to gather information
from other ranks. I still need to add the MCA parameters to enable/disable this
feature along with a bunch of other stuff.
Examples from this commit on 2 nodes of IU's Odin Machine:
{{{
shell$ mpirun -np 6 -mca btl tcp,sm,self hello
[odin001.cs.indiana.edu:28548] Connected to Process 0 on odin001 via: self
[odin001.cs.indiana.edu:28548] Connected to Process 1 on odin001 via: sm
[odin001.cs.indiana.edu:28548] Connected to Process 2 on odin001 via: sm
[odin001.cs.indiana.edu:28548] Connected to Process 3 on odin001 via: sm
[odin001.cs.indiana.edu:28548] Connected to Process 4 on odin002 via: tcp
[odin001.cs.indiana.edu:28548] Connected to Process 4 on odin002 via: tcp
[odin001.cs.indiana.edu:28548] Connected to Process 5 on odin002 via: tcp
[odin001.cs.indiana.edu:28548] Connected to Process 5 on odin002 via: tcp
[odin001.cs.indiana.edu:28548] Unique connection types: self,sm,tcp
(Hello World) I am 0 of 6 running on odin001.cs.indiana.edu (PID 28548)
(Hello World) I am 1 of 6 running on odin001.cs.indiana.edu (PID 28549)
(Hello World) I am 2 of 6 running on odin001.cs.indiana.edu (PID 28550)
(Hello World) I am 3 of 6 running on odin001.cs.indiana.edu (PID 28551)
(Hello World) I am 4 of 6 running on odin002.cs.indiana.edu (PID 7809)
(Hello World) I am 5 of 6 running on odin002.cs.indiana.edu (PID 7810)
}}}
In this example you can see that we have 2 tcp connections to odin002 for each
process, since Odin has 2 tcp interfaces to each machine.
{{{
shell$ mpirun -np 6 -mca btl tcp,sm,openib,self hello
[odin001.cs.indiana.edu:28566] Connected to Process 0 on odin001 via: self
[odin001.cs.indiana.edu:28566] Connected to Process 1 on odin001 via: sm
[odin001.cs.indiana.edu:28566] Connected to Process 2 on odin001 via: sm
[odin001.cs.indiana.edu:28566] Connected to Process 3 on odin001 via: sm
[odin001.cs.indiana.edu:28566] Connected to Process 4 on odin002 via: openib
[odin001.cs.indiana.edu:28566] Connected to Process 5 on odin002 via: openib
[odin001.cs.indiana.edu:28566] Unique connection types: self,sm,openib
(Hello World) I am 0 of 6 running on odin001.cs.indiana.edu (PID 28566)
(Hello World) I am 1 of 6 running on odin001.cs.indiana.edu (PID 28567)
(Hello World) I am 2 of 6 running on odin001.cs.indiana.edu (PID 28568)
(Hello World) I am 3 of 6 running on odin001.cs.indiana.edu (PID 28569)
(Hello World) I am 4 of 6 running on odin002.cs.indiana.edu (PID 7820)
(Hello World) I am 5 of 6 running on odin002.cs.indiana.edu (PID 7821)
}}}
The above also occurs when passing no mca arguments. But here you can see that
tcp is not being used due to exclucivity rules in Open MPI. So even though
we specified {{{-mca btl tcp,sm,openib,self}}} only {{{self,sm,openib}}} are
being used.
Text files modified:
tmp-public/connect-map/ompi/runtime/ompi_mpi_init.c | 6 +++
tmp-public/connect-map/ompi/runtime/ompi_mpi_params.c | 65 ++++++++++++++++++++++++++++++++++++++++
tmp-public/connect-map/ompi/runtime/params.h | 8 ++++
3 files changed, 79 insertions(+), 0 deletions(-)
Modified: tmp-public/connect-map/ompi/runtime/ompi_mpi_init.c
==============================================================================
--- tmp-public/connect-map/ompi/runtime/ompi_mpi_init.c (original)
+++ tmp-public/connect-map/ompi/runtime/ompi_mpi_init.c 2008-02-07 10:28:28 EST
(Thu, 07 Feb 2008)
@@ -749,6 +749,12 @@
opal_progress_set_event_poll_rate(value);
}
+
+ /*
+ * Display connectivity information
+ */
+ ompi_show_connectivity_info();
+
/* At this point, we are fully configured and in MPI mode. Any
communication calls here will work exactly like they would in
the user's code. Setup the connections between procs and warm
Modified: tmp-public/connect-map/ompi/runtime/ompi_mpi_params.c
==============================================================================
--- tmp-public/connect-map/ompi/runtime/ompi_mpi_params.c (original)
+++ tmp-public/connect-map/ompi/runtime/ompi_mpi_params.c 2008-02-07
10:28:28 EST (Thu, 07 Feb 2008)
@@ -33,6 +33,10 @@
#include "opal/util/show_help.h"
#include "opal/mca/base/mca_base_param.h"
+#include "orte/util/proc_info.h"
+#include "ompi/proc/proc.h"
+#include "ompi/mca/bml/bml.h"
+
/*
* Global variables
*
@@ -335,3 +339,64 @@
return OMPI_SUCCESS;
}
+
+
+int ompi_show_connectivity_info(void)
+{
+ int exit_status = OMPI_SUCCESS;
+ ompi_proc_t** procs = NULL;
+ size_t nprocs, p, nbtls, b;
+ char *unique_set = NULL;
+ size_t new_size;
+
+ /* JJH: Add MCA parameter here */
+
+ if( 0 == ORTE_PROC_MY_NAME->vpid ) {
+ /* Get all ompi_proc_t's */
+ if (NULL == (procs = ompi_proc_world(&nprocs))) {
+ opal_output(0, "ompi_proc_world() failed\n");
+ goto cleanup;
+ }
+
+ for(p = 0; p < nprocs; ++p ) {
+ if( NULL != procs[p]->proc_bml ) {
+ mca_bml_base_btl_t *bml_btl = NULL;
+ nbtls =
mca_bml_base_btl_array_get_size(&(procs[p]->proc_bml->btl_send));
+
+ /* For each btl */
+ for(b = 0; b < nbtls; ++b) {
+ char *component_name = NULL;
+ bml_btl =
mca_bml_base_btl_array_get_index(&(procs[p]->proc_bml->btl_send), b);
+ component_name =
strdup(bml_btl->btl->btl_component->btl_version.mca_component_name);
+
+ opal_output(0, "Connected to Process %ld on %s via: %s\n",
+ (long)procs[p]->proc_name.vpid,
+ procs[p]->proc_hostname,
+ component_name);
+
+ if( NULL == unique_set ) {
+ unique_set = strdup(component_name);
+ }
+ else {
+ /* Add this component if it is not already included */
+ if( NULL == strstr(unique_set, component_name) ) {
+ new_size = sizeof(char)*(strlen(unique_set) +
strlen(component_name) + 1);
+ unique_set = (char *)realloc(unique_set, new_size);
+
+ strncat(unique_set, ",", strlen(","));
+ strncat(unique_set,
+ component_name,
+ strlen(component_name));
+ }
+ }
+ }
+ }
+ }
+ opal_output(0, "Unique connection types: %s\n",
+ unique_set);
+ free(unique_set);
+ }
+
+ cleanup:
+ return exit_status;
+}
Modified: tmp-public/connect-map/ompi/runtime/params.h
==============================================================================
--- tmp-public/connect-map/ompi/runtime/params.h (original)
+++ tmp-public/connect-map/ompi/runtime/params.h 2008-02-07 10:28:28 EST
(Thu, 07 Feb 2008)
@@ -170,6 +170,14 @@
*/
int ompi_show_all_mca_params(int32_t, int, char *);
+/**
+ * Display Connectivity information
+ *
+ * @returns OMPI_SUCCESS
+ *
+ */
+int ompi_show_connectivity_info(void);
+
END_C_DECLS
#endif /* OMPI_RUNTIME_PARAMS_H */
_______________________________________________
svn-full mailing list
svn-f...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/svn-full