Hi,
I have built openmpi-v1.10.3rc4 on my machines (Solaris 10 Sparc,
Solaris 10 x86_64, and openSUSE Linux 12.1 x86_64) with gcc-5.1.0
and Sun C 5.13. Unfortunately I have once more a problem with
"--slot-list". This time a small program breaks on my Sparc machine
while it works as expected on Linux and SunOS x86_64.
tyr hello_1 104 ompi_info | grep -e "OPAL repo revision:" -e "C compiler
absolute:"
OPAL repo revision: v1.10.2-244-g34e1f22
C compiler absolute: /usr/local/gcc-5.1.0/bin/gcc
tyr hello_1 105 mpiexec -np 3 --host tyr --slot-list 0:0-1,1:0-1 hello_1_mpi
[tyr.informatik.hs-fulda.de:23717] [[64131,0],0] ORTE_ERROR_LOG: Not found in
file ../../../../../openmpi-1.10.3rc4/orte/mca/rmaps/rank_file/rmaps_rank_file.c
at line 326
[tyr.informatik.hs-fulda.de:23717] [[64131,0],0] ORTE_ERROR_LOG: Not found in
file ../../../../openmpi-1.10.3rc4/orte/mca/rmaps/base/rmaps_base_map_job.c at
line 377
tyr hello_1 106 /usr/local/gdb-7.6.1_64_gcc/bin/gdb mpiexec
GNU gdb (GDB) 7.6.1
...
Reading symbols from
/export2/prog/SunOS_sparc/openmpi-1.10.3_64_gcc/bin/orterun...done.
(gdb) set args -np 3 --host tyr --slot-list 0:0-1,1:0-1 hello_1_mpi
(gdb) r
Starting program: /usr/local/openmpi-1.10.3_64_gcc/bin/mpiexec -np 3 --host tyr
--slot-list 0:0-1,1:0-1 hello_1_mpi
[Thread debugging using libthread_db enabled]
[New Thread 1 (LWP 1)]
[New LWP 2 ]
[tyr.informatik.hs-fulda.de:23719] [[64129,0],0] ORTE_ERROR_LOG: Not found in
file ../../../../../openmpi-1.10.3rc4/orte/mca/rmaps/rank_file/rmaps_rank_file.c
at line 326
[tyr.informatik.hs-fulda.de:23719] [[64129,0],0] ORTE_ERROR_LOG: Not found in
file ../../../../openmpi-1.10.3rc4/orte/mca/rmaps/base/rmaps_base_map_job.c at
line 377
[LWP 2 exited]
[New Thread 2 ]
[Switching to Thread 1 (LWP 1)]
sol_thread_fetch_registers: td_ta_map_id2thr: no thread can be found to satisfy
query
(gdb) bt
#0 0xffffffff7f6173d0 in rtld_db_dlactivity () from /usr/lib/sparcv9/ld.so.1
#1 0xffffffff7f6175a8 in rd_event () from /usr/lib/sparcv9/ld.so.1
#2 0xffffffff7f618950 in lm_delete () from /usr/lib/sparcv9/ld.so.1
#3 0xffffffff7f6226bc in remove_so () from /usr/lib/sparcv9/ld.so.1
#4 0xffffffff7f624574 in remove_hdl () from /usr/lib/sparcv9/ld.so.1
#5 0xffffffff7f61d97c in dlclose_core () from /usr/lib/sparcv9/ld.so.1
#6 0xffffffff7f61d9d4 in dlclose_intn () from /usr/lib/sparcv9/ld.so.1
#7 0xffffffff7f61db0c in dlclose () from /usr/lib/sparcv9/ld.so.1
#8 0xffffffff7eccbd4c in dlopen_close (handle=0x100181820)
at
../../../../../openmpi-1.10.3rc4/opal/mca/dl/dlopen/dl_dlopen_module.c:148
#9 0xffffffff7eccb480 in opal_dl_close (handle=0x100181820)
at ../../../../openmpi-1.10.3rc4/opal/mca/dl/base/dl_base_fns.c:53
#10 0xffffffff7ec9094c in ri_destructor (obj=0x100183c40)
at
../../../../openmpi-1.10.3rc4/opal/mca/base/mca_base_component_repository.c:357
#11 0xffffffff7ec8f448 in opal_obj_run_destructors (object=0x100183c40)
at ../../../../openmpi-1.10.3rc4/opal/class/opal_object.h:451
#12 0xffffffff7ec9023c in mca_base_component_repository_release (
component=0xffffffff7b824938 <mca_oob_tcp_component>)
at
../../../../openmpi-1.10.3rc4/opal/mca/base/mca_base_component_repository.c:223
#13 0xffffffff7ec923dc in mca_base_component_unload (
component=0xffffffff7b824938 <mca_oob_tcp_component>, output_id=-1)
at
../../../../openmpi-1.10.3rc4/opal/mca/base/mca_base_components_close.c:47
#14 0xffffffff7ec92474 in mca_base_component_close (
component=0xffffffff7b824938 <mca_oob_tcp_component>, output_id=-1)
at
../../../../openmpi-1.10.3rc4/opal/mca/base/mca_base_components_close.c:60
#15 0xffffffff7ec92544 in mca_base_components_close (output_id=-1,
components=0xffffffff7f12c6e0 <orte_oob_base_framework+80>, skip=0x0)
at
../../../../openmpi-1.10.3rc4/opal/mca/base/mca_base_components_close.c:86
#16 0xffffffff7ec924b4 in mca_base_framework_components_close (
framework=0xffffffff7f12c690 <orte_oob_base_framework>, skip=0x0)
at
../../../../openmpi-1.10.3rc4/opal/mca/base/mca_base_components_close.c:66
#17 0xffffffff7efadd34 in orte_oob_base_close ()
at ../../../../openmpi-1.10.3rc4/orte/mca/oob/base/oob_base_frame.c:94
#18 0xffffffff7eca91e8 in mca_base_framework_close (
framework=0xffffffff7f12c690 <orte_oob_base_framework>)
at ../../../../openmpi-1.10.3rc4/opal/mca/base/mca_base_framework.c:198
#19 0xffffffff7c807c68 in rte_finalize ()
at ../../../../../openmpi-1.10.3rc4/orte/mca/ess/hnp/ess_hnp_module.c:882
#20 0xffffffff7ef31180 in orte_finalize ()
at ../../openmpi-1.10.3rc4/orte/runtime/orte_finalize.c:65
#21 0x00000001000074d4 in orterun (argc=8, argv=0xffffffff7fffdf78)
at ../../../../openmpi-1.10.3rc4/orte/tools/orterun/orterun.c:1151
#22 0x0000000100003e78 in main (argc=8, argv=0xffffffff7fffdf78)
at ../../../../openmpi-1.10.3rc4/orte/tools/orterun/main.c:13
(gdb) q
A debugging session is active.
Inferior 1 [process 23719 ] will be killed.
Quit anyway? (y or n) y
Quitting: sol_thread_fetch_registers: td_ta_map_id2thr: no thread can be found
to satisfy query
tyr hello_1 107
I would be grateful if somebody can fix the problem. Please let me
know, if you need more information. Thank you very much for any help
in advance.
Kind regards
Siegmar
/* An MPI-version of the "hello world" program, which delivers some
* information about its machine and operating system.
*
*
* Compiling:
* Store executable(s) into local directory.
* mpicc -o <program name> <source code file name>
*
* Store executable(s) into predefined directories.
* make
*
* Make program(s) automatically on all specified hosts. You must
* edit the file "make_compile" and specify your host names before
* you execute it.
* make_compile
*
* Running:
* LAM-MPI:
* mpiexec -boot -np <number of processes> <program name>
* or
* mpiexec -boot \
* -host <hostname> -np <number of processes> <program name> : \
* -host <hostname> -np <number of processes> <program name>
* or
* mpiexec -boot [-v] -configfile <application file>
* or
* lamboot [-v] [<host file>]
* mpiexec -np <number of processes> <program name>
* or
* mpiexec [-v] -configfile <application file>
* lamhalt
*
* OpenMPI:
* "host1", "host2", and so on can all have the same name,
* if you want to start a virtual computer with some virtual
* cpu's on the local host. The name "localhost" is allowed
* as well.
*
* mpiexec -np <number of processes> <program name>
* or
* mpiexec --host <host1,host2,...> \
* -np <number of processes> <program name>
* or
* mpiexec -hostfile <hostfile name> \
* -np <number of processes> <program name>
* or
* mpiexec -app <application file>
*
* Cleaning:
* local computer:
* rm <program name>
* or
* make clean_all
* on all specified computers (you must edit the file "make_clean_all"
* and specify your host names before you execute it.
* make_clean_all
*
*
* File: hello_1_mpi.c Author: S. Gross
* Date: 01.10.2012
*
*/
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <sys/utsname.h>
#include "mpi.h"
#define BUF_SIZE 255 /* message buffer size */
#define MAX_TASKS 12 /* max. number of tasks */
#define SENDTAG 1 /* send message command */
#define EXITTAG 2 /* termination command */
#define MSGTAG 3 /* normal message token */
#define ENTASKS -1 /* error: too many tasks */
static void master (void);
static void slave (void);
int main (int argc, char *argv[])
{
int mytid, /* my task id */
ntasks, /* number of parallel tasks */
namelen; /* length of processor name */
char processor_name[MPI_MAX_PROCESSOR_NAME];
MPI_Init (&argc, &argv);
MPI_Comm_rank (MPI_COMM_WORLD, &mytid);
MPI_Comm_size (MPI_COMM_WORLD, &ntasks);
MPI_Get_processor_name (processor_name, &namelen);
/* With the next statement every process executing this code will
* print one line on the display. It may happen that the lines will
* get mixed up because the display is a critical section. In general
* only one process (mostly the process with rank 0) will print on
* the display and all other processes will send their messages to
* this process. Nevertheless for debugging purposes (or to
* demonstrate that it is possible) it may be useful if every
* process prints itself.
*/
fprintf (stdout, "Process %d of %d running on %s\n",
mytid, ntasks, processor_name);
fflush (stdout);
MPI_Barrier (MPI_COMM_WORLD); /* wait for all other processes */
if (mytid == 0)
{
master ();
}
else
{
slave ();
}
MPI_Finalize ();
return EXIT_SUCCESS;
}
/* Function for the "master task". The master sends a request to all
* slaves asking for a message. After receiving and printing the
* messages he sends all slaves a termination command.
*
* input parameters: not necessary
* output parameters: not available
* return value: nothing
* side effects: no side effects
*
*/
void master (void)
{
int ntasks, /* number of parallel tasks */
mytid, /* my task id */
num, /* number of entries */
i; /* loop variable */
char buf[BUF_SIZE + 1]; /* message buffer (+1 for '\0') */
MPI_Status stat; /* message details */
MPI_Comm_rank (MPI_COMM_WORLD, &mytid);
MPI_Comm_size (MPI_COMM_WORLD, &ntasks);
if (ntasks > MAX_TASKS)
{
fprintf (stderr, "Error: Too many tasks. Try again with at most "
"%d tasks.\n", MAX_TASKS);
/* terminate all slave tasks */
for (i = 1; i < ntasks; ++i)
{
MPI_Send ((char *) NULL, 0, MPI_CHAR, i, EXITTAG, MPI_COMM_WORLD);
}
MPI_Finalize ();
exit (ENTASKS);
}
printf ("\n\nNow %d slave tasks are sending greetings.\n\n",
ntasks - 1);
/* request messages from slave tasks */
for (i = 1; i < ntasks; ++i)
{
MPI_Send ((char *) NULL, 0, MPI_CHAR, i, SENDTAG, MPI_COMM_WORLD);
}
/* wait for messages and print greetings */
for (i = 1; i < ntasks; ++i)
{
MPI_Recv (buf, BUF_SIZE, MPI_CHAR, MPI_ANY_SOURCE,
MPI_ANY_TAG, MPI_COMM_WORLD, &stat);
MPI_Get_count (&stat, MPI_CHAR, &num);
buf[num] = '\0'; /* add missing end-of-string */
printf ("Greetings from task %d:\n"
" message type: %d\n"
" msg length: %d characters\n"
" message: %s\n\n",
stat.MPI_SOURCE, stat.MPI_TAG, num, buf);
}
/* terminate all slave tasks */
for (i = 1; i < ntasks; ++i)
{
MPI_Send ((char *) NULL, 0, MPI_CHAR, i, EXITTAG, MPI_COMM_WORLD);
}
}
/* Function for "slave tasks". The slave task sends its hostname,
* operating system name and release, and processor architecture
* as a message to the master.
*
* input parameters: not necessary
* output parameters: not available
* return value: nothing
* side effects: no side effects
*
*/
void slave (void)
{
struct utsname sys_info; /* system information */
int mytid, /* my task id */
more_to_do;
char buf[BUF_SIZE]; /* message buffer */
MPI_Status stat; /* message details */
MPI_Comm_rank (MPI_COMM_WORLD, &mytid);
more_to_do = 1;
while (more_to_do == 1)
{
/* wait for a message from the master task */
MPI_Recv (buf, BUF_SIZE, MPI_CHAR, 0, MPI_ANY_TAG,
MPI_COMM_WORLD, &stat);
if (stat.MPI_TAG != EXITTAG)
{
uname (&sys_info);
strcpy (buf, "\n hostname: ");
strncpy (buf + strlen (buf), sys_info.nodename,
BUF_SIZE - strlen (buf));
strncpy (buf + strlen (buf), "\n operating system: ",
BUF_SIZE - strlen (buf));
strncpy (buf + strlen (buf), sys_info.sysname,
BUF_SIZE - strlen (buf));
strncpy (buf + strlen (buf), "\n release: ",
BUF_SIZE - strlen (buf));
strncpy (buf + strlen (buf), sys_info.release,
BUF_SIZE - strlen (buf));
strncpy (buf + strlen (buf), "\n processor: ",
BUF_SIZE - strlen (buf));
strncpy (buf + strlen (buf), sys_info.machine,
BUF_SIZE - strlen (buf));
MPI_Send (buf, strlen (buf), MPI_CHAR, stat.MPI_SOURCE,
MSGTAG, MPI_COMM_WORLD);
}
else
{
more_to_do = 0; /* terminate */
}
}
}
