Hi,
I've installed (tried to install) openmpi-master-201901030305-ee26ed9 on
my "SUSE Linux Enterprise Server 12.3 (x86_64)" with gcc-7.3.0, icc-19.0.1.144
pgcc-18.4-0, and Sun C 5.15 (Oracle Developer Studio 12.6). Unfortunately, I
still cannot build it with Sun C and I get a segmentation fault for one of
my small programs for the other compilers.
I get the following error for Sun C that I reported some time ago.
https://www.mail-archive.com/users@lists.open-mpi.org/msg32816.html
The program runs as expected if I only use my local machine "loki" and it
breaks if I add a remote machine (even if I only use the remote machine
without "loki").
loki hello_1 114 ompi_info | grep -e "Open MPI repo revision" -e"Configure
command line"
Open MPI repo revision: v2.x-dev-6601-gee26ed9
Configure command line: '--prefix=/usr/local/openmpi-master_64_gcc'
'--libdir=/usr/local/openmpi-master_64_gcc/lib64'
'--with-jdk-bindir=/usr/local/jdk-11/bin'
'--with-jdk-headers=/usr/local/jdk-11/include' 'JAVA_HOME=/usr/local/jdk-11'
'LDFLAGS=-m64 -L/usr/local/cuda/lib64' 'CC=gcc' 'CXX=g++' 'FC=gfortran'
'CFLAGS=-m64 -I/usr/local/cuda/include' 'CXXFLAGS=-m64
-I/usr/local/cuda/include' 'FCFLAGS=-m64' 'CPP=cpp -I/usr/local/cuda/include'
'CXXCPP=cpp -I/usr/local/cuda/include' '--enable-mpi-cxx'
'--enable-cxx-exceptions' '--enable-mpi-java' '--with-cuda=/usr/local/cuda'
'--with-valgrind=/usr/local/valgrind' '--with-hwloc=internal' '--without-verbs'
'--with-wrapper-cflags=-std=c11 -m64' '--with-wrapper-cxxflags=-m64'
'--with-wrapper-fcflags=-m64' '--enable-debug'
loki hello_1 115 mpiexec -np 4 --host loki:2,nfs2:2 hello_1_mpi
Process 0 of 4 running on loki
Process 1 of 4 running on loki
Process 2 of 4 running on nfs2
Process 3 of 4 running on nfs2
Now 3 slave tasks are sending greetings.
Greetings from task 1:
message type: 3
msg length: 132 characters
... (complete output of my program)
[nfs2:01336] *** Process received signal ***
[nfs2:01336] Signal: Segmentation fault (11)
[nfs2:01336] Signal code: Address not mapped (1)
[nfs2:01336] Failing at address: 0x7feea4849268
[nfs2:01336] [ 0] /lib64/libpthread.so.0(+0x10c10)[0x7feeacbbec10]
[nfs2:01336] [ 1]
/usr/local/openmpi-master_64_gcc/lib64/libopen-pal.so.0(+0x7cd34)[0x7feeadd94d34]
[nfs2:01336] [ 2]
/usr/local/openmpi-master_64_gcc/lib64/libopen-pal.so.0(+0x78673)[0x7feeadd90673]
[nfs2:01336] [ 3]
/usr/local/openmpi-master_64_gcc/lib64/libopen-pal.so.0(+0x7ac2c)[0x7feeadd92c2c]
[nfs2:01336] [ 4]
/usr/local/openmpi-master_64_gcc/lib64/libopen-pal.so.0(opal_finalize_cleanup_domain+0x3e)[0x7feeadd56507]
[nfs2:01336] [ 5]
/usr/local/openmpi-master_64_gcc/lib64/libopen-pal.so.0(opal_finalize_util+0x56)[0x7feeadd56667]
[nfs2:01336] [ 6]
/usr/local/openmpi-master_64_gcc/lib64/libopen-pal.so.0(opal_finalize+0xd3)[0x7feeadd567de]
[nfs2:01336] [ 7]
/usr/local/openmpi-master_64_gcc/lib64/libopen-rte.so.0(orte_finalize+0x1ba)[0x7feeae09d7ea]
[nfs2:01336] [ 8]
/usr/local/openmpi-master_64_gcc/lib64/libopen-rte.so.0(orte_daemon+0x3ddd)[0x7feeae0cf55d]
[nfs2:01336] [ 9] orted[0x40086d]
[nfs2:01336] [10] /lib64/libc.so.6(__libc_start_main+0xf5)[0x7feeac829725]
[nfs2:01336] [11] orted[0x400739]
[nfs2:01336] *** End of error message ***
Segmentation fault (core dumped)
loki hello_1 116
I would be grateful, if somebody can fix the problem. Do you need anything
else? 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:
* mpicc -o <program name> <source code file name> -lm
*
* Running:
* mpiexec -np <number of processes> <program name>
*
*
* File: hello_1_mpi.c Author: S. Gross
* Date: 04.08.2017
*
*/
#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, (int) strlen (buf), MPI_CHAR, stat.MPI_SOURCE,
MSGTAG, MPI_COMM_WORLD);
}
else
{
more_to_do = 0; /* terminate */
}
}
}
_______________________________________________
users mailing list
users@lists.open-mpi.org
https://lists.open-mpi.org/mailman/listinfo/users
