Hi,
yesterday I installed openmpi-dev-4010-g6c9d65c on my "SUSE Linux
Enterprise Server 12 (x86_64)" with Sun C 5.13 and gcc-5.3.0.
Unfortunately I get the following warning message.
loki hello_1 128 ompi_info | grep -e "OPAL repo revision" -e "C compiler
absolute"
OPAL repo revision: dev-4010-g6c9d65c
C compiler absolute: /opt/solstudio12.4/bin/cc
loki hello_1 129 mpiexec -np 3 --host loki --slot-list 0:0-5,1:0-5 hello_1_mpi
--------------------------------------------------------------------------
WARNING: a request was made to bind a process. While the system
supports binding the process itself, at least one node does NOT
support binding memory to the process location.
Node: loki
Open MPI uses the "hwloc" library to perform process and memory
binding. This error message means that hwloc has indicated that
processor binding support is not available on this machine.
On OS X, processor and memory binding is not available at all (i.e.,
the OS does not expose this functionality).
On Linux, lack of the functionality can mean that you are on a
platform where processor and memory affinity is not supported in Linux
itself, or that hwloc was built without NUMA and/or processor affinity
support. When building hwloc (which, depending on your Open MPI
installation, may be embedded in Open MPI itself), it is important to
have the libnuma header and library files available. Different linux
distributions package these files under different names; look for
packages with the word "numa" in them. You may also need a developer
version of the package (e.g., with "dev" or "devel" in the name) to
obtain the relevant header files.
If you are getting this message on a non-OS X, non-Linux platform,
then hwloc does not support processor / memory affinity on this
platform. If the OS/platform does actually support processor / memory
affinity, then you should contact the hwloc maintainers:
https://github.com/open-mpi/hwloc.
This is a warning only; your job will continue, though performance may
be degraded.
--------------------------------------------------------------------------
Process 0 of 3 running on loki
Process 2 of 3 running on loki
Process 1 of 3 running on loki
Now 2 slave tasks are sending greetings.
Greetings from task 1:
message type: 3
...
loki openmpi-dev-4010-g6c9d65c-Linux.x86_64.64_cc 122 ls -l /usr/lib64/*numa*
-rwxr-xr-x 1 root root 48256 Nov 24 16:29 /usr/lib64/libnuma.so.1
loki openmpi-dev-4010-g6c9d65c-Linux.x86_64.64_cc 123 grep numa
log.configure.Linux.x86_64.64_cc
checking numaif.h usability... no
checking numaif.h presence... yes
configure: WARNING: numaif.h: present but cannot be compiled
configure: WARNING: numaif.h: check for missing prerequisite headers?
configure: WARNING: numaif.h: see the Autoconf documentation
configure: WARNING: numaif.h: section "Present But Cannot Be Compiled"
configure: WARNING: numaif.h: proceeding with the compiler's result
checking for numaif.h... no
loki openmpi-dev-4010-g6c9d65c-Linux.x86_64.64_cc 124
I didn't get the warning for openmpi-v1.10.2-176-g9d45e07 and
openmpi-v2.x-dev-1404-g74d8ea0 as you can see in my previous emails,
although I have the same messages in log.configure.*. I would be
grateful, if somebody can fix the problem if it is a problem
and not an intended message. 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 */
}
}
}
