Mpiexec and mcnpx

[Ben Vanhaeren]

On Wednesday 20 October 2004 08:37, you wrote:
> Hello Pete,
>
> I have followed up on your advice and installed the Fortran Patch and
> compiled it with the Fortran Compiler. But it still doesn't work. I've
> added the output of mpiexec. Any ideas on what has gone wrong ?


I've executed the commands in a shell to d an strace. It seams that the master 
process opens several sockets:



strace /export/neutronics/mcnpx_2.5.e/bin/mcnpx i=test.i -p4wd /home/bvanhaer/
mcnpx_testjob -execer_id mpiexec -master_host fermi -my_hostname fermi 
-my_nodenum 0 -my_numprocs 4 -total_numnodes 2 -master_port 32844 
-remote_info einstein 1


socket(PF_INET, SOCK_STREAM, IPPROTO_IP) = 3
setsockopt(3, SOL_SOCKET, SO_SNDBUF, [16384], 4) = 0
setsockopt(3, SOL_SOCKET, SO_RCVBUF, [16384], 4) = 0
getsockopt(3, SOL_SOCKET, SO_SNDBUF, [32768], [4]) = 0
getsockopt(3, SOL_SOCKET, SO_RCVBUF, [32768], [4]) = 0
setsockopt(3, SOL_TCP, TCP_NODELAY, [1], 4) = 0
bind(3, {sin_family=AF_INET, sin_port=htons(0), 
sin_addr=inet_addr("0.0.0.0")}}, 16) = 0
listen(3, 32)                           = 0
getsockname(3, {sin_family=AF_INET, sin_port=htons(47726), 
sin_addr=inet_addr("0.0.0.0")}}, [16]) = 0
socket(PF_INET, SOCK_DGRAM, IPPROTO_IP) = 9
sendto(9, "n\272\0\0", 4, 0, {sin_family=AF_INET, sin_port=htons(32844), 
sin_addr=inet_addr("127.0.0.1")}}, 16) = 4
close(9)                                = 0
accept(3,


Then the slave proces tries to connect several times but gives up becouse it 
can't connect to the master port:


strace /export/neutronics/mcnpx_2.5.e/bin/mcnpx i=test.i -p4wd /home/bvanhaer/
mcnpx_testjob -execer_id mpiexec -master_host fermi -my_hostname einstein 
-my_nodenum 1 -my_numprocs 1 -total_numnodes 2 -master_port 47592


rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0
rt_sigaction(SIGCHLD, NULL, {SIG_DFL}, 8) = 0
rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0
nanosleep({2, 0}, {2, 0})               = 0
socket(PF_INET, SOCK_STREAM, IPPROTO_IP) = 3
setsockopt(3, SOL_SOCKET, SO_SNDBUF, [16384], 4) = 0
setsockopt(3, SOL_SOCKET, SO_RCVBUF, [16384], 4) = 0
getsockopt(3, SOL_SOCKET, SO_SNDBUF, [32768], [4]) = 0
getsockopt(3, SOL_SOCKET, SO_RCVBUF, [32768], [4]) = 0
setsockopt(3, IPPROTO_TCP1, [1], 4)     = 0
connect(3, {sin_family=AF_INET, sin_port=htons(47592), 
sin_addr=inet_addr("192.168.1.1")}}, 16) = -1 ECONNREFUSED (Connection 
refused)
close(3)                                = 0
rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0
rt_sigaction(SIGCHLD, NULL, {SIG_DFL}, 8) = 0
rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0
nanosleep({2, 0}, {2, 0})               = 0
socket(PF_INET, SOCK_STREAM, IPPROTO_IP) = 3
setsockopt(3, SOL_SOCKET, SO_SNDBUF, [16384], 4) = 0
setsockopt(3, SOL_SOCKET, SO_RCVBUF, [16384], 4) = 0
getsockopt(3, SOL_SOCKET, SO_SNDBUF, [32768], [4]) = 0
getsockopt(3, SOL_SOCKET, SO_RCVBUF, [32768], [4]) = 0
setsockopt(3, IPPROTO_TCP1, [1], 4)     = 0
connect(3, {sin_family=AF_INET, sin_port=htons(47592), 
sin_addr=inet_addr("192.168.1.1")}}, 16) = -1 ECONNREFUSED (Connection 
refused)
close(3)                                = 0
rt_sigaction(SIGINT, NULL, {0x82fa1f0, [INT], SA_RESTART|SA_NOMASK|0x4000000}, 
8) = 0
rt_sigaction(SIGINT, {SIG_IGN}, NULL, 8) = 0
fstat64(1, {st_mode=S_IFCHR|0620, st_rdev=makedev(136, 2), ...}) = 0
old_mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 
0x40017000
ioctl(1, TCGETS, {B38400 opost isig icanon echo ...}) = 0
write(1, "rm_13403:  p4_error: rm_start: n"..., 66rm_13403:  p4_error: 
rm_start: net_conn_to_listener failed: 47592
) = 66
--- SIGSEGV (Segmentation fault) ---
munmap(0x40017000, 4096)                = 0
_exit(1)                                = ?