/* Hi OpenMPI people,
This mail is itself the c code that will reproduce the
bug.
The basic idea is that in a sigle processor debian
machine, only TCP messaging, 1.1.2 (and previous
versions)
abort with this sample program during MPI_Barrier when
run with
three processes (more will fail too but more
unpredictable).
My best guess is that PtoP messaging (if not fully
paired in sends and recevs between collective
instrucs) is interfering with collective messaging.
Attached is the gzip of config.log (the zip one
"may cause irreparable damage to your computer and
your files").
Thanks for OpenMPI.
JLQ.
*/
#include <stdio.h>
#include <stdlib.h>
#include <mpi.h>
// One debian machine. 3 processes. Only TCP
messaging.
// IT MIGHT BE A LITTLE TRICKY TO GET THE ACTUAL ERROR
// (one more reason to think is a bug) because the
// program might just run !
// Playing a little bit with the following defines
// should get you the error listed at the end.
// Observation. This is a simple scenario to reproduce
// the bug and you cannnot use a big BUFF_SZ because
// the program might lock (all processes trying to
// send).
#define KNT_1 10
#define BUFF_SZ 100
enum brain_exception_code {
k_tag_1 = 100,
k_tag_2
};
void BARRIER_BUG_CALL(){
int ok = MPI_Barrier(MPI_COMM_WORLD);
}
int main (int argc, char **argv) {
int my_rank = 0, num_ranks = 0;
MPI_Request request;
MPI_Status status;
long out_buff[BUFF_SZ], in_buff[BUFF_SZ];
int in_flag = 0;
MPI_Init(&argc, &argv);
MPI_Comm_rank(MPI_COMM_WORLD, &my_rank);
MPI_Comm_size(MPI_COMM_WORLD, &num_ranks);
MPI_Irecv(in_buff, BUFF_SZ, MPI_LONG, MPI_ANY_SOURCE,
MPI_ANY_TAG, MPI_COMM_WORLD, &request );
for(long bb = 0; bb < KNT_1; bb++){
long hh = 0;
for(hh = 0; hh < num_ranks; hh++){
if(hh != my_rank){
for(long nn = 0; nn < BUFF_SZ; nn++){
out_buff[nn] = bb;
}
MPI_Send(out_buff, BUFF_SZ, MPI_LONG, hh,
k_tag_1,
MPI_COMM_WORLD);
}
}
MPI_Test(&request, &in_flag, &status);
if(in_flag){
int src = status.MPI_SOURCE;
//printf(" %i.%i.%i.%i.", my_rank, bb, src,
in_buff[0]);
MPI_Irecv(in_buff, BUFF_SZ, MPI_LONG,
MPI_ANY_SOURCE,
MPI_ANY_TAG, MPI_COMM_WORLD, &request);
}
}
BARRIER_BUG_CALL();
if(my_rank == 0){
printf("FINISHED 0.\n");
}
MPI_Finalize();
return 0;
}
/* run command:
mpirun -np 3 -host 127.0.0.1 barrier_bug
*/
/*
Signal:11 info.si_errno:0(Success)
si_code:1(SEGV_MAPERR)
Failing at addr:0x28
[0] func:/lib/openmpi/lib/libopal.so.0 [0x4011cd8f]
[1] func:/lib/libpthread.so.0 [0x402588cb]
[2] func:/lib/libc.so.6 [0x402c76f0]
[3]
func:/lib/openmpi-1.1.2/lib/openmpi/mca_pml_ob1.so(mca_pml_ob1_recv_frag_match+0x1e3)
[0x404782e3]
[4]
func:/lib/openmpi-1.1.2/lib/openmpi/mca_pml_ob1.so(mca_pml_ob1_recv_frag_callback+0x88)
[0x40477cf8]
[5]
func:/lib/openmpi-1.1.2/lib/openmpi/mca_btl_sm.so(mca_btl_sm_component_progress+0x84b)
[0x4048a80b]
[6]
func:/lib/openmpi-1.1.2/lib/openmpi/mca_bml_r2.so(mca_bml_r2_progress+0x36)
[0x40480dc6]
[7]
func:/lib/openmpi/lib/libopal.so.0(opal_progress+0xb9)
[0x40106bd9]
[8] func:/lib/openmpi-1.1.2/lib/openmpi/mca_pml_ob1.so
[0x404764b5]
[9]
func:/lib/openmpi-1.1.2/lib/openmpi/mca_pml_ob1.so(mca_pml_ob1_recv+0x1dc)
[0x4047624c]
[10]
func:/lib/openmpi-1.1.2/lib/openmpi/mca_coll_tuned.so(ompi_coll_tuned_barrier_intra_recursivedoubling+0x253)
[0x404b1da3]
[11]
func:/lib/openmpi-1.1.2/lib/openmpi/mca_coll_tuned.so(ompi_coll_tuned_barrier_intra_dec_fixed+0x28)
[0x404af818]
[12]
func:/lib/openmpi/lib/libmpi.so.0(PMPI_Barrier+0xdc)
[0x4007959c]
[13] func:barrier_bug(_Z16BARRIER_BUG_CALLv+0x12)
[0x804ea16]
[14] func:barrier_bug(main+0x1db) [0x804ebf7]
[15] func:/lib/libc.so.6(__libc_start_main+0xc6)
[0x402b3e36]
[16] func:barrier_bug(__gxx_personality_v0+0x42d)
[0x804e961]
*** End of error message ***
*/
/* ompi_info output:
Open MPI: 1.1.2
Open MPI SVN revision: r12073
Open RTE: 1.1.2
Open RTE SVN revision: r12073
OPAL: 1.1.2
OPAL SVN revision: r12073
Prefix: /lib/openmpi-1.1.2
Configured architecture: i686-pc-linux-gnu
Configured by: webmgr
Configured on: Sun Oct 29 09:49:39 COT 2006
Configure host: aculiar.aculiar.com
Built by: webmgr
Built on: dom oct 29 12:15:26 COT 2006
Built host: aculiar.aculiar.com
C bindings: yes
C++ bindings: yes
Fortran77 bindings: no
Fortran90 bindings: no
Fortran90 bindings size: na
C compiler: gcc
C compiler absolute: /usr/bin/gcc
C++ compiler: g++
C++ compiler absolute: /usr/bin/g++
Fortran77 compiler: none
Fortran77 compiler abs: none
Fortran90 compiler: none
Fortran90 compiler abs: none
C profiling: yes
C++ profiling: yes
Fortran77 profiling: no
Fortran90 profiling: no
C++ exceptions: no
Thread support: posix (mpi: no, progress:
no)
Internal debug support: no
MPI parameter check: runtime
Memory profiling support: no
Memory debugging support: no
libltdl support: yes
MCA memory: ptmalloc2 (MCA v1.0, API
v1.0, Component v1.1.2)
MCA paffinity: linux (MCA v1.0, API v1.0,
Component v1.1.2)
MCA maffinity: first_use (MCA v1.0, API
v1.0, Component v1.1.2)
MCA timer: linux (MCA v1.0, API v1.0,
Component v1.1.2)
MCA allocator: basic (MCA v1.0, API v1.0,
Component v1.0)
MCA allocator: bucket (MCA v1.0, API v1.0,
Component v1.0)
MCA coll: basic (MCA v1.0, API v1.0,
Component v1.1.2)
MCA coll: hierarch (MCA v1.0, API
v1.0, Component v1.1.2)
MCA coll: self (MCA v1.0, API v1.0,
Component v1.1.2)
MCA coll: sm (MCA v1.0, API v1.0,
Component v1.1.2)
MCA coll: tuned (MCA v1.0, API v1.0,
Component v1.1.2)
MCA io: romio (MCA v1.0, API v1.0,
Component v1.1.2)
MCA mpool: sm (MCA v1.0, API v1.0,
Component v1.1.2)
MCA pml: ob1 (MCA v1.0, API v1.0,
Component v1.1.2)
MCA bml: r2 (MCA v1.0, API v1.0,
Component v1.1.2)
MCA rcache: rb (MCA v1.0, API v1.0,
Component v1.1.2)
MCA btl: self (MCA v1.0, API v1.0,
Component v1.1.2)
MCA btl: sm (MCA v1.0, API v1.0,
Component v1.1.2)
MCA btl: tcp (MCA v1.0, API v1.0,
Component v1.0)
MCA topo: unity (MCA v1.0, API v1.0,
Component v1.1.2)
MCA osc: pt2pt (MCA v1.0, API v1.0,
Component v1.0)
MCA gpr: null (MCA v1.0, API v1.0,
Component v1.1.2)
MCA gpr: proxy (MCA v1.0, API v1.0,
Component v1.1.2)
MCA gpr: replica (MCA v1.0, API v1.0,
Component v1.1.2)
MCA iof: proxy (MCA v1.0, API v1.0,
Component v1.1.2)
MCA iof: svc (MCA v1.0, API v1.0,
Component v1.1.2)
MCA ns: proxy (MCA v1.0, API v1.0,
Component v1.1.2)
MCA ns: replica (MCA v1.0, API v1.0,
Component v1.1.2)
MCA oob: tcp (MCA v1.0, API v1.0,
Component v1.0)
MCA ras: dash_host (MCA v1.0, API
v1.0, Component v1.1.2)
MCA ras: hostfile (MCA v1.0, API
v1.0, Component v1.1.2)
MCA ras: localhost (MCA v1.0, API
v1.0, Component v1.1.2)
MCA ras: poe (MCA v1.0, API v1.0,
Component v1.1.2)
MCA ras: slurm (MCA v1.0, API v1.0,
Component v1.1.2)
MCA rds: hostfile (MCA v1.0, API
v1.0, Component v1.1.2)
MCA rds: resfile (MCA v1.0, API v1.0,
Component v1.1.2)
MCA rmaps: round_robin (MCA v1.0, API
v1.0, Component v1.1.2)
MCA rmgr: proxy (MCA v1.0, API v1.0,
Component v1.1.2)
MCA rmgr: urm (MCA v1.0, API v1.0,
Component v1.1.2)
MCA rml: oob (MCA v1.0, API v1.0,
Component v1.1.2)
MCA pls: fork (MCA v1.0, API v1.0,
Component v1.1.2)
MCA pls: rsh (MCA v1.0, API v1.0,
Component v1.1.2)
MCA pls: slurm (MCA v1.0, API v1.0,
Component v1.1.2)
MCA sds: env (MCA v1.0, API v1.0,
Component v1.1.2)
MCA sds: pipe (MCA v1.0, API v1.0,
Component v1.1.2)
MCA sds: seed (MCA v1.0, API v1.0,
Component v1.1.2)
MCA sds: singleton (MCA v1.0, API
v1.0, Component v1.1.2)
MCA sds: slurm (MCA v1.0, API v1.0,
Component v1.1.2)
*/
/*
P.S. Talking about FUD look at my previous mail.
*/
____________________________________________________________________________________
Cheap Talk? Check out Yahoo! Messenger's low PC-to-Phone call rates
(http://voice.yahoo.com)
config.log.gz
Description: 1225647031-config.log.gz
