Skip to content

Commit fc17dec

Browse files
committed
Fix NBC iBarrier for inter-communicators.
Remove send of the extra message. This bug hase triggered on MPICH/coll/nbicbarrier test. In this test a series of communicators are created. This extre-message was reseived after original communicator was destroyed and queued into non_existing_communicator_pending. When new completely unrelated communicator with the same id as original was created this message was pushed into the frags_cant_match queue and caused seq numbers skew and hang.
1 parent 3a3b13e commit fc17dec

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

ompi/mca/coll/libnbc/nbc_ibarrier.c

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -177,7 +177,7 @@ int ompi_coll_libnbc_ibarrier_inter(struct ompi_communicator_t *comm, ompi_reque
177177
}
178178

179179
/* inform remote peers that all local peers have entered the barrier */
180-
for (int peer = 0 ; peer < rsize ; ++peer) {
180+
for (int peer = 1; peer < rsize ; ++peer) {
181181
res = NBC_Sched_send (0, true, 1, MPI_BYTE, peer, schedule, false);
182182
if (OPAL_UNLIKELY(OMPI_SUCCESS != res)) {
183183
NBC_Return_handle (handle);

0 commit comments

Comments
 (0)