Skip to content

SPML/UCX: fixed hang in SHMEM_FINALIZE - v4.0 #6922

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Aug 26, 2019
Merged

SPML/UCX: fixed hang in SHMEM_FINALIZE - v4.0 #6922

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
66e1856
SPML/UCX: fixed hang in SHMEM_FINALIZE
Aug 21, 2019
1f9fce8
SPML/UCX: fixed comment
Aug 21, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 5 additions & 2 deletions opal/mca/common/ucx/common_ucx.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -186,8 +186,11 @@ static void opal_common_ucx_wait_all_requests(void **reqs, int count, ucp_worker
}
}

OPAL_DECLSPEC int opal_common_ucx_del_procs_nofence(opal_common_ucx_del_proc_t *procs, size_t count,
size_t my_rank, size_t max_disconnect, ucp_worker_h worker) {
OPAL_DECLSPEC int opal_common_ucx_del_procs_nofence(opal_common_ucx_del_proc_t *procs,
size_t count, size_t my_rank,
size_t max_disconnect,
ucp_worker_h worker)
{
size_t num_reqs;
size_t max_reqs;
void *dreq, **dreqs;
Expand Down
12 changes: 6 additions & 6 deletions oshmem/mca/spml/ucx/spml_ucx.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -127,18 +127,16 @@ int mca_spml_ucx_del_procs(ompi_proc_t** procs, size_t nprocs)
mca_spml_ucx_ctx_default.ucp_peers[i].ucp_conn = NULL;
}

ret = opal_common_ucx_del_procs(del_procs, nprocs, oshmem_my_proc_id(),
mca_spml_ucx.num_disconnect,
mca_spml_ucx_ctx_default.ucp_worker);

ret = opal_common_ucx_del_procs_nofence(del_procs, nprocs, oshmem_my_proc_id(),
mca_spml_ucx.num_disconnect,
mca_spml_ucx_ctx_default.ucp_worker);
/* No need to barrier here - barrier is called in _shmem_finalize */
free(del_procs);
free(mca_spml_ucx.remote_addrs_tbl);
free(mca_spml_ucx_ctx_default.ucp_peers);

mca_spml_ucx_ctx_default.ucp_peers = NULL;

opal_common_ucx_mca_proc_added();

return ret;
}

Expand Down Expand Up @@ -326,6 +324,8 @@ int mca_spml_ucx_add_procs(ompi_proc_t** procs, size_t nprocs)
free(wk_roffs);

SPML_UCX_VERBOSE(50, "*** ADDED PROCS ***");

opal_common_ucx_mca_proc_added();
return OSHMEM_SUCCESS;

error2:
Expand Down