Skip to content

[v5.0.x] mtl/ofi: bail gracefully if completion error context is null #12394

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 1 commit into from
Mar 6, 2024
Merged

[v5.0.x] mtl/ofi: bail gracefully if completion error context is null #12394

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
28 changes: 18 additions & 10 deletions ompi/mca/mtl/ofi/mtl_ofi.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -158,8 +158,7 @@ ompi_mtl_ofi_context_progress(int ctxt_id)
"%s:%d: Error returned by request (type: %d) event callback: %zd.\n"
"*** The Open MPI OFI MTL is aborting the MPI job (via exit(3)).\n",
__FILE__, __LINE__, req_type, ret);
fflush(stderr);
exit(1);
goto bail;
}
}
}
Expand All @@ -181,16 +180,23 @@ ompi_mtl_ofi_context_progress(int ctxt_id)
* thread fetches the entry while others get -FI_EAGAIN
* indicating an empty queue, which is not erroneous.
*/
if (ret == -FI_EAGAIN)
if (ret == -FI_EAGAIN) {
return count;
}
opal_output(0, "%s:%d: Error returned from fi_cq_readerr: %s(%zd).\n"
"*** The Open MPI OFI MTL is aborting the MPI job (via exit(3)).\n",
__FILE__, __LINE__, fi_strerror(-ret), ret);
fflush(stderr);
exit(1);
goto bail;
}

if (!error.op_context) {
opal_output(0, "%s:%d: Error returned from fi_cq_readerr with null context. "
"Completion flags: %016lx\n"
"*** The Open MPI OFI MTL is aborting the MPI job (via exit(3)).\n",
__FILE__, __LINE__, error.flags);
goto bail;
}

assert(error.op_context);
ofi_req = TO_OFI_REQ(error.op_context);
assert(ofi_req);
req_type = ofi_req->type;
Expand All @@ -200,18 +206,20 @@ ompi_mtl_ofi_context_progress(int ctxt_id)
"%s:%d: Error returned by request (type: %d) error callback: %zd.\n"
"*** The Open MPI OFI MTL is aborting the MPI job (via exit(3)).\n",
__FILE__, __LINE__, req_type, ret);
fflush(stderr);
exit(1);
goto bail;
}
} else if (ret != -FI_EAGAIN && ret != -EINTR) {
opal_output(0, "%s:%d: Error returned from fi_cq_read: %s(%zd).\n"
"*** The Open MPI OFI MTL is aborting the MPI job (via exit(3)).\n",
__FILE__, __LINE__, fi_strerror(-ret), ret);
fflush(stderr);
exit(1);
goto bail;
}

return count;

bail:
fflush(stderr);
exit(1);
}

__opal_attribute_always_inline__ static inline int
Expand Down