Skip to content

orte/pmix/server: Fix direct modex response with error status #3942

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
Jul 20, 2017
Merged

orte/pmix/server: Fix direct modex response with error status #3942

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
30 changes: 19 additions & 11 deletions orte/orted/pmix/pmix_server.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@
* Copyright (c) 2009-2012 Cisco Systems, Inc. All rights reserved.
* Copyright (c) 2011 Oak Ridge National Labs. All rights reserved.
* Copyright (c) 2013-2017 Intel, Inc. All rights reserved.
* Copyright (c) 2014 Mellanox Technologies, Inc.
* Copyright (c) 2014-2017 Mellanox Technologies, Inc.
* All rights reserved.
* Copyright (c) 2014-2015 Research Organization for Information Science
* and Technology (RIST). All rights reserved.
Expand Down Expand Up @@ -322,7 +322,7 @@ void pmix_server_finalize(void)
}

static void send_error(int status, opal_process_name_t *idreq,
orte_process_name_t *remote)
orte_process_name_t *remote, int remote_room)
{
opal_buffer_t *reply;
int rc;
Expand All @@ -331,21 +331,29 @@ static void send_error(int status, opal_process_name_t *idreq,
/* pack the status */
if (OPAL_SUCCESS != (rc = opal_dss.pack(reply, &status, 1, OPAL_INT))) {
ORTE_ERROR_LOG(rc);
OBJ_RELEASE(reply);
return;
goto error;
}
/* pack the id of the requested proc */
if (OPAL_SUCCESS != (rc = opal_dss.pack(reply, idreq, 1, OPAL_NAME))) {
ORTE_ERROR_LOG(rc);
OBJ_RELEASE(reply);
return;
goto error;
}

/* pack the remote daemon's request room number */
if (OPAL_SUCCESS != (rc = opal_dss.pack(reply, &remote_room, 1, OPAL_INT))) {
ORTE_ERROR_LOG(rc);
goto error;
}

/* send the response */
orte_rml.send_buffer_nb(orte_mgmt_conduit,
remote, reply,
ORTE_RML_TAG_DIRECT_MODEX_RESP,
orte_rml_send_callback, NULL);
return;
error:
OBJ_RELEASE(reply);
return;
}

static void _mdxresp(int sd, short args, void *cbdata)
Expand Down Expand Up @@ -472,18 +480,18 @@ static void pmix_server_dmdx_recv(int status, orte_process_name_t* sender,
if (OPAL_SUCCESS != (rc = opal_hotel_checkin(&orte_pmix_server_globals.reqs, req, &req->room_num))) {
orte_show_help("help-orted.txt", "noroom", true, req->operation, orte_pmix_server_globals.num_rooms);
OBJ_RELEASE(req);
send_error(rc, &idreq, sender);
send_error(rc, &idreq, sender, room_num);
}
return;
}
if (NULL == (proc = (orte_proc_t*)opal_pointer_array_get_item(jdata->procs, name.vpid))) {
/* this is truly an error, so notify the sender */
send_error(ORTE_ERR_NOT_FOUND, &idreq, sender);
send_error(ORTE_ERR_NOT_FOUND, &idreq, sender, room_num);
return;
}
if (!ORTE_FLAG_TEST(proc, ORTE_PROC_FLAG_LOCAL)) {
/* send back an error - they obviously have made a mistake */
send_error(ORTE_ERR_NOT_FOUND, &idreq, sender);
send_error(ORTE_ERR_NOT_FOUND, &idreq, sender, room_num);
return;
}
/* track the request since the call down to the PMIx server
Expand All @@ -499,7 +507,7 @@ static void pmix_server_dmdx_recv(int status, orte_process_name_t* sender,
if (OPAL_SUCCESS != (rc = opal_hotel_checkin(&orte_pmix_server_globals.reqs, req, &req->room_num))) {
orte_show_help("help-orted.txt", "noroom", true, req->operation, orte_pmix_server_globals.num_rooms);
OBJ_RELEASE(req);
send_error(rc, &idreq, sender);
send_error(rc, &idreq, sender, room_num);
return;
}

Expand All @@ -508,7 +516,7 @@ static void pmix_server_dmdx_recv(int status, orte_process_name_t* sender,
ORTE_ERROR_LOG(rc);
opal_hotel_checkout(&orte_pmix_server_globals.reqs, req->room_num);
OBJ_RELEASE(req);
send_error(rc, &idreq, sender);
send_error(rc, &idreq, sender, room_num);
return;
}
return;
Expand Down