Merge pull request #6294 from bwbarrett/mtl-ofi-no-device-warning

mtl/ofi: Print descriptive error message on modex failure

ompi/mca/mtl/ofi/help-mtl-ofi.txt

@@ -65,3 +65,13 @@ are more threads than the available contexts.
 
   Local host: %s
   Location: %s:%d
+
+[modex failed]
+The OFI MTL was not able to find endpoint information for a remote
+endpoint.  Most likely, this means that the remote process was unable
+to initialize the Libfabric NIC correctly.  This error is not
+recoverable and your application is likely to abort.
+
+  Local host: %s
+  Remote host: %s
+  Error: %s (%d)

ompi/mca/mtl/ofi/mtl_ofi.c

@@ -98,9 +98,10 @@ ompi_mtl_ofi_add_procs(struct mca_mtl_base_module_t *mtl,
                               (void**)&ep_name,
                               &size);
         if (OMPI_SUCCESS != ret) {
-            opal_output_verbose(1, ompi_mtl_base_framework.framework_output,
-                                "%s:%d: modex_recv failed: %d\n",
-                                __FILE__, __LINE__, ret);
+            opal_show_help("help-mtl-ofi.txt", "modex failed",
+                           true, ompi_process_info.nodename,
+			   procs[i]->super.proc_hostname,
+			   opal_strerror(ret), ret);
             goto bail;
         }
         memcpy(&ep_names[i*namelen], ep_name, namelen);