Improve error message to help user figure out what to do

opal/mca/common/cuda/common_cuda.c

@@ -1107,7 +1107,7 @@ int cuda_openmemhandle(void *base, size_t size, mca_mpool_base_registration_t *n
     }
     if (OPAL_UNLIKELY(CUDA_SUCCESS != result)) {
         opal_show_help("help-mpi-common-cuda.txt", "cuIpcOpenMemHandle failed",
-                       true, result, base);
+                       true, OPAL_PROC_MY_HOSTNAME, result, base);
         /* Currently, this is a non-recoverable error */
         return OPAL_ERROR;
     } else {

opal/mca/common/cuda/help-mpi-common-cuda.txt

@@ -80,10 +80,12 @@ Rerun with --mca mpi_common_cuda_event_max %d
 [cuIpcOpenMemHandle failed]
 The call to cuIpcOpenMemHandle failed. This is an unrecoverable error
 and will cause the program to abort.
-  cuIpcOpenMemHandle return value:   %d
-  address: %p
-Check the cuda.h file for what the return value means. Perhaps a reboot
-of the node will clear the problem.
+  Hostname:                         %s
+  cuIpcOpenMemHandle return value:  %d
+  address:                          %p
+Check the cuda.h file for what the return value means. A possible cause
+for this is not enough free device memory.  Try to reduce the device
+memory footprint of your application.
 #
 [cuIpcCloseMemHandle failed]
 The call to cuIpcCloseMemHandle failed. This is a warning and the program