Take all sugestions into account

Signed-off-by: laraPPr <[email protected]>

Author: laraPPr

EESSI-install-software.sh

@@ -310,18 +310,10 @@ else
 fi
 
 # Install NVIDIA drivers in host_injections (if they exist)
-# Accept that this may fail
-set +e
-verify_nvidia-smi
-ec=$?
-if [ ${ec} -eq 0 ]; then
-    echo "Installing NVIDIA drivers for use in prefix shell...""
-    export LD_LIBRARY_PATH="/.singularity.d/libs:${LD_LIBRARY_PATH}"
+if nvidia_gpu_available; then
+    echo "Installing NVIDIA drivers for use in prefix shell..."
     ${EESSI_PREFIX}/scripts/gpu_support/nvidia/link_nvidia_host_libraries.sh
-elif [ ${ec} -eq 1 ]; then
-    export LD_LIBRARY_PATH="/.singularity.d/libs:${LD_LIBRARY_PATH}"
 fi
-set -e
 
 if [ ! -z "${shared_fs_path}" ]; then
     shared_eb_sourcepath=${shared_fs_path}/easybuild/sources

bot/build.sh

@@ -220,18 +220,11 @@ BUILD_STEP_ARGS+=("--save" "${TARBALL_TMP_BUILD_STEP_DIR}")
 BUILD_STEP_ARGS+=("--storage" "${STORAGE}")
 
 # add options required to handle NVIDIA support
-# Accept that this may fail
-set +e
-verify_nvidia-smi
-ec=$?
-if [ ${ec} -eq 0 ]; then
+if nvidia_gpu_available; then
     BUILD_STEP_ARGS+=("--nvidia" "all")
-elif [ ${ec} -eq 1 ]; then
-    BUILD_STEP_ARGS+=("--nvidia" "install")
-elif [  ${ec} -eq 2  ]; then 
+else
     BUILD_STEP_ARGS+=("--nvidia" "install")
 fi
-set -e
 
 # Retain location for host injections so we don't reinstall CUDA
 # (Always need to run the driver installation as available driver may change)

bot/test.sh

@@ -225,7 +225,7 @@ fi
 TEST_STEP_ARGS+=("--extra-bind-paths" "/sys/fs/cgroup:/hostsys/fs/cgroup:ro")
 
 # add options required to handle NVIDIA support
-if verify_nvidia-smi; then
+if nvidia_gpu_available; then
     TEST_STEP_ARGS+=("--nvidia" "run")
 fi
 

scripts/utils.sh

@@ -148,21 +148,21 @@ function get_ipv4_address {
     return 0
 }
 
-function verify_nvidia-smi {
+function nvidia_gpu_available {
     if command_exists "nvidia-smi"; then
-        nvidia-smi --version
+        # We are careful here in case we are running in a container and LD_LIBARY_PATH has been wiped
+        LD_LIBRARY_PATH="/.singularity.d/libs:${LD_LIBRARY_PATH}" nvidia-smi --version
         ec=$?
         if [ ${ec} -eq 0 ]; then
             echo "Command 'nvidia-smi' found."
 	    return 0
         else
             echo "Warning: command 'nvidia-smi' found, but 'nvidia-smi --version' did not run succesfully."
             echo "This script now assumes this is NOT a GPU node."
-            echo "If, and only if, the current node actually does contain Nvidia GPUs, this should be considered an error."
 	    return 1
 	fi
     else
-        echo "No 'nvidia-smi' found, no available GPU but allowing overriding this check" 
+        echo "No 'nvidia-smi' found, no available GPU." 
 	return 2
     fi
 }