Merge pull request #910 from casparvl/fix_behavior_for_present_but_failing_nvidiasmi

Fix behavior for present but failing nvidiasmi

Author: laraPPr

EESSI-install-software.sh

@@ -271,11 +271,18 @@ fi
 
 # Install NVIDIA drivers in host_injections (if they exist)
 if command_exists "nvidia-smi"; then
-    echo "Command 'nvidia-smi' found. Installing NVIDIA drivers for use in prefix shell..."
-    ${EESSI_PREFIX}/scripts/gpu_support/nvidia/link_nvidia_host_libraries.sh
+    nvidia-smi --version
+    ec=$?
+    if [ ${ec} -eq 0 ]; then 
+        echo "Command 'nvidia-smi' found. Installing NVIDIA drivers for use in prefix shell..."
+        ${EESSI_PREFIX}/scripts/gpu_support/nvidia/link_nvidia_host_libraries.sh
+    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."
+    fi
 fi
 
-
 if [ ! -z "${shared_fs_path}" ]; then
     shared_eb_sourcepath=${shared_fs_path}/easybuild/sources
     echo ">> Using ${shared_eb_sourcepath} as shared EasyBuild source path"

bot/build.sh

@@ -244,14 +244,28 @@ mkdir -p ${TARBALL_TMP_BUILD_STEP_DIR}
 # prepare arguments to eessi_container.sh specific to build step
 BUILD_STEP_ARGS+=("--save" "${TARBALL_TMP_BUILD_STEP_DIR}")
 BUILD_STEP_ARGS+=("--storage" "${STORAGE}")
+
 # add options required to handle NVIDIA support
 if command_exists "nvidia-smi"; then
-    echo "Command 'nvidia-smi' found, using available GPU"
-    BUILD_STEP_ARGS+=("--nvidia" "all")
+    # Accept that this may fail
+    set +e
+    nvidia-smi --version
+    ec=$?
+    set -e
+    if [ ${ec} -eq 0 ]; then
+        echo "Command 'nvidia-smi' found, using available GPU"
+        BUILD_STEP_ARGS+=("--nvidia" "all")
+    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."
+        BUILD_STEP_ARGS+=("--nvidia" "install")
+    fi
 else
     echo "No 'nvidia-smi' found, no available GPU but allowing overriding this check"
     BUILD_STEP_ARGS+=("--nvidia" "install")
 fi
+
 # Retain location for host injections so we don't reinstall CUDA
 # (Always need to run the driver installation as available driver may change)
 if [[ ! -z ${SHARED_FS_PATH} ]]; then

bot/test.sh

@@ -215,8 +215,19 @@ TEST_STEP_ARGS+=("--extra-bind-paths" "/sys/fs/cgroup:/hostsys/fs/cgroup:ro")
 
 # add options required to handle NVIDIA support
 if command_exists "nvidia-smi"; then
-    echo "Command 'nvidia-smi' found, using available GPU"
-    TEST_STEP_ARGS+=("--nvidia" "run")
+    # Accept that this may fail
+    set +e
+    nvidia-smi --version
+    ec=$?
+    set -e
+    if [ ${ec} -eq 0 ]; then
+        echo "Command 'nvidia-smi' found, using available GPU"
+        TEST_STEP_ARGS+=("--nvidia" "run")
+    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."
+    fi
 fi
 
 # prepare arguments to test_suite.sh (specific to test step)