Build CUDA under host_injections and make EESSI aware of host CUDA drivers

eessi_container.sh

@@ -46,6 +46,7 @@ SAVE_ERROR_EXITCODE=$((${ANY_ERROR_EXITCODE} << 8))
 HTTP_PROXY_ERROR_EXITCODE=$((${ANY_ERROR_EXITCODE} << 9))
 HTTPS_PROXY_ERROR_EXITCODE=$((${ANY_ERROR_EXITCODE} << 10))
 RUN_SCRIPT_MISSING_EXITCODE=$((${ANY_ERROR_EXITCODE} << 11))
+NVIDIA_MODE_UNKNOWN_EXITCODE=$((${ANY_ERROR_EXITCODE} << 12))
 
 # CernVM-FS settings
 CVMFS_VAR_LIB="var-lib-cvmfs"
@@ -72,12 +73,17 @@ display_help() {
   echo "  -a | --access {ro,rw}  - ro (read-only), rw (read & write) [default: ro]"
   echo "  -c | --container IMG   - image file or URL defining the container to use"
   echo "                           [default: docker://ghcr.io/eessi/build-node:debian11]"
-  echo "  -h | --help            - display this usage information [default: false]"
   echo "  -g | --storage DIR     - directory space on host machine (used for"
   echo "                           temporary data) [default: 1. TMPDIR, 2. /tmp]"
+  echo "  -h | --help            - display this usage information [default: false]"
+  echo "  -i | --host-injections - directory to link to for host_injections "
+  echo "                           [default: /..storage../opt-eessi]"
   echo "  -l | --list-repos      - list available repository identifiers [default: false]"
   echo "  -m | --mode MODE       - with MODE==shell (launch interactive shell) or"
   echo "                           MODE==run (run a script or command) [default: shell]"
+  echo "  -n | --nvidia MODE     - configure the container to work with NVIDIA GPUs,"
+  echo "                           MODE==install for a CUDA installation, MODE==run to"
+  echo "                           attach a GPU, MODE==all for both [default: false]"
   echo "  -r | --repository CFG  - configuration file or identifier defining the"
   echo "                           repository to use [default: EESSI-pilot via"
   echo "                           default container, see --container]"
@@ -111,6 +117,8 @@ VERBOSE=0
 STORAGE=
 LIST_REPOS=0
 MODE="shell"
+SETUP_NVIDIA=0
+ADDITIONAL_SINGULARITY_FLAGS=
 REPOSITORY="EESSI-pilot"
 RESUME=
 SAVE=
@@ -141,6 +149,10 @@ while [[ $# -gt 0 ]]; do
       display_help
       exit 0
       ;;
+    -i|--host-injections)
+      USER_HOST_INJECTIONS="$2"
+      shift 2
+      ;;
     -l|--list-repos)
       LIST_REPOS=1
       shift 1
@@ -149,6 +161,11 @@ while [[ $# -gt 0 ]]; do
       MODE="$2"
       shift 2
       ;;
+    -n|--nvidia)
+      SETUP_NVIDIA=1
+      NVIDIA_MODE="$2"
+      shift 2
+      ;;
     -r|--repository)
       REPOSITORY="$2"
       shift 2
@@ -224,6 +241,13 @@ if [[ "${MODE}" != "shell" && "${MODE}" != "run" ]]; then
     fatal_error "unknown execution mode '${MODE}'" "${MODE_UNKNOWN_EXITCODE}"
 fi
 
+# Also validate the NVIDIA GPU mode (if present)
+if [[ ${SETUP_NVIDIA} -eq 1 ]]; then
+    if [[ "${NVIDIA_MODE}" != "run" && "${NVIDIA_MODE}" != "install" && "${NVIDIA_MODE}" != "all" ]]; then
+        fatal_error "unknown NVIDIA mode '${NVIDIA_MODE}'" "${NVIDIA_MODE_UNKNOWN_EXITCODE}"
+    fi
+fi
+
 # TODO (arg -r|--repository) check if repository is known
 # REPOSITORY_ERROR_EXITCODE
 if [[ ! -z "${REPOSITORY}" && "${REPOSITORY}" != "EESSI-pilot" && ! -r ${EESSI_REPOS_CFG_FILE} ]]; then
@@ -294,6 +318,7 @@ else
   echo "Using ${EESSI_HOST_STORAGE} as tmp directory (to resume session add '--resume ${EESSI_HOST_STORAGE}')."
 fi
 
+
 # if ${RESUME} is a file (assume a tgz), unpack it into ${EESSI_HOST_STORAGE}
 if [[ ! -z ${RESUME} && -f ${RESUME} ]]; then
   tar xf ${RESUME} -C ${EESSI_HOST_STORAGE}
@@ -310,12 +335,25 @@ fi
 #      |-overlay-work
 #      |-home
 #      |-repos_cfg
+#      |-opt-eessi (unless otherwise specificed for host_injections)
 
 # tmp dir for EESSI
 EESSI_TMPDIR=${EESSI_HOST_STORAGE}
 mkdir -p ${EESSI_TMPDIR}
 [[ ${VERBOSE} -eq 1 ]] && echo "EESSI_TMPDIR=${EESSI_TMPDIR}"
 
+# Set host_injections directory and ensure it is a writable directory (if user provided)
+if [ -z ${USER_HOST_INJECTIONS+x} ]; then
+    # Not set, so use our default
+    HOST_INJECTIONS=${EESSI_TMPDIR}/opt-eessi
+    mkdir -p $HOST_INJECTIONS
+else
+    # Make sure the host_injections directory specified exists and is a folder
+    mkdir -p ${USER_HOST_INJECTIONS} || fatal_error "host_injections directory ${USER_HOST_INJECTIONS} is either not a directory or cannot be created"
+    HOST_INJECTIONS=${USER_HOST_INJECTIONS}
+fi
+[[ ${VERBOSE} -eq 1 ]] && echo "HOST_INJECTIONS=${HOST_INJECTIONS}"
+
 # configure Singularity: if SINGULARITY_CACHEDIR is already defined, use that
 #   a global SINGULARITY_CACHEDIR would ensure that we don't consume
 #   storage space again and again for the container & also speed-up
@@ -394,12 +432,30 @@ fi
 [[ ${VERBOSE} -eq 1 ]] && echo "SINGULARITY_HOME=${SINGULARITY_HOME}"
 
 # define paths to add to SINGULARITY_BIND (added later when all BIND mounts are defined)
-BIND_PATHS="${EESSI_CVMFS_VAR_LIB}:/var/lib/cvmfs,${EESSI_CVMFS_VAR_RUN}:/var/run/cvmfs"
+BIND_PATHS="${EESSI_CVMFS_VAR_LIB}:/var/lib/cvmfs,${EESSI_CVMFS_VAR_RUN}:/var/run/cvmfs,${HOST_INJECTIONS}:/opt/eessi"
 # provide a '/tmp' inside the container
 BIND_PATHS="${BIND_PATHS},${EESSI_TMPDIR}:${TMP_IN_CONTAINER}"
 
 [[ ${VERBOSE} -eq 1 ]] && echo "BIND_PATHS=${BIND_PATHS}"
 
+# Configure anything we need for NVIDIA GPUs and CUDA installation
+if [[ ${SETUP_NVIDIA} -eq 1 ]]; then
+    if [[ "${NVIDIA_MODE}" == "run" || "${NVIDIA_MODE}" == "all" ]]; then
+        # Give singularity the appropriate flag
+        ADDITIONAL_SINGULARITY_FLAGS="--nv ${ADDITIONAL_SINGULARITY_FLAGS}"
+        [[ ${VERBOSE} -eq 1 ]] && echo "ADDITIONAL_SINGULARITY_FLAGS=${ADDITIONAL_SINGULARITY_FLAGS}"
+    fi
+    if [[ "${NVIDIA_MODE}" == "install" || "${NVIDIA_MODE}" == "all" ]]; then
+        # Add additional bind mounts to allow CUDA to install within a container
+        EESSI_VAR_LOG=${EESSI_TMPDIR}/var-log
+        EESSI_USR_LOCAL_CUDA=${EESSI_TMPDIR}/usr-local-cuda
+        mkdir -p ${EESSI_VAR_LOG}
+        mkdir -p ${EESSI_USR_LOCAL_CUDA}
+        BIND_PATHS="${BIND_PATHS},${EESSI_VAR_LOG}:/var/log,${EESSI_USR_LOCAL_CUDA}:/usr/local/cuda"
+        [[ ${VERBOSE} -eq 1 ]] && echo "BIND_PATHS=${BIND_PATHS}"
+    fi
+fi
+
 # set up repository config (always create directory repos_cfg and populate it with info when
 # arg -r|--repository is used)
 mkdir -p ${EESSI_TMPDIR}/repos_cfg
@@ -558,8 +614,8 @@ if [ ! -z ${EESSI_SOFTWARE_SUBDIR_OVERRIDE} ]; then
 fi
 
 echo "Launching container with command (next line):"
-echo "singularity ${RUN_QUIET} ${MODE} ${EESSI_FUSE_MOUNTS[@]} ${CONTAINER} $@"
-singularity ${RUN_QUIET} ${MODE} "${EESSI_FUSE_MOUNTS[@]}" ${CONTAINER} "$@"
+echo "singularity ${RUN_QUIET} ${MODE} ${ADDITIONAL_SINGULARITY_FLAGS} ${EESSI_FUSE_MOUNTS[@]} ${CONTAINER} $@"
+singularity ${RUN_QUIET} ${MODE} ${ADDITIONAL_SINGULARITY_FLAGS} "${EESSI_FUSE_MOUNTS[@]}" ${CONTAINER} "$@"
 exit_code=$?
 
 # 6. save tmp if requested (arg -s|--save)

gpu_support/nvidia/install_cuda_host_injections.sh

@@ -0,0 +1,92 @@
+#!/usr/bin/env bash
+
+# Initialise our bash functions
+TOPDIR=$(dirname $(realpath $BASH_SOURCE))
+source "$TOPDIR"/../../scripts/utils.sh
+
+# Make sure EESSI is initialised
+check_eessi_initialised
+
+if [[ $# -eq 0 ]] ; then
+    fatal_error "You must provide the CUDA version as an argument, e.g.:\n $0 11.3.1"
+fi
+install_cuda_version=$1
+if [[ -z "${EESSI_SOFTWARE_PATH}" ]]; then
+  fatal_error "This script cannot be used without having first defined EESSI_SOFTWARE_PATH"
+else
+  # As an installation location just use $EESSI_SOFTWARE_PATH but replacing `versions` with `host_injections`
+  # (CUDA is a binary installation so no need to worry too much about the EasyBuild setup)
+  cuda_install_parent=${EESSI_SOFTWARE_PATH/versions/host_injections}
+fi
+
+# Only install CUDA if specified version is not found.
+# This is only relevant for users, the shipped CUDA installation will
+# always be in versions instead of host_injections and have symlinks pointing
+# to host_injections for everything we're not allowed to ship
+# (existence of easybuild subdir implies a successful install)
+if [ -d "${cuda_install_parent}"/software/CUDA/"${install_cuda_version}"/easybuild ]; then
+  echo_green "CUDA software found! No need to install CUDA again, proceed with testing."
+else
+  # We need to be able write to the installation space so let's make sure we can
+  if ! create_directory_structure "${cuda_install_parent}"/software/CUDA ; then
+    fatal_error "No write permissions to directory ${cuda_install_parent}/software/CUDA"
+  fi
+
+  # we need a directory we can use for temporary storage
+  if [[ -z "${CUDA_TEMP_DIR}" ]]; then
+    tmpdir=$(mktemp -d)
+  else
+    tmpdir="${CUDA_TEMP_DIR}"/temp
+    if ! mkdir "$tmpdir" ; then
+      fatal_error "Could not create directory ${tmpdir}"
+    fi
+  fi
+
+  required_space_in_tmpdir=50000
+  # Let's see if we have sources and build locations defined if not, we use the temporary space
+  if [[ -z "${EASYBUILD_BUILDPATH}" ]]; then
+    export EASYBUILD_BUILDPATH=${tmpdir}/build
+    required_space_in_tmpdir=$((required_space_in_tmpdir + 5000000))
+  fi
+  if [[ -z "${EASYBUILD_SOURCEPATH}" ]]; then
+    export EASYBUILD_SOURCEPATH=${tmpdir}/sources
+    required_space_in_tmpdir=$((required_space_in_tmpdir + 5000000))
+  fi
+
+  # The install is pretty fat, you need lots of space for download/unpack/install (~3*5GB),
+  # need to do a space check before we proceed
+  avail_space=$(df --output=avail "${cuda_install_parent}"/ | tail -n 1 | awk '{print $1}')
+  if (( avail_space < 5000000 )); then
+    fatal_error "Need at least 5GB disk space to install CUDA under ${cuda_install_parent}, exiting now..."
+  fi
+  avail_space=$(df --output=avail "${tmpdir}"/ | tail -n 1 | awk '{print $1}')
+  if (( avail_space < required_space_in_tmpdir )); then
+    error="Need at least ${required_space_in_tmpdir} disk space under ${tmpdir}.\n"
+    error="${error}Set the environment variable CUDA_TEMP_DIR to a location with adequate space to pass this check."
+    error="${error}You can alternatively set EASYBUILD_BUILDPATH and/or EASYBUILD_SOURCEPATH "
+    error="${error}to reduce this requirement. Exiting now..."
+    fatal_error "${error}"
+  fi
+
+  if [[ -z "${EBROOTEASYBUILD}" ]]; then
+    echo_yellow "Loading EasyBuild module to do actual install"
+    module load EasyBuild
+  fi
+
+  # we need the --rebuild option and a (random) dir for the module since we are
+  # fixing the broken links of the EESSI-shipped installation
+  extra_args="--rebuild --installpath-modules=${tmpdir}"
+
+  # We don't want hooks used in this install, we need a vanilla CUDA installation
+  touch "$tmpdir"/none.py
+  # shellcheck disable=SC2086  # Intended splitting of extra_args
+  eb --prefix="$tmpdir" ${extra_args} --hooks="$tmpdir"/none.py --installpath="${cuda_install_parent}"/ CUDA-"${install_cuda_version}".eb
+  ret=$?
+  if [ $ret -ne 0 ]; then
+    fatal_error  "CUDA installation failed, please check EasyBuild logs..."
+  else
+    echo_green "CUDA installation at ${cuda_install_parent}/software/CUDA/${install_cuda_version} succeeded!"
+  fi
+  # clean up tmpdir
+  rm -rf "${tmpdir}"
+fi

scripts/utils.sh

@@ -14,7 +14,7 @@ ANY_ERROR_EXITCODE=1
 function fatal_error() {
     echo_red "ERROR: $1" >&2
     if [[ $# -gt 1 ]]; then
-      exit $2
+      exit "$2"
     else
       exit "${ANY_ERROR_EXITCODE}"
     fi
@@ -32,11 +32,81 @@ function check_exit_code {
     fi
 }
 
+function check_eessi_initialised() {
+  if [[ -z "${EESSI_SOFTWARE_PATH}" ]]; then
+    fatal_error "EESSI has not been initialised!"
+  else
+    return 0
+  fi
+}
+
+function float_greater_than() {
+  # Make sure we have two arguments
+  if [ $# -ne 2 ]; then
+    echo_red "greater_than_float requires two (float) numbers" >&2
+    return $ANY_ERROR_EXITCODE
+  fi
+  # Make sure the arguments are numbers
+  if [[ ! $1 =~ ^[+-]?[0-9]+\.?[0-9]*$ ]]; then
+    echo_yellow "Input to float_greater_than is not a float, ignoring"
+    return $ANY_ERROR_EXITCODE
+  fi
+  if [[ ! $2 =~ ^[+-]?[0-9]+\.?[0-9]*$ ]]; then
+    echo_yellow "Input to float_greater_than is not a float, ignoring"
+    return $ANY_ERROR_EXITCODE
+  fi
+  # Now do the actual evaluation
+  return_code=$ANY_ERROR_EXITCODE
+  result=$(echo "$1" "$2" | awk '{if ($1 > $2) print "true"}')
+  if [ "$result" = true ] ; then
+    return_code=0
+  fi
+  return $return_code
+}
+
+function check_in_prefix_shell() {
+  # Make sure EPREFIX is defined
+  if [[ -z "${EPREFIX}" ]]; then
+    fatal_error "This script cannot be used without having first defined EPREFIX"
+  fi
+  if [[ ! ${SHELL} = ${EPREFIX}/bin/bash ]]; then
+    fatal_error "Not running in Gentoo Prefix environment, run '${EPREFIX}/startprefix' first!"
+  fi
+}
+
+function create_directory_structure() {
+  # Ensure we are given a single path argument
+  if [ $# -ne 1 ]; then
+    echo_red "Function requires a single (relative or absolute) path argument" >&2
+    return $ANY_ERROR_EXITCODE
+  fi
+  dir_structure="$1"
+
+  # Attempt to create the directory structure
+  error_message=$(mkdir -p "$dir_structure" 2>&1)
+  return_code=$?
+  # If it fails be explicit about the error
+  if [ ${return_code} -ne 0 ]; then
+    real_dir=$(realpath -m "$dir_structure")
+    echo_red "Creating ${dir_structure} (real path ${real_dir}) failed with:\n ${error_message}" >&2
+  else
+    # If we're creating it, our use case is that we want to be able to write there
+    # (this is a check in case the directory already existed)
+    if [ ! -w "${dir_structure}" ]; then
+      real_dir=$(realpath -m "$dir_structure")
+      echo_red "You do not have (required) write permissions to ${dir_structure} (real path ${real_dir})!"
+      return_code=$ANY_ERROR_EXITCODE
+    fi
+  fi
+
+  return $return_code
+}
+
 function get_path_for_tool {
     tool_name=$1
     tool_envvar_name=$2
 
-    which_out=$(which ${tool_name} 2>&1)
+    which_out=$(which "${tool_name}" 2>&1)
     exit_code=$?
     if [[ ${exit_code} -eq 0 ]]; then
         echo "INFO: found tool ${tool_name} in PATH (${which_out})" >&2
@@ -68,7 +138,7 @@ function get_host_from_url {
     url=$1
     re="(http|https)://([^/:]+)"
     if [[ $url =~ $re ]]; then
-        echo ${BASH_REMATCH[2]}
+        echo "${BASH_REMATCH[2]}"
         return 0
     else
         echo ""
@@ -80,7 +150,7 @@ function get_port_from_url {
     url=$1
     re="(http|https)://[^:]+:([0-9]+)"
     if [[ $url =~ $re ]]; then
-        echo ${BASH_REMATCH[2]}
+        echo "${BASH_REMATCH[2]}"
         return 0
     else
         echo ""
@@ -90,7 +160,7 @@ function get_port_from_url {
 
 function get_ipv4_address {
     hname=$1
-    hipv4=$(grep ${hname} /etc/hosts | grep -v '^[[:space:]]*#' | cut -d ' ' -f 1)
+    hipv4=$(grep "${hname}" /etc/hosts | grep -v '^[[:space:]]*#' | cut -d ' ' -f 1)
     # TODO try other methods if the one above does not work --> tool that verifies
     #      what method can be used?
     echo "${hipv4}"