Optimización del rendimiento de Amazon FSx para Lustre en nodos (sin EFA)

Abra la consola de Amazon EC2 en https://console.aws.amazon.com/ec2/.

Seleccione Plantillas de lanzamiento.

Elija Crear plantilla de inicialización.

En Detalles avanzados, ubique la sección de Datos de usuario.

Pegue el siguiente script y actualice los valores según sea necesario.

FSX_DNS="<your-fsx-filesystem-dns>" # Needs to be adjusted.
MOUNT_NAME="<your-mount-name>" # Needs to be adjusted.
MOUNT_POINT="</your/mount/point>" # Needs to be adjusted.

MIME-Version: 1.0
Content-Type: multipart/mixed; boundary="==MYBOUNDARY=="
--==MYBOUNDARY==
Content-Type: text/x-shellscript; charset="us-ascii"
#!/bin/bash
exec 1> >(logger -s -t $(basename $0)) 2>&1
# Function definitions
check_success() {
    if [ $? -eq 0 ]; then
        echo "SUCCESS: $1"
    else
        echo "FAILED: $1"
        return 1
    fi
}
apply_tunings() {
    local NUM_CPUS=$(nproc)
    local LRU_SIZE=$((100 * NUM_CPUS))
    local params=(
        "ldlm.namespaces.*.lru_max_age=600000"
        "ldlm.namespaces.*.lru_size=$LRU_SIZE"
        "llite.*.max_cached_mb=64"
        "osc.*OST*.max_rpcs_in_flight=32"
        "mdc.*.max_rpcs_in_flight=64"
        "mdc.*.max_mod_rpcs_in_flight=50"
    )
    for param in "${params[@]}"; do
        lctl set_param $param
        check_success "Set ${param%%=*}"
    done
}
verify_param() {
    local param=$1
    local expected=$2
    local actual=$3

    if [ "$actual" == "$expected" ]; then
        echo "SUCCESS: $param is correctly set to $expected"
    else
        echo "WARNING: $param is set to $actual (expected $expected)"
    fi
}
verify_tunings() {
    local NUM_CPUS=$(nproc)
    local LRU_SIZE=$((100 * NUM_CPUS))
    local params=(
        "ldlm.namespaces.*.lru_max_age:600000"
        "ldlm.namespaces.*.lru_size:$LRU_SIZE"
        "llite.*.max_cached_mb:64"
        "osc.*OST*.max_rpcs_in_flight:32"
        "mdc.*.max_rpcs_in_flight:64"
        "mdc.*.max_mod_rpcs_in_flight:50"
    )
    echo "Verifying all parameters:"
    for param in "${params[@]}"; do
        name="${param%%:*}"
        expected="${param#*:}"
        actual=$(lctl get_param -n $name | head -1)
        verify_param "${name##*.}" "$expected" "$actual"
    done
}
setup_persistence() {
    # Create functions file
    cat << 'EOF' > /usr/local/bin/lustre_functions.sh
#!/bin/bash
apply_lustre_tunings() {
    local NUM_CPUS=$(nproc)
    local LRU_SIZE=$((100 * NUM_CPUS))

    echo "Applying Lustre performance tunings..."
    lctl set_param ldlm.namespaces.*.lru_max_age=600000
    lctl set_param ldlm.namespaces.*.lru_size=$LRU_SIZE
    lctl set_param llite.*.max_cached_mb=64
    lctl set_param osc.*OST*.max_rpcs_in_flight=32
    lctl set_param mdc.*.max_rpcs_in_flight=64
    lctl set_param mdc.*.max_mod_rpcs_in_flight=50
}
EOF
    # Create tuning script
    cat << 'EOF' > /usr/local/bin/apply_lustre_tunings.sh
#!/bin/bash
exec 1> >(logger -s -t $(basename $0)) 2>&1
# Source the functions
source /usr/local/bin/lustre_functions.sh
# FSx details
FSX_DNS="<your-fsx-filesystem-dns>" # Needs to be adjusted.
MOUNT_NAME="<your-mount-name>" # Needs to be adjusted.
MOUNT_POINT="</your/mount/point>" # Needs to be adjusted.
# Function to check if Lustre is mounted
is_lustre_mounted() {
    mount | grep -q "type lustre"
}
# Function to mount Lustre
mount_lustre() {
    echo "Mounting Lustre filesystem..."
    mkdir -p ${MOUNT_POINT}
    mount -t lustre ${FSX_DNS}@tcp:/${MOUNT_NAME} ${MOUNT_POINT}
    return $?
}
# Main execution
# Try to mount if not already mounted
if ! is_lustre_mounted; then
    echo "Lustre filesystem not mounted, attempting to mount..."
    mount_lustre
fi
# Wait for successful mount (up to 5 minutes)
for i in {1..30}; do
    if is_lustre_mounted; then
        echo "Lustre filesystem mounted, applying tunings..."
        apply_lustre_tunings
        exit 0
    fi
    echo "Waiting for Lustre filesystem to be mounted... (attempt $i/30)"
    sleep 10
done
echo "Timeout waiting for Lustre filesystem mount"
exit 1
EOF
    # Create systemd service
    cat << 'EOF' > /etc/systemd/system/lustre-tunings.service
[Unit]
Description=Apply Lustre Performance Tunings
After=network.target remote-fs.target
StartLimitIntervalSec=0
[Service]
Type=oneshot
ExecStart=/usr/local/bin/apply_lustre_tunings.sh
RemainAfterExit=yes
Restart=on-failure
RestartSec=30
[Install]
WantedBy=multi-user.target
EOF
    chmod +x /usr/local/bin/lustre_functions.sh
    chmod +x /usr/local/bin/apply_lustre_tunings.sh
    systemctl enable lustre-tunings.service
    systemctl start lustre-tunings.service
}
echo "Starting FSx for Lustre configuration..."
# 1. Install Lustre client
if grep -q 'VERSION="2"' /etc/os-release; then
    amazon-linux-extras install -y lustre
elif grep -q 'VERSION="2023"' /etc/os-release; then
    dnf install -y lustre-client
fi
check_success "Install Lustre client"
# 2. Apply network and RPC tunings
export PATH=$PATH:/usr/sbin
echo "Applying network and RPC tunings..."
if ! grep -q "options ptlrpc ptlrpcd_per_cpt_max" /etc/modprobe.d/modprobe.conf; then
    echo "options ptlrpc ptlrpcd_per_cpt_max=64" | tee -a /etc/modprobe.d/modprobe.conf
    echo "options ksocklnd credits=2560" | tee -a /etc/modprobe.d/modprobe.conf
fi
# 3. Load Lustre modules
modprobe lustre
check_success "Load Lustre modules" || exit 1
# 4. Lustre Network Initialization
lctl network up
check_success "Initialize Lustre networking" || exit 1
# 5. Mount FSx filesystem
FSX_DNS="<your-fsx-filesystem-dns>" # Needs to be adjusted.
MOUNT_NAME="<your-mount-name>" # Needs to be adjusted.
MOUNT_POINT="</your/mount/point>" # Needs to be adjusted.
if [ ! -z "$FSX_DNS" ] && [ ! -z "$MOUNT_NAME" ]; then
    mkdir -p $MOUNT_POINT
    mount -t lustre ${FSX_DNS}@tcp:/${MOUNT_NAME} ${MOUNT_POINT}
    check_success "Mount FSx filesystem"
fi
# 6. Apply tunings
apply_tunings
# 7. Verify tunings
verify_tunings
# 8. Setup persistence
setup_persistence
echo "FSx for Lustre configuration completed."
--==MYBOUNDARY==--

Al crear grupos de nodos de Amazon EKS, seleccione esta plantilla de lanzamiento. Para obtener más información, consulte Creación de un grupo de nodos administrados para un clúster.