创建lanuch template

aws ec2 describe-images \
  --owners amazon \
  --filters "Name=name,Values=aws-pcs-sample_ami-*-x86_64-slurm-*" \
  --query "Images | sort_by(@, &CreationDate) | [-1].{Name:Name,ImageId:ImageId}" \
  --output table \
  --region us-east-2

export INFRA_STACK="pcs-workshop-infra"
export AWS_DEFAULT_REGION="us-east-2"

export HPC_SUBNET=$(aws cloudformation describe-stacks \
  --stack-name $INFRA_STACK \
  --query "Stacks[0].Outputs[?OutputKey=='HpcSubnetId'].OutputValue" \
  --output text)

export PRIVATE_SG=$(aws cloudformation describe-stacks \
  --stack-name $INFRA_STACK \
  --query "Stacks[0].Outputs[?OutputKey=='PrivateSecurityGroupId'].OutputValue" \
  --output text)

export EFA_SG=$(aws cloudformation describe-stacks \
  --stack-name $INFRA_STACK \
  --query "Stacks[0].Outputs[?OutputKey=='EfaSecurityGroupId'].OutputValue" \
  --output text)

export EFS_ID=$(aws cloudformation describe-stacks \
  --stack-name $INFRA_STACK \
  --query "Stacks[0].Outputs[?OutputKey=='EfsFileSystemId'].OutputValue" \
  --output text)

export FSX_ID=$(aws cloudformation describe-stacks \
  --stack-name $INFRA_STACK \
  --query "Stacks[0].Outputs[?OutputKey=='FsxLustreFileSystemId'].OutputValue" \
  --output text)

export FSX_MOUNT=$(aws cloudformation describe-stacks \
  --stack-name $INFRA_STACK \
  --query "Stacks[0].Outputs[?OutputKey=='FsxLustreMountName'].OutputValue" \
  --output text)

export FSX_DNS="${FSX_ID}.fsx.${AWS_DEFAULT_REGION}.amazonaws.com"

echo "HPC Subnet: $HPC_SUBNET"
echo "Private SG: $PRIVATE_SG"
echo "EFA SG: $EFA_SG"
echo "EFS ID: $EFS_ID"
echo "FSx DNS: $FSX_DNS"
echo "FSx Mount: $FSX_MOUNT"

aws ec2 create-placement-group \
  --group-name hpc-cluster-pg \
  --strategy cluster \
  --region $AWS_DEFAULT_REGION

cat > hpc-userdata.txt << USERDATA
MIME-Version: 1.0
Content-Type: multipart/mixed; boundary="==//=="

--==//==
Content-Type: text/x-shellscript; charset="us-ascii"
MIME-Version: 1.0

#!/bin/bash

# Mount EFS at /home
echo "${EFS_ID}.efs.${AWS_DEFAULT_REGION}.amazonaws.com:/ /home nfs4 nfsvers=4.1,rsize=1048576,wsize=1048576,hard,timeo=600,retrans=2,_netdev 0 0" >> /etc/fstab
mount /home

# Configure Lustre over EFA for hpc7a
modprobe lnet
modprobe kefalnd ipif_name=enp34s0
modprobe ksocklnd

lnetctl lnet configure
lnetctl net del --net tcp
lnetctl net add --net tcp --if enp34s0
lnetctl net add --net efa --if rdmap36s0 --peer-credits 32
lnetctl net add --net efa --if rdmap42s0 --peer-credits 32
lnetctl set discovery 1
lnetctl udsp add --src efa --priority 0
modprobe lustre

# Mount FSx Lustre at /fsx
echo "${FSX_DNS}@tcp:/${FSX_MOUNT} /fsx lustre defaults,_netdev,flock,user_xattr,noatime 0 0" >> /etc/fstab
mkdir -p /fsx
chmod a+rwx /fsx
mount /fsx
chmod 777 /fsx

# Configure Enroot for container support
# Cache on Lustre (shared across nodes), everything else on EBS (needs overlayfs xattr support)
cat > /etc/enroot/enroot.conf << 'ENROOTCFG'
ENROOT_RUNTIME_PATH /var/tmp/enroot/runtime
ENROOT_CONFIG_PATH  /var/tmp/enroot/config
ENROOT_CACHE_PATH   /fsx/enroot/cache
ENROOT_DATA_PATH    /var/tmp/enroot/data
ENROOT_TEMP_PATH    /var/tmp/enroot/tmp
ENROOTCFG
mkdir -p /var/tmp/enroot/runtime /var/tmp/enroot/config /var/tmp/enroot/data /var/tmp/enroot/tmp /fsx/enroot/cache
chmod 1777 /var/tmp/enroot /var/tmp/enroot/runtime /var/tmp/enroot/config /var/tmp/enroot/data /var/tmp/enroot/tmp
chmod 1777 /fsx/enroot/cache

# Remove NVIDIA container hook (CPU-only workshop)
rm -f /etc/enroot/hooks.d/98-nvidia.sh

--==//==
USERDATA

export KEY_NAME="${KEY_NAME:-ws-default-keypair}"

PG_ID=$(aws ec2 describe-placement-groups \
  --group-names hpc-cluster-pg \
  --query "PlacementGroups[0].GroupId" \
  --output text \
  --region $AWS_DEFAULT_REGION)

aws ec2 create-launch-template \
  --launch-template-name hpc-compute-lt \
  --launch-template-data "{
    \"KeyName\": \"${KEY_NAME}\",
    \"MetadataOptions\": {
      \"HttpEndpoint\": \"enabled\",
      \"HttpPutResponseHopLimit\": 2,
      \"HttpTokens\": \"required\"
    },
    \"Monitoring\": {\"Enabled\": true},
    \"Placement\": {\"GroupId\": \"${PG_ID}\"},
    \"NetworkInterfaces\": [
      {
        \"DeviceIndex\": 0,
        \"NetworkCardIndex\": 0,
        \"InterfaceType\": \"efa\",
        \"Groups\": [\"${PRIVATE_SG}\", \"${EFA_SG}\"]
      },
      {
        \"DeviceIndex\": 1,
        \"NetworkCardIndex\": 1,
        \"InterfaceType\": \"efa\",
        \"Groups\": [\"${PRIVATE_SG}\", \"${EFA_SG}\"]
      }
    ],
    \"UserData\": \"$(base64 -w 0 hpc-userdata.txt 2>/dev/null || base64 -i hpc-userdata.txt | tr -d '\n')\"
  }" \
  --region $AWS_DEFAULT_REGION

export HPC_LT_ID=$(aws ec2 describe-launch-templates \
  --launch-template-names hpc-compute-lt \
  --query "LaunchTemplates[0].LaunchTemplateId" \
  --output text \
  --region $AWS_DEFAULT_REGION)
echo "Launch Template ID: $HPC_LT_ID"