IMAGE_NAME="eks-node-gpu"
IMAGE_DESCRIPTION="Ubuntu EKS K3s GPU worker node — NVIDIA server driver (DKMS pre-built) + nvidia-container-toolkit; agent-only (GPU nodes never run the EKS control plane)"
DISTRO="ubuntu"
UBUNTU_VERSION="26.04"
UBUNTU_CODENAME="resolute"

# 16G — headroom for kernel headers, NVIDIA driver + DKMS build artefacts, and
# nvidia-container-toolkit, mirroring scripts/images/ubuntu-gpu-nvidia.conf.
IMAGE_SIZE="16G"

# K3s bundles its own containerd, so no containerd/runc package here. The
# NVIDIA server driver + nvidia-utils come from the stock Ubuntu repos and are
# installed in setup.sh (kernel-version-pinned DKMS build, like the ubuntu-gpu
# recipe). nvidia-container-toolkit lives in its own NVIDIA-hosted apt repo,
# which is not enabled on the base cloud image, so it is also added+installed
# in setup.sh rather than here (see scripts/images/ubuntu-gpu-nvidia-setup.sh).
APT_PACKAGES="ca-certificates curl jq iptables conntrack cgroup-tools initramfs-tools"

# ecr-credential-provider is the ONLY server binary a GPU worker needs: the
# nodegroup userdata points kubelet at it (image-credential-provider-config +
# bin-dir=/usr/local/bin) for ECR pulls, and kubelet treats a referenced-but-
# missing provider binary as a FATAL init error (RegisterCredentialProviderPlugins),
# so the node never registers. The Alpine eks-node ships it; the GPU AMI must too.
# Server-only binaries (token-webhook, gateway-*, konnectivity, k3s server) stay
# omitted — GPU nodes are agent-only.
BUILD_COMMANDS="CGO_ENABLED=0 GOFIPS140=v1.0.0 go build -o bin/ecr-credential-provider ./cmd/ecr-credential-provider"
INSTALL_BINARIES="bin/ecr-credential-provider:/usr/local/bin/ecr-credential-provider"

# Role-agnostic helper scripts (including k3s-agent-prestart, the shared
# start_pre logic for the k3s agent role: env require + IMDS provider-id) are
# reused verbatim from scripts/images/eks-node/ — only the init wiring
# changes: OpenRC -> systemd. Server-only units (role selector, k3s server,
# eks-token-webhook, konnectivity, state-report, k3s recovery, mgmt-net) are
# intentionally not ported — GPU nodes are single-NIC workers.
INSTALL_FILES="\
scripts/images/eks-node/mulga-ebs-byid.sh:/usr/local/sbin/mulga-ebs-byid \
scripts/images/eks-node/mulga-eks-provider-id.sh:/usr/local/sbin/mulga-eks-provider-id \
scripts/images/eks-node/mulga-vpc-mtu.sh:/usr/local/sbin/mulga-vpc-mtu \
scripts/images/eks-node/k3s-agent-prestart.sh:/usr/local/sbin/k3s-agent-prestart \
scripts/images/eks-node-gpu/k3s-agent.service:/etc/systemd/system/k3s-agent.service \
scripts/images/eks-node-gpu/mulga-ebs-byid.service:/etc/systemd/system/mulga-ebs-byid.service \
scripts/images/eks-node-gpu/mulga-eks-provider-id.service:/etc/systemd/system/mulga-eks-provider-id.service \
scripts/images/eks-node-gpu/mulga-vpc-mtu.service:/etc/systemd/system/mulga-vpc-mtu.service \
scripts/images/eks-node-gpu/mulga-cdi-generate.service:/etc/systemd/system/mulga-cdi-generate.service \
scripts/images/eks-node-gpu/99-mulga-ebs-byid.rules:/etc/udev/rules.d/99-mulga-ebs-byid.rules"

ENABLE_SERVICES="k3s-agent mulga-ebs-byid mulga-eks-provider-id mulga-vpc-mtu mulga-cdi-generate"

SETUP_SCRIPT="scripts/images/eks-node-gpu/setup.sh"

AMI_NAME="spinifex-eks-node-gpu"
SYSTEM_TAG="spinifex:managed-by=eks gpu-vendor=nvidia"