mirror of
https://github.com/mulgadc/spinifex.git
synced 2026-10-19 19:01:42 +00:00
Josh Siviour
f14fb64562
* feat(eks): unify eks-server + eks-agent into one eks-node AMI Collapse the two K3s AMIs into a single spinifex-eks-node image whose role (server vs agent) is chosen per-instance at first boot, halving build time, storage, and CVE-rotation surface. - scripts/images/eks-node/: superset manifest + merged setup.sh; all role services baked but only crond + the new eks-node-role selector enabled. - eks-node-role first-boot selector reads SPINIFEX_K3S_ROLE, rc-update adds + starts the matching services (server: k3s + eks-token-webhook + k3s-first-boot publisher; agent: k3s-agent), records /etc/spinifex-eks/role, self-disables. Paths are env-overridable; eks-node-role_test.sh covers all five cases. - mulga-eks-etcd-snapshot.sh early-exits on agent nodes. - k3s_server_vm.go seeds SPINIFEX_K3S_ROLE=server into first-boot.env. - Makefile/dev-install: build-eks-node-image / import-eks-node-image replace the server+agent targets. - Delete scripts/images/eks-server + eks-agent. The launcher resolves the AMI by the spinifex:managed-by=eks tag, so running clusters (which hold the resolved AMI ID) are unaffected. AMI bake + cluster boot are operational integration steps, not yet run. * fix(eks): order eks-node-role after cloud-config/cloud-final The first-boot role selector reads /etc/spinifex-eks/first-boot.env, which cloud-init delivers via write_files in the cloud-config/cloud-final stages. The selector only depended on net+cgroups, so on a fast boot it could start before write_files landed and read a missing role env. Add an after-ordering on cloud-config + cloud-final so the env file is always present first.
107 lines
5.2 KiB
Bash
Executable File
107 lines
5.2 KiB
Bash
Executable File
#!/bin/sh
|
|
set -eu
|
|
|
|
# setup.sh — chroot customisation for the unified eks-node AMI (server + agent).
|
|
#
|
|
# Runs inside an Alpine 3.21 chroot under build-system-image.sh after packages
|
|
# and binaries are installed. Downloads the pinned K3s binary, verifies its
|
|
# SHA256, drops it into /usr/local/bin, sets executable bits on all role init
|
|
# scripts + cron entries, and writes the K3s server config skeleton. The role
|
|
# (server vs agent) is selected per-instance at first boot by eks-node-role.
|
|
#
|
|
# Network access inside the chroot is provided by the host's /etc/resolv.conf
|
|
# (build-system-image.sh copies it in). curl is in APK_PACKAGES.
|
|
|
|
K3S_VERSION="v1.32.5+k3s1"
|
|
K3S_URL_BASE="https://github.com/k3s-io/k3s/releases/download/${K3S_VERSION}"
|
|
|
|
# Pull the upstream signed checksums file and pin the amd64 line. A tampered
|
|
# release replacing both files would still produce a self-consistent download,
|
|
# so the SHA file URL is the trust anchor — anyone forging a Mulga AMI build
|
|
# would need to compromise the k3s-io GitHub release artefacts.
|
|
echo "[eks-node-setup] fetching k3s checksums ${K3S_VERSION}"
|
|
curl -fsSL -o /tmp/k3s-checksums.txt "${K3S_URL_BASE}/sha256sum-amd64.txt"
|
|
K3S_SHA256=$(awk '/[ \t]k3s$/{print $1; exit}' /tmp/k3s-checksums.txt)
|
|
if [ -z "${K3S_SHA256}" ]; then
|
|
echo "[eks-node-setup] could not parse k3s sha256 from upstream checksums"
|
|
cat /tmp/k3s-checksums.txt
|
|
exit 1
|
|
fi
|
|
echo "[eks-node-setup] downloading k3s ${K3S_VERSION} (sha256=${K3S_SHA256})"
|
|
curl -fsSL -o /usr/local/bin/k3s "${K3S_URL_BASE}/k3s"
|
|
echo "${K3S_SHA256} /usr/local/bin/k3s" > /tmp/k3s.sha256
|
|
if ! sha256sum -c /tmp/k3s.sha256; then
|
|
echo "[eks-node-setup] k3s SHA256 mismatch — refusing to bake AMI"
|
|
exit 1
|
|
fi
|
|
chmod 0755 /usr/local/bin/k3s
|
|
ln -sf /usr/local/bin/k3s /usr/local/bin/kubectl
|
|
ln -sf /usr/local/bin/k3s /usr/local/bin/crictl
|
|
ln -sf /usr/local/bin/k3s /usr/local/bin/ctr
|
|
|
|
# nats-cli is not in Alpine main/community — pull the upstream release binary.
|
|
# Used by k3s-first-boot.sh (one-shot publishes) and mulga-eks-state-report.sh
|
|
# (periodic publishes).
|
|
NATS_CLI_VERSION="0.4.0"
|
|
NATS_CLI_URL="https://github.com/nats-io/natscli/releases/download/v${NATS_CLI_VERSION}/nats-${NATS_CLI_VERSION}-linux-amd64.zip"
|
|
echo "[eks-node-setup] downloading nats-cli ${NATS_CLI_VERSION}"
|
|
curl -fsSL -o /tmp/nats-cli.zip "${NATS_CLI_URL}"
|
|
apk add --no-cache unzip
|
|
unzip -q -d /tmp/nats-cli /tmp/nats-cli.zip
|
|
install -m 0755 /tmp/nats-cli/nats-${NATS_CLI_VERSION}-linux-amd64/nats /usr/local/bin/nats
|
|
rm -rf /tmp/nats-cli /tmp/nats-cli.zip
|
|
apk del --no-cache unzip
|
|
|
|
# Init scripts ship as 0644 from INSTALL_FILES; OpenRC requires 0755. Every
|
|
# role's services are baked; the selector enables the right ones at first boot.
|
|
chmod 0755 /etc/init.d/eks-node-role /etc/init.d/k3s /etc/init.d/k3s-agent \
|
|
/etc/init.d/eks-token-webhook /etc/init.d/k3s-first-boot
|
|
chmod 0755 /usr/local/sbin/eks-node-role /usr/local/sbin/k3s-first-boot
|
|
chmod 0755 /etc/periodic/15min/mulga-eks-state-report
|
|
chmod 0755 /etc/periodic/daily/mulga-eks-etcd-snapshot
|
|
|
|
# K3s server config — skeleton; cloud-init / first-boot fills in the
|
|
# per-cluster fields (cluster-cidr, service-cidr, token-file, etc). Agents
|
|
# ignore this file (they run `k3s agent`).
|
|
# IAM token-auth is wired here via kube-apiserver-arg: the eks-token-webhook
|
|
# service (ordered `before k3s`) writes its kubeconfig to
|
|
# /etc/spinifex-eks/token-webhook.kubeconfig before the apiserver reads it.
|
|
# This only affects bearer-token requests; anonymous and client-cert paths
|
|
# (the first-boot /readyz probe uses the admin kubeconfig) are unaffected.
|
|
mkdir -p /etc/rancher/k3s
|
|
cat > /etc/rancher/k3s/config.yaml.skel <<'EOF'
|
|
# Populated at first boot by cloud-init user-data via k3s-first-boot.sh.
|
|
# Fields documented at https://docs.k3s.io/installation/configuration.
|
|
# No cluster-init: single-node v1 uses the embedded SQLite datastore, not etcd.
|
|
disable:
|
|
- traefik
|
|
- servicelb
|
|
- local-storage
|
|
kube-apiserver-arg:
|
|
- "authentication-token-webhook-config-file=/etc/spinifex-eks/token-webhook.kubeconfig"
|
|
- "authentication-token-webhook-cache-ttl=5m"
|
|
EOF
|
|
|
|
# Shared state dir for both roles (agent.env / role marker live here).
|
|
mkdir -p /etc/spinifex-eks
|
|
|
|
# Sentinel file marker — k3s-first-boot (server role) self-disables after first
|
|
# success by checking for this path. Initial state is "not yet run".
|
|
touch /var/lib/spinifex-eks/first-boot.pending 2>/dev/null || {
|
|
mkdir -p /var/lib/spinifex-eks
|
|
touch /var/lib/spinifex-eks/first-boot.pending
|
|
}
|
|
|
|
# Bind /dev/console to the serial port so userspace boot output — OpenRC
|
|
# service starts, cloud-init, role selection, and k3s-first-boot diagnostics —
|
|
# reaches ttyS0, which the orchestrator captures to a host-side log. The stock
|
|
# Alpine cloud image lists `console=tty0` LAST in default_kernel_opts; Linux
|
|
# makes the last console= the controlling /dev/console, so userspace logs to
|
|
# the framebuffer and the serial capture sees only kernel dmesg. Reorder so
|
|
# ttyS0 is last in both the generator config and the rendered extlinux.conf.
|
|
sed -i \
|
|
's|console=ttyS0,115200n8 console=ttyAMA0,115200n8 console=tty0|console=tty0 console=ttyAMA0,115200n8 console=ttyS0,115200n8|' \
|
|
/etc/update-extlinux.conf /boot/extlinux.conf
|
|
|
|
echo "[eks-node-setup] done"
|