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.
70 lines
2.4 KiB
Bash
Executable File
70 lines
2.4 KiB
Bash
Executable File
#!/bin/sh
|
|
set -eu
|
|
|
|
# eks-node-role — first-boot role selector for the unified eks-node AMI.
|
|
#
|
|
# The same image boots either as a K3s control-plane server or a worker agent;
|
|
# the role is chosen per-instance at first boot from SPINIFEX_K3S_ROLE in the
|
|
# cloud-init env file. This script enables + starts the matching OpenRC services
|
|
# (none are in the default runlevel at bake time), records the resolved role to
|
|
# ROLE_FILE so later boots and the etcd-snapshot cron can branch without
|
|
# re-parsing, then removes itself from the runlevel so it runs exactly once.
|
|
#
|
|
# server → eks-token-webhook, k3s (server), k3s-first-boot (bootstrap publish)
|
|
# agent → k3s-agent
|
|
#
|
|
# Paths are overridable via env so the selection logic is unit-testable (bats)
|
|
# without root or a real /etc.
|
|
|
|
ROLE_FILE="${EKS_NODE_ROLE_FILE:-/etc/spinifex-eks/role}"
|
|
ENVFILE="${EKS_NODE_ENVFILE:-/etc/spinifex-eks/first-boot.env}"
|
|
AGENT_ENVFILE="${EKS_NODE_AGENT_ENVFILE:-/etc/spinifex-eks/agent.env}"
|
|
LOGTAG="eks-node-role"
|
|
|
|
log() { echo "[${LOGTAG}] $*"; }
|
|
die() { log "ERROR: $*"; exit 1; }
|
|
|
|
# Already resolved on a prior boot — the role services are in the runlevel and
|
|
# this service should have been pulled, but guard anyway so a stray re-run is a
|
|
# no-op rather than a double-enable.
|
|
if [ -f "${ROLE_FILE}" ]; then
|
|
log "role already resolved ($(cat "${ROLE_FILE}")); nothing to do"
|
|
exit 0
|
|
fi
|
|
|
|
# Resolve the role. Server seeds SPINIFEX_K3S_ROLE in first-boot.env; a worker
|
|
# seed that predates the explicit var is inferred from the presence of agent.env
|
|
# (K3S_URL/K3S_TOKEN live there).
|
|
ROLE=""
|
|
if [ -f "${ENVFILE}" ]; then
|
|
ROLE=$(. "${ENVFILE}"; printf '%s' "${SPINIFEX_K3S_ROLE:-}")
|
|
fi
|
|
if [ -z "${ROLE}" ] && [ -f "${AGENT_ENVFILE}" ]; then
|
|
ROLE="agent"
|
|
fi
|
|
|
|
case "${ROLE}" in
|
|
server)
|
|
log "configuring server role"
|
|
rc-update add eks-token-webhook default
|
|
rc-update add k3s default
|
|
rc-update add k3s-first-boot default
|
|
rc-service eks-token-webhook start
|
|
rc-service k3s start
|
|
rc-service k3s-first-boot start
|
|
;;
|
|
agent)
|
|
log "configuring agent role"
|
|
rc-update add k3s-agent default
|
|
rc-service k3s-agent start
|
|
;;
|
|
*)
|
|
die "SPINIFEX_K3S_ROLE missing or invalid: '${ROLE}'"
|
|
;;
|
|
esac
|
|
|
|
mkdir -p "$(dirname "${ROLE_FILE}")"
|
|
printf '%s\n' "${ROLE}" > "${ROLE_FILE}"
|
|
rc-update del eks-node-role default 2>/dev/null || true
|
|
log "role '${ROLE}' configured"
|