mirror of
https://github.com/mulgadc/spinifex.git
synced 2026-10-15 17:11:30 +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.
109 lines
4.6 KiB
Bash
Executable File
109 lines
4.6 KiB
Bash
Executable File
#!/bin/bash
|
|
# dev-install.sh — Full local development setup via production installer.
|
|
# Builds from source, assembles a tarball, runs setup.sh for scaffolding
|
|
# (user creation, directories, systemd units), initializes the cluster,
|
|
# and starts services via systemd.
|
|
#
|
|
# Environment variables:
|
|
# SPINIFEX_REGION Region for spx admin init (default: ap-southeast-2)
|
|
# SPINIFEX_AZ AZ for spx admin init (default: ${SPINIFEX_REGION}a)
|
|
# DEV_INSTALL_SKIP_INIT Internal flag used by reset-dev-env.sh. When 1,
|
|
# stops after setup.sh and skips setup-ovn, init,
|
|
# CA trust, service start, and LB image import —
|
|
# caller owns those steps. Do not set manually.
|
|
#
|
|
# Usage: ./scripts/dev-install.sh
|
|
set -euo pipefail
|
|
|
|
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
|
|
PROJECT_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
|
|
MULGA_ROOT="$(cd "$PROJECT_ROOT/.." && pwd)"
|
|
|
|
echo "=== Building ==="
|
|
cd "$PROJECT_ROOT" && make build
|
|
cd "$MULGA_ROOT/viperblock" && make go_build_nbd
|
|
|
|
echo "=== Assembling tarball for setup.sh ==="
|
|
STAGING=$(mktemp -d)
|
|
trap 'rm -rf "$STAGING"' EXIT
|
|
cp "$PROJECT_ROOT/bin/spx" "$STAGING/spx"
|
|
cp "$MULGA_ROOT/viperblock/lib/nbdkit-viperblock-plugin.so" "$STAGING/"
|
|
cp "$PROJECT_ROOT/scripts/setup-ovn.sh" "$STAGING/"
|
|
mkdir -p "$STAGING/systemd"
|
|
cp "$PROJECT_ROOT/build/systemd/"* "$STAGING/systemd/"
|
|
mkdir -p "$STAGING/scripts"
|
|
cp "$PROJECT_ROOT/build/scripts/"* "$STAGING/scripts/"
|
|
mkdir -p "$STAGING/udev"
|
|
cp "$PROJECT_ROOT/build/udev/"* "$STAGING/udev/"
|
|
cp "$PROJECT_ROOT/build/logrotate/spinifex" "$STAGING/logrotate-spinifex"
|
|
tar czf /tmp/spinifex-local.tar.gz -C "$STAGING" .
|
|
|
|
echo "=== Cleaning stale state from previous installs ==="
|
|
# Stop any running services before modifying files
|
|
sudo systemctl stop spinifex.target 2>/dev/null || true
|
|
sudo systemctl reset-failed 'spinifex-*' 2>/dev/null || true
|
|
|
|
# Remove stale files owned by the dev user in production paths.
|
|
# Previous dev-mode installs (admin init without sudo, start-dev.sh) leave
|
|
# files owned by tf-user that service users (spinifex-nats, etc.) can't read
|
|
# under systemd's ProtectSystem=strict sandboxing.
|
|
for dir in /var/lib/spinifex /var/log/spinifex /etc/spinifex; do
|
|
if [ -d "$dir" ]; then
|
|
# Remove PID files, stale logs, and the legacy ~/spinifex/config symlink
|
|
sudo find "$dir" -name '*.pid' -delete 2>/dev/null || true
|
|
sudo find "$dir" -name '*.log' -delete 2>/dev/null || true
|
|
sudo find "$dir" -name '*.log.*' -delete 2>/dev/null || true
|
|
fi
|
|
done
|
|
# Remove legacy data dir contents that conflict with production layout
|
|
if [ -d /var/lib/spinifex/config ]; then
|
|
sudo rm -rf /var/lib/spinifex/config
|
|
fi
|
|
|
|
echo "=== Running setup.sh (creates users, dirs, systemd units) ==="
|
|
sudo INSTALL_SPINIFEX_TARBALL=/tmp/spinifex-local.tar.gz INSTALL_SPINIFEX_SKIP_NEWGRP=1 bash "$PROJECT_ROOT/scripts/setup.sh"
|
|
rm -f /tmp/spinifex-local.tar.gz
|
|
|
|
if [ "${DEV_INSTALL_SKIP_INIT:-0}" = "1" ]; then
|
|
echo "=== DEV_INSTALL_SKIP_INIT=1 — stopping after setup.sh ==="
|
|
echo "Caller owns: setup-ovn, spx admin init, CA trust, service start, LB image."
|
|
exit 0
|
|
fi
|
|
|
|
echo "=== Setting up OVN ==="
|
|
sudo /usr/local/share/spinifex/setup-ovn.sh --management
|
|
|
|
SPINIFEX_REGION="${SPINIFEX_REGION:-ap-southeast-2}"
|
|
SPINIFEX_AZ="${SPINIFEX_AZ:-${SPINIFEX_REGION}a}"
|
|
|
|
echo "=== Initializing (region=$SPINIFEX_REGION az=$SPINIFEX_AZ) ==="
|
|
sudo spx admin init --force --region "$SPINIFEX_REGION" --az "$SPINIFEX_AZ" --node node1 --nodes 1
|
|
|
|
echo "=== Starting services ==="
|
|
sudo systemctl start spinifex.target
|
|
|
|
# Check if user needs to re-login for spinifex group membership
|
|
if ! id -Gn 2>/dev/null | grep -qw spinifex; then
|
|
newgrp spinifex
|
|
fi
|
|
|
|
echo "=== Building and installing microVM artifacts ==="
|
|
cd "$PROJECT_ROOT" && make build-lb-agent install-microvm
|
|
|
|
# Unified EKS node AMI (server + agent; role chosen at first boot). Heavy (full
|
|
# Alpine + K3s build, needs sudo + network), so it is opt-in: set
|
|
# DEV_INSTALL_EKS=1 to build + register it. Without it, `aws eks create-cluster`
|
|
# fails AMI resolution until the operator runs `make import-eks-node-image`.
|
|
if [ "${DEV_INSTALL_EKS:-0}" = "1" ]; then
|
|
echo "=== Building + importing eks-node AMI ==="
|
|
cd "$PROJECT_ROOT" && make import-eks-node-image
|
|
else
|
|
echo "=== Skipping eks-node AMI (set DEV_INSTALL_EKS=1 to enable, or run 'make import-eks-node-image') ==="
|
|
fi
|
|
|
|
echo "=== Done ==="
|
|
echo "Services: sudo systemctl status spinifex.target"
|
|
echo "Logs: journalctl -u 'spinifex-*' -f"
|
|
echo "Test: AWS_PROFILE=spinifex aws ec2 describe-instances"
|
|
echo "Iterate: make deploy (rebuild + restart all)"
|