From Kubernetes to a Self-Healing, Low-Cost Infrastructure

#!/bin/bash

GREEN='\033[0;32m'
YELLOW='\033[1;33m'
RED='\033[0;31m'
NC='\033[0m'
if [[ "$(uname)" == "Darwin" ]]; then
    echo "Skipping Traefik on Mac (not needed)"
    exit 0
fi

echo -e "${GREEN}🚀 Starting Traefik...${NC}"

# Ensure network exists
docker network create fid-network 2>/dev/null

# Start Traefik
docker compose -f docker-compose-traefik.yml up -d

sleep 3

if curl -s -o /dev/null -w "%{http_code}" http://localhost:80 | grep -q "200\|301\|302"; then
    echo -e "${GREEN}✅ Traefik is running${NC}"
    echo ""
    echo "Traefik is listening on ports 80 (HTTP) and 443 (HTTPS)."
    echo "Check logs: docker compose -f docker-compose-traefik.yml logs -f traefik"
else
    echo -e "${RED}❌ Traefik may not be ready. Check logs.${NC}"
fi

services:
  traefik:
    image: traefik:v3.2
    container_name: fid-traefik
    command:
      - "--entrypoints.web.address=:80"
      - "--entrypoints.websecure.address=:443"
      - "--providers.file.directory=/etc/traefik/conf"
      - "--certificatesresolvers.letsencrypt.acme.httpchallenge=true"
      - "--certificatesresolvers.letsencrypt.acme.httpchallenge.entrypoint=web"
      - "--certificatesresolvers.letsencrypt.acme.email=admin@xliberation.com"
      - "--certificatesresolvers.letsencrypt.acme.storage=/letsencrypt/acme.json"
      - "--entrypoints.web.http.redirections.entrypoint.to=websecure"
      - "--entrypoints.web.http.redirections.entrypoint.scheme=https"
      - "--entrypoints.web.http.redirections.entrypoint.permanent=true"
    ports:
      - "80:80"
      - "443:443"
    volumes:
      - ./conf:/etc/traefik/conf
      - traefik_certs:/letsencrypt
    networks:
      - fid-network
    restart: unless-stopped

volumes:
  traefik_certs:

networks:
  fid-network:
    external: true

#!/bin/bash
set -e

# --- 1. Wait for persistent disk to physically attach ---
echo "Waiting for persistent disk to attach..."
while [ ! -e /dev/disk/by-id/google-existing-data ]; do
    sleep 1
done

# Give the storage driver a brief moment to stabilize the block mapping
sleep 2

# --- 2. Mount persistent disk ---
mkdir -p /mnt/disks/fid-data
if ! mountpoint -q /mnt/disks/fid-data; then
    mount -o discard,defaults /dev/disk/by-id/google-existing-data /mnt/disks/fid-data
fi

# --- 3. Create symlink to repo on persistent disk ---
mkdir -p /home/brucemcpherson
chown -R brucemcpherson:brucemcpherson /home/brucemcpherson
ln -sf /mnt/disks/fid-data/fidmaster /home/brucemcpherson/fidmaster

# --- 4. Install Official Modern Docker Engine & Compose ---
apt-get update -qq
apt-get install -y -qq ca-certificates curl gnupg

# Add Docker's official GPG key and repository
install -m 0755 -d /etc/apt/keyrings
curl -fsSL https://download.docker.com/linux/debian/gpg | gpg --dearmor --yes -o /etc/apt/keyrings/docker.gpg
chmod a+r /etc/apt/keyrings/docker.gpg

echo \
  "deb [arch="$(dpkg --print-architecture)" signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/debian \
  "$(. /etc/os-release && echo "$VERSION_CODENAME")" stable" | \
  tee /etc/apt/sources.list.d/docker.list > /dev/null

# Install the exact modern packages (restores "docker compose" with a space)
apt-get update -qq
apt-get install -y -qq docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin

# --- 5. Configure Docker data root ---
if ! grep -q '"data-root": "/mnt/disks/fid-data/docker"' /etc/docker/daemon.json 2>/dev/null; then
    echo '{"data-root": "/mnt/disks/fid-data/docker"}' | tee /etc/docker/daemon.json
    systemctl restart docker
fi

# --- 6. Create systemd service file ---
# Using 'tee' inside the script ensures no root permission redirection blocks
cat << 'EOF' | tee /etc/systemd/system/fid-platform.service > /dev/null
[Unit]
Description=FID Platform (all services)
After=docker.service network.target
Requires=docker.service

[Service]
Type=oneshot
RemainAfterExit=yes
User=brucemcpherson
WorkingDirectory=/home/brucemcpherson/fidmaster/vm-docker/local-compose
ExecStartPre=/bin/sleep 5
ExecStart=/bin/bash /home/brucemcpherson/fidmaster/vm-docker/local-compose/start-all.sh
ExecStop=/bin/bash /home/brucemcpherson/fidmaster/vm-docker/local-compose/stop-all.sh
StandardOutput=journal
StandardError=journal

[Install]
WantedBy=multi-user.target
EOF

systemctl daemon-reload
systemctl enable fid-platform

# --- 7. Start all services ---
cd /home/brucemcpherson/fidmaster/vm-docker/local-compose
./start-all.sh

echo "Startup complete."

gcloud compute instance-templates create fid-vm-template-ephemeral \
    --region=europe-west2 \
    --machine-type=e2-standard-4 \
    --image-family=debian-12 \
    --image-project=debian-cloud \
    --boot-disk-size=50GB \
    --boot-disk-type=pd-ssd \
    --provisioning-model=SPOT \
    --metadata-from-file startup-script=startup-script.shgcloud 

#!/bin/bash

# 1. Define your known environment variables
PROJECT_ID="your project"
REGION="europe-west2"
ZONE="europe-west2-b"
MIG_NAME="the name for your new mig"
IP_NAME="your static ip name"
DISK_NAME="your persistent disk name"

# Check if the MIG already exists before trying to create it
if gcloud compute instance-groups managed describe "$MIG_NAME" --zone="$ZONE" >/dev/null 2>&1; then
    echo "Managed Instance Group '$MIG_NAME' already exists. Skipping creation..."
else
    echo "Creating Managed Instance Group '$MIG_NAME'..."
    gcloud compute instance-groups managed create "$MIG_NAME" \
        --zone="$ZONE" \
        --template=fid-vm-template-ephemeral \
        --size=1

    # Give GCP a moment to spin up the instance before querying it
    echo "Waiting 15 seconds for instance to initialize..."
    sleep 15
fi

# 2. Automatically grab the dynamic instance name
INSTANCE_NAME=$(gcloud compute instances list --filter="name~'^fid-mig-'" --format="value(name)")

# Safety check: Ensure an instance actually exists
if [ -z "$INSTANCE_NAME" ]; then
    echo "Error: No running instance found starting with '$MIG_NAME-'."
    exit 1
fi

echo "Found target instance: $INSTANCE_NAME"

# 3. Handle the per-instance config cleanly (Create if missing, update if exists)
echo "Configuring stateful IP and Disk resources..."

if gcloud compute instance-groups managed instance-configs describe "$MIG_NAME" --instance="$INSTANCE_NAME" --zone="$ZONE" >/dev/null 2>&1; then
    CONFIG_ACTION="update"
else
    CONFIG_ACTION="create"
fi

gcloud compute instance-groups managed instance-configs $CONFIG_ACTION "$MIG_NAME" \
    --zone="$ZONE" \
    --instance="$INSTANCE_NAME" \
    --stateful-external-ip interface-name=nic0,address=projects/"$PROJECT_ID"/regions/"$REGION"/addresses/"$IP_NAME" \
    --stateful-disk=device-name=existing-data,source=projects/"$PROJECT_ID"/zones/"$ZONE"/disks/"$DISK_NAME",auto-delete=never

# 4. Trigger the MIG to apply these stateful settings to the live VM
echo "Applying configurations to $INSTANCE_NAME..."
gcloud compute instance-groups managed update-instances "$MIG_NAME" \
    --zone="$ZONE" \
    --instances="$INSTANCE_NAME"

echo "Done! Dynamic setup complete."#!/bin/bash

gcloud compute ssh $(gcloud compute instances list --filter="name~'^fid-mig-'" --format="value(name)") --zone=europe-west2-b

# 1. Find the current instance name
INSTANCE_NAME=$(gcloud compute instances list --filter="name~'^fid-mig-'" --format="value(name)")

# 2. Simulate a sudden crash/preemption by deleting the instance body directly
gcloud compute instances delete $INSTANCE_NAME --zone=europe-west2-b --quiet

gcloud compute instance-groups managed list

Take down the VM (down-mig.sh)

If you're not using it, might as well save the cost. All you have to do is set the Mig size to 0.

gcloud compute instance-groups managed resize fid-mig \
    --size=0 \
    --zone=europe-west2-b \
    --quiet

gcloud compute instance-groups managed list

gcloud compute instance-groups managed resize fid-mig \
    --size=1 \
    --zone=europe-west2-b \
    --quiet

gcloud compute instance-groups managed list