navidrome-litefs/entrypoint.sh

#!/bin/bash
set -e

# Configuration from environment
SERVICE_NAME="navidrome"
# Use Nomad allocation ID for a unique service ID
SERVICE_ID="${SERVICE_NAME}-${NOMAD_ALLOC_ID:-$(hostname)}"
PORT=4533
CONSUL_HTTP_ADDR="${CONSUL_URL:-http://localhost:8500}"
NODE_IP="${ADVERTISE_IP}"
DB_LOCK_FILE="/litefs/.primary"
NAVIDROME_PID=0

# --- Helper Functions ---

# Check if this node is the LiteFS Primary
check_primary() {
  # Use the local LiteFS API to get the most accurate status
  local status=$(curl -s http://localhost:20202/status || echo "{}")
  local is_primary=$(echo "$status" | jq -r '.isPrimary // false')
  
  if [ "$is_primary" = "true" ]; then
    return 0 # We are the primary
  fi
  return 1 # We are a replica
}

# Wait for LiteFS to be fully initialized and connected
wait_for_litefs() {
  echo "Waiting for LiteFS to settle..."
  local timeout=60
  local count=0
  while [ $count -lt $timeout ]; do
    local status=$(curl -s http://localhost:20202/status || echo "{}")
    # If isPrimary is not null, LiteFS has determined its role
    if [ "$(echo "$status" | jq -r '.isPrimary // "null"')" != "null" ]; then
      echo "LiteFS initialized. Role: $(echo "$status" | jq -r '.isPrimary | if . then "primary" else "replica" end')"
      return 0
    fi
    sleep 2
    count=$((count + 2))
    echo -n "."
  done
  echo "ERROR: LiteFS failed to settle after ${timeout}s"
  return 1
}

# Tags for the Primary service (Traefik enabled)
PRIMARY_TAGS='["navidrome","web","traefik.enable=true","urlprefix-/navidrome","tools","traefik.http.routers.navidromelan.rule=Host(`navidrome.service.dc1.consul`)","traefik.http.routers.navidromewan.rule=Host(`m.fbleagh.duckdns.org`)","traefik.http.routers.navidromewan.middlewares=dex@consulcatalog","traefik.http.routers.navidromewan.tls=true"]'

# --- Helper Functions ---

# Backup Database (Only on Primary)
run_backup() {
  local backup_dir="/data/backup"
  local timestamp=$(date +%Y%m%d_%H%M%S)
  local backup_file="${backup_dir}/navidrome.db_${timestamp}.bak"
  
  echo "Backing up database to ${backup_file}..."
  mkdir -p "$backup_dir"
  
  if litefs export -name navidrome.db "$backup_file"; then
    echo "Backup successful."
    # Keep only last 7 days
    find "$backup_dir" -name "navidrome.db_*.bak" -mtime +7 -delete
    echo "Old backups cleaned."
  else
    echo "ERROR: Backup failed!"
  fi
}

# Register Service with TTL Check
register_service() {
  echo "Promoted! Registering service ${SERVICE_ID}..."
  # Convert bash list string to JSON array if needed, but PRIMARY_TAGS is already JSON-like
  curl -s -X PUT "${CONSUL_HTTP_ADDR}/v1/agent/service/register" -d "{
    \"ID\": \"${SERVICE_ID}\",
    \"Name\": \"${SERVICE_NAME}\",
    \"Tags\": ${PRIMARY_TAGS},
    \"Address\": \"${NODE_IP}\",
    \"Port\": ${PORT},
    \"Check\": {
      \"DeregisterCriticalServiceAfter\": \"1m\",
      \"TTL\": \"15s\"
    }
  }"
}

# Send Heartbeat to Consul
pass_ttl() {
  curl -s -X PUT "${CONSUL_HTTP_ADDR}/v1/agent/check/pass/service:${SERVICE_ID}" > /dev/null
}

# Deregister Service
deregister_service() {
  echo "Demoted/Stopping. Deregistering service ${SERVICE_ID}..."
  curl -s -X PUT "${CONSUL_HTTP_ADDR}/v1/agent/service/deregister/${SERVICE_ID}"
}

# Start Navidrome in Background
start_app() {
  echo "Node is Primary. Starting Navidrome..."
  
  # Ensure shared directories exist on persistent host volume
  mkdir -p /data/plugins /data/cache /data/backup

  # Explicitly wait for the DB file to appear in the LiteFS mount
  local db_file="/litefs/navidrome.db"
  local timeout=30
  local count=0
  
  echo "Waiting for LiteFS database at ${db_file}..."
  while [ ! -f "$db_file" ] && [ $count -lt $timeout ]; do
    sleep 1
    count=$((count + 1))
  done

  if [ ! -f "$db_file" ]; then
     echo "WARNING: Database file ${db_file} not found after ${timeout}s. LiteFS may still be initializing."
     # We continue anyway as Navidrome might create it, but logging this is vital for debugging.
  fi

  # Tell Navidrome to use the database directly from the LiteFS mount.
  # We include standard Navidrome SQLite params for stability.
  export ND_DBPATH="${db_file}?cache=shared&_busy_timeout=15000&_journal_mode=WAL&_foreign_keys=on"

  /app/navidrome &
  NAVIDROME_PID=$!
  echo "Navidrome started with PID ${NAVIDROME_PID} using DB at ${ND_DBPATH}"
}

# Stop Navidrome
stop_app() {
  if [ "${NAVIDROME_PID}" -gt 0 ]; then
    echo "Stopping Navidrome (PID ${NAVIDROME_PID})..."
    kill -SIGTERM "${NAVIDROME_PID}"
    wait "${NAVIDROME_PID}" 2>/dev/null || true
    NAVIDROME_PID=0
  fi
}

# --- Signal Handling (The Safety Net) ---
# If Nomad stops the container, we stop the app and deregister.
cleanup() {
  echo "Caught signal, shutting down..."
  stop_app
  deregister_service
  exit 0
}

trap cleanup TERM INT

# --- Main Loop ---

echo "Starting Supervisor. Waiting for leadership settle..."
echo "Node IP: $NODE_IP"
echo "Consul: $CONSUL_HTTP_ADDR"

# Wait for LiteFS to be fully ready before making decisions
wait_for_litefs || exit 1

LAST_BACKUP_TIME=0
BACKUP_INTERVAL=86400 # 24 hours

while true; do
  # Use explicit LiteFS status check instead of file existence
  if check_primary; then
    # === WE ARE PRIMARY ===
    
    # 1. If App is not running, start it and register
    if [ "${NAVIDROME_PID}" -eq 0 ] || ! kill -0 "${NAVIDROME_PID}" 2>/dev/null; then
      if [ "${NAVIDROME_PID}" -gt 0 ]; then
        echo "CRITICAL: Navidrome crashed! Restarting..."
      fi
      start_app
      register_service
    fi

    # 2. Maintain the heartbeat (TTL)
    pass_ttl
    
    # 3. Handle periodic backup
    CURRENT_TIME=$(date +%s)
    if [ $((CURRENT_TIME - LAST_BACKUP_TIME)) -ge $BACKUP_INTERVAL ]; then
      run_backup
      LAST_BACKUP_TIME=$CURRENT_TIME
    fi
    
  else
    # === WE ARE REPLICA ===
    
    # If App is running (we were just demoted), stop it
    if [ "${NAVIDROME_PID}" -gt 0 ]; then
      echo "Lost leadership. Demoting..."
      stop_app
      deregister_service
      # Reset backup timer so the next primary can start fresh or we start fresh if promoted again
      LAST_BACKUP_TIME=0
    fi
    
    # No service registration exists for replicas to keep Consul clean.
  fi

  # Sleep short enough to update TTL (every 5s is safe for 15s TTL)
  sleep 5 &
  wait $! # Wait allows the 'trap' to interrupt the sleep instantly
done