#!/bin/bash
#
# Cassandra Cluster Sequential Deployment Script
# This script deploys Cassandra nodes sequentially to avoid race conditions
# during cluster formation.
#

set -e

STACK_NAME="cassandra"
STACK_FILE="cassandra-stack.yml"

echo "=== Cassandra Cluster Sequential Deployment ==="
echo ""

# Check if stack file exists
if [ ! -f "$STACK_FILE" ]; then
    echo "ERROR: $STACK_FILE not found in current directory"
    exit 1
fi

echo "Step 1: Deploying cassandra-1 (seed node)..."
docker stack deploy -c "$STACK_FILE" "$STACK_NAME"

# Scale down cassandra-2 and cassandra-3 temporarily
docker service scale "${STACK_NAME}_cassandra-2=0" > /dev/null 2>&1
docker service scale "${STACK_NAME}_cassandra-3=0" > /dev/null 2>&1

echo "Waiting for cassandra-1 to become healthy (this takes ~5-8 minutes)..."
echo "Checking every 30 seconds..."

# Wait for cassandra-1 to be running
COUNTER=0
MAX_WAIT=20  # 20 * 30 seconds = 10 minutes max
while [ $COUNTER -lt $MAX_WAIT ]; do
    REPLICAS=$(docker service ls --filter "name=${STACK_NAME}_cassandra-1" --format "{{.Replicas}}")
    if [ "$REPLICAS" = "1/1" ]; then
        echo "✓ cassandra-1 is running"
        # Give it extra time to fully initialize
        echo "Waiting additional 2 minutes for cassandra-1 to fully initialize..."
        sleep 120
        break
    fi
    echo "  cassandra-1 status: $REPLICAS (waiting...)"
    sleep 30
    COUNTER=$((COUNTER + 1))
done

if [ $COUNTER -eq $MAX_WAIT ]; then
    echo "ERROR: cassandra-1 failed to start within 10 minutes"
    echo "Check logs with: docker service logs ${STACK_NAME}_cassandra-1"
    exit 1
fi

echo ""
echo "Step 2: Starting cassandra-2..."
docker service scale "${STACK_NAME}_cassandra-2=1"

echo "Waiting for cassandra-2 to become healthy (this takes ~5-8 minutes)..."
COUNTER=0
while [ $COUNTER -lt $MAX_WAIT ]; do
    REPLICAS=$(docker service ls --filter "name=${STACK_NAME}_cassandra-2" --format "{{.Replicas}}")
    if [ "$REPLICAS" = "1/1" ]; then
        echo "✓ cassandra-2 is running"
        echo "Waiting additional 2 minutes for cassandra-2 to join cluster..."
        sleep 120
        break
    fi
    echo "  cassandra-2 status: $REPLICAS (waiting...)"
    sleep 30
    COUNTER=$((COUNTER + 1))
done

if [ $COUNTER -eq $MAX_WAIT ]; then
    echo "ERROR: cassandra-2 failed to start within 10 minutes"
    echo "Check logs with: docker service logs ${STACK_NAME}_cassandra-2"
    exit 1
fi

echo ""
echo "Step 3: Starting cassandra-3..."
docker service scale "${STACK_NAME}_cassandra-3=1"

echo "Waiting for cassandra-3 to become healthy (this takes ~5-8 minutes)..."
COUNTER=0
while [ $COUNTER -lt $MAX_WAIT ]; do
    REPLICAS=$(docker service ls --filter "name=${STACK_NAME}_cassandra-3" --format "{{.Replicas}}")
    if [ "$REPLICAS" = "1/1" ]; then
        echo "✓ cassandra-3 is running"
        echo "Waiting additional 2 minutes for cassandra-3 to join cluster..."
        sleep 120
        break
    fi
    echo "  cassandra-3 status: $REPLICAS (waiting...)"
    sleep 30
    COUNTER=$((COUNTER + 1))
done

if [ $COUNTER -eq $MAX_WAIT ]; then
    echo "ERROR: cassandra-3 failed to start within 10 minutes"
    echo "Check logs with: docker service logs ${STACK_NAME}_cassandra-3"
    exit 1
fi

echo ""
echo "=== Deployment Complete ==="
echo ""
echo "All 3 Cassandra nodes should now be running and forming a cluster."
echo ""
echo "Verify cluster status by SSH'ing to any worker node and running:"
echo "  docker exec -it \$(docker ps -q --filter \"name=cassandra\") nodetool status"
echo ""
echo "You should see 3 nodes with status 'UN' (Up Normal)."
echo ""