loc_az_hci/infrastructure/proxmox/update-cluster-ips.sh

#!/bin/bash
# Update Proxmox cluster node IP addresses
# Updates corosync.conf and /etc/hosts on both nodes

set -e

# Node configuration
PVE_NODE="pve"
PVE_IP="192.168.1.207"
PVE2_NODE="pve2"
PVE2_IP="192.168.1.55"

# SSH configuration
SSH_USER="root"
SSH_KEY=""
if [ -f ~/.ssh/id_ed25519_proxmox ]; then
    SSH_KEY="-i ~/.ssh/id_ed25519_proxmox"
elif [ -f ~/.ssh/id_rsa ]; then
    SSH_KEY="-i ~/.ssh/id_rsa"
fi

# Colors
RED='\033[0;31m'
GREEN='\033[0;32m'
YELLOW='\033[1;33m'
BLUE='\033[0;34m'
NC='\033[0m'

log_info() {
    echo -e "${GREEN}[INFO]${NC} $1"
}

log_warn() {
    echo -e "${YELLOW}[WARN]${NC} $1"
}

log_error() {
    echo -e "${RED}[ERROR]${NC} $1"
}

log_node() {
    echo -e "${BLUE}[$1]${NC} $2"
}

backup_file() {
    local server_ip=$1
    local file=$2
    local node=$3
    
    log_node "$node" "Backing up $file..."
    ssh $SSH_KEY "$SSH_USER@$server_ip" "cp $file ${file}.backup.\$(date +%Y%m%d_%H%M%S)" 2>/dev/null || {
        log_warn "Could not backup $file (may not exist yet)"
    }
}

update_hosts_file() {
    local server_ip=$1
    local node=$2
    local node_name=$3
    local node_ip=$4
    local other_node_name=$5
    local other_node_ip=$6
    
    log_node "$node" "Updating /etc/hosts..."
    
    # Check if entry exists
    if ssh $SSH_KEY "$SSH_USER@$server_ip" "grep -q '$other_node_name' /etc/hosts" 2>/dev/null; then
        # Update existing entry
        ssh $SSH_KEY "$SSH_USER@$server_ip" "sed -i 's/.*$other_node_name/$other_node_ip $other_node_name/' /etc/hosts" 2>/dev/null
        log_node "$node" "  Updated $other_node_name -> $other_node_ip"
    else
        # Add new entry
        ssh $SSH_KEY "$SSH_USER@$server_ip" "echo '$other_node_ip $other_node_name' >> /etc/hosts" 2>/dev/null
        log_node "$node" "  Added $other_node_name -> $other_node_ip"
    fi
}

update_corosync_conf() {
    local server_ip=$1
    local node=$2
    local node_name=$3
    local node_ip=$4
    local other_node_name=$5
    local other_node_ip=$6
    
    log_node "$node" "Updating corosync.conf..."
    
    COROSYNC_FILE="/etc/pve/corosync.conf"
    
    # Check if file exists
    if ! ssh $SSH_KEY "$SSH_USER@$server_ip" "test -f $COROSYNC_FILE" 2>/dev/null; then
        log_warn "corosync.conf not found - cluster may not be configured yet"
        return
    fi
    
    # Get current config
    CURRENT_CONFIG=$(ssh $SSH_KEY "$SSH_USER@$server_ip" "cat $COROSYNC_FILE" 2>/dev/null)
    
    # Update node IPs in corosync.conf
    # This updates the ring0_addr for each node
    UPDATED_CONFIG=$(echo "$CURRENT_CONFIG" | sed "s/ring0_addr:.*pve/ring0_addr: $PVE_IP/" | \
                     sed "s/ring0_addr:.*pve2/ring0_addr: $PVE2_IP/")
    
    # Write updated config
    ssh $SSH_KEY "$SSH_USER@$server_ip" "cat > $COROSYNC_FILE << 'EOFCORO'
$UPDATED_CONFIG
EOFCORO
" 2>/dev/null
    
    log_node "$node" "  Updated corosync.conf with new IPs"
}

update_on_server() {
    local server_ip=$1
    local node=$2
    local node_name=$3
    local node_ip=$4
    local other_node_name=$5
    local other_node_ip=$6
    
    log_info "Updating $node ($node_name) at $server_ip..."
    
    # Backup files
    backup_file "$server_ip" "/etc/hosts" "$node"
    backup_file "$server_ip" "/etc/pve/corosync.conf" "$node"
    
    # Update /etc/hosts
    update_hosts_file "$server_ip" "$node" "$node_name" "$node_ip" "$other_node_name" "$other_node_ip"
    
    # Update corosync.conf
    update_corosync_conf "$server_ip" "$node" "$node_name" "$node_ip" "$other_node_name" "$other_node_ip"
    
    log_node "$node" "✓ Updates complete"
}

restart_cluster_services() {
    local server_ip=$1
    local node=$2
    
    log_node "$node" "Restarting cluster services..."
    log_warn "This may temporarily interrupt cluster communication"
    
    ssh $SSH_KEY "$SSH_USER@$server_ip" "systemctl restart corosync && systemctl restart pve-cluster" 2>/dev/null || {
        log_warn "Could not restart services (may need manual restart)"
    }
}

main() {
    log_info "========================================="
    log_info "Update Proxmox Cluster IP Addresses"
    log_info "========================================="
    echo ""
    
    log_info "Configuration:"
    log_info "  $PVE_NODE: $PVE_IP"
    log_info "  $PVE2_NODE: $PVE2_IP"
    echo ""
    
    # Update pve (ML110)
    update_on_server "$PVE_IP" "ML110" "$PVE_NODE" "$PVE_IP" "$PVE2_NODE" "$PVE2_IP"
    echo ""
    
    # Update pve2 (R630)
    update_on_server "$PVE2_IP" "R630" "$PVE2_NODE" "$PVE2_IP" "$PVE_NODE" "$PVE_IP"
    echo ""
    
    log_warn "Cluster services need to be restarted for changes to take effect"
    read -p "Restart cluster services now? (yes/no): " RESTART
    
    if [ "$RESTART" = "yes" ]; then
        log_info "Restarting cluster services..."
        restart_cluster_services "$PVE_IP" "ML110"
        sleep 2
        restart_cluster_services "$PVE2_IP" "R630"
        log_info "✓ Cluster services restarted"
    else
        log_info "Skipping service restart"
        log_info "Manually restart with: systemctl restart corosync && systemctl restart pve-cluster"
    fi
    
    echo ""
    log_info "========================================="
    log_info "Update Complete!"
    log_info "========================================="
    log_info "Verify cluster status:"
    log_info "  pvecm status"
    log_info "  pvecm nodes"
}

main "$@"